Methods, networking devices, and media for queuing rdma packets

Abstract

Techniques and apparatuses for data networking are described. In one example, a method of queuing remote direct memory access (RDMA) packets includes receiving a first RDMA packet having a first quality of service (QoS) data field; based on a value of the first QoS data field, enqueuing the first RDMA packet into a first queue of a plurality of queues; receiving a second RDMA packet having a second QoS data field; based on a value of the second QoS data field, enqueuing the second RDMA packet into a second queue of the plurality of queues, the second queue being different from the first queue.

Description

[0001] Cross-references to related applications

[0002] This application claims priority to U.S. Provisional Application No. 63 / 132,417, filed December 30, 2020, entitled “CLOUD SCALE MULTI-TENANCY FOR RDMA OVER CONVERGED ETHERNET (RoCE)”; U.S. Non-Provisional Application No. 17 / 165,877, filed February 2, 2021, entitled “CLOUD SCALE MULTI-TENANCY FOR RDMA OVER CONVERGED ETHERNET (RoCE)”; and U.S. Non-Provisional Application No. 17 / 166,922, filed February 3, 2021, entitled “CLASS-BASED QUEUEING FOR SCALABLE MULTI-TENANT RDMA TRAFFIC”, all of which are incorporated herein by reference in their entirety for all purposes. Background Technology

[0003] RDMA over Converged Ethernet (RoCE) is a network protocol that allows Remote Direct Memory Access (RDMA) over lossless Ethernet networks. RoCE achieves this by encapsulating InfiniBand (IB) transport packets over Ethernet. Typically, RoCE involves Layer 2 networks with dedicated RDMA queues and dedicated VLANs. However, Layer 2 networks are scalable and perform poorly because they lack the key features and characteristics present in more scalable and high-performance Layer 3 networks. Therefore, existing public cloud implementations cannot use the RoCE protocol for data delivery. Summary of the Invention

[0004] This disclosure generally relates to data networking. More specifically, techniques are described that enable Layer 2 traffic to be transmitted over Layer 3 networks using Layer 3 protocols. In some embodiments, the techniques described herein enable Remote Direct Memory Access (RDMA) traffic (e.g., RDMA (RoCE) traffic over Converged Ethernet) to be transmitted from a computing instance on a multi-tenant host machine (i.e., a host machine hosting computing instances belonging to different tenants or customers) to a computing instance on another multi-tenant host machine via a shared Layer 3 physical network or a switch architecture using Layer 3 routing protocols. Such communication may also optionally include other traffic (e.g., TCP and / or UDP traffic). The customer or tenant experiences the communication as occurring on a dedicated Layer 2 network, while the actual communication occurs on a shared (i.e., shared among multiple customers or tenants) Layer 3 network using Layer 3 routing protocols. Various embodiments are described herein, including methods, systems, non-transitory computer-readable storage media storing programs, code, or instructions executable by one or more processors, etc.

[0005] In some embodiments, a data networking method includes receiving a first RDMA packet having a first Quality of Service (QoS) data field by a networking device; queuing the first RDMA packet into a first queue of a plurality of queues based on the value of the first QoS data field; receiving a second RDMA packet having a second QoS data field by the networking device; and queuing the second RDMA packet into a second queue of a plurality of queues, the second queue being different from the first queue, based on the value of the second QoS data field. The method may further include retrieving the first RDMA packet from the first queue and retrieving the second RDMA packet from the second queue within the plurality of queues according to a first weight. The first weight may be a weighted round-robin scheme. Additionally or alternatively, the plurality of queues may include a control queue, and the method may further include retrieving a plurality of control packets from the control queue by the networking device, wherein retrieving the plurality of control packets has a stricter priority than retrieving the first RDMA packet and retrieving the second RDMA packet. In this case, the plurality of queues may include a plurality of RDMA queues, including the first queue and the second queue, and the control queue may be configured to have a lower bandwidth than any of the plurality of RDMA queues. The plurality of control packets may include at least one of network control protocol packets or congestion notification packets.

[0006] In the method described above, the first QoS data field may be the Differential Service Code Point (DSCP) data field of the Internet Protocol (IP) header of the first RDMA packet. Each of the first and second RDMA packets may be a RoCEv2 packet; alternatively, each of the first and second RDMA packets may be a Layer 3 encapsulated packet formatted according to an overlay encapsulation protocol (e.g., one of VxLAN, NVGRE, GENEVE, STT, and MPLS), and the method may further include decapsulating the first RDMA packet to obtain a first decapsulated RDMA packet, and copying congestion indication information from at least one external header of the first RDMA packet to the first decapsulated RDMA packet. Any of the above methods may further include receiving a plurality of RDMA packets, each of the plurality of RDMA packets having a corresponding QoS data field; for each of the plurality of RDMA packets, queuing the RDMA packets into queues of a plurality of queues based on the value of the QoS data field of the RDMA packet; retrieving the plurality of RDMA packets from the plurality of queues, wherein the plurality of RDMA packets comprise a plurality of packet flows, and wherein the method further includes routing the plurality of packet flows according to a per-flow equal cost multipath scheme.

[0007] In other embodiments, class-based queuing techniques for RDMA traffic are described (e.g., in a Layer 3 network), which can be used to maintain class-based separation in cloud-scale network architectures, ensuring that RDMA traffic in a particular queue does not affect RDMA traffic in other queues. According to some embodiments, the system can be implemented as including a shared architecture for transmitting RDMA traffic of different classes and from different tenants, wherein each device in the path across the shared architecture from one RDMA network interface controller (NIC) to another NIC includes multiple queues dedicated to different classes of RDMA traffic.

[0008] According to some embodiments, a method of queuing RDMA packets includes receiving a plurality of RDMA packets by a networking device. Each of the plurality of RDMA packets includes a Quality of Service (QoS) data field, and for each of the plurality of RDMA packets, the QoS data field has a QoS value indicating the class of service in which the RDMA packet resides. The method also includes distributing the plurality of RDMA packets among a plurality of RDMA queues by the networking device. Distribution is performed according to a first mapping of the plurality of QoS values ​​to the plurality of RDMA queues. The method also includes retrieving the plurality of RDMA packets from the plurality of RDMA queues by the networking device according to a first weight. The retrieved plurality of RDMA packets may include a plurality of packet flows, in which case the example may also include a plurality of packet flows that route the retrieved plurality of RDMA packets according to a per-flow equal cost multipath scheme. Each of the plurality of RDMA packets may be a RoCEv2 packet, or each of the plurality of RDMA packets may be a Layer 3 encapsulated packet formatted according to an overlay encapsulation protocol (e.g., VxLAN, NVGRE, GENEVE, STT, or MPLS).

[0009] In a further example, the distribution includes storing the first RDMA packet into a first RDMA queue of a plurality of RDMA queues in response to determining that the QoS data field of a first RDMA packet among a plurality of RDMA packets has a first QoS value; and storing the second RDMA packet into a second RDMA queue of a plurality of RDMA queues in response to determining that the QoS data field of a second RDMA packet among a plurality of RDMA packets has a second QoS value, wherein the second QoS value is different from the first QoS value.

[0010] According to some embodiments, another method of queuing RDMA packets includes retrieving multiple control packets from a control queue by a networking device, wherein retrieving the multiple control packets has a stricter priority than retrieving the multiple RDMA packets. In this case, the control queue may be configured to have a lower bandwidth than any of the multiple RDMA queues. Alternatively or additionally, the multiple control packets may include at least one network control protocol packet (e.g., a BGP packet) and / or at least one congestion notification packet (CNP packet).

[0011] According to some embodiments, a networking device (e.g., a leaf switch or a backbone switch) may be configured to include multiple RDMA queues, and a processing circuitry system coupled to the multiple RDMA queues and configured to receive multiple RDMA packets, wherein each of the multiple RDMA packets includes a Quality of Service (QoS) data field; the multiple RDMA packets are distributed among the multiple RDMA queues according to a first mapping of multiple QoS values ​​to multiple RDMA queues; and the multiple RDMA packets are retrieved from the multiple RDMA queues according to a first weight. For each of the multiple RDMA packets, the QoS data field has a value indicating the service class of the RDMA packet and among multiple QoS values.

[0012] In other embodiments, a technique for class-based tagging of encapsulated Remote Direct Memory Access (RDMA) traffic is described. This technique can be used to maintain consistent class-based separation across network architectures at cloud scale (e.g., during Layer 3 transports) so that RDMA traffic in a particular queue does not affect RDMA traffic in other queues. According to some embodiments, a system can be implemented as including a shared architecture for transporting different classes of RDMA traffic from different tenants, wherein each device in the path across the shared architecture from one RDMA network interface controller (NIC) to another NIC includes multiple queues dedicated to different classes of RDMA traffic. Various inventive embodiments are described herein, including methods, systems, and non-transitory computer-readable storage media storing program code, instructions, etc., executable by one or more processors.

[0013] According to some embodiments, a data networking method includes receiving a plurality of RDMA packets by a networking device. Each of the plurality of RDMA packets includes a Quality of Service (QoS) data field having a QoS value indicating the service class of the RDMA packet. The plurality of RDMA packets includes RDMA packets whose QoS data field has a first QoS value and RDMA packets whose QoS data field has a second QoS value different from the first QoS value. The method further includes, for each of the plurality of RDMA packets, encapsulating the RDMA packet to produce a corresponding one of a plurality of Layer 3 encapsulated packets, the corresponding Layer 3 encapsulated packet having at least one external header. For each of the plurality of RDMA packets, the encapsulation of the RDMA packet includes adding at least one external header of the corresponding Layer 3 encapsulated packet to the RDMA packet. For each of the plurality of Layer 3 encapsulated packets, the QoS data field of the at least one external header of the Layer 3 encapsulated packet adopts a QoS value based on the QoS value of the QoS data field of the corresponding RDMA packet. For each of the plurality of Layer 3 encapsulated packets, the at least one external header may include a Virtual Network Identifier field based on the VLAN ID of the corresponding RDMA packet. In this scenario, multiple RDMA packets may include RDMA packets each having a first VLAN ID (some packets may have different QoS values ​​than others) and RDMA packets each having a second VLAN ID different from the first VLAN ID. Alternatively or additionally, at least one of the multiple Layer 3 encapsulated packets may include a first VLAN tag and a second VLAN tag different from the first VLAN tag.

[0014] For each of the multiple Layer 3 encapsulated packets, at least one outer header of the encapsulated packet may include a User Datagram Protocol (UDP) header with destination port number 4791 (e.g., a UDP port reserved for RoCEv2). Alternatively or additionally, at least one outer header of the Layer 3 encapsulated packet may include an Internet Protocol (IP) header with a destination IP address associated with the destination Media Access Control (MAC) address of the corresponding RDMA packet.

[0015] For each of the multiple RDMA packets, the QoS data field of the RDMA packet can be the DSCP data field of the IP header of the RDMA packet. In this case, for each of the multiple Layer 3 encapsulated packets, the QoS value in the QoS data field of at least one outer header of the Layer 3 encapsulated packet can be equal to the QoS value in the QoS data field of the corresponding RDMA packet. Alternatively, for each of the multiple RDMA packets, the QoS data field of the RDMA packet can be the IEEE 802.1p data field of the VLAN tag. In this case, encapsulating the RDMA packet may include obtaining the QoS value of the QoS data field of at least one outer header of the corresponding Layer 3 encapsulated packet from the QoS value of the RDMA packet's QoS data field and the mapping of QoS values, and storing the obtained QoS value in the QoS data field of at least one outer header of the Layer 3 encapsulated packet.

[0016] According to some embodiments, a further data networking method includes, for each of at least one of a plurality of layer 3 encapsulated packets, copying congestion indication information from the corresponding RDMA packet to at least one external header in the layer 3 encapsulated packet. Alternatively or additionally, the data networking method may further include decapsulating each of a second plurality of layer 3 encapsulated packets to obtain a corresponding one of a plurality of decapsulated RDMA packets. For at least one of the plurality of decapsulated RDMA packets, decapsulation may include copying congestion indication information from at least one external header of the corresponding layer 3 encapsulated packet to the decapsulated RDMA packet.

[0017] According to some embodiments, a non-transitory computer-readable storage device may store a plurality of instructions executable by one or more processors, including instructions that, when executed by one or more processors, cause one or more processors to perform any of the methods described above.

[0018] According to some embodiments, a system may include one or more processors, and memory coupled to the one or more processors. The memory may store a plurality of instructions executable by the one or more processors, including instructions that, when executed by the one or more processors, cause the one or more processors to perform any of the methods described above.

[0019] The foregoing, along with other features and embodiments, will become clearer with reference to the following description, claims, and drawings. Attached Figure Description

[0020] Figure 1 This is a high-level diagram of a distributed environment, illustrating a virtual or overlay cloud network hosted by a cloud service provider infrastructure according to certain embodiments.

[0021] Figure 2 A simplified architecture diagram of the physical components in the physical network within the CSPI according to certain embodiments is depicted.

[0022] Figure 3 An example arrangement within CSPI according to certain embodiments is shown, in which a host machine is connected to multiple network virtualization devices (NVDs).

[0023] Figure 4 The connectivity between the host machine and the NVD, according to certain embodiments, is described for providing I / O virtualization to support multiple tenancy.

[0024] Figure 5 A simplified block diagram of a physical network provided by CSPI according to certain embodiments is depicted.

[0025] Figure 6 An example of a distributed cloud environment for data networking, according to certain embodiments, is shown.

[0026] Figures 7A-7C A simplified flowchart is shown depicting, according to certain embodiments, the process of performing RDMA data transfer from a source compute instance on a multi-tenant source host machine to a destination compute instance on a multi-tenant destination host machine using a Layer 3 routing protocol through a shared Layer 3 switch architecture.

[0027] Figure 8A The RDMA packet format according to version 2 of the RDMA (RoCEv2) protocol over Converged Ethernet is shown.

[0028] Figure 8B The format of RoCEv2 packets with VLAN tags according to certain embodiments is shown.

[0029] Figure 8C The format of RoCEv2 grouping with Q-in-Q tags according to certain embodiments is shown.

[0030] Figure 9A This shows the format of the Internet Protocol (IP) header.

[0031] Figure 9B and 9C Implementations of multiple queues according to certain embodiments are shown.

[0032] Figure 10 The format of a VxLAN packet according to certain embodiments is shown.

[0033] Figure 11This is a block diagram illustrating a pattern for implementing cloud infrastructure as a service system according to at least one embodiment.

[0034] Figure 12 This is a block diagram illustrating another pattern for implementing cloud infrastructure as a service system according to at least one embodiment.

[0035] Figure 13 This is a block diagram illustrating another pattern for implementing cloud infrastructure as a service system according to at least one embodiment.

[0036] Figure 14 This is a block diagram illustrating another pattern for implementing cloud infrastructure as a service system according to at least one embodiment.

[0037] Figure 15 This is a block diagram illustrating an example computer system according to at least one embodiment. Detailed Implementation

[0038] In the following description, specific details are set forth for purposes of explanation in order to provide a thorough understanding of certain embodiments. However, it will be apparent that various embodiments may be practiced without these specific details. The accompanying drawings and description are not intended to be limiting. The word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or superior to other embodiments or designs.

[0039] This disclosure generally relates to networking, and more specifically to techniques that enable Layer 2 traffic to be transmitted over Layer 3 networks using Layer 3 protocols. In some embodiments, the techniques described herein enable RDMA (RoCE) traffic over converged Ethernet to be transmitted using Layer 3 routing protocols over a shared Layer 3 physical network or switch architecture from a compute instance on a multi-tenant host machine (i.e., a host machine hosting compute instances belonging to different tenants or customers) to a compute instance on another multi-tenant host machine. The customer or tenant experiences the communication occurring on a dedicated Layer 2 network, while the actual communication occurs on a shared (i.e., shared among multiple customers or tenants) Layer 3 network using Layer 3 routing protocols.

[0040] The technology that enables tenant-identifying VLAN identification information (e.g., VLAN ID) to be specified in the Layer 2 header of RoCE packets (e.g., the VLAN ID is included in an 802.1Q tag added to the RoCE packet) and the technique for mapping VLAN identification information to information included in a Layer 3 overlay encapsulation protocol wrapper, which is added to the 802.1Q-tagged RoCE Layer 2 packet as the packet passes through the switch architecture, are also disclosed. Mapping VLAN identification information (or tenant information) to fields in the Layer 3 encapsulation wrapper makes the distinction between traffic from different tenants visible to the network in a Layer 3 switch architecture. Networked devices can use this information to isolate traffic belonging to different customers or tenants.

[0041] A technique is disclosed that enables QoS information associated with Layer 2 RDMA packets (e.g., RoCE packets) to be stored end-to-end along the switch architecture from the source host machine to the destination host machine to which the data is to be transmitted. By encoding that information into a Layer 3 overlay encapsulation protocol wrapper, the QoS information encoded in the Layer 2 RoCE packet is visible to networking devices within the switch architecture. When a packet enters the switch architecture, this wrapper is added to the RoCE packet with the 802.1Q tag by the initial switch handling traffic sent by a host (e.g., an ingress top-of-rack (TOR) switch). Mapping (e.g., copying) the QoS information into the encapsulation wrapper enables networking devices within the switch architecture to use Layer 3 routing protocols and route RoCE traffic through the switch architecture based on the QoS information associated with each packet.

[0042] A technique is also disclosed that enables any networking device in a switching architecture to signal congestion on a per-packet basis. This congestion information is stored in the packet as it travels through the switching architecture from a TOR switch (“ingress TOR switch”) connected to a source host machine to a TOR switch (“egress TOR switch”) connected to a destination host machine. At the TOR switch connected to the destination host machine, the congestion information from the Layer 3 encapsulation wrapper is translated (e.g., copied) into the RoCE packet header (e.g., translated into the ECN bit in the IP header of the RoCE packet) and thus stored and made available to the destination host machine. The destination host machine can then respond to the congestion information by sending a congestion notification packet (e.g., indicating congestion to the source host machine so that it can, for example, reduce its transmission rate accordingly).

[0043] In a typical computing environment, when data is exchanged between two computers, the transmitted data is copied multiple times by the network protocol stack software executed by the computers. This is known as the multiple-copy problem. Furthermore, the OS kernel and the computer's CPU are involved in these communications because the network stack (e.g., the TCP stack) is inherent to the kernel. This introduces significant latency into data transmission, latency that is intolerable for some applications.

[0044] Remote Direct Memory Access (RDMA) is a direct memory access mechanism that enables the movement of data between application memory in a computer or server without involving the computer's CPU (CPU bypass) or operating system (OS kernel bypass). This mechanism allows for high-throughput, high-data-rate, and low-latency networking. RDMA supports zero-copy networking by enabling network adapters or network interface cards (NICs) on the computer to transfer data directly from the line to the computer's application memory or vice versa, eliminating the need to copy data between application memory and the data buffers in the computer's operating system. Such transfers require almost no work from the CPU or cache, avoid context switching, and can continue in parallel with other system operations. RDMA is highly useful for high-performance computing (HPC) and applications requiring low latency.

[0045] RDMA over Converged Ethernet (RoCE) is a network protocol that allows Remote Direct Memory Access (RDMA) over lossless Ethernet networks. RoCE achieves this by encapsulating InfiniBand (IB) transport packets over Ethernet. Typically, RoCE involves dedicated RDMA queues and dedicated VLANs, as well as the use of Layer 2 networks. However, Layer 2 networks are scalable and perform poorly because they lack the key features and characteristics present in more scalable and high-performance Layer 3 networks. For example, Layer 2 networks: do not support multiple paths between data producers (e.g., sources) and data consumers (e.g., destinations) in the network architecture; Layer 2 loop problems exist; there is a flooding problem with Layer 2 frames; a lack of support for hierarchical structures in addressing schemes (e.g., Layer 2 lacks the concepts of CIDR, prefixes, and subnets); problems with large amounts of broadcast traffic; a lack of control protocols that allow advertising network connectivity (e.g., Layer 2 lacks protocols similar to BGP, RIP, or IS-IS); a lack of troubleshooting protocols and tools (e.g., Layer 2 lacks tools such as ICMP or Traceroute); and so on.

[0046] There are currently two versions of the RoCE protocol—RoCEv1 and RoCEv2. RoCEv2, also known as "Routeable RoCE," is defined in the document InfiniBand™ Architecture Specification Release 1.2.1 Annex A17: RoCEv2 (InfiniBand Trade Association, Beaverton, OR, September 2, 2014). RoCEv2 uses the User Datagram Protocol (UDP) as its transport protocol. Unfortunately, UDP lacks the sophisticated congestion control and congestion management mechanisms provided by TCP. Therefore, RoCEv2 suffers from the following problems: network livelock (e.g., a process is changing state, a frame moves but the frame doesn't advance); network deadlock (e.g., a process remains in a waiting state due to circular resource dependencies); head-of-line (HOL) blocking (e.g., the inability to forward packets at the head of the queue prevents packets following them); victimized flow (e.g., flow between non-congested nodes via congested switches); unfairness (e.g., high-bandwidth flow increases the latency of other flows); and adverse effects on lossy flow (e.g., lossless flow (e.g., RDMA) consuming buffers on lossy flow (e.g., TCP).

[0047] Successful RoCEv2 implementations typically also require dedicated network paths and VLANs for RDMA traffic. Furthermore, RoCEv2 as a protocol relies on Layer 2 Priority Flow Control (PFC), Explicit Congestion Notification (ECN), or a combination of PFC and ECN to achieve some form of congestion management, but these approaches are often insufficient in practice. PFC supports up to eight independent traffic classes and allows receivers to request the sender to pause traffic of a specified class by sending a PAUSE frame. Unfortunately, PFC is prone to PAUSE frame storms (e.g., too many PAUSE frames affecting all traffic of a specified class along the entire path from the traffic source), which can lead to a complete network deadlock. Additionally, PFC PAUSE frames do not allow multi-tenant operation because PAUSE causes the sender to pause transmission of all traffic of the specified class—although PFC provides a maximum of eight traffic classes, the number of tenants can be many times greater than eight.

[0048] The embodiments disclosed herein include systems, methods, and apparatuses for implementing RDMA (RoCE) over multi-tenant converged Ethernet at the scale of a public cloud. For example, the environment can scale to very large networks spanning hundreds, thousands, or more hosts. Such embodiments disclosed herein include techniques for supporting multi-tenant RoCE traffic in a public cloud while avoiding head-of-line congestion and maintaining high performance, low latency, and lossless operation for RDMA applications. Simultaneously, the disclosed techniques can also be implemented to support conventional non-RDMA applications using TCP / IP or UDP as their transport protocols. These techniques can be applied to all standard speeds of RoCE-capable Ethernet network interfaces, including, for example, 25G, 40G, 100G, 400G, and 800G.

[0049] The technologies disclosed herein for scaling RoCE in the cloud may include one or more of the following aspects: providing each customer with a VLAN or set of VLANs for their traffic; allowing hosts to use 802.1q-in-802.1q to isolate traffic between customers and across different applications for a given customer (e.g., packets may have two 802.1Q labels: a public VLAN label and a private VLAN label); mapping each VLAN to a VxLAN VNI on the ToR and assigning a unique VxLAN VNI to each customer and each of its VLANs; using VxLAN overlay to carry customer Layer 2 traffic over a Layer 3 network; and using EVPN (Ethernet VPN) to carry MAC address information across the underlying Layer 3 network (the base layer).

[0050] Implementations can be implemented as described herein to support multiple RDMA applications (e.g., cloud services, high-performance computing (HPC), and / or database applications), each with multiple traffic classes. This support can be provided by isolating their traffic using the concept of network QoS traffic classes, where dedicated sets of RDMA queues are allocated to different traffic classes with mission-critical traffic. This isolation using RDMA queues ensures that congestion in one queue does not affect another. Such techniques can be used to support multiple RDMA tenants (also known as “public cloud customers”), making the queue configuration in the Clos architecture transparent to the end-customer host (cloud customer). The network can be configured to map DSCP tags received from customer hosts to the correct settings for network queues, thereby decoupling host QoS policies (configurations) from architecture QoS policies (configurations). Customers can use DSCP traffic classes (also known as DSCP code points) and / or 802.1p traffic classes to represent their performance expectations. These DSCP and 802.1p classes are mapped to QoS queues in the Clos network in a manner that provides decoupling between host QoS configuration and Clos architecture QoS configuration.

[0051] To communicate QoS queuing information and ECN tags over a Clos architecture, it may be necessary to ensure that QoS queuing information is carried across multiple network domains: for example, from a Layer 2 port to a host, from a Layer 3 port to another switch, or from a VxLAN virtual Layer 2 port to another VxLAN interface on another switch. This cross-domain transmission of QoS queuing information can include carrying and enforcing QoS tags and ECN bit marking across these different network domains, as described herein.

[0052] Example Virtual Networking Architecture

[0053] The term cloud service generally refers to services provided by a cloud service provider (CSP) to users or customers on demand (e.g., via a subscription model) using systems and infrastructure (cloud infrastructure) provided by the CSP. Typically, the servers and systems that make up the CSP infrastructure are separate from the customer's own on-premises servers and systems. Therefore, customers can utilize cloud services provided by the CSP without having to purchase separate hardware and software resources for the service. Cloud services are designed to provide subscribers with simple, scalable access to applications and computing resources without requiring customers to invest in the infrastructure used to provide the service.

[0054] Several cloud service providers offer various types of cloud services. There are various types or models of cloud services, including Software as a Service (SaaS), Platform as a Service (PaaS), Infrastructure as a Service (IaaS), etc.

[0055] Customers can subscribe to one or more cloud services provided by a CSP. Customers can be any entity, such as individuals, organizations, or businesses. When a customer subscribes to or registers for a service provided by a CSP, a lease or account is created for that customer. The customer can then access one or more cloud resources associated with that account through their subscription.

[0056] As mentioned above, Infrastructure as a Service (IaaS) is a specific type of cloud computing service. In the IaaS model, a CSP provides infrastructure (called Cloud Service Provider Infrastructure or CSPI) that customers can use to build their own customizable networks and deploy customer resources. Therefore, the customer's resources and network are hosted in a distributed environment by the infrastructure provided by the CSP. This differs from traditional computing, where the customer's resources and network are hosted by the infrastructure provided by the customer.

[0057] CSPI can include interconnected high-performance computing resources forming a physical network, including various host machines, memory resources, and network resources. This physical network is also known as a substrate network or underlying network. Resources in CSPI can be distributed across one or more data centers, which may be geographically dispersed across one or more geographic regions. Virtualization software can be executed by these physical resources to provide a virtualized distributed environment. Virtualization creates an overlay network (also known as a software-based network, software-defined network, or virtual network) on the physical network. The CSPI physical network provides the underlying foundation for creating one or more overlay or virtual networks on top of the physical network. Virtual or overlay networks can include one or more Virtual Cloud Networks (VCNs). A virtual network is a layer of network abstraction that can run on top of a physical network, implemented using software virtualization technologies (e.g., hypervisors, functions performed by network virtualization devices (NVDs) (e.g., smartNICs), top-of-rack (TOR) switches, smart TORs implementing one or more functions performed by NVDs, and other mechanisms). Virtual networks can take many forms, including peer-to-peer networks, IP networks, etc. Virtual networks are typically either Layer 3 IP networks or Layer 2 VLANs. This method of virtual or overlay networking is often referred to as virtual or overlay layer 3 networking. Examples of protocols developed for virtual networks include IP-in-IP (or Generic Routing Encapsulation (GRE)), Virtual Scalable Local Area Network (VXLAN—IETF RFC 7348), Virtual Private Network (VPN) (e.g., MPLS layer 3 Virtual Private Network (RFC 4364)), VMware's NSX, GENEVE (Generic Network Virtualization Encapsulation), etc.

[0058] For IaaS, the infrastructure provided by a CSP (Center for Service Providers) can be configured to offer virtualized computing resources over a public network (e.g., the Internet). In the IaaS model, cloud service providers can host infrastructure components (e.g., servers, storage devices, network nodes (e.g., hardware), deployment software, platform virtualization (e.g., hypervisor layer), etc.). In some cases, IaaS providers can also provision various services to accompany those infrastructure components (e.g., billing, monitoring, logging, security, load balancing, and clustering, etc.). Therefore, since these services can be policy-driven, IaaS users can implement policies to drive load balancing to maintain application availability and performance. CSPI provides a collection of infrastructure and complementary cloud services that enable customers to build and run a wide range of applications and services in a highly available, hosted, distributed environment. CSPI provides high-performance computing resources and capabilities, as well as storage capacity, in a flexible virtual network securely accessible from various networked locations, such as the customer's on-premises network. When a customer subscribes to or enrolls in an IaaS service provided by a CSP, the lease created for that customer is a secure and isolated partition within the CSP, where the customer can create, organize, and manage their cloud resources.

[0059] Customers can build their own virtual networks using the compute, storage, and networking resources provided by CSPI. One or more customer resources or workloads, such as compute instances, can be deployed on these virtual networks. For example, a customer can use resources provided by CSPI to build one or more customizable and private virtual networks, called Virtual Cloud Networks (VCNs). A customer can deploy one or more customer resources, such as compute instances, on a customer VCN. Compute instances can take the form of virtual machines, bare metal instances, etc. Therefore, CSPI provides a collection of infrastructure and complementary cloud services that enable customers to build and run a wide range of applications and services in a highly available, virtually managed environment. Customers do not manage or control the underlying physical resources provided by CSPI, but they can control the operating system, storage devices, and deployed applications; and may have limited control over selected networking components (e.g., firewalls).

[0060] The CSP can provide a console that enables customers and network administrators to configure, access, and manage resources deployed in the cloud using CSPI resources. In some embodiments, the console provides a web-based user interface that can be used to access and manage the CSPI. In other embodiments, the console is a web-based application provided by the CSP.

[0061] CSPI can support single-tenant or multi-tenant architectures. In a single-tenant architecture, software (e.g., applications, databases) or hardware components (e.g., host machines or servers) serve a single customer or tenant. In a multi-tenant architecture, the software or hardware components serve multiple customers or tenants. Therefore, in a multi-tenant architecture, CSPI resources are shared among multiple customers or tenants. In a multi-tenant scenario, precautions and safeguards are implemented in CSPI to ensure that each tenant's data is isolated and invisible to other tenants.

[0062] In a physical network, a network endpoint (“endpoint”) is a computing device or system that connects to and communicates with the physical network. Network endpoints in a physical network can connect to a Local Area Network (LAN), a Wide Area Network (WAN), or other types of physical networks. Examples of traditional endpoints in a physical network include modems, hubs, bridges, switches, routers and other network devices, physical computers (or host machines), etc. Each physical device in a physical network has a fixed network address that can be used to communicate with the device. This fixed network address can be a Layer 2 address (e.g., a MAC address), a fixed Layer 3 address (e.g., an IP address), etc. In a virtualized environment or virtual network, endpoints can include various virtual endpoints, such as virtual machines hosted by components of the physical network (e.g., hosted by physical host machines). These endpoints in a virtual network are addressed by overlay addresses, such as overlay Layer 2 addresses (e.g., overlay MAC addresses) and overlay Layer 3 addresses (e.g., overlay IP addresses). Network overlays provide flexibility by allowing network administrators to move around the overlay addresses associated with network endpoints using software management (e.g., via software implementing a control plane for virtual networks). Therefore, unlike physical networks, in virtual networks, overlay addresses (e.g., overlay IP addresses) can be moved from one endpoint to another using network management software. Since virtual networks are built on top of physical networks, communication between components in a virtual network involves both the virtual network and the underlying physical network. To facilitate this communication, CSPI components are configured to learn and store mappings that map overlay addresses in the virtual network to actual physical addresses in the baseboard network, and vice versa. These mappings are then used to facilitate communication. Client traffic is encapsulated to facilitate routing within the virtual network.

[0063] Therefore, physical addresses (e.g., physical IP addresses) are associated with components in a physical network, and overlay addresses (e.g., overlay IP addresses) are associated with entities in a virtual network. Both physical IP addresses and overlay IP addresses are types of real IP addresses. These are separate from virtual IP addresses, which map to multiple real IP addresses. Virtual IP addresses provide a one-to-many mapping between virtual IP addresses and multiple real IP addresses.

[0064] Cloud infrastructure, or CSPI, is physically hosted in one or more data centers in one or more regions of the world. CSPI can include components in a physical or substrate network and virtualized components (e.g., virtual networks, compute instances, virtual machines, etc.) in a virtual network built on top of the physical network components. In some embodiments, CSPI is organized and hosted in domains, regions, and availability domains. A region is typically a localized geographical area containing one or more data centers. Regions are generally independent of each other and can be geographically distant, for example, spanning countries or even continents. For example, one region might be in Australia, another in Japan, another in India, and so on. CSPI resources are partitioned between regions, so that each region has its own independent subset of CSPI resources. Each region can provide a set of core infrastructure services and resources, such as compute resources (e.g., bare metal servers, virtual machines, containers, and related infrastructure); storage resources (e.g., block volume storage devices, file storage devices, object storage devices, archive storage devices); network resources (e.g., virtual cloud networks (VCNs), load balancing resources, connections to on-premises networks), database resources; edge networking resources (e.g., DNS); and access management and monitoring resources, etc. Each region typically has multiple paths connecting it to other regions within the domain.

[0065] Generally, applications are deployed in the areas where they are used most frequently (i.e., on infrastructure associated with that area) because using nearby resources is faster than using distant ones. Applications may also be deployed in different areas for various reasons, such as redundancy to mitigate the risk of events within a region (such as large weather systems or earthquakes), or to meet different requirements of legal jurisdictions, tax areas, and other business or social standards.

[0066] Data centers within a region can be further organized and subdivided into Availability Domains (ADs). An Availability Domain can correspond to one or more data centers located within a region. A region can consist of one or more Availability Domains. In this distributed environment, CSPI resources are either region-specific, such as Virtual Cloud Networks (VCNs), or Availability Domain-specific, such as compute instances.

[0067] Availability Zones (ADs) within a region are isolated from each other, fault-tolerant, and configured to make simultaneous failures highly unlikely. This is achieved by ensuring that ADs do not share critical infrastructure resources (such as networking, physical cabling, cable paths, cable entry points, etc.), making a failure at one AD within a region unlikely to affect the availability of other ADs in the same region. ADs within the same region can be interconnected via low-latency, high-bandwidth networks, enabling high-availability connectivity to other networks (e.g., the internet, customer on-premises networks, etc.) and allowing for replication systems across multiple ADs to achieve high availability and disaster recovery. Cloud services use multiple ADs to ensure high availability and prevent resource failures. As the infrastructure provided by an IaaS provider grows, more regions and ADs, along with additional capacity, can be added. Traffic between availability domains is typically encrypted.

[0068] In some embodiments, regions are grouped into domains. A domain is a logical collection of regions. Domains are isolated from each other and do not share any data. Regions within the same domain can communicate with each other, but regions in different domains cannot. A customer's lease or account with the CSP resides in a single domain and can be distributed across one or more regions belonging to that domain. Typically, when a customer subscribes to an IaaS service, a lease or account is created for that customer in a region within the domain that the customer designates (called the "primary" region). A customer can extend their lease to one or more other regions within the domain. A customer cannot access regions that are not within the domain where their lease is located.

[0069] IaaS providers can offer multiple domains, each catering to a specific set of customers or users. For example, a business domain can be offered for business customers. As another example, a domain can be offered for customers within a specific country. As yet another example, a government domain can be offered for governments, etc. For instance, a government domain can cater to a specific government and may have a higher level of security than the business domain. For example, Oracle Cloud Infrastructure (OCI) currently offers domains for the business region and two domains for the government cloud region (e.g., FedRAMP licensed and IL5 licensed).

[0070] In some embodiments, an Active Directory (AD) can be subdivided into one or more fault domains. A fault domain is a grouping of infrastructure resources within an AD to provide anti-affinity. Fault domains allow for the distribution of compute instances such that these instances do not reside on the same physical hardware within a single AD. This is known as anti-affinity. A fault domain refers to a collection of hardware components (computers, switches, etc.) that share a single point of failure. Compute pools are logically divided into fault domains. Therefore, a hardware failure or compute hardware maintenance event affecting one fault domain does not affect instances in other fault domains. Depending on the embodiment, the number of fault domains for each AD can vary. For example, in some embodiments, each AD contains three fault domains. Fault domains act as logical data centers within the AD.

[0071] When a customer subscribes to IaaS services, resources from CSPI are provisioned to the customer and associated with the customer's lease. Customers can use these provisioned resources to build private networks and deploy resources on those networks. Customer networks hosted in the cloud by CSPI are called Virtual Cloud Networks (VCNs). Customers can use the CSPI resources allocated to them to set up one or more VCNs. A VCN is a virtual or software-defined private network. Customer resources deployed in a customer's VCN can include compute instances (e.g., virtual machines, bare metal instances) and other resources. These compute instances can represent various customer workloads, such as applications, load balancers, databases, etc. Compute instances deployed on a VCN can communicate with publicly accessible endpoints (“public endpoints”) via public networks (such as the Internet), with other instances in the same VCN or other VCNs (e.g., other VCNs belonging to the customer or VCNs not belonging to the customer), with the customer's on-premises data center or network, and with service endpoints and other types of endpoints.

[0072] CSPs can use CSPIs to provide various services. In some cases, CSPI clients can function as service providers themselves and use CSPI resources to provide services. Service providers can expose service endpoints, characterized by identifying information such as IP addresses, DNS names, and ports. Client resources (e.g., compute instances) can access a specific service by visiting the service endpoints exposed by the service for that specific service. These service endpoints are generally publicly accessible to users via public communication networks such as the Internet using the public IP addresses associated with the endpoints. Publicly accessible network endpoints are sometimes also referred to as public endpoints.

[0073] In some embodiments, a service provider may expose the service via an endpoint (sometimes referred to as a service endpoint) for the service. Clients of the service can then use this service endpoint to access the service. In some implementations, the service endpoint provided for the service can be accessed by multiple clients intending to consume the service. In other implementations, a dedicated service endpoint can be provided to a client, so that only that client can use that dedicated service endpoint to access the service.

[0074] In some embodiments, when a VCN is created, it is associated with a Private Overlay Classless Inter-Domain Routing (CIDR) address space, which refers to a set of private overlay IP addresses (e.g., 10.0 / 16) assigned to the VCN. A VCN includes associated subnets, routing tables, and gateways. A VCN resides within a single region but can span one or more of the availability domains within that region. A gateway is a virtual interface configured for the VCN and enables communication between the VCN and one or more endpoints outside the VCN. One or more different types of gateways can be configured for a VCN to enable communication to and from different types of endpoints.

[0075] A VCN can be subdivided into one or more subnets, such as one or more subnets. Therefore, a subnet is a configurable unit or subdivision that can be created within a VCN. A VCN can have one or more subnets. Each subnet within a VCN is associated with a contiguous range of overlay IP addresses (e.g., 10.0.0.0 / 24 and 10.0.1.0 / 24), which do not overlap with other subnets within that VCN and represent a subset of the VCN's address space.

[0076] Each compute instance is associated with a Virtual Network Interface Card (VNIC), which enables the compute instance to participate in subnets within a VCN. A VNIC is the logical representation of a physical network interface card (NIC). Generally, a VNIC is the interface between an entity (e.g., a compute instance, a service) and the virtual network. A VNIC exists within a subnet and has one or more associated IP addresses, along with associated security rules or policies. A VNIC is equivalent to a Layer 2 port on a switch. A VNIC is attached to both the compute instance and the subnet within the VCN. The VNIC associated with a compute instance makes the compute instance part of the VCN's subnet and enables the compute instance to communicate (e.g., send and receive packets) with endpoints on the same subnet as the compute instance, with endpoints in different subnets within the VCN, or with endpoints outside the VCN. Therefore, the VNIC associated with a compute instance determines how the compute instance connects to endpoints inside and outside the VCN. When a compute instance is created and added to a subnet within a VCN, a VNIC for the compute instance is created and associated with that compute instance. For a subnet that includes a set of compute instances, the subnet contains a VNIC corresponding to that set of compute instances, and each VNIC is attached to a compute instance within that set of compute instances.

[0077] A private overlay IP address is assigned to each compute instance via the VNIC associated with it. This private overlay network IP address is assigned to the VNIC associated with the compute instance when the compute instance is created and is used to route traffic to and from the compute instance. All VNICs within a given subnet use the same routing table, security list, and DHCP options. As described above, each subnet within a VCN is associated with a contiguous range of overlay IP addresses (e.g., 10.0.0.0 / 24 and 10.0.1.0 / 24) that do not overlap with other subnets within that VCN and represent a subset of the VCN's address space. For a VNIC on a specific subnet of a VCN, the private overlay IP address assigned to that VNIC is an address from the contiguous range of overlay IP addresses allocated to the subnet.

[0078] In some embodiments, in addition to a private overlay IP address, a compute instance may optionally be assigned additional overlay IP addresses, such as one or more public IP addresses, for example, if in a public subnet. These multiple addresses may be assigned either on the same VNIC or on multiple VNICs associated with the compute instance. However, each instance has a primary VNIC, which is created during instance startup and associated with the overlay private IP address assigned to that instance—this primary VNIC cannot be deleted. Additional VNICs, called secondary VNICs, can be added to existing instances in the same availability domain as the primary VNIC. All VNICs are in the same availability domain as the instance. Secondary VNICs may reside in a subnet within the same VCN as the primary VNIC, or in a different subnet within the same VCN or different VCNs.

[0079] If a compute instance is in a public subnet, it can optionally be assigned a public IP address. When creating a subnet, it can be specified as either a public or private subnet. A private subnet means that resources within the subnet (such as compute instances) and associated VNICs cannot have public overriding IP addresses. A public subnet means that resources within the subnet and associated VNICs can have public IP addresses. Customers can specify that a subnet exists within a single availability domain or across multiple availability domains in regions or domains.

[0080] As described above, a VCN can be subdivided into one or more subnets. In some embodiments, a virtual router (VR) configured for the VCN (referred to as a VCN VR or simply VR) enables communication between the subnets of the VCN. For a subnet within the VCN, the VR represents a logical gateway for that subnet, enabling that subnet (i.e., compute instances on that subnet) to communicate with endpoints on other subnets within the VCN and other endpoints outside the VCN. The VCN VR is a logical entity configured to route traffic between the VNIC within the VCN and the virtual gateway (“gateway”) associated with the VCN. The following section discusses… Figure 1Further description of the gateway. A VCN VR is a Layer 3 / IP layer concept. In one embodiment, there exists a VCN VR for a VCN, where the VCN VR has a potentially unlimited number of IP-addressable ports, one port for each subnet of the VCN. In this way, the VCN VR has a different IP address for each subnet within the VCN to which the VCN VR is attached. The VR also connects to various gateways configured for the VCN. In some embodiments, a specific overlay IP address within the overlay IP address range for a subnet is reserved for the port of the VCN VR for that subnet. For example, consider a VCN with two subnets, associated with address ranges 10.0 / 16 and 10.1 / 16. For the first subnet in the VCN with an address range of 10.0 / 16, addresses within this range are reserved for the port of the VCN VR for that subnet. In some cases, the first IP address within the range can be reserved for the VCN VR. For example, for a subnet covering the IP address range of 10.0 / 16, the IP address 10.0.0.1 could be reserved for the port of the VCN VR for that subnet. For a second subnet within the same VCN with an address range of 10.1 / 16, the VCN VR can have a port for the second subnet with the IP address 10.1.0.1. The VCN VR has a different IP address for each subnet within the VCN.

[0081] In some other embodiments, each subnet within a VCN may have its own associated VR, which can be addressed by the subnet using a reserved or default IP address associated with the VR. For example, the reserved or default IP address may be the first IP address in a range of IP addresses associated with the subnet. The VNICs within the subnet can use this default or reserved IP address to communicate with the VR associated with the subnet (e.g., send and receive packets). In this embodiment, the VR is the ingress / egress point of the subnet. The VR associated with a subnet within the VCN can communicate with other VRs associated with other subnets within the VCN. The VR can also communicate with the gateway associated with the VCN. The VR functionality of a subnet runs on or is performed by one or more NVDs that perform VNIC functionality for the VNICs within the subnet.

[0082] You can configure routing tables, security rules, and DHCP options for a VCN. A routing table is a virtual routing table used by the VCN and contains rules that route traffic from subnets within the VCN to destinations outside the VCN via gateways or specially configured instances. You can customize the VCN's routing table to control how packets are forwarded / routed to and from the VCN. DHCP options refer to configuration information automatically provided to the instance when it starts up.

[0083] Security rules configured for a VCN represent overlay firewall rules used by the VCN. Security rules can include ingress and egress rules, specifying the types of traffic allowed to enter and exit the VCN instance (e.g., based on protocol and port). Clients can choose whether a given rule is stateful or stateless. For example, a client can allow a set of incoming SSH traffic from anywhere to the instance by setting a stateful ingress rule with source CIDR 0.0.0.0 / 0 and destination TCP port 22. Security rules can be implemented using network security groups or security lists. A network security group consists of a set of security rules that apply only to resources within that group. A security list, on the other hand, includes rules applicable to all resources in any subnet using that security list. A default security list with default security rules can be provided to the VCN. DHCP options configured for the VCN provide configuration information that is automatically provided to instances within the VCN at instance startup.

[0084] In some embodiments, configuration information for a VCN is determined and stored by the VCN control plane. For example, configuration information for a VCN may include information about: the address range associated with the VCN, subnets and associated information within the VCN, one or more VRs associated with the VCN, compute instances and associated VNICs within the VCN, NVDs (e.g., VNICs, VRs, gateways) that perform various virtualization network functions associated with the VCN, status information for the VCN, and other VCN-related information. In some embodiments, a VCN distribution service publishes configuration information stored by the VCN control plane or a portion thereof to the NVD. The distributed information can be used to update information stored and used by the NVD (e.g., forwarding tables, routing tables, etc.) to forward packets to or from compute instances within the VCN.

[0085] In some embodiments, the creation of VCNs and subnets is handled by the VCN control plane (CP), and the initiation of compute instances is handled by the compute control plane. The compute control plane is responsible for allocating physical resources to the compute instances and then invoking the VCN control plane to create VNICs and attach them to the compute instances. The VCN CP also maps VCN data to the VCN data plane, which is configured to perform packet forwarding and routing functions. In some embodiments, the VCN CP provides a distribution service responsible for providing updates to the VCN data plane. Examples of VCN control planes are also available in... Figure 11 , Figure 12 , Figure 13 and Figure 14 It is depicted in (see reference numerals 1116, 1216, 1316 and 1416) and described below.

[0086] Customers can create one or more VCNs using resources hosted by CSPI. Compute instances deployed on a customer's VCN can communicate with different endpoints. These endpoints can include endpoints hosted by CSPI and endpoints external to CSPI.

[0087] Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 11 , Figure 12 , Figure 13 and Figure 15 The document describes various architectures for implementing cloud-based services using CSPI, and these are described below. Figure 1 This is a high-level diagram of a distributed environment 100, illustrating an overlay or client VCN hosted by CSPI according to certain embodiments. Figure 1 The distributed environment described includes multiple components in the overlay network. Figure 1 The distributed environment 100 depicted herein is merely an example and is not intended to unduly limit the scope of the claimed embodiments. Many variations, substitutions, and modifications are possible. For example, in some implementations, Figure 1 The distributed environment described in the text can have more than Figure 1 The more or fewer systems or components shown can be combined into two or more systems, or can have different system configurations or arrangements.

[0088] like Figure 1 As illustrated in the example, distributed environment 100 includes a CSPI 101 that provides services and resources that customers can subscribe to and use to build their Virtual Cloud Network (VCN). In some embodiments, CSPI 101 provides IaaS services to subscribing customers. Data centers within CSPI 101 can be organized into one or more regions. Figure 1 The example shown is a region "Region US" 102. The customer has already configured customer VCN 104 for Region 102. The customer can deploy various compute instances on VCN 104, which can include virtual machines or bare metal instances. Examples of instances include applications, databases, load balancers, etc.

[0089] exist Figure 1 In the embodiment depicted, customer VCN 104 includes two subnets, namely "Subnet-1" and "Subnet-2", each with its own CIDR IP address range. Figure 1In this configuration, subnet-1 covers the IP address range of 10.0 / 16, and subnet-2 covers the address range of 10.1 / 16. VCN Virtual Router 105 represents the logical gateway for the VCN, enabling communication between subnets of VCN 104 and with other endpoints outside the VCN. VCN VR 105 is configured to route traffic between the VNICs within VCN 104 and the gateway associated with VCN 104. VCN VR 105 provides a port for each subnet of VCN 104. For example, VR 105 could provide a port with IP address 10.0.0.1 for subnet-1 and a port with IP address 10.1.0.1 for subnet-2.

[0090] Multiple compute instances can be deployed on each subnet, where compute instances can be virtual machine instances and / or bare metal instances. Compute instances within a subnet can be hosted by one or more host machines within CSPI 101. Compute instances participate in the subnet via a VNIC associated with the compute instance. For example, as... Figure 1 As shown, compute instance C1 becomes part of subnet-1 via the VNIC associated with it. Similarly, compute instance C2 becomes part of subnet-1 via the VNIC associated with it. In a similar manner, multiple compute instances (which can be virtual machine instances or bare metal instances) can be part of subnet-1. Each compute instance is assigned a private overlay IP address and MAC address via its associated VNIC. For example, in... Figure 1 In this subnet, compute instance C1 has an overlay IP address of 10.0.0.2 and a MAC address of M1, while compute instance C2 has a private overlay IP address of 10.0.0.3 and a MAC address of M2. Each compute instance in subnet-1 (including compute instances C1 and C2) has a default route to VCN VR 105 using IP address 10.0.0.1, which is the IP address of the port of VCN VR 105 used in subnet-1.

[0091] Multiple compute instances, including virtual machine instances and / or bare metal instances, can be deployed on subnet-2. For example, such as Figure 1 As shown, compute instances D1 and D2 become part of subnet-2 via the VNIC associated with the respective compute instance. Figure 1 In the illustrated embodiment, compute instance D1 has an overlay IP address of 10.1.0.2 and a MAC address of MM1, while compute instance D2 has a private overlay IP address of 10.1.0.3 and a MAC address of MM2. Each compute instance in subnet-2 (including compute instances D1 and D2) has a default route to VCN VR 105 using IP address 10.1.0.1, which is the IP address of the port of VCN VR 105 in subnet-2.

[0092] VCN A 104 may also include one or more load balancers. For example, a load balancer can be provided for a subnet, and the load balancer can be configured to load balance traffic across multiple compute instances on the subnet. Load balancers can also be provided to load balance traffic across subnets within a VCN.

[0093] A specific compute instance deployed on VCN 104 can communicate with a variety of different endpoints. These endpoints can include endpoints hosted by CSPI 200 and endpoints outside of CSPI 200. Endpoints hosted by CSPI 101 can include: endpoints on the same subnet as the specific compute instance (e.g., communication between two compute instances in subnet-1); endpoints on different subnets but within the same VCN (e.g., communication between a compute instance in subnet-1 and a compute instance in subnet-2); endpoints in different VCNs within the same region (e.g., communication between a compute instance in subnet-1 and endpoints in VCNs in the same region 106 or 110, or communication between a compute instance in subnet-1 and an endpoint in service point 110 within the same region); or endpoints in VCNs in different regions (e.g., communication between a compute instance in subnet-1 and endpoints in VCNs in different regions 108). Compute instances in subnets hosted by CSPI 101 can also communicate with endpoints not hosted by CSPI 101 (i.e., outside of CSPI 101). These external endpoints include endpoints in the customer’s on-premises network 116, endpoints in other remote cloud-hosted networks 118, public endpoints 114 that are accessible via public networks such as the Internet, and other endpoints.

[0094] VNICs associated with source and destination compute instances facilitate communication between compute instances on the same subnet. For example, compute instance C1 in subnet-1 might want to send a packet to compute instance C2 in subnet-1. For a packet originating from the source compute instance and destined for another compute instance in the same subnet, the packet is first processed by the VNIC associated with the source compute instance. The processing performed by the VNIC associated with the source compute instance may include determining the packet's destination information from the packet header, identifying any policies (e.g., security lists) configured for the VNIC associated with the source compute instance, determining the next hop for the packet, performing any packet encapsulation / decapsulation functions as needed, and then forwarding / routing the packet to the next hop to facilitate communication to its intended destination. When the destination compute instance is in the same subnet as the source compute instance, the VNIC associated with the source compute instance is configured to identify the VNIC associated with the destination compute instance and forward the packet to that VNIC for processing. The VNIC associated with the destination compute instance then performs the processing and forwards the packet to the destination compute instance.

[0095] For packets to be transferred from compute instances in a subnet to endpoints in different subnets within the same VCN, communication is facilitated by the VNIC associated with the source and destination compute instances, as well as the VCN VR. For example, if Figure 1 If compute instance C1 in subnet-1 wants to send a packet to compute instance D1 in subnet-2, the packet is first processed by the VNIC associated with compute instance C1. The VNIC associated with compute instance C1 is configured to route the packet to VCN VR 105 using the default route or port 10.0.0.1 of the VCN VR. VCN VR 105 is configured to route the packet to subnet-2 using port 10.1.0.1. Then, the VNIC associated with D1 receives and processes the packet and forwards it to compute instance D1.

[0096] For packets to be transferred from a compute instance in VCN 104 to an endpoint outside VCN 104, communication is facilitated by the VNIC associated with the source compute instance, VCN VR 105, and the gateway associated with VCN 104. One or more types of gateways can be associated with VCN 104. A gateway is an interface between a VCN and another endpoint located outside the VCN. A gateway is a Layer 3 / IP concept and enables a VCN to communicate with endpoints outside the VCN. Therefore, a gateway facilitates traffic flow between a VCN and other VCNs or networks. Various different types of gateways can be configured for a VCN to facilitate different types of communication with different types of endpoints. Depending on the gateway, communication can occur over a public network (e.g., the Internet) or over a private network. Various communication protocols can be used for these communications.

[0097] For example, compute instance C1 might want to communicate with an endpoint outside of VCN 104. The packet can first be processed by the VNIC associated with the source compute instance C1. The VNIC processing determines that the packet's destination is outside subnet-1 of C1. The VNIC associated with C1 can then forward the packet to VCN VR 105 for VCN 104. VCN VR 105 then processes the packet and, as part of the processing, determines a specific gateway associated with VCN 104 as the next hop for the packet based on its destination. VCN VR 105 can then forward the packet to the specific identified gateway. For example, if the destination is an endpoint within a customer's on-premises network, the packet can be forwarded by VCN VR 105 to the Dynamic Routing Gateway (DRG) gateway 122 configured for VCN 104. The packet can then be forwarded from the gateway to the next hop to facilitate delivery to its final intended destination.

[0098] Various types of gateways can be configured for a VCN. Examples of gateways that can be configured for a VCN are available in [link / details]. Figure 1 It is depicted in [the text] and described below. Examples of gateways associated with VCNs are also [described in the text]. Figure 11 , Figure 12 , Figure 13 and Figure 14 The gateways are depicted (e.g., referenced by reference numerals 1134, 1136, 1138, 1234, 1236, 1238, 1334, 1336, 1338, 1434, 1436, and 1438) and are described below. Figure 1As depicted in the embodiments, a Dynamic Routing Gateway (DRG) 122 can be added to or associated with a customer VCN 104 and provides a path for private network traffic communication between the customer VCN 104 and another endpoint, which can be the customer's on-premises network 116, a VCN 108 in a different region of CSPI 101, or another remote cloud network 118 not hosted by CSPI 101. The customer's on-premises network 116 can be a customer network or customer data center built using the customer's resources. Access to the customer's on-premises network 116 is generally very restricted. For customers who have both a customer's on-premises network 116 and one or more VCNs 104 deployed or hosted in the cloud by CSPI 101, the customer may want their on-premises network 116 and their cloud-based VCN 104 to be able to communicate with each other. This allows customers to build extended hybrid environments that include the customer's VCN 104 hosted by CSPI 101 and their on-premises network 116. DRG 122 enables this communication. To enable this type of communication, a communication channel 124 is set up, with one endpoint located in the customer's on-premises network 116 and the other endpoint located in CSPI 101 and connected to the customer's VCN 104. Communication channel 124 can be over a public communication network (such as the Internet) or a private communication network. Various communication protocols can be used, such as IPsec VPN technology over a public communication network (such as the Internet), Oracle's FastConnect technology using a private network instead of a public network, etc. The device or equipment forming one endpoint of communication channel 124 in the customer's on-premises network 116 is referred to as a customer field equipment (CPE), such as... Figure 1 The CPE126 is depicted in the diagram. On the CSPI 101 side, the endpoint can be a host machine executing DRG 122.

[0099] In some embodiments, a remote peering connection (RPC) can be added to the DRG, which allows a customer to peer one VCN to another VCN in a different region. Using such an RPC, customer VCN 104 can use DRG 122 to connect to VCN 108 in another region. DRG 122 can also be used to communicate with other remote cloud networks 118 (such as Microsoft Azure, Amazon AWS, etc.) not hosted by CSPI 101.

[0100] like Figure 1As shown, an Internet Gateway (IGW) 120 can be configured for customer VCN 104, enabling compute instances on VCN 104 to communicate with a public endpoint 114 accessible via a public network, such as the Internet. IGW 1120 is a gateway connecting the VCN to a public network such as the Internet. IGW 120 enables public subnets within the VCN (such as VCN 104), where resources have publicly overridden IP addresses, to directly access a public endpoint 112 on the public network 114 (such as the Internet). Using IGW 120, connections can be initiated from subnets within VCN 104 or from the Internet.

[0101] A Network Address Translation (NAT) gateway 128 can be configured for a customer's VCN 104, enabling cloud resources within the customer's VCN that do not have dedicated public overlay IP addresses to access the internet, and doing so to direct incoming internet connections (e.g., L4-L7 connections) without exposing those resources. This allows private subnets within the VCN (such as private subnet-1 in VCN 104) to privately access public endpoints on the internet. With a NAT gateway, connections can only originate from private subnets to the public internet, not from the internet to private subnets.

[0102] In some embodiments, a Service Gateway (SGW) 126 can be configured for customer VCN 104, providing a path for private network traffic between VCN 104 and service endpoints supported in service network 110. In some embodiments, service network 110 may be provided by a CSP and may offer a variety of services. An example of such a service network is Oracle's service network, which provides a variety of services available to customers. For example, compute instances (e.g., database systems) in a private subnet of customer VCN 104 can back up data to service endpoints (e.g., object storage devices) without requiring public IP addresses or access to the Internet. In some embodiments, a VCN may have only one SGW, and connections can only originate from subnets within the VCN, not from service network 110. If a VCN is peered to another, resources in the other VCN typically cannot access the SGW. Resources in the on-premises network of a VCN connected using FastConnect or VPN Connect can also use the service gateway configured for that VCN.

[0103] In some implementations, the SGW 126 uses the concept of a Service Classless Inter-Domain Routing (CIDR) label, which is a string representing all regional public IP address ranges for the service or group of services of interest. Customers use the Service CIDR label when configuring the SGW and associated routing rules to control traffic to the service. If the public IP address of the service changes in the future, customers can optionally use it when configuring security rules without having to adjust them.

[0104] Local peering gateway (LPG) 132 is a gateway that can be added to customer VCN 104 and enable VCN 104 to peer with another VCN in the same region. Peering means that VCNs communicate using private IP addresses, and traffic does not need to traverse public networks (such as the Internet) or be routed through the customer's on-premises network 116. In a preferred embodiment, a VCN has a separate LPG for each peer it establishes. Local peering, or VCN peering, is a common practice for establishing network connectivity between different applications or infrastructure management functions.

[0105] Service providers (such as those providing services in service network 110) can offer access to services using different access models. Under the public access model, a service can be exposed as a public endpoint that is publicly accessible by compute instances within a customer's VCN via a public network (such as the Internet), and / or can be privately accessed via SGW 126. Under a specific private access model, a service can be accessed as a private IP endpoint within a private subnet of the customer's VCN. This is called private endpoint (PE) access and enables service providers to expose their services as instances within the customer's private network. A private endpoint resource represents a service within the customer's VCN. Each PE is represented as a VNIC (called a PE-VNIC, with one or more private IPs) within the customer's VCN in a subnet selected by the customer. Thus, the PE provides a way to present services within a private customer VCN subnet using a VNIC. Because the endpoint is exposed as a VNIC, all characteristics associated with the VNIC (such as routing rules, security lists, etc.) are now available for the PE VNIC.

[0106] Service providers can register their services to enable access via PE. Providers can associate policies with services, which restricts the visibility of the service to customer leases. Providers can register multiple services under a single Virtual IP address (VIP), especially for multi-tenant services. Multiple such private endpoints (across multiple VCNs) can represent the same service.

[0107] Compute instances in a private subnet can then access the service using the private IP address or service DNS name of the PE VNIC. Compute instances in a customer VCN can access the service by sending traffic to the private IP address of the PE in the customer VCN. A Private Access Gateway (PAGW) 130 is a gateway resource that can be attached to a service provider VCN (e.g., a VCN in service network 110), which acts as the ingress / egress point for all traffic from / to the private endpoints of the customer subnet. PAGW 130 enables providers to scale the number of PE connections without utilizing their internal IP address resources. A provider only needs to configure one PAGW for any number of services registered in a single VCN. A provider can represent a service as a private endpoint in multiple VCNs of one or more customers. From the customer's perspective, the PE VNIC is not an instance attached to the customer, but rather appears to be attached to the service that the customer wants to interact with. Traffic to the private endpoint is routed to the service via PAGW 130. These are referred to as customer-to-service private connections (C2S connections).

[0108] The PE concept can also be used to extend private access to services to the customer's on-premises network and data center by allowing traffic to flow through FastConnect / IPsec links and private endpoints in the customer's VCN. Private access to services can also be extended to the customer's peering VCN by allowing traffic to flow between the LPG 132 and the PE in the customer's VCN.

[0109] Customers can control routing within a VCN at the subnet level, allowing them to specify which subnets within a customer's VCN (such as VCN104) use each gateway. The VCN's routing table is used to determine whether traffic is allowed to leave the VCN via a specific gateway. For example, in a given instance, a routing table for a public subnet within customer VCN 104 might send non-local traffic via IGW 120. A routing table for a private subnet within the same customer VCN 104 might send traffic destined for a CSP service via SGW 126. All remaining traffic can be sent via NAT gateway 128. The routing table only controls traffic flowing out of the VCN.

[0110] Security lists associated with a VCN are used to control traffic entering the VCN via a gateway through inbound connections. All resources within a subnet use the same routing tables and security lists. Security lists can be used to control specific types of traffic allowed to enter or leave instances within a subnet of the VCN. Security list rules can include inbound and outbound rules. For example, inbound rules can specify allowed source address ranges, while outbound rules can specify allowed destination address ranges. Security rules can specify specific protocols (e.g., TCP, ICMP), specific ports (e.g., port 22 for SSH, port 3389 for Windows RDP), etc. In some implementations, the instance's operating system can enforce its own firewall rules that conform to the security list rules. Rules can be stateful (e.g., tracking connections and automatically allowing responses without explicit security list rules for response traffic) or stateless.

[0111] Access from a customer's VCN (i.e., through resources or compute instances deployed on VCN 104) can be categorized as public access, private access, or dedicated access. Public access refers to an access model that uses a public IP address or NAT to access a public endpoint. Private access enables customer workloads with private IP addresses within VCN 104 (e.g., resources in a private subnet) to access services without traversing a public network such as the Internet. In some embodiments, CSPI 101 enables customer VCN workloads with private IP addresses to access the service's (public service endpoint) using a service gateway. Thus, the service gateway provides a private access model by establishing a virtual link between the customer's VCN and the public endpoint of the service residing outside the customer's private network.

[0112] Furthermore, CSPI can provide dedicated public access using technologies such as FastConnect public peering, where on-premises instances can access one or more services within a customer's VCN using FastConnect connections without traversing public networks such as the internet. CSPI can also provide dedicated private access using FastConnect private peering, where on-premises instances with private IP addresses can access a customer's VCN workloads using FastConnect connections. FastConnect is a network connectivity alternative to using the public internet to connect a customer's on-premises network to CSPI and its services. Compared to internet-based connections, FastConnect offers a simple, flexible, and cost-effective way to create dedicated and private connections with higher bandwidth options and a more reliable and consistent network experience.

[0113] Figure 1The accompanying description above describes the various virtualized components in the example virtual network. As mentioned above, the virtual network is built on the underlying physical or substrate network. Figure 2 A simplified architecture diagram of the physical components within the physical network of the CSPI 200, which provides the underlying layer for virtual networks according to certain embodiments, is depicted. As shown, the CSPI 200 provides a distributed environment including components and resources (e.g., compute, storage, and network resources) provided by a cloud service provider (CSP). These components and resources are used to provide cloud services (e.g., IaaS services) to subscribed customers (i.e., customers who have subscribed to one or more services provided by the CSP). Based on the services subscribed to by the customer, a subset of the resources of the CSPI 200 (e.g., compute, storage, and network resources) is provisioned to the customer. The customer can then use the physical compute, storage, and networking resources provided by the CSPI 200 to build their own cloud-based (i.e., CSPI-hosted) customizable and private virtual networks. As indicated above, these customer networks are referred to as Virtual Cloud Networks (VCNs). Customers can deploy one or more customer resources, such as compute instances, on these customer VCNs. Compute instances can take the form of virtual machines, bare metal instances, etc. The CSPI 200 provides a collection of infrastructure and complementary cloud services, enabling customers to build and run a wide range of applications and services in a highly available managed environment.

[0114] exist Figure 2 In the example embodiment depicted, the physical components of CSPI 200 include one or more physical host machines or physical servers (e.g., 202, 206, 208), network virtualization devices (NVDs) (e.g., 210, 212), top-of-rack (TOR) switches (e.g., 214, 216), and a physical network (e.g., 218), as well as switches within physical network 218. The physical host machines or servers can host and execute various compute instances participating in one or more subnets of the VCN. Compute instances can include virtual machine instances and bare metal instances. For example, Figure 1 The various computational examples described in the text can be derived from... Figure 2 The physical host machine described in the diagram is used for hosting virtual machine compute instances in a VCN. Virtual machine compute instances in a VCN can be executed by one host machine or multiple different host machines. A physical host machine can also host virtual host machines, container-based hosts, or functions, etc. Figure 1 The VNIC and VCN VR described in the text can be generated by Figure 2 The NVD execution described in the text. Figure 1 The gateway described in the text can be... Figure 2 The host machine and / or NVD execution described in the document.

[0115] A host machine or server can execute a hypervisor (also known as a virtual machine monitor or VMM) that creates and enables virtualized environments on the host machine. Virtualization or virtualized environments facilitate cloud-based computing. One or more compute instances can be created, executed, and managed on the host machine by a hypervisor on that host machine. The hypervisor on the host machine enables the host machine's physical computing resources (e.g., compute, storage, and network resources) to be shared among various compute instances executed by the host machine.

[0116] For example, such as Figure 2 As depicted, host machines 202 and 208 execute hypervisors 260 and 266, respectively. These hypervisors can be implemented using software, firmware, or hardware, or a combination thereof. Typically, a hypervisor is a process or software layer residing above the host machine's operating system (OS), which in turn executes on the host machine's hardware processor. Hypervisors provide a virtualized environment by enabling the host machine's physical computing resources (e.g., processing resources such as processors / cores, memory resources, network resources) to be shared among various virtual machine computing instances executed by the host machine. For example, in... Figure 2 In this configuration, the hypervisor 260 can reside on top of the operating system of the host machine 202 and enable the computing resources (e.g., processing, memory, and network resources) of the host machine 202 to be shared among computing instances (e.g., virtual machines) executed by the host machine 202. Virtual machines can have their own operating systems (called guest operating systems), which can be the same as or different from the host machine's operating system. The operating system of a virtual machine executed by the host machine can be the same as or different from the operating system of another virtual machine executed by the same host machine. Therefore, the hypervisor enables multiple operating systems to be executed simultaneously, while sharing the same computing resources of the host machine. Figure 2 The host machines described in the text may have the same or different types of management programs.

[0117] A compute instance can be a virtual machine instance or a bare metal instance. Figure 2 In the diagram, compute instance 268 on host machine 202 and compute instance 274 on host machine 208 are examples of virtual machine instances. Host machine 206 is an example of a bare metal instance provided to a customer.

[0118] In some cases, an entire host machine can be provisioned to a single customer, and one or more compute instances (or virtual machines or bare metal instances) hosted by that host machine all belong to the same customer. In other cases, the host machine can be shared among multiple customers (i.e., multiple tenants). In this multi-tenancy scenario, the host machine can host virtual machine compute instances belonging to different customers. These compute instances can be members of different VCNs for different customers. In some embodiments, bare metal compute instances are hosted by bare metal servers without a hypervisor. When provisioning bare metal compute instances, a single customer or tenant maintains control over the physical CPU, memory, and network interfaces of the host machine hosting the bare metal instance, and the host machine is not shared with other customers or tenants.

[0119] As previously mentioned, each compute instance as part of a VCN is associated with a VNIC that enables that compute instance to become a member of a subnet of the VCN. The VNIC associated with a compute instance facilitates communication to and from the compute instance. The VNIC is associated with the compute instance when the compute instance is created. In some embodiments, for compute instances executed by a host machine, the VNIC associated with that compute instance is executed by an NVD connected to the host machine. For example, in Figure 2 In this example, host machine 202 executes a virtual machine compute instance 268 associated with VNIC 276, and VNIC 276 is executed by NVD 210 connected to host machine 202. As another example, a bare metal instance 272 hosted by host machine 206 is associated with VNIC 280 executed by NVD 212 connected to host machine 206. As yet another example, VNIC 284 is associated with compute instance 274 executed by host machine 208, and VNIC 284 is executed by NVD 212 connected to host machine 208.

[0120] For compute instances hosted by a host machine, NVDs connected to that host machine also execute VCN VR corresponding to the VCN where the compute instance is a member. For example, in Figure 2 In the embodiment depicted, NVD 210 executes VCN VR 277 corresponding to a VCN that is a member of compute instance 268. NVD 212 may also execute one or more VCN VR 283 corresponding to a VCN that corresponds to a compute instance hosted by host machines 206 and 208.

[0121] The host machine may include one or more network interface cards (NICs) that enable the host machine to connect to other devices. The NIC on the host machine may provide one or more ports (or interfaces) that allow the host machine to communicate with another device. For example, the host machine may use one or more ports (or interfaces) provided on the host machine and the NVD to connect to the NVD. The host machine may also connect to other devices (such as another host machine).

[0122] For example, in Figure 2 In this configuration, host machine 202 is connected to NVD 210 via link 220, which extends between port 234 provided by NIC 232 of host machine 202 and port 236 of NVD 210. Host machine 206 is connected to NVD 212 via link 224, which extends between port 246 provided by NIC 244 of host machine 206 and port 248 of NVD 212. Host machine 208 is connected to NVD 212 via link 226, which extends between port 252 provided by NIC 250 of host machine 208 and port 254 of NVD 212.

[0123] The NVD is then connected to top-of-rack (TOR) switches via communication links, which are connected to physical network 218 (also known as a switch architecture). In some embodiments, the links between the host machine and the NVD, and between the NVD and the TOR switches, are Ethernet links. For example, in Figure 2 In this configuration, NVDs 210 and 212 are connected to TOR switches 214 and 216 via links 228 and 230, respectively. In some embodiments, links 220, 224, 226, 228, and 230 are Ethernet links. The collection of host machines and NVDs connected to the TOR is sometimes referred to as a rack.

[0124] Physical network 218 provides a communication architecture that enables TOR switches to communicate with each other. Physical network 218 can be a multi-layer network. In some implementations, physical network 218 is a multi-layer Clos network of switches, where TOR switches 214 and 216 represent leaf-level nodes of the multi-layer and multi-node physical switching network 218. Different Clos network configurations are possible, including but not limited to Layer 2 networks, Layer 3 networks, Layer 4 networks, Layer 5 networks, and general "n"-layer networks. Examples of Clos networks are provided in... Figure 5 It is depicted in the middle and described below.

[0125] Various connection configurations can exist between the host machine and the NVD, such as one-to-one, many-to-one, and one-to-many configurations. In a one-to-one configuration, each host machine connects to its own individual NVD. For example, in... Figure 2 In this configuration, host machine 202 connects to NVD 210 via its NIC 232. In a many-to-one configuration, multiple host machines connect to a single NVD. For example, in... Figure 2 In this configuration, host machines 206 and 208 are connected to the same NVD 212 via NICs 244 and 250, respectively.

[0126] In a one-to-many configuration, a host machine connects to multiple NVDs. Figure 3 An example within the CSPI 300 is shown, where a host machine is connected to multiple NVDs. (Example follows) Figure 3 As shown, host machine 302 includes a network interface card (NIC) 304, which includes multiple ports 306 and 308. Host machine 300 is connected to a first NVD 310 via port 306 and link 320, and to a second NVD 312 via port 308 and link 322. Ports 306 and 308 may be Ethernet ports, and links 320 and 322 between host machine 302 and NVDs 310 and 312 may be Ethernet links. NVD 310 is further connected to a first TOR switch 314, and NVD 312 is connected to a second TOR switch 316. Links between NVDs 310 and 312 and TOR switches 314 and 316 may be Ethernet links. TOR switches 314 and 316 represent Layer 0 switching devices in a multi-layer physical network 318.

[0127] Figure 3 The layout depicted provides two separate physical network paths from physical switch network 318 to host machine 302: the first path traverses TOR switch 314 to NVD 310 and then to host machine 302, and the second path traverses TOR switch 316 to NVD 312 and then to host machine 302. These separate paths provide enhanced availability (referred to as high availability) for host machine 302. If one of the paths (e.g., a link in one of the paths breaks) or a device (e.g., a particular NVD is not running) experiences a problem, the other path can be used for communication with host machine 302.

[0128] exist Figure 3 In the configuration depicted, the host machine connects to two different NVDs using two different ports provided by the host machine's NIC. In other embodiments, the host machine may include multiple NICs that enable the host machine to connect to multiple NVDs.

[0129] Go back to reference Figure 2An NVD is a physical device or component that performs one or more network and / or storage virtualization functions. An NVD can be any device with one or more processing units (e.g., CPU, Network Processing Unit (NPU), FPGA, packet processing pipeline, etc.), memory (including cache), and ports. Various virtualization functions can be executed by software / firmware performed by one or more processing units of the NVD.

[0130] NVDs can be implemented in various different forms. For example, in some embodiments, an NVD is implemented as an interface card called a smartNIC or a smart NIC with an onboard embedded processor. A smartNIC is a device that is independent of the NIC on the host machine. Figure 2 In this context, NVD 210 and 212 can be implemented as smartNICs connected to host machine 202 and host machines 206 and 208, respectively.

[0131] However, smartNIC is just one example of an NVD implementation. Various other implementations are possible. For example, in some other implementations, the NVD, or one or more functions performed by the NVD, may be integrated into or performed by one or more host machines, one or more TOR switches, and other components of the CSPI 200. For example, the NVD may be implemented within a host machine, where the functions performed by the NVD are performed by the host machine. As another example, the NVD may be part of a TOR switch, or the TOR switch may be configured to perform functions performed by the NVD, enabling the TOR switch to perform various complex packet transformations for public clouds. TORs performing the functions of the NVD are sometimes referred to as smart TORs. In other implementations that serve virtual machine (VM) instances rather than bare metal (BM) instances to customers, the functions performed by the NVD may be implemented within the hypervisor of the host machine. In some other implementations, some of the functions of the NVD may be offloaded to a centralized service running on a set of host machines.

[0132] In some embodiments, such as when implemented as Figure 2 As shown in the smartNIC diagram, the NVD can include multiple physical ports that enable it to connect to one or more host machines and one or more TOR switches. Ports on the NVD can be classified as host-facing ports (also known as "south ports") or network-facing or TOR-facing ports (also known as "north ports"). The host-facing ports of the NVD are those used to connect the NVD to the host machine. Figure 2 Examples of host-facing ports include port 236 on the NVD 210 and ports 248 and 254 on the NVD 212. Network-facing ports on the NVD are used to connect the NVD to a TOR switch. Figure 2 Examples of network-facing ports include port 256 on the NVD 210 and port 258 on the NVD 212. Figure 2 As shown, NVD 210 is connected to TOR switch 214 via link 228, which extends from port 256 of NVD 210 to TOR switch 214. Similarly, NVD 212 is connected to TOR switch 216 via link 230, which extends from port 258 of NVD 212 to TOR switch 216.

[0133] The NVD receives packets and frames from the host machine (e.g., packets and frames generated by compute instances hosted by the host machine) via its host-facing port, and after performing the necessary packet processing, can forward the packets and frames to the TOR switch via its network-facing port. The NVD can also receive packets and frames from the TOR switch via its network-facing port, and after performing the necessary packet processing, can forward the packets and frames to the host machine via its host-facing port.

[0134] In some embodiments, there can be multiple ports and associated links between the NVD and TOR switches. These ports and links can be aggregated to form a link aggregation group (called a LAG) of multiple ports or links. Link aggregation allows multiple physical links between two endpoints (e.g., between the NVD and TOR switches) to be treated as a single logical link. All physical links in a given LAG can operate at the same speed in full-duplex mode. LAGs help increase the bandwidth and reliability of the connection between two endpoints. If one of the physical links in the LAG fails, traffic is dynamically and transparently reassigned to one of the other physical links in the LAG. Aggregated physical links deliver higher bandwidth than each individual link. Multiple ports associated with an LAG are treated as a single logical port. Traffic can be load-balanced across the multiple physical links of the LAG. One or more LAGs can be configured between two endpoints. These endpoints can be located between the NVD and TOR switches, between a host machine and the NVD, etc.

[0135] The NVD implements or performs network virtualization functions. These functions are performed by software / firmware executed by the NVD. Examples of network virtualization functions include, but are not limited to: packet encapsulation and decapsulation functions; functions for creating VCN networks; functions for implementing network policies, such as VCN security list (firewall) functionality; functions for facilitating packet routing and forwarding to and from compute instances within the VCN; and so on. In some embodiments, upon receiving a packet, the NVD is configured to perform a packet processing pipeline to process the packet and determine how to forward or route it. As part of this packet processing pipeline, the NVD may perform one or more virtual functions associated with the overlay network, such as performing a VNIC associated with the CIS in the VCN, performing a virtual router (VR) associated with the VCN, encapsulating and decapsulating packets to facilitate forwarding or routing in the virtual network, performing certain gateways (e.g., local peer gateways), implementing security lists, network security groups, Network Address Translation (NAT) functionality (e.g., translating public IPs to private IPs host-by-host), throttling functions, and other functions.

[0136] In some embodiments, the packet processing data path in the NVD may include multiple packet pipelines, each consisting of a series of packet transformation stages. In some implementations, upon receiving a packet, the packet is parsed and classified into a single pipeline. The packet is then processed linearly, stage by stage, until the packet is either dropped or sent out through the NVD's interface. These stages provide basic functional packet processing building blocks (e.g., header verification, throttling, insertion of new Layer 2 headers, L4 firewall enforcement, VCN encapsulation / decapsulation, etc.) so that new pipelines can be built by combining existing stages, and new functionality can be added by creating new stages and inserting them into existing pipelines.

[0137] NVD can perform control plane and data plane functions corresponding to those of VCN's control plane and data plane. An example of the VCN control plane is also available in... Figure 11 , Figure 12 , Figure 13 and Figure 14 Depicted in (see reference numerals 1116, 1216, 1316, and 1416) and described below. An example of the VCN data plane is shown in... Figure 11 , Figure 12 , Figure 13 and Figure 14The data plane is depicted (see reference numerals 1118, 1218, 1318, and 1418) and described below. Control plane functions include features for configuring how control data is forwarded on the network (e.g., setting routes and routing tables, configuring VNICs, etc.). In some embodiments, a VCN control plane is provided that centrally computes all overlay mappings to the baseboard and publishes them to the NVD and virtual network edge devices (such as various gateways, such as DRGs, SGWs, IGWs, etc.). Firewall rules can also be published using the same mechanism. In some embodiments, the NVD only receives mappings associated with that NVD. Data plane functions include the ability to actually route / forward packets based on the configuration set using the control plane. The VCN data plane is implemented by encapsulating client network packets before they traverse the baseboard network. Encapsulation / decapsulation functionality is implemented on the NVD. In some embodiments, the NVD is configured to intercept all network packets entering and leaving the host machine and perform network virtualization functions.

[0138] As indicated above, NVD performs various virtualization functions, including VNIC and VCN VR. NVD can execute VNICs associated with compute instances hosted on one or more host machines connected to the VNIC. For example, as... Figure 2 As depicted, NVD 210 performs the functionality of VNIC 276 associated with compute instance 268 hosted by host machine 202 connected to NVD 210. As another example, NVD 212 performs VNIC 280 associated with bare-metal compute instance 272 hosted by host machine 206, and VNIC 284 associated with compute instance 274 hosted by host machine 208. Host machines can host compute instances belonging to different VCNs (belonging to different customers), and NVDs connected to host machines can perform VNICs corresponding to compute instances (i.e., perform VNIC-related functionality).

[0139] NVD also executes a VCN virtual router corresponding to the VCN of the compute instance. For example, in Figure 2 In the embodiments depicted, NVD 210 executes VCN VR 277 corresponding to the VCN to which compute instance 268 belongs. NVD 212 executes one or more VCN VR 283 corresponding to one or more VCNs to which compute instances hosted by host machines 206 and 208 belong. In some embodiments, the VCN VR corresponding to a VCN is executed by all NVDs connected to host machines hosting at least one compute instance belonging to that VCN. If a host machine hosts compute instances belonging to different VCNs, then NVDs connected to that host machine can execute VCN VR corresponding to those different VCNs.

[0140] In addition to VNIC and VCN VR, NVD can execute various software (e.g., daemons) and include one or more hardware components that facilitate various network virtualization functions performed by NVD. For simplicity, these various components are grouped together as... Figure 2 The “packet processing component” shown is illustrated. For example, NVD 210 includes packet processing component 286 and NVD 212 includes packet processing component 288. For instance, a packet processing component for an NVD may include a packet processor configured to interact with the NVD’s ports and hardware interface to monitor all packets received by and transmitted using the NVD and to store network information. Network information may include, for example, network flow information identifying different network flows handled by the NVD and per-flow information (e.g., per-flow statistics). In some embodiments, network flow information may be stored on a per-VNIC basis. The packet processor may perform per-packet manipulation and implement stateful NAT and L4 firewall (FW). As another example, a packet processing component may include a replication agent configured to replicate information stored by the NVD to one or more different replication target repositories. As yet another example, a packet processing component may include a logging agent configured to perform logging functions of the NVD. The packet processing component may also include software for monitoring the performance and health of the NVD and may also monitor the status and health of other components connected to the NVD.

[0141] Figure 1 The components of an example virtual or overlay network are shown, including a VCN, subnets within the VCN, compute instances deployed on the subnets, VNICs associated with the compute instances, VRs for the VCN, and a collection of gateways configured for the VCN. Figure 1 The overlay component described in the text can be made by Figure 2 One or more executions or hosts are described in the physical components. For example, a compute instance in a VCN can be executed or managed by... Figure 2 The VNIC described herein is executed or hosted by one or more host machines. For a compute instance hosted by a host machine, the VNIC associated with that compute instance is typically executed by an NVD connected to that host machine (i.e., VNIC functionality is provided by an NVD connected to that host machine). The VCN VR functionality for a VCN is executed by all NVDs connected to the host machine hosting or executing a compute instance as part of that VCN. The gateway associated with a VCN can be executed by one or more different types of NVDs. For example, some gateways can be executed by smartNICs, while others can be executed by one or more host machines or other implementations of NVDs.

[0142] As described above, compute instances in a client VCN can communicate with various endpoints, which can be within the same subnet as the source compute instance, in a different subnet but within the same VCN as the source compute instance, or communicate with endpoints located outside the VCN of the source compute instance. These communications are facilitated using VNICs, VCN VRs, and gateways associated with the VCNs.

[0143] For communication between two compute instances on the same subnet within a VCN, a VNIC associated with both the source and destination compute instances facilitates the communication. The source and destination compute instances can be hosted by the same host machine or different host machines. Packets originating from the source compute instance can be forwarded from the host machine hosting the source compute instance to an NVD connected to that host machine. On the NVD, packets are processed using a packet processing pipeline, which may include the execution of the VNIC associated with the source compute instance. Because the destination endpoint for the packet is within the same subnet, the execution of the VNIC associated with the source compute instance results in the packet being forwarded to the NVD executing the VNIC associated with the destination compute instance, whereupon the NVD processes the packet and forwards it to the destination compute instance. The VNIC associated with the source and destination compute instances can execute on the same NVD (e.g., when the source and destination compute instances are hosted by the same host machine) or on different NVDs (e.g., when the source and destination compute instances are hosted by different host machines connected to different NVDs). The VNIC can use a routing / forwarding table stored by the NVD to determine the next hop for the packet.

[0144] For packets destined for endpoints in different subnets within the same VCN, the packet originating from the source compute instance is forwarded from the host machine hosting the source compute instance to an NVD connected to that host machine. On the NVD, the packet is processed using a packet processing pipeline, which may include the execution of one or more VNICs and the VR associated with the VCN. For example, as part of the packet processing pipeline, the NVD executes or invokes functionality associated with the VNIC associated with the source compute instance (also known as executing the VNIC). Functionality executed by the VNIC may include viewing the VLAN tag on the packet. Since the packet's destination is outside the subnet, the VCN VR functionality is then invoked and executed by the NVD. The VCN VR then routes the packet to the NVD executing the VNIC associated with the destination compute instance. The VNIC associated with the destination compute instance then processes the packet and forwards it to the destination compute instance. The VNICs associated with the source and destination compute instances may execute on the same NVD (e.g., when the source and destination compute instances are hosted by the same host machine) or on different NVDs (e.g., when the source and destination compute instances are hosted by different host machines connected to different NVDs).

[0145] If the destination of the packet is outside the VCN of the source compute instance, the packet originating from the source compute instance is forwarded from the host machine hosting the source compute instance to the NVD connected to that host machine. The NVD executes the VNIC associated with the source compute instance. Since the destination endpoint of the packet is outside the VCN, the packet is subsequently processed by the VCN VR used by that VCN. The NVD invokes the VCN VR functionality, which results in the packet being forwarded to the NVD executing the appropriate gateway associated with the VCN. For example, if the destination is an endpoint within a customer's on-premises network, the packet may be forwarded by the VCN VR to the NVD executing the DRG gateway configured for the VCN. The VCN VR may execute on the same NVD as the NVD executing the VNIC associated with the source compute instance, or it may be executed by a different NVD. The gateway may be executed by the NVD, which may be a smartNIC, a host machine, or another NVD implementation. The packet is then processed by the gateway and forwarded to the next hop, which facilitates the forwarding of the packet to its intended destination endpoint. For example, in Figure 2 In the embodiment depicted, packets originating from compute instance 268 can be transmitted from host machine 202 to NVD 210 via link 220 (using NIC 232). On NVD 210, VNIC 276 is invoked because it is the VNIC associated with the source compute instance 268. VNIC 276 is configured to examine the information encapsulated in the packet and determine the next hop for forwarding the packet, with the aim of facilitating the transmission of the packet to its intended destination endpoint, and then forwarding the packet to the determined next hop.

[0146] Compute instances deployed on a VCN can communicate with a variety of endpoints. These endpoints can include endpoints hosted by CSPI 200 and endpoints outside of CSPI 200. Endpoints hosted by CSPI 200 can include instances within the same VCN or other VCNs, which can be the customer's VCN or a VCN not belonging to the customer. Communication between endpoints hosted by CSPI 200 can be performed via physical network 218. Compute instances can also communicate with endpoints not hosted by CSPI 200 or outside of CSPI 200. Examples of these endpoints include endpoints within the customer's on-premises network or data center, or public endpoints accessible via public networks such as the Internet. Communication with endpoints outside of CSPI 200 can use various communication protocols over public networks (e.g., the Internet). Figure 2 (not shown in the image) or a dedicated network ( Figure 2 (Not shown in the image) to execute.

[0147] Figure 2The architecture of the CSPI 200 depicted herein is merely an example and is not intended to be limiting. Variations, alternatives, and modifications are possible in alternative embodiments. For example, in some implementations, the CSPI 200 may have a more advanced architecture than... Figure 2 The systems or components shown may include more or fewer systems or components, and may combine two or more systems, or may have different system configurations or arrangements. Figure 2 The systems, subsystems, and other components described herein may be implemented in software (e.g., code, instructions, programs) executed by one or more processing units (e.g., processors, cores) of the respective system, using hardware, or a combination thereof. The software may be stored on a non-transitory storage medium (e.g., a memory device).

[0148] Figure 4 The diagram depicts a connection between a host machine and an NVD, according to certain embodiments, for providing I / O virtualization to support multi-tenancy. For example... Figure 4 As depicted, host machine 402 executes a hypervisor 404 that provides a virtualized environment. Host machine 402 executes two virtual machine instances, VM1 406 belonging to customer / tenant #1 and VM2 408 belonging to customer / tenant #2. Host machine 402 includes a physical NIC 410 connected to NVD 412 via link 414. Each compute instance is attached to a VNIC executed by NVD 412. Figure 4 In the embodiment, VM1 406 is attached to VNIC-VM1 420 and VM2 408 is attached to VNIC-VM2 422.

[0149] like Figure 4 As shown, NIC 410 includes two logical NICs, logical NIC A 416 and logical NIC B 418. Each virtual machine is attached to its own logical NIC and configured to work with its own logical NIC. For example, VM1 406 is attached to logical NIC A 416 and VM2 408 is attached to logical NIC B 418. Although host machine 402 includes only one physical NIC 410 shared by multiple tenants, due to the logical NICs, each tenant's virtual machines believe they have their own host machine and network interface card.

[0150] In some embodiments, each logical NIC is assigned its own VLAN ID. Therefore, a specific VLAN ID is assigned to logical NIC A 416 for tenant #1, and a separate VLAN ID is assigned to logical NIC B 418 for tenant #2. When a packet is transmitted from VM1 406, the hypervisor appends a tag assigned to tenant #1 to the packet, and the packet is then transmitted from host machine 402 to NVD 412 via link 414. Similarly, when a packet is transmitted from VM2 408, the hypervisor appends a tag assigned to tenant #2 to the packet, and the packet is then transmitted from host machine 402 to NVD 412 via link 414. Thus, a packet 424 transmitted from host machine 402 to NVD 412 has an associated tag 426 identifying the specific tenant and the associated VM. On the NVD, for a packet 424 received from the host machine 402, the tag 426 associated with the packet is used to determine whether the packet is processed by VNIC-VM1 420 or VNIC-VM2 422. The packet is then processed by the corresponding VNIC. Figure 4 The configuration described in [the document] enables each tenant's compute instance to believe that they own their own host machine and NIC. Figure 4 The setup described in [the document] provides I / O virtualization to support multi-tenancy.

[0151] Figure 5 A simplified block diagram of a physical network 500 according to certain embodiments is depicted. Figure 5 The embodiments depicted are structured as Clos networks. Clos networks are a specific type of network topology designed to provide connectivity redundancy while maintaining high bandwidth and maximum resource utilization. Clos networks are non-blocking, multi-stage or multi-layer switching networks, where the number of stages or layers can be two, three, four, five, etc. Figure 5 The embodiment depicted is a Layer 3 network, including Layer 1, Layer 2, and Layer 3. TOR switch 504 represents a Layer 0 switch in a Clos network. One or more NVDs are connected to the TOR switch. Layer 0 switches are also referred to as edge devices of the physical network. Layer 0 switches are connected to Layer 1 switches, also known as leaf switches. Figure 5In the embodiments depicted, a set of “m” Layer 0 TOR switches is connected to a set of “r” Layer 1 switches, forming a pod (where integers m and r can have the same or different values). Each Layer 0 switch in the pod is interconnected to all Layer 1 switches in that pod, but there is no switch connectivity between pods. In some implementations, two pods are referred to as blocks. Each block is served by or connected to a set of “q” Layer 2 switches (sometimes called backbone switches). There can be several blocks in the physical network topology. The Layer 2 switches are then connected to “p” Layer 3 switches (sometimes called superbackbone switches) (where integers p and q can have the same or different values). Communication of packets over the physical network 500 is typically performed using one or more Layer 3 communication protocols. Typically, all layers of the physical network (except the TOR layer) are redundant (e.g., p-way, q-way, or r-way redundancy), thus allowing high availability. Policies can be specified for pods and blocks to control the visibility of switches to each other in the physical network, thereby enabling the scaling of the physical network.

[0152] A key characteristic of Clos networks is that the maximum number of hops from one Layer 0 switch to another (or from an NVD connected to a Layer 0 switch to another NVD connected to a Layer 0 switch) is fixed. For example, in a Layer 3 Clos network, a packet takes a maximum of seven hops to reach another NVD, where the source and destination NVDs are connected to the leaf layers of the Clos network. Similarly, in a Layer 4 Clos network, a packet takes a maximum of nine hops to reach another NVD, where the source and destination NVDs are connected to the leaf layers of the Clos network. Therefore, the Clos network architecture maintains consistent latency throughout the network, which is important for communication within and between data centers. Clos topologies are horizontally scalable and cost-effective. Network bandwidth / throughput capacity can be easily increased by adding more switches at each layer (e.g., more leaf switches and backbone switches) and by increasing the number of links between switches in adjacent layers.

[0153] In some embodiments, each resource within the CSPI is assigned a unique identifier called a Cloud Identifier (CID). This identifier is included as part of the resource's information and can be used to manage the resource, for example, via a console or API. An example syntax for a CID is:

[0154] in, ocid1: A text string indicating the version of the CID; resource type: The type of resource (e.g., instance, volume, VCN, subnet, user, group, etc.); realm: The realm where the resource resides. Example values ​​are "c1" for the commercial realm, "c2" for the government cloud realm, or "c3" for the federal government cloud realm, etc. Each realm can have its own domain name; region: The region where the resource is located. This section may be empty if the region is not applicable to the resource. future use: to be reserved for future use.

[0155] Unique ID: The unique part of the ID. The format may vary depending on the type of resource or service.

[0156] RDMA / RoCE technology

[0157] Figure 6 An example of a distributed, multi-tenant cloud environment 600 that can be hosted by Cloud Service Provided Infrastructure (CSPI) is shown. Figure 6 As shown, multiple hosts (e.g., 602 and 622) are communicatively coupled via a physical network or switch architecture 640 that includes multiple switches or more generally networking devices. In some embodiments, switch architecture 640 may be as follows: Figure 5 The n-layer Clos network described above and illustrated in the text can be optimized for Clos architecture performance and the placement of physical switches 642, 644, and 646. The value of "n" can be one, two, three, etc., depending on the implementation. However, it should be noted that each additional layer is expected to increase packet transmission latency within the architecture, which may be undesirable for some applications. Top-of-rack (TOR) switches 642 and 644 represent leaf or layer 0 devices in switch architecture 640. Depending on the value of "n", switch architecture 640 may include one or more backbone switches, super backbone switches, etc. Figure 6 In the middle, the switch between TOR switch 642 and TOR switch 644 (e.g., Figure 5 The Layer 1, Layer 2, and Layer 3 switches in the architecture 640 are represented by intermediate switch 646. Intermediate switch 646 typically includes one or more switches or networking devices. Switch architecture 640 can also be implemented to include switchboard IP addresses that are unreachable from client compute instances (e.g., for management purposes). It is expected that Spanning Tree Protocol (STP) will be implemented on the TOR switches of switch architecture 640 (e.g., to avoid loops, which can occur, for example, due to errors). In some configurations, each TOR switch on switch architecture 640 is service-specific (e.g., database cloud service, HPC cloud service, GPU cloud service, etc.), and traffic for different services is mixed only at higher layers (for example, in intermediate switch 646).

[0158] Host machines 602 and 622 can host multiple client or tenant compute instances and are therefore referred to as multi-tenant host machines. For example, as Figure 6 As depicted, host machine 602 hosts compute instance A-1 604 for client A and compute instance B-1 for client B. Host machine 604 hosts compute instance A-2 624 for client A and compute instance B-2 626 for client B. In some embodiments, compute instances 604, 606, 624, and 626 are virtual machines. In this way, virtual machines belonging to different clients can be hosted on the same host machine. However, each of these compute instances experiences ownership of the entire host machine. In some embodiments, the compute instance for a client may also include a bare metal host. The teachings of this disclosure apply to compute instances in the form of virtual machines or bare metal hosts. For ease of explanation, Figure 1 The example shown only illustrates two multitenant host machines, 602 and 622, but this is not intended to be limiting; the principles disclosed herein are not limited to any particular number of multitenant hosts, and specific examples can be implemented that include a greater number of multitenant hosts and / or include one or more compute instances as bare metal hosts (e.g., single-tenant hosts).

[0159] In a multi-tenant environment, such as Figure 6 As shown, the goal is to appropriately isolate traffic originating from and destined for compute instances of different customers. In some embodiments, this traffic isolation is accomplished by configuring separate network domains for separate customers. For example, a compute instance of customer A may be assigned to a specific network domain that is separate from and different from the network domain assigned to a compute instance of customer B. In some implementations, these network domains may be configured in the form of Virtual LANs (VLANs), where each VLAN is identified by a unique VLAN identifier. For example, in Figure 6 In this example, customer A's compute instances A-1 604 and A-2 624 are assigned to VLAN 1001, where "1001" represents a unique VLAN identifier. Customer B's compute instances B-1 606 and B-2 626 are assigned to VLAN 1002, where "1002" represents a unique VLAN identifier. For ease of explanation, Figure 1 The example shows only two members for each VLAN 1001 and 1002, but this is not intended to be limiting; the principles disclosed herein are not limited to any specific number of VLAN members. Furthermore, there can be multiple VLANs, not just... Figure 6 The two are described in the text. For example, the IEEE 802.1Q standard supports the identification of up to 4096 different VLANs.

[0160] In some implementations, compute instances belonging to the same customer can have different quality of service (QoS) expectations. For example, a customer may have compute instances belonging to two or more different services (or applications or departments), such as a first set of one or more compute instances corresponding to service A (e.g., simulation service) and a second set of compute instances corresponding to service B (e.g., backup service), where the two services have very different QoS expectations (e.g., in terms of latency, packet loss, bandwidth requirements, etc.). For example, service A may be more latency-sensitive than service B; therefore, the customer may expect traffic associated with service A to be assigned a different traffic class (e.g., higher priority) than traffic associated with service B. In this case, different compute instances belonging to the same customer can have different QoS requirements.

[0161] Compute instances on the same VLAN or peering VLANs (e.g., VLANs belonging to the same tenant but on different Tier 2 domains with different VLAN IDs) may expect to communicate with each other. In some implementations, compute instances on a VLAN (or peering VLAN) may be able to exchange data using RDMA and RoCE protocols. In such implementations, the host machine hosting the compute instances is equipped with special hardware and software that enables RDMA and RoCE-based communication. For example, as Figure 6 As depicted, host machines 602 and 622 respectively include RDMA network interface cards (NICs) (e.g., RoCE NICs) 608 and 628, which enable compute instances hosted on host machine 602 to exchange data with compute instances hosted on host machine 622 and on the same VLAN (or peer VLAN) using RDMA and RoCE protocols. The RoCE NIC can be implemented as, for example, a hardware component (e.g., an interface card) installed within the host machine (e.g., RoCE NIC 608 installed in multi-tenant host machine 602 and RoCE NIC 628 installed in host machine 622). Compute instances A-1 604 and A-2 624 belonging to the same VLAN 1001 can exchange data using RoCE NICs 608 and 628 in host machines 602 and 622 respectively, using RDMA and RoCE protocols. In some implementations, the RoCE NIC and... Figure 2 and Figure 3 The NICs depicted and described above are separate. In other embodiments, Figure 2 and Figure 3 The NIC described in the diagram can be configured to also operate as a RoCE NIC.

[0162] like Figure 6As illustrated in the example, the RoCE NIC includes a RoCE engine and implements virtualization functions (e.g., SR-IOV functions), where each virtual function can be configured for a different corresponding virtual machine within a virtual machine supported by a host machine. In this example, the RoCE NIC is implemented to support multi-tenancy using a technology called SR-IOV (Single Root Input / Output Virtualization), which allows the physical device to appear on the Peripheral Component Fast Interconnect (PCI Express or PCIe) bus as multiple different virtual instances (also called "virtual functions" or VFs), each VF being assigned to a corresponding VM and having resources separate from those of the other VFs. For example, in Figure 6 In the above, the RoCE NIC 608 on host machine 602 includes a RoCE engine 610, a virtualization function VF-A-1 612 for virtual machine compute instance A-1 604, and a virtualization function VF-B-1 614 for virtual machine compute instance B-1 606. The RoCE NIC 628 on host machine 622 includes a RoCE engine 630, a virtualization function VF-A-2 632 for virtual machine compute instance A-2 624, and a virtualization function VF-B-2 634 for virtual machine compute instance B-2 626. For ease of explanation, Figure 6 The examples shown only illustrate two virtual functions per host machine, but this does not imply any limitation in any way; the principles described herein are not limited to any particular number of virtual functions. In one example, SR-IOV can support up to 16 VFs for a single physical NIC port, and a host machine can also have multiple RDMA NICs (e.g., multiple RoCE NICs).

[0163] In some embodiments, the virtualization functionality for the RoCE NIC is programmed by a hypervisor on the host machine for a specific virtual machine compute instance and is configured to force packets from the virtual machine that will communicate over a network (such as switch architecture 640) to be labeled with a VLAN tag (e.g., an 802.1Q VLAN tag) corresponding to the VLAN to which the virtual machine belongs. Figure 6As illustrated in the examples, virtual function VF-A-1 612 can be configured to add a VLAN tag indicating VLAN 1001 (e.g., a VLAN tag with a VLAN ID of 1001) to a packet carrying data from virtual machine computing instance A-1 604, and virtual function VF-B-1 614 can be configured to add a VLAN tag indicating VLAN 1002 (e.g., a VLAN tag with a VLAN ID of 1002) to a packet carrying data from virtual machine computing instance B-1 606. Similarly, virtual function VF-A-2 632 can be configured to add a VLAN tag indicating VLAN 1001 (e.g., a VLAN tag with a VLAN ID of 1001) to packets carrying data from virtual machine compute instance A-2 624, and virtual function VF-B-2 634 can be configured to add a VLAN tag indicating VLAN 1002 (e.g., a VLAN tag with a VLAN ID of 1002) to packets carrying data from virtual machine compute instance B-2 626. Downstream network components can use these VLAN tags to isolate or separate traffic belonging to different VLANs (e.g., in...). Figure 6 In this process, traffic belonging to the compute instance of customer A is isolated from traffic belonging to the compute instance of customer B.

[0164] In some implementations, the virtual functions assigned to the corresponding compute instance are configured (e.g., in conjunction with the RoCE engine on the RoCE NIC) to perform direct memory access (DMA) read operations and DMA write operations for the memory space of the corresponding compute instance used for RDMA data transfer. Figure 6 In the example, virtual function VF-A-1 612 is configured to perform direct memory access read and write operations for compute instance A-1 604 in conjunction with RoCE engine 608 as part of RDMA processing. Virtual function VF-B-1 614 is similarly configured to perform direct memory access read and write operations for compute instance B-1 606 in conjunction with RoCE engine 608 as part of RDMA processing.

[0165] The RoCE engine in the RoCE NIC is configured to facilitate the transmission of RDMA / RoCE traffic from a host machine and the reception of RDMA / RoCE traffic transmitted from another host machine. In some embodiments, the RoCE engine receives instructions (e.g., metadata) identifying address ranges in the application memory of a compute instance, where the address ranges represent data blocks to be transferred to the application memory of a target compute instance using RDMA and RoCE. For example, RoCE engine 610 may receive information identifying an RDMA channel set up for data transfer and an address range representing data blocks to be transferred using RDMA from compute instance A-1604 (i.e., from the application memory for A-1 provided by host machine 602) to the application memory of compute instance A-2624 on host machine 622 (i.e., to the application memory for A-2 provided by host machine 622). The RoCE engine is configured to access data from the application memory of the source compute instance to package the data in an appropriate packet format that enables communication with the target or destination compute instance (i.e., to generate and assemble Layer 2 frames for the data), and then transmit the packets to a TOR switch (e.g., a leaf switch in a switch architecture for transferring data to the destination compute instance). Therefore, the RoCE engine is an offloading engine, and the host machine's CPU or operating system does not need to participate in data transmission. This offloading reduces the latency involved in data transmission.

[0166] For example, RoCE engine 610 can be configured to append headers (e.g., UDP and IP headers) and VLAN tags (e.g., enforced by virtual functions 612 and 614) to the data payload to create VLAN-tagged RoCEv2 format packets, and send the RoCEv2 packets over a line (e.g., Ethernet cable) to a leaf switch (e.g., TOR switch 642) of switch architecture 640. Regarding traffic entering the RoCE engine from the switch architecture, RoCE engine 610 can be configured to receive RoCEv2 packets from TOR switch 642, remove UDP and IP headers, strip VLAN tags, and forward each resulting frame (e.g., as an IB payload sent by the source host machine) to an SR-IOV virtual function mapped to the VLAN ID on which the packet was received. The virtual function can be configured to store the packet's data payload in the memory space of the destination compute instance on the corresponding VLAN.

[0167] Layer 2 frames assembled by the RoCE NIC are then transmitted via a Layer 3 routing protocol through multiple networked devices in a Layer 3 switch architecture to the RoCE NIC of the host machine hosting the destination or target compute instance. For example, if RDMA and RoCE are used to transfer data from... Figure 6If computation instance A-1 604 in the host machine is transmitted to target computation instance A-2 624 on host machine 622, then the path used by the packet with data payload is as follows: source computation instance A-1 604 on host machine 602 RoCE NIC 608 on host machine 602 TOR Switch 642 One or more intermediate switches 646 TOR Switch 644 RoCE NIC 628 on host machine 622 Computation instance A-2 624 is located on host machine 622. As part of this communication, TOR switch 642, representing the ingress edge device for switch architecture 640, is configured to convert Layer 2 frames received from the RoCE NIC into Layer 3 packets by encapsulating packets within wrappers (e.g., including one or more headers) corresponding to the Layer 3 tunneling protocol used to transmit packets through switch architecture 640. Various tunneling protocols can be used, such as VxLAN, NVGRE, STT, GENEVE, MPLS, etc. The Layer 3 packets then travel from TOR switch 642 to TOR switch 644 via one or more intermediate switches 646, representing the egress edge device for switch architecture 640. TOR switch 644 is configured to decapsulate the packets and convert them into Layer 2 frames, which are then transmitted to the RoCE NIC 628 on host machine 622, which hosts the destination or target computation instance A-2 624. RoCE NIC 628 on host machine 622 then transmits the data to the destination computation instance A-2 624. Packets can be transferred to compute instance A-2 by writing packet data to the application memory of compute instance A-2624. Details related to the processing performed by various network components to facilitate data transfer from one multi-tenant host machine to another using RDMA and RoCE are described below.

[0168] As another example, if compute instance B-1 606 wants to transfer data to compute instance B-2 626, the packet would use the following path: source compute instance B-1 606 on host machine 602. RoCENIC 608 on host machine 602 TOR Switch 642 One or more intermediate switches 646 TOR Switch 644 RoCE NIC 628 on host machine 622 Compute instance B-2 626 on host machine 622. As can be seen, switch architecture 640 is shared by customers or tenants for their Layer 2 RoCE traffic communication. The same switch architecture is used to transmit RoCE packets for different tenants. RoCE packets from different tenants (and optionally non-RoCE normal IP traffic) flow through the same shared network architecture. Traffic in this shared network architecture is isolated using tags associated with the packets. Each customer (e.g., a customer's compute instance on a VLAN or a peering VLAN) experiences as having a dedicated Layer 2 network to transmit RoCE traffic, while the traffic is actually carried through the shared Layer 3 cloud-based switch architecture network. The host machine that generates RoCE traffic based on the customer's application generates Layer 2 Ethernet frames (also known as Layer 2 packets), not Layer 3 packets.

[0169] Figure 7A , 7B Figure 7C presents a simplified flowchart 700, according to certain embodiments, depicting the processing of RDMA data transfer from a source compute instance on a multi-tenant source host machine to a destination compute instance on a multi-tenant destination host machine using a Layer 3 routing protocol over a shared Layer 3 switch architecture. Figure 7A The processing described in -C can be implemented using software (e.g., code, instructions, programs) executed by one or more processing units (e.g., processors, cores) of the corresponding system, using hardware or a combination thereof. The software can be stored on a non-transitory storage medium (e.g., a memory device). Figure 7A The methods presented in -C and described below are intended to be illustrative rather than restrictive. Although Figure 7A -C describes various processing steps that occur in a specific order or sequence, but this description is not intended to be limiting. In some alternative embodiments, processing may be performed in a different order and / or some steps may be performed in parallel. In some embodiments, such as in Figure 6 In the embodiments depicted, Figure 7A The processing described in -C can be performed collaboratively by RoCE NIC 608 and 628, TOR switches 642 and 644, and one or more intermediate switches 646 of switch architecture 640. Figure 7A The methods described in -C and below can be used in different versions of RoCE, such as RoCEv2 and other future versions, as well as Layer 2 RDMA packets according to other RDMA protocols that support VLAN tagging.

[0170] For the purpose of describing the method and as a means of use Figure 6The example of the embodiment depicted assumes that data will be transferred using RDMA and RoCE from compute instance A-1 604 hosted by host machine 602 to compute instance A-2 624 hosted by host machine 622, where A-1 and A-2 belong to the same customer A and are in the same VLAN 1001. The compute instance initiating the data transfer (e.g., A-1 604) may be referred to as the source compute instance, and the host machine hosting the source compute instance (e.g., host machine 602) may be referred to as the source host machine. The compute instance to which the data is to be transferred (e.g., A-2 624) may be referred to as the destination or target compute instance, and the host machine hosting the destination compute instance (e.g., host machine 622) may be referred to as the destination or target host machine. The source and destination compute instances may be virtual machines or bare metal instances. The source and destination host machines may be in the same Ethernet domain or in different Ethernet domains.

[0171] At 702, the RoCE NIC on the source host machine hosting the source compute instance receives information (e.g., from a virtual function) identifying data to be transferred from the source compute instance to the destination compute instance using RDMA and RoCE. For example, the RoCE NIC may receive information identifying the source compute instance and the memory address range identifying the data blocks to be transferred from the source compute instance to the destination compute instance. Figure 6 In the embodiment depicted, the RoCE NIC 608 can receive information about data blocks to be transferred from compute instance A-1 604 hosted by host machine 602 to compute instance A-2 624 hosted by host machine 622.

[0172] At 704, the RoCE NIC accesses the data to be transmitted from the application memory of the source compute instance on the source host machine and generates Layer 2 802.1Q-tagged RoCE packets for the data to be transmitted, where VLAN information is encoded in an 802.1Q tag appended to each packet and QoS information is encoded in one or more headers of the packet. Each Layer 2 802.1Q-tagged RoCE packet may have one or more 802.1Q tags (e.g., 802.1ad or the “Q-in-Q tag” described herein). The data can be accessed from memory using the Direct Memory Access (DMA) controller on the RoCE NIC, and then packaged by breaking the accessed data into RDMA payload blocks for packetization. For example, 1 megabyte (MB) of data can be tagged for transmission from the source compute instance to the destination compute instance. The RoCE NIC can access this data from the application memory of the source compute instance and divide the data into 2-kilobyte (KB) blocks, where each block represents an RDMA payload to be transmitted to the destination compute instance. Each payload is then packaged by the RoCE NIC to generate RoCE Layer 2 packets (or “frames”). The packets are formatted according to the appropriate version of the RoCE protocol, such as RoCEv2 (or other RoCE protocols, or another RDMA protocol that supports VLAN tagging).

[0173] The RoCE NIC adds an 802.1Q tag to each RoCE packet. The 802.1Q tag encodes information identifying the VLAN to which the source compute instance belongs (e.g., a VLAN identifier). The 802.1Q protocol covers the use and support of VLANs on Ethernet networks. The 802.1Q protocol uses tags (simply called 802.1Q tags) to distinguish traffic that travels through the trunk and belongs to different VLANs.

[0174] In some embodiments, the processing in 704 is performed collaboratively by the RoCE engine on the RoCE NIC and the virtual function on the RoCE NIC corresponding to the source compute instance. The RoCE engine is responsible for generating RoCE packets. The RoCE engine may not have information identifying the VLAN identifier or QoS information used for the packets; this information will be encoded in an 802.1Q tag added to the packets. In some embodiments, the virtual function corresponding to the source compute instance provides a specific VLAN identifier indicating the VLAN of the source compute instance. This VLAN identifier is then encoded as an 802.1Q tag added to each packet. In some implementations, the virtual function on the host machine is programmed by a hypervisor to force packets from the host machine's RoCE NIC to the switch-based network to have 802.1Q VLAN tags. For example, for Figure 6The embodiments described herein can be implemented such that VF VF-A-1 612 can force RoCE packets from source compute instance A-1 604 to be labeled with a VLAN ID indicating VLAN 1001, and VF VF-B-1 614 can be implemented such that RoCE packets from source compute instance B-1606 can be labeled with a VLAN ID indicating VLAN 1002.

[0175] QoS information can be encoded in one or more different portions of an 802.1Q-tagged RoCE packet. In some implementations, QoS information is encoded in the DSCP bit of the IP header of each packet. In some other implementations, QoS information can be encoded in the 802.1p bit of the Ethernet header of each packet. QoS information generally includes information indicating the priority (or class) for different traffic flows. The QoS information for a packet can specify the particular priority class used for that packet, which will be used to forward / route the packet to its destination. For example, QoS information can contain information identifying the priority (e.g., high, low, etc.) assigned to the RoCE packet. QoS information can also include other information, such as information specifying various parameters for each priority class related to flow control, buffer allocation, queuing, scheduling, etc. In one example, QoS information is provided by the computation instance that initiates the RDMA transfer.

[0176] Figure 8A The RoCE packet format according to RoCE protocol version 2 (RoCEv2) is shown. Figure 8A As shown, the RoCEv2 packet 800 includes a 22-byte Ethernet header 801, a 20-byte IP header 803, and an 8-byte UDP header 804. The Ethernet header 801 includes an eight-byte preamble field 816, a six-byte destination MAC address field 809, a six-byte source MAC address field 810, and a two-byte Ethernet type field 811 whose value indicates that this header is appended to the IP packet. The UDP header 804 includes a value indicating the destination port number as 4791, which specifies RoCEv2. The RoCEv2 packet 800 also includes a twelve-byte Infiniband (IB) base transport header 805, an RDMA data payload 806 (which may be up to approximately 1400 bytes in length), a 32-bit RoCE end-to-end invariant cyclic redundancy check (ICRC) field 807, and a four-byte per-Ethernet hop frame check sequence (FCS) field 808. RoCEv2 is presented as an example only, and it is envisioned that the systems, methods, and apparatus described herein can also be implemented using one or more other protocols, such as VLAN tagging that supports RDMA traffic.

[0177] As used to generate such Figure 8AAs part of the processing in 704 of the RoCEv2 Layer 2 packet shown, the RoCE NIC on the host machine is configured to access the data to be transmitted and prepare the RDMA payload 806. The RoCE NIC is then configured to add headers 805, 804, 803, and 801 (as well as check fields 807 and 808) to generate the RoCEv2 Layer 2 packet.

[0178] As described above, virtual functions are programmed (e.g., by a hypervisor on the host machine) to force RDMA packets outgoing to the architecture to be tagged with an IEEE 802.1Q header (sometimes also called a "VLAN tag") that identifies the VLAN of the source compute instance on which the packet was found. In some embodiments, VLANs are associated with individual customers or tenants, and thus the associated VLAN identifier is used within the architecture to enforce traffic isolation between different tenants at Layer 2. Figure 8B The format of a RoCEv2 packet 820 with an 802.1Q VLAN tag is shown, which includes a four-byte VLAN tag 802 inserted between a source MAC address field 810 and an Ethernet type field 811. The VLAN tag 802 includes a sixteen-bit tag protocol ID data field 812 with a value of 0x8100, a three-bit User Priority Code Point (PCP) data field 813, a one-bit drop qualifier data field 814, and a twelve-bit VLAN identifier data field 815 identifying the VLAN. In some implementations, the VLAN identifier used for the packet is encoded in this VLAN identifier field 815. In some implementations, the PCP data field 813 in the VLAN tag 802 (also referred to as the "IEEE 802.1p" or "802.1p" data field) can be used to encode QoS information (e.g., traffic class priority information) used for the packet.

[0179] In some other embodiments, QoS information may be encoded in the DSCP bit of the IP header 803 of each packet. Figure 9AThe format of IP header 803 is shown, which includes an octet version and header length data field 901, a 6-bit Differential Service Code Point (DSCP) data field 902, a 2-bit Explicit Congestion Notification (ECN) data field 903, a 16-bit length data field 904, a 16-bit identification data field 905, a 16-bit fragment flag and offset data field 906, an octet Time to Live (TTL) data field 907, an octet protocol data field 908, a 16-bit header checksum data field 909, a 4-byte source IP address data field 910, and a 4-byte destination IP address data field 911. In RoCEv2 packets, the protocol data field 908 has a value indicating whether the header is appended to the UDP packet. The DSCP data field 902 can be used to carry QoS information for the packet. As described in more detail below, the ECN data field 903 can be used to indicate congestion information, indicating whether the packet encountered congestion on its path from the source compute instance to the destination compute instance.

[0180] As previously mentioned, QoS information can be used to indicate the traffic class of a packet. For example, QoS information can be used to specify different levels of traffic class priority for packets, where the priority associated with the packet is used to determine the priority at which the packet will be forwarded from the source host machine to the destination host machine in the network path. The priority assigned to a packet originating from one application can be different from the priority assigned to packets originating from different applications. Generally, packets associated with applications that are more sensitive to network latency have a higher priority than packets associated with applications that are less sensitive to network latency. The QoS information of a packet can be specified by the compute instance that initiates the RDMA transfer (e.g., by the application running on the compute instance). In such an example, the initiating compute instance can instruct the corresponding virtual function to perform an RDMA transfer according to a specified Quality of Service (QoS) (e.g., a specified traffic class), and the virtual function then causes the RDMA engine on the RoCE NIC to generate packets that include a VLAN tag to identify the VLAN of the source compute instance, and also encode the specified QoS information in the data fields (e.g., 802.1p fields or DSCP fields) of the RoCE packets marked with 802.1Q.

[0181] Customers can use QoS values ​​to indicate performance expectations. For example, a customer can assign a low QoS priority to RoCE packets carrying large amounts of data for latency-tolerant applications, and / or assign a higher QoS priority value to RoCE packets carrying low amounts of data for latency-sensitive applications.

[0182] In another example, the value of the QoS data field is indicated by the type of RoCE transmission being performed (e.g., a predetermined mapping from QoS priority values ​​to RDMA transmission types). For example, a RoCE packet carrying a large volume of data transmission could be labeled with a different QoS than a RoCE packet carrying a small volume of data transmission that is extremely sensitive to latency. Examples of large volume transmissions could include backups, reports, or batch messages, while examples of low-latency critical transmissions could include congestion information notifications, cluster heartbeats, transaction commits, cache fusion operations, etc.

[0183] For example, in Figure 6 If a packet represents data to be transmitted via RDMA from compute instance A-1 604 to compute instance A-2 624 on VLAN 1001, then the RoCE NIC 608 generates Layer 2 802.1Q-tagged RoCE packets for the data to be transmitted. Each packet has an 802.1Q tag, and the VLAN ID field 815 of each packet encodes information identifying VLAN 1001. Furthermore, QoS information for each packet can be encoded in the packet's DSCP and / or PCP fields.

[0184] The 12-bit VLAN tag field defined in the IEEE 802.1Q standard can identify up to 4096 VLANs. The 802.1ad Q-in-Q standard (also known as "802.1q-in-802.1q", "Q-in-Q-tagging", or "Q-in-Q standard") was developed to extend this to more than 4096 VLANs. According to the Q-in-Q standard, two (or more) 802.1Q VLAN tags can be attached to a packet. These two tags, called the internal tag and the external tag, can be used for a variety of different purposes (e.g., the internal tag can represent an attached security rule). For example, in some implementations, internal and external tags can be used to support application-specific network enforcement. It may be desirable to differentiate packets based on tenant and application, with one tag corresponding to the tenant and another tag corresponding to one of the tenant's specific applications. In one such example, a host machine configured to run multiple compute instances for the same customer on the same serving VLAN can use the customer VLAN tag to isolate traffic across multiple compute instances on the serving VLAN. Alternatively or additionally, host machines configured to run multiple applications for the same customer on the same serving VLAN can use customer VLAN tags to separate traffic across multiple applications on the serving VLAN. Thus, in some cases, as part of the processing performed in a 704 error, the RoCE NIC can attach two tags to each RoCE packet according to the Q-in-Q standard. For example, in cases where tenants have different applications, such as tenant A having an emulation application and a backup application, two separate 802.1Q tags can be attached to the RoCE packet: one with a VLAN ID identifying the tenant (e.g., tenant A) and a second with a VLAN ID identifying the application (e.g., emulation, backup).

[0185] Figure 8C An example of a RoCEv2 packet 830 with Q-in-Q tagging is depicted. In this case, each packet includes a second VLAN tag 822 (also known as an "internal" VLAN tag, "private" VLAN tag, or service VLAN (S-VLAN) tag) in addition to a first VLAN tag 802 (also known as an "internal" VLAN tag, "private" VLAN tag, or customer VLAN (C-VLAN) tag). One or more additional VLAN tags can be added to a RoCEv2 packet with Q-in-Q tagging in the same manner.

[0186] Go back to reference Figure 7AAt position 706, RoCE packets labeled 802.1Q are forwarded from the RoCE NIC on the source host machine to the TOR switch connected to the source host machine. The TOR switch receiving 802.1Q-labeled RoCE packets can also be called an ingress TOR switch, as it represents the ingress edge device used in a switch architecture. A TOR switch represents the lowest-level (or leaf-level) networking device in a switch network or architecture, used to forward packets from a source compute instance on the source host machine to a destination compute instance on the destination host machine. For example, in Figure 6 In this process, RoCE packets with 802.1Q tags generated by RoCE NIC 608 are transmitted to TOR switch 642, which is a Layer 0 switch in switch architecture 640.

[0187] Although Figure 6 Examples and Figure 7A The flowchart in -C describes the processing performed by the TOR switch, but this example is not intended to be limiting. Generally, RoCE packets can be forwarded from a source host machine to a networking device providing Layer 2 functionality (e.g., a switch), a networking device providing Layer 3 functionality (e.g., a router), or a networking device providing both Layer 2 and Layer 3 functionality. For example, Figure 6 The TOR switches 642 and 644 described herein can provide Layer 2 and Layer 3 functionality. Typically, networking devices that receive RoCE packets from source host machines are edge devices in a switch architecture used to transmit data from source host machines to destination host machines.

[0188] Source host machine 602 can be connected to TOR switch 642 via Ethernet cable (e.g., copper, fiber, etc.). In some embodiments, packets arrive at the trunk port of TOR switch 642. The trunk port can allow packets belonging to multiple VLANs to enter, and traffic isolation is accomplished by VLAN information encoded in the packets. For example, a RoCE packet representing data to be transmitted from compute instance A-1604 will be labeled with a tag identifying VLAN 1001, while a RoCE packet representing data to be transmitted from compute instance B-1606 will be labeled with a tag identifying VLAN 1002.

[0189] At 708, the receiving ingress TOR switch (e.g., TOR switch 642) will convert each Layer 2 802.1Q-tagged RoCE packet to be forwarded via intermediate switch 646 into a Layer 3 packet. The Layer 3 packet format is based on a specific Overlay Encapsulation Protocol (OEP) used to transmit packets through a switch architecture. Various OEP protocols can be used to transmit RoCE packets through a switch architecture, such as Virtual Extensible LAN (VxLAN), Network Virtualization with Generic Routing Encapsulation (NVGRE), Generic Networking Virtualization Encapsulation (GENEVE), MPLS, Stateless Transport Tunneling (STT), etc. For example, for... Figure 6 In the embodiment described in 708, the ingress TOR switch 642 receives RoCE packets marked with 802.1Q from the RoCE NIC 608 and transforms each packet by encapsulating the packets as described in 708. Encapsulation is performed by adding a wrapper corresponding to the overlay encapsulation protocol to the packet, which will be used to transmit the packet over a Layer 3 switch architecture using a Layer 3 routing protocol, wherein the wrapper includes one or more headers. (For completeness, note that in some implementations of method 700, the ingress TOR switch may receive RoCE packets marked with 802.1Q from a source compute instance that are directed to a destination compute instance located in the same rack as the source compute instance. In such cases, the ingress TOR switch may forward the packets to the destination compute instance via Layer 2 transport (e.g., via the appropriate RoCE NIC) without processing them in 708 and beyond.)

[0190] As part of the processing in 708, the ingress TOR switch 642 generates one or more appropriate headers corresponding to the overlay encapsulation protocol being used, and adds a wrapper including one or more of the headers to each received Layer 2 802.1Q-tagged RoCE packet to convert the packet into a Layer 3 packet, wherein the overlay encapsulation protocol header added to the packet is visible to the networking devices in the switch architecture 640. Layer 2 frames are converted into Layer 3 packets so that the packet can be routed from the TOR switch 642 connected to the source host machine to the TOR switch 644 connected to the destination host machine 622, wherein routing occurs on the Layer 3 switch architecture 640 and uses a Layer 3 routing protocol that is more robust and scalable than the Layer 2 forwarding protocol.

[0191] As part of the processing performed in 708, at 708-1, for each received 802.1Q-tagged RoCE packet, the TOR switch 642 determines the VLAN information from the received packet and maps or translates that information into fields (or fields) added to the packet's wrapper in 708. In this way, the VLAN identifier information is mapped to a Layer 3 header, which is added to the packet in 708 and is visible to the various networking devices in the switch architecture 640. The Layer 3 packet includes at least one external header, which is added to the Layer 2 packet in 708.

[0192] For example, if the VxLAN protocol is used as the Layer 3 encapsulation protocol for transmitting packets through switch architecture 640, then in 708, Layer 2 802.1Q packets are converted into VxLAN packets by adding a VxLAN header (and other fields of the VxLAN wrapper) to the packets received in 708. As part of this operation, at 708-1, the TOR switch 642 determines the VLAN identifier information encoded in the 802.1Q tag of the packet and maps (or encodes) this information to a field added to the VxLAN header of the packet in 708. In some implementations, the VLAN information in the 802.1Q tag of the RoCE packet is mapped (e.g., according to VNI-VLAN mapping) to a corresponding unique VNI, which is copied to the VNI field added to the VxLAN header of the packet. In this way, the VLAN identifier information in the 802.1Q tag that identifies a specific tenant can also be included or forwarded to the corresponding identifier in the packet's overlay encapsulation header.

[0193] For RoCE packets with more than one VLAN tag (e.g., RoCE packet 830 with a Q-in-Q tag), the TOR switch 642 maps the VLAN ID in the outer tag of the RoCE packet to the corresponding VNI according to the VNI-VLAN mapping. The VNI-VLAN mapping (e.g., as a table) that can be stored in the memory of the TOR switch 642 is a one-to-one correspondence between VNIs assigned on the TOR switch 642 and the VLANs to which they are assigned. VLANs have only local meaning on the switch; therefore, the same VLAN ID can be mapped to a different VNI elsewhere in the architecture (although for convenience, it may be desirable to use the same VNI-VLAN mapping on multiple switches in the architecture) and / or the same VNI can be mapped to a different VLAN ID elsewhere in the architecture (e.g., another VLAN ID assigned to the same tenant). The VNI is copied to the corresponding data field of at least one outer header (e.g., the encapsulation protocol header) of the corresponding Layer 2 encapsulated packet, thereby extending multi-tenancy across the L3 network boundary. For packets encapsulating VxLAN (or GENEVE), the VNI is carried in the 24-bit VNI field of the VxLAN (or GENEVE) header of the Layer 3 encapsulated packet. For packets encapsulating NVGRE, the VNI is carried in the 24-bit Virtual Subnet ID (VSID) field of the NVGRE header of the Layer 3 encapsulated packet. For packets encapsulating STT, the VNI is carried in the 64-bit Context ID field of the STT header of the Layer 3 encapsulated packet.

[0194] Furthermore, as part of the processing in 708, at 708-2, for each received 802.1Q-tagged RoCE packet, the TOR switch 642 determines QoS information from the received packet and maps or translates that information into fields (or fields) added to the packet header in 708. In this way, the QoS information is mapped to a portion of the packet wrapper (e.g., an outer header) added in 708, which is visible to various networking devices in the switch architecture 640.

[0195] For example, if the VxLAN protocol is used as the Layer 3 encapsulation protocol for transmitting packets through switch architecture 640, then in 708, Layer 2 802.1Q packets are converted into VxLAN packets by adding a VxLAN envelope or wrapper (including a VxLAN header and several external headers) to the packets received in 708. As part of this operation, at 708-2, TOR switch 642 determines the QoS information encoded in the received packets and maps (or encodes) that information into fields added to the VxLAN wrapper in 708. As described above, depending on the implementation, the QoS information may be encoded in one or more different parts of the received Layer 2 packets. For example, the QoS information may be encoded in the PCP or 802.1p bits of the 802.1Q tag and / or may be encoded in the DSCP field of the Ethernet header of the received Layer 2 packets. As part of 708-2, TOR switch 642 determines this QoS information and maps or translates it into one (or more) fields added to the VxLAN wrapper in 708. In some implementations, QoS information from RoCE packets is mapped to the DSCP field in the outer IP header of the VxLAN wrapper. In this way, QoS information in RoCE packets marked with Layer 2 802.1Q is included or forwarded to the Layer 3 wrapper of the VxLAN packet in a way that makes it visible to various networking devices in the switch architecture 640.

[0196] Figure 10 The format of a Layer 3 encapsulated Packet 1000 (also known as a VxLAN packet) generated by an ingress TOR switch using VxLAN as an OEP is shown. Figure 10 As shown, the VxLAN packet 1000 includes an external Ethernet header 1010, an external IP header 1020, an external UDP header 1040, a VxLAN header 1050, a raw packet (e.g., a RoCEv2 packet) 1060, and a Frame Check Sequence (FCS) 1070. In the processing performed in 708, when VxLAN is an overlay encapsulation protocol, as part of an encapsulated 802.1Q-tagged RoCE packet, the TOR switch places the VxLAN header 1050 outside the "raw" 802.1Q-tagged RoCE packet, then places the external UDP header 1040 outside the VxLAN header, then places the external IP header 1020 outside the external UDP header, and finally adds the external Ethernet header 1010 on top of the external IP header.

[0197] The external Ethernet header 1010 includes a destination MAC address field 1011, a source MAC address field 1012, an optional VLAN type field 1013, an optional VLAN ID tag 1014, and an Ethernet type field 1015 carrying the value 0x0800. The external IP header 1020 includes an octet version and header length data field 1021, a six-bit DSCP data field 1022, a two-bit ECN data field 1024, a sixteen-bit length data field 1024, a sixteen-bit identification data field 1025, a sixteen-bit fragmentation flag and offset data field 1026, an octet time-to-live (TTL) data field 1027, an octet protocol data field carrying the value 17 (indicating UDP) 1028, a sixteen-bit header checksum data field 1029, a four-byte source IP address data field 1030 indicating the IP address of the ingress TOR switch, and a four-byte destination IP address data field 1031 indicating the IP address of the egress TOR switch. The external UDP header 1040 includes a source port field 1041 that can carry a hash value as information from the original RDMA packet, a destination (VxLAN) port field 1042 carrying the value 4789, a UDP length field 1043, and a checksum field 1044. The VxLAN header 1050 includes an octet flag field 1051, a 24-bit VNI field carrying the VNI 1053, and two reserved fields 1052 and 1054.

[0198] As part of creating a Layer 3 VxLAN packet by encapsulating a RoCE packet with the "original" 802.1Q tag in 708, the TOR switch stores VLAN ID information (e.g., lease information), QoS information (e.g., traffic class), and congestion information in various fields from the original packet to one or more of the headers added to the RoCE packet with the original 802.1Q tag. For example, in some implementations, the VLAN ID field is mapped to a VNI and carried in the VNI field 1053, the QoS information from the RoCE packet is copied to the DSCP field 1022 in the IP header 1020 (or the value mapped to it and carried therein), and congestion can be signaled by setting a bit (called the ECN bit) in the ECN field 1023. In this way, the QoS information in the DSCP data field of the IP header of the RoCE packet (e.g., from the DSCP field 902 in Figure 9) can be copied or otherwise mapped to the DSCP data field 1022 of the outer IP header 1020 of the encapsulated VxLAN packet. In an embodiment where QoS information in a RoCE packet is encoded in the PCP data field 813 of the 802.1Q tag of the RoCE packet, this information can also be mapped to the DSCP data field 1022 of the outer IP header 1020 of the VxLAN packet.

[0199] Therefore, in 708, an overlay encapsulation protocol wrapper is added to RoCE packets, and the VLAN ID and QoS information from the RoCE packets are mapped to the overlay encapsulation protocol wrapper and encoded therein in a way that is visible to the devices in the switch architecture. (Reference) Figure 7B At 710, the encapsulated Layer 3 packet generated in 708 is routed through the switch architecture, from the TOR switch that receives the packet from the source host machine to the TOR switch connected to the destination host machine. In some embodiments, the packet is forwarded and sent along a tunnel (e.g., a VxLAN tunnel if a VxLAN overlay encapsulation protocol is used), which allows the packet to travel through the switch architecture from the TOR switch connected to the source host machine to the TOR switch connected to the destination host machine. The path taken by the packet in the switch architecture can traverse multiple networking devices, each configured to receive the packet via the networking device's ingress port and forward the packet to the next-hop networking device via the networking device's egress port to facilitate the delivery of the packet to the TOR switch connected to the destination host machine. For example, in Figure 6 In the embodiments depicted, the encapsulated Layer 3 packets are forwarded from TOR switch 642 to TOR switch 644 via one or more intermediate switches 646 of switch architecture 640.

[0200] In 708, by translating the VLAN ID and QoS information from Layer 2 802.1Q RoCE packets into information carried in a wrapper encapsulated in Layer 3, the VLAN information (e.g., lease information) and QoS information are now visible to the switches and networking devices in switch architecture 640, enabling packet routing using Layer 3 routing protocols. As part of the processing in 710, each networking device (including TOR switches 642 and 644) in switch architecture 640 that receives and forwards Layer 3 encapsulated RoCE packets is configured at 710-1 to forward packets based on Layer 3 and according to the QoS information specified in the packet encapsulation wrapper. In some implementations, each networking device receiving packets may have multiple RDMA data queues corresponding to different QoS priority levels. Upon receiving a packet, the networking device is configured to determine the packet's QoS information from one or more fields of the encapsulation wrapper (or from the Layer 2 header, for the first TOR switch receiving the packet) and queue the packet into an RDMA data queue corresponding to the priority specified by the QoS information. The packet is then removed from the networking device and forwarded according to the specific priority of the queue. Multiple RDMA data queues can be implemented using, for example, one or more buffers, and the networking device may also include queuing logic and dequeueing logic. The queuing logic is configured to distribute incoming packets among multiple queues according to a specified priority level (e.g., traffic class), and the dequeueing logic is configured to serve multiple queues according to a desired scheduling scheme (e.g., weighted round-robin scheduling and / or strict priority scheduling). When implementing the networking device using commercial chips, it may be desirable to make full use of a relatively small number of buffers. For example, it may be desirable to reuse unused buffers (e.g., from queues that are not otherwise used) as at least a portion of multiple queues. For example, it may be desirable to implement at least a portion of environment 600 (e.g., TOR switches 642 and 644, switch architecture 640) to exclude support for multicast traffic, and in this case, buffers previously assigned to store multicast traffic can instead be reprogrammed as storage devices for multiple queues.

[0201] As part of 710, in 710-2, each networking device in a switch architecture that receives and forwards Layer 3 encapsulated RoCE packets can signal congestion by marking the outer header of the Layer 3 encapsulation wrapper of the packet. In some embodiments, the RoCE protocol uses a mechanism called Explicit Congestion Notification (ECN) to specify congestion information, which is an IP protocol concept. According to this mechanism, the ECN bit in the IP header of the packet is used to specify or encode congestion information. Thus, as part of the processing in 710-2, if a networking device receiving and forwarding packets detects congestion (e.g., detects that a buffer is full beyond a threshold), then the networking device can signal congestion by setting the ECN bit in the outer IP header of the overlay encapsulation protocol wrapper of the packet. For example, if VxLAN is an overlay encapsulation protocol, then the bit in the ECN field 1023 of the outer IP header 1020 can be set by the networking device (e.g., if the bit has not already been set) to signal congestion.

[0202] In this way, as packets travel through the switching architecture, congestion information is included in and updated within the packets, and carried along with the packets to their destination. For example, in Figure 6 In the embodiments depicted, as a packet travels from source host machine 602 to destination host machine 622, the packet passes through a series of networking devices in the switch architecture 640. Any networking device the packet passes through can signal congestion by setting congestion bits (e.g., bits in the ECN field of the outer IP header) in the packet's Layer 3 encapsulation wrapper. This series of networking devices includes TOR switch 642, TOR switch 644, and any intermediate switches 646 along the path the packet traverses.

[0203] Congestion indication or labeling within packets can be accomplished by any networking device in the switching architecture that routes packets from the source host machine to the destination host machine. The egress TOR copies the ECN bits from the Layer 3 wrapper to the IP header of the inner packet and sends that inner packet as a Layer 2 packet to the destination host machine. In this way, congestion information is carried in the packet all the way to the destination host machine. The congestion information is carried across the boundary of the Layer 2 network, which includes the source and destination compute instances and host machines, and the Layer 3 network, which includes the TOR switch and intermediate switches in the switching architecture.

[0204] Traditionally, RoCE relies on Layer 2 Priority Flow Control (PFC) or ECN, or a combination of PFC and ECN, for congestion control. It may be desirable to implement TOR switches (e.g., TOR switches 642 and 644) to perform Priority Flow Control (PFC). When the receive buffer of a PFC-enabled switch fills to a threshold level, the switch sends a PAUSE frame for the corresponding priority class back to the sender. PFC provides up to eight priority classes, and it may be desirable to implement switches that use the PCP value of the packet in the receive buffer header as the priority class indicated by the PAUSE frame (or alternatively, use a mapping of the packet's DSCP value to the priority indicated by the PAUSE frame).

[0205] It might be desirable to implement congestion control on an application-by-application basis, ensuring that congestion control that pauses one customer's RDMA traffic does not pause another customer's RDMA traffic. Because a PAUSE frame causes the sender to pause all traffic of the indicated priority class and thus potentially affect multiple customers, it might be desirable to configure each TOR switch to prevent any PAUSE frames from traveling outside the TOR switch's architecture. For example, it might be desirable to restrict PFC to the host-facing interfaces of each TOR switch (e.g., by configuring each input port of the TOR switch to only pass PAUSE frames down to the host or another input port of the TOR switch). Including PAUSE frames locally in this way can help prevent congestion from spreading across large architectures and / or avoid real-time lockout.

[0206] At position 712, the TOR switch (also known as the egress TOR switch, as it stands for egress edge device in switch architecture) connected to the destination host machine receives Layer 3 encapsulated RoCE packets. For example, in Figure 6 In the embodiment depicted, the egress TOR switch 644 receives packets.

[0207] At 714, for each received Layer 3 encapsulated packet, the TOR switch determines congestion information from the packet's Layer 3 overlay encapsulation protocol wrapper and maps or translates the congestion information into fields within the Layer 2 802.1Q-tagged RoCE frame encapsulated by the Layer 3 wrapper. In this way, for each Layer 3 encapsulated RoCE packet received by the egress TOR switch, the congestion information, which may have been signaled by one or more networking devices (e.g., TOR switch 642, one or more intermediate switches 646) along the path the packet traverses in the switch architecture and encoded in fields (e.g., ECN fields) of the Layer 3 overlay encapsulation protocol wrapper header, is mapped to and retained in the header of the 802.1Q-tagged RoCE Layer 2 frame. In some implementations, the congestion information determined from the Layer 3 wrapper (e.g., ECN field 1023 in the IP header 1020 of the VxLAN packet) is copied to the ECN field (e.g., ECN field 903 depicted in Figure 9) of the IP header of the Layer 2 802.1Q-tagged RoCE frame.

[0208] At 716, for each received Layer 3 encapsulated RoCE packet, the egress TOR switch decapsulates the packet by removing the encapsulation wrappers added to the packet in 708 (e.g., external Ethernet header 1010, external IP header 1020, external UDP header 1040, VxLAN header 1050, and FCS 1070), restoring the inner Layer 2 802.1Q-labeled RoCE packet. For example, if a VxLAN wrapper is added to the packet, that wrapper is removed in 714 to leave the 802.1Q-labeled RoCE packet. Because congestion information is mapped to the header of the 802.1Q-labeled RoCE packet in 714, the congestion information in the Layer 3 overlay encapsulation protocol wrapper is not lost due to the decapsulation of the Layer 3 encapsulated packet. The mapping (e.g., copying) of the congestion information in 714 can be performed before, during, or after decapsulation in 716.

[0209] As part of the processing in 716, in addition to translating congestion information from the Layer 3 overlay encapsulation protocol wrapper into a header within a Layer 2 802.1Q marked RoCE packet, the egress TOR switch 644 itself can set the ECN congestion bit to signal congestion when experiencing congestion.

[0210] refer to Figure 7C At point 718, the decapsulated Layer 2 802.1Q marked RoCE packets are forwarded by the egress TOR switch to the destination host machine. For example, in Figure 6In this embodiment, the RoCE packets decapsulated by the TOR switch 644 are forwarded to the destination host machine 622. On the destination host machine, the packets are received and processed by the RoCE NIC on the destination host machine.

[0211] At 720, for each received 802.1Q-tagged RoCE packet, the RoCENIC on the destination host machine checks whether congestion is signaled in the header of the received packet. For example, if the ECN bit in the packet's IP header is set, congestion can be signaled. If congestion is determined in 720, then in 722, the RoCE NIC sends a congestion-indicating response to the packet's sender (e.g., to the RoCE NIC on the source host machine) and requests the sender to slow down the data transmission rate. In some implementations using the ECN protocol, the response takes the form of a congestion notification packet (CNP packet) sent from the RoCENIC on the destination host machine to the RoCE NIC on the source host machine. For example, Data Center Quantized Congestion Notification (DCQCN) can be implemented in the RoCE NIC (e.g., an RDMA NIC card and its corresponding software driver) to use ECN information to inform the sender of congestion by sending CNP packets for flow control. These CNP packets indicate to the source host machine that there is congestion in the network and request that the source host machine slow down the rate at which it sends RoCE packets. CNP packets are sent to the appropriate sender identified based on information in the received Layer 2 RoCE packets (e.g., source MAC address and / or source IP address). Upon receiving such notification, the sender (e.g., the RoCE NIC on the source host machine) may, in response, reduce the transmission of RoCE packets accordingly. Further details regarding CNP packets and how they are transmitted from the destination host machine to the source host machine are provided below.

[0212] In some implementations, the sender may use an algorithm that calculates a percentage reduction in the data transmission rate. For example, upon receiving a first CNP packet, the sender (e.g., a RoCE NIC on the source host machine) may reduce its transmission rate by a certain percentage. Upon receiving another CNP packet, it may further reduce its transmission rate by an additional percentage, and so on. In this way, the sender can perform adaptive rate control in response to receiving CNP packets.

[0213] At point 724, for each received 802.1Q-tagged RoCE packet, the RoCENIC on the destination host machine retrieves the RDMA data payload from the packet and transfers the data to the application memory on the destination host machine of the destination compute instance via the corresponding Virtual Function (VF). In some embodiments, the Virtual Function on the RoCENIC corresponding to the destination compute instance is configured to control the RoCE engine of the RoCE NIC to transfer the RDMA data payload to the memory space of the application memory on the destination host machine in a DMA transfer manner. This operation completes the RDMA data transfer from the source compute instance to the destination compute instance.

[0214] As described above, the VLAN identifier that identifies the tenant is included in the 802.1Q tag added to the RoCE packet: for example, in the VLAN ID field of the 802.1Q tag. The VLAN ID or lease information is also mapped to the VNI included in the Layer 3 overlay encapsulation protocol wrapper, which is added to the RoCE packet labeled with the 802.1Q tag by the TOR switch connected to the source host machine. Mapping the VLAN identifier (or lease information) to the identifier in the field of the Layer 3 encapsulation wrapper makes the lease information visible to networked devices in the Layer 3 switch architecture. These networked devices use this information to isolate traffic belonging to different customers or tenants.

[0215] The QoS information associated with the packets is also maintained from the RoCE NIC on the source host machine to the RoCE NIC on the destination host machine. This information is encoded in a Layer 3 overlay encapsulation protocol wrapper added to RoCE packets marked with 802.1Q by the ingress TOR switch, making the QoS information encoded in the Layer 2 RoCE packets visible to networking devices in the switch architecture. This allows networking devices in the switch architecture to use Layer 3 routing protocols and route RoCE traffic through the switch architecture based on the QoS information associated with each packet.

[0216] Any networking device in a switching architecture can signal congestion on a per-packet basis. This congestion information is stored in the packet as it travels through the switching architecture from the TOR connected to the source host machine to the TOR connected to the destination host machine. At the TOR switch connected to the destination host machine, the congestion information from the Layer 3 encapsulation wrapper is translated (e.g., copied) into the RoCE packet header (e.g., translated into the ECN bit in the IP header of the RoCE packet) and thus stored and made available to the destination host machine. The destination host machine can then respond to the congestion information by sending a CNP packet.

[0217] Congestion Notification Information Routing

[0218] RDMA data transmission is generally highly sensitive to network latency caused by congestion in switched network architectures. RDMA Congestion Notification Packets (CNP packets) are crucial because they help signal RDMA congestion management (flow control). Therefore, they are particularly sensitive to packet loss and network latency, while not requiring large network bandwidth. Consequently, CNP packets sent by the destination host in response to congestion indicated by received packets are given high priority so that they reach the source host with minimal latency and can notify the sender to slow down data transmission to minimize or avoid packet loss due to congestion. Furthermore, the priority queuing of CNP packets minimizes the likelihood of CNP packets themselves being dropped due to congestion.

[0219] To achieve this, Congestion Notification Packet (CNP) traffic is assigned high priority, such that at each networked device in the switch architecture, as CNP packets travel from the destination host machine to the source host machine, CNP packets are assigned to a queue with very high priority. In some implementations, CNP traffic is assigned to the second highest queue (e.g., second only to the network control queue) on each networked device in the switch architecture.

[0220] Furthermore, strict priority queuing is used for CNP packets. According to strict priority queuing, traffic assigned to a strict priority queue will starve other traffic. For example, if a network device in a switch architecture has packets from tenant #1, packets from tenant #2, and CNP packets, and if the network device can only send one packet, then tenant #1 and tenant #2 packets will be queued, and the CNP packet will be sent instead. In some implementations, CNP packets are configured with QoS information indicating a special class for CNP packets, and strict priority queuing will be used to queue packets for transmission.

[0221] However, in strict queuing implementations, it must be noted that strict priority queuing will not indefinitely starve other traffic. Therefore, a limit can be imposed on how much CNP traffic is allowed through the switch architecture. In some implementations, this limit is a small fraction of the total link bandwidth. For example, a dedicated strict priority queue can be allocated to CNP traffic with low bandwidth guarantees so that it does not starve the actual RDMA traffic class. Therefore, if a malicious or misconfigured application starts generating a large number of CNP packets, causing CNP traffic to starve other traffic (e.g., RDMA data traffic), then a limit threshold is needed to minimize the impact of this problem on other traffic.

[0222] Feedback latency occurs between the time it takes for an ECN-enabled device to tag a packet and the time it takes for the sender to receive the resulting CNP packet. In the worst case, this latency can lead to congestion collapse, a long-standing problem in high-performance networks. To avoid lengthy feedback loops between switch ECN tagging, receiving host CNP responses, and subsequent RDMA congestion management actions by the sending host, it is desirable to configure low and deterministic ECN tagging thresholds for networking devices in the Switch Architecture 640. For example, once congestion is detected, it is desirable to configure each of the TOR switches and intermediate switches to tag every packet. An aggressive ECN tagging policy ensures that switches initiate ECN tagging at the first sign of network congestion, thus providing a tight loop for congestion management and helping to protect the network from congestion collapse.

[0223] Queue-based routing to avoid head-of-line blocking

[0224] As described above, QoS information associated with packets is used by networking devices in a switch architecture to route packets using Layer 3 routing protocols. QoS information can identify specific priorities or classes. Networking devices in a switch architecture (e.g., any one or more (or all) of TOR switch 642, TOR switch 644, and intermediate switch 646) can use this priority information to identify specific priority queues from multiple queues used by the networking device for forwarding packets. For example, a networking device can maintain a set of queues, each for a different priority class. Packets corresponding to different customers or tenants can have different assigned priorities or classes; therefore, packets of different classes can be assigned to different queues on the networking devices in the switch architecture. Because packets for different classes (e.g., different tenants, different applications) are assigned to different queues on the networking devices in the switch architecture, congestion caused by traffic for one class (e.g., one tenant) will not affect traffic for another class (e.g., another tenant). In some embodiments, it is also possible to assign RDMA packet streams from different tenants to the same queue of the networked device (e.g., according to the same priority class they are assigned) and / or RDMA packet streams from the same tenant (e.g., packet streams from different applications of the tenant) to different queues of the networked device (e.g., according to their respective different assigned priority classes).

[0225] In some embodiments, multiple queues are used on the networking device to handle RDMA / RoCE traffic to avoid head-of-line (HOL) congestion. Providing multiple queues for RDMA data traffic avoids queueing all RDMA / RoCE traffic into a single queue, which can lead to congestion. Multiple (e.g., four) RDMA queues also allow for multiple different applications requiring different levels of performance, all of which need lossless networking. In this way, an environment can provide dedicated network paths for latency-sensitive RDMA applications across the entire architecture at cloud scale, and can do so while avoiding HOL congestion. Each core network queue can support configurable weighted bandwidth distribution.

[0226] In some cases, customers or tenants can control which priority queues will be used to route their traffic via QoS information set for packets. In some implementations, a certain percentage of queues are reserved for RDMA traffic on networking devices in a switch architecture with multiple queues (e.g., multiple queues) for packet transmission. For example, in one implementation, if the switches in the switch architecture have eight queues, then six queues can be reserved for RDMA traffic. These RDMA queues can be weighted round-robin queues, each receiving a share of network bandwidth but not starving each other (e.g., to provide fairness across RDMA applications). In one such scheme, each RDMA queue is equally weighted such that each RDMA queue is served once per dequeue cycle. For example, 95% of the link capacity (shared by traffic allocated to different queues) can be allocated to six RDMA queues, each receiving one-sixth of 95% (e.g., via a weighted round-robin scheme with equal weights). Additionally, it is desirable to ensure that the switch architecture is not overutilized, ensuring sufficient bandwidth to handle traffic transmitted through the switch architecture. Traffic from different customers or tenants can be assigned to the same RDMA queue, but will be distinguished based on the VLAN ID and / or VNI encoded in the packet.

[0227] Switch architecture 640 can use network control traffic classes for underlying IP routing protocol functions (e.g., between TOR switches). In one example, multiple queues on a networked device include network control queues to carry Ethernet VPN (EVPN) traffic, which can be used to propagate MAC address information across the underlying network and / or to advertise Virtual Tunnel Endpoint (VTEP) flood lists. These network control protocols (e.g., Border Gateway Protocol (BGP)) can be allocated the highest traffic class. For example, network control queues can be dedicated to network control traffic classes and implemented as strictly priority queues, such that they are emptied before any RDMA queues are served. Because network control traffic does not consume a large amount of network bandwidth, network control traffic classes can allocate a small portion of the total bandwidth of multiple queues.

[0228] Figure 9B Example 950 shows multiple queues of networking devices (e.g., TOR switch 642 or 644, intermediate switch 646, etc.), including four RDMA queues 960-1 to 960-4 and a network control (NC) queue 964. Figure 9B As shown, multiple queues 950 may also include a dedicated congestion notification (CN) queue 962 to carry CNP packets. Timely delivery of CNP packets to the sending host is critical for successful RDMA congestion management because if they are lost, the flow control signaling them will not occur. Therefore, while CNP traffic is particularly sensitive to packet loss and network latency, it does not require a large amount of network bandwidth. These requirements can be balanced by configuring the CN queue 962 as a strictly priority queue, ensuring it is emptied before any RDMA queues (e.g., queues 960-1 through 960-4) are served, but with only low-priority bandwidth guarantees so that it does not starve the actual RDMA traffic class. To prevent the congestion notification queue 962 from starving the network control queue 964 (e.g., in cases of misconfiguration or other problems leading to excessive CNP traffic), it is desirable to configure the congestion notification queue 962 with a lower priority than the network control queue 964.

[0229] Additionally or alternatively, the networked device's multiple queues may also include scavenger queues for non-RDMA traffic (e.g., other protocols such as TCP). Scavenger traffic classes utilize unused network bandwidth without adversely affecting RDMA traffic classes. The networked device's dequeueing logic can be configured to serve scavenger queues with a lower priority than RDMA queues, for example, by assigning them a lower weight in a weighted round-robin scheme (e.g., the weight is guaranteed bandwidth). Figure 9C Example 952 shows multiple queues 950 of a networking device (e.g., TOR switch 642 or 644, intermediate switch 646, etc.) as described above, which also includes a scavenger queue 966.

[0230] As described herein, RDMA packets (Layer 2 RDMA packets, or packets encapsulated in Layer 3 containing Layer 2 RDMA packets) carry QoS values ​​(e.g., in the PCP data field and / or in the DSCP data field) indicating the packet's priority (e.g., traffic class), and the networking device's enqueueing logic can be configured to distribute incoming packets across multiple RDMA queues of the networking device based on their QoS values. For the PCP data field used to carry QoS values ​​and RDMA packets distributed in... Figure 9BThe example shown, between RDMA queues 960-1 and 960-4, can use a mapping such as the following: RDMA packets with a PCP value of 6 or 7 are stored in RDMA queue 960-1, RDMA packets with a PCP value of 4 or 5 are stored in RDMA queue 960-2, RDMA packets with a PCP value of 2 or 3 are stored in RDMA queue 960-3, and RDMA packets with a PCP value of 0 or 1 are stored in RDMA queue 960-4. For cases where the DSCP data field is used to carry QoS values ​​and RDMA packets are as follows... Figure 9B The example shown, distributed across RDMA queues 960-1 to 960-4, can use mappings such as the following: RDMA packets with DSCP values ​​in the range of 48 to 64 are stored in RDMA queue 960-1, RDMA packets with DSCP values ​​in the range of 32 to 47 are stored in RDMA queue 960-2, RDMA packets with DSCP values ​​in the range of 16 to 32 are stored in RDMA queue 960-3, and RDMA packets with DSCP values ​​in the range of 0 to 15 are stored in RDMA queue 960-4. Those skilled in the art will recognize that the two mappings described above are merely non-limiting examples, and that the distribution of RDMA packets across multiple queues on a networked device can be performed based on such mappings or any other mapping from QoS values ​​to RDMA queues (e.g., via enqueue logic).

[0231] Deterministic congestion (e.g., ECN bit) flag

[0232] In some embodiments, a deterministic congestion marking scheme is used, where congestion marking is performed on a per-packet basis. Thus, for each packet, if a networking device in the switching architecture experiences or detects congestion, the networking device signals the congestion by marking a field in the packet: for example, by marking the ECN bit in the IP header of the Layer 3 encapsulation wrapper of the RoCE packet. Therefore, when congestion occurs, multiple packets arriving at the destination host machine will set their congestion bits. In response to each such packet, the destination host machine can send a CNP packet. The sender can reduce its transmission rate in response to the CNP packet. The goal is to detect congestion early so that the sender can slow down transmission early, thereby reducing the likelihood of packet drop or loss.

[0233] The switch architecture also plays a role in reducing RoCE packet latency and packet loss. As mentioned above, the switch architecture can be structured as a Clos network, such as... Figure 5The network described above is illustrated in the diagram. For example, in a Clos network with a two-layer topology of only Layer 0 (TOR switches) and Layer 1 switches (backbone switches), RoCE packets can reach any destination host machine from any source host machine in three hops. Minimizing the number of hops translates to very low latency, which is ideal for RoCE traffic.

[0234] In some embodiments, RDMA traffic belonging to the same flow follows the same path from the source host machine to the destination host machine because RDMA traffic is sensitive to packet reordering. This flow-based routing avoids packets arriving at the destination host machine out of order. For example, an ingress TOR switch can be configured to maintain packet order within each flow via an Equal Cost Per Flow (ECMP) scheme (e.g., an n-way ECMP scheme, where "n" should not be confused with the tier "n" in a Clos network). The flow to which a packet belongs is generally defined by a combination of the packet's source IP address, destination IP address, source port, destination port, and protocol identifier (also known as a 5-tuple).

[0235] Example Infrastructure as a Service architecture

[0236] As noted above, Infrastructure as a Service (IaaS) is a specific type of cloud computing. IaaS can be configured to provide virtualized computing resources over a public network (e.g., the Internet). In the IaaS model, cloud providers can host infrastructure components (e.g., servers, storage devices, network nodes (e.g., hardware), deployment software, platform virtualization (e.g., hypervisor layer), etc.). In some cases, IaaS providers can also offer various services accompanying these infrastructure components (e.g., billing, monitoring, logging, security, load balancing, and clustering, etc.). Therefore, because these services may be policy-driven, IaaS users can implement policies to drive load balancing to maintain application availability and performance.

[0237] In some cases, IaaS customers can access resources and services over a wide area network (WAN) such as the Internet and can use the cloud provider's services to install the remaining elements of the application stack. For example, a user can log in to the IaaS platform to create virtual machines (VMs), install an operating system (OS) on each VM, deploy middleware such as databases, create buckets for workloads and backups, and even install enterprise software into that VM. The customer can then use the provider's services to perform various functions, including balancing network traffic, troubleshooting application issues, monitoring performance, and managing disaster recovery.

[0238] In most cases, cloud computing models will require the involvement of cloud providers. Cloud providers can, but are not necessarily, third-party providers specializing in (e.g., provisioning, renting, selling) IaaS services. Entities may also choose to deploy private clouds, thus becoming their own infrastructure service providers.

[0239] In some examples, IaaS deployment is the process of placing a new application or a new version of an application onto a prepared application server, etc. It may also include the processing of server preparation (e.g., installation libraries, daemons, etc.). This is typically managed by the cloud provider, below the hypervisor layer (e.g., servers, storage devices, network hardware, and virtualization). Therefore, the customer can be responsible for processing (OS), middleware, and / or application deployment (e.g., on self-service virtual machines, etc., which can be started on demand).

[0240] In some examples, IaaS provisioning can refer to acquiring computers or virtual hosts for use, or even installing necessary libraries or services on them. In most cases, deployment does not include provisioning, and provisioning may need to be performed first.

[0241] In some cases, IaaS provisioning presents two distinct challenges. First, there's the initial challenge of provisioning the initial infrastructure set before anything is operational. Second, once everything is provisioned, there's the challenge of evolving the existing infrastructure (e.g., adding new services, changing services, removing services, etc.). In some cases, both challenges can be addressed by enabling configuration that declaratively defines the infrastructure. In other words, the infrastructure (e.g., which components are needed and how they interact) can be defined by one or more configuration files. Therefore, the overall topology of the infrastructure (e.g., which resources depend on which resources and how they work together) can be described declaratively. In some cases, once the topology is defined, workflows for creating and / or managing the different components described in the configuration files can be generated.

[0242] In some examples, the infrastructure can have many interconnected components. For example, there may be one or more Virtual Private Clouds (VPCs) (e.g., potential on-demand pools of configurable and / or shared computing resources), also known as the core network. In some examples, one or more security group rules may also be provided to define how the network's security is configured, as well as one or more virtual machines (VMs). Other infrastructure elements, such as load balancers, databases, etc., may also be provided. The infrastructure can evolve incrementally as more and / or more infrastructure elements are expected and added.

[0243] In some cases, continuous deployment techniques can be used to enable the deployment of infrastructure code across various virtual computing environments. Furthermore, the described techniques enable infrastructure management within these environments. In some examples, service teams may write code that they expect to deploy to one or more, but often many, different production environments (e.g., across various geographical locations, sometimes spanning the entire world). However, in some examples, the infrastructure on which the code will be deployed must first be set up. In some cases, provisioning can be done manually, resources can be provisioned using provisioning tools, and / or once the infrastructure is provisioned, the code can be deployed using deployment tools.

[0244] Figure 11 This is a block diagram 1100 illustrating an example pattern of an IaaS architecture according to at least one embodiment. Service operator 1102 may be communicatively coupled to a secure host lease 1104, which may include a virtual cloud network (VCN) 1106 and a secure host subnet 1108. In some examples, service operator 1102 may use one or more client computing devices, which may be portable handheld devices (e.g., iPhone®, cellular phone, iPad®, computing tablet, personal digital assistant (PDA)) or wearable devices (e.g., Google Glass® head-mounted display), running software (such as Microsoft Windows Mobile®) and / or various mobile operating systems (such as iOS, Windows Phone, Android, BlackBerry 8, Palm OS, etc.), and supporting the Internet, email, short message service (SMS), Blackberry®, or other communication protocols. Alternatively, client computing devices may be general-purpose personal computers, including, for example, personal computers and / or laptops running various versions of Microsoft Windows®, Apple Macintosh®, and / or Linux operating systems. Client computing devices can be workstation computers running a variety of commercially available UNIX® or UNIX-like operating systems, including but not limited to any of the various GNU / Linux operating systems (such as, for example, Google Chrome OS). Alternatively or additionally, client computing devices can be any other electronic device, such as thin client computers, internet-enabled gaming systems (e.g., Microsoft Xbox game consoles with or without Kinect® gesture input devices), and / or personal messaging devices capable of communicating over a network that can access VCN 1106 and / or the internet.

[0245] VCN 1106 may include a local peering gateway (LPG) 1110, which may be communicatively coupled to a secure shell (SSH) VCN 1112 via LPG 1110 contained in SSH VCN 1112. SSH VCN 1112 may include an SSH subnet 1114, and SSH VCN 1112 may be communicatively coupled to a control plane VCN 1116 via LPG 1110 contained in control plane VCN 1116. Furthermore, SSH VCN 1112 may be communicatively coupled to a data plane VCN 1118 via LPG 1110. Control plane VCN 1116 and data plane VCN 1118 may be contained in a service lease 1119 that may be owned and / or operated by an IaaS provider.

[0246] The control plane VCN 1116 may include a control plane demilitarized zone (DMZ) layer 1120 that acts as a peripheral network (e.g., a portion of a corporate network between a corporate intranet and an external network). DMZ-based servers can assume limited liability and help control vulnerabilities. Furthermore, the DMZ layer 1120 may include one or more load balancer (LB) subnets 1122, a control plane application (app) layer 1124 that may include one or more application (app) subnets 1126, and a control plane data layer 1128 that may include one or more database (DB) subnets 1130 (e.g., one or more front-end DB subnets and / or one or more back-end DB subnets). One or more LB subnets 1122 contained in the control plane DMZ layer 1120 may be communicatively coupled to one or more application subnets 1126 contained in the control plane application layer 1124 and an Internet gateway 1134 that may be contained in the control plane VCN 1116. The application subnets 1126 may be communicatively coupled to one or more DB subnets 1130 contained in the control plane data layer 1128, as well as a service gateway 1136 and a Network Address Translation (NAT) gateway 1138. The control plane VCN 1116 may include the service gateway 1136 and the NAT gateway 1138.

[0247] The control plane VCN 1116 may include a data plane mirror application (app) layer 1140, which may include one or more application subnets 1126. The one or more application subnets 1126 included in the data plane mirror application layer 1140 may include a virtual network interface controller (VNIC) 1142 capable of executing a compute instance 1144. The compute instance 1144 may communicatively couple the one or more application subnets 1126 of the data plane mirror application layer 1140 to the one or more application subnets 1126 that may be included in the data plane application (app) layer 1146.

[0248] Data plane VCN 1118 may include data plane application layer 1146, data plane DMZ layer 1148, and data plane data layer 1150. Data plane DMZ layer 1148 may include one or more LB subnets 1122 communicatively coupled to one or more application subnets 1126 of data plane application layer 1146 and Internet gateway 1134 of data plane VCN 1118. One or more application subnets 1126 communicatively coupled to service gateway 1136 and NAT gateway 1138 of data plane VCN 1118. Data plane data layer 1150 may also include one or more DB subnets 1130 communicatively coupled to one or more application subnets 1126 of data plane application layer 1146.

[0249] The Internet gateway 1134 of control plane VCN 1116 and data plane VCN 1118 can be communicatively coupled to metadata management service 1152, and metadata management service 1152 can be communicatively coupled to public Internet 1154. Public Internet 1154 can be communicatively coupled to NAT gateway 1138 of control plane VCN 1116 and data plane VCN 1118. Service gateway 1136 of control plane VCN 1116 and data plane VCN 1118 can be communicatively coupled to cloud service 1156.

[0250] In some examples, service gateway 1136, either control plane VCN 1116 or data plane VCN 1118, can make application programming interface (API) calls to cloud service 1156 without traversing the public internet 1154. API calls from service gateway 1136 to cloud service 1156 can be unidirectional: service gateway 1136 can make API calls to cloud service 1156, and cloud service 1156 can send requested data to service gateway 1136. However, cloud service 1156 may not initiate API calls to service gateway 1136.

[0251] In some examples, secure host lease 1104 can be directly connected to service lease 1119, which would otherwise be isolated. Secure host subnet 1108 can communicate with SSH subnet 1114 via LPG 1110, which enables bidirectional communication between otherwise isolated systems. Connecting secure host subnet 1108 to SSH subnet 1114 allows secure host subnet 1108 to access other entities within service lease 1119.

[0252] Control plane VCN 1116 may allow users of service lease 1119 to configure or otherwise provision desired resources. Desired resources provisioned in control plane VCN 1116 may be deployed or otherwise used in data plane VCN 1118. In some examples, control plane VCN 1116 may be isolated from data plane VCN 1118, and the data plane mirror application layer 1140 of control plane VCN 1116 may communicate with the data plane application layer 1146 of data plane VCN 1118 via VNIC 1142, which may be included in both the data plane mirror application layer 1140 and the data plane application layer 1146.

[0253] In some examples, users or clients of the system can make requests, such as create, read, update, or delete (CRUD) operations, via the public internet 1154, which can transmit requests to the metadata management service 1152. The metadata management service 1152 can transmit requests to the control plane VCN 1116 via internet gateway 1134. Requests can be received by one or more LB subnets 1122 contained in the control plane DMZ layer 1120. The LB subnets 1122 can determine that the request is valid, and in response to this determination, they can transmit the request to one or more application subnets 1126 contained in the control plane application layer 1124. If the request is validated and requires a call to the public internet 1154, the call to the public internet 1154 can be transmitted to a NAT gateway 1138 that can make calls to the public internet 1154. The request may expect the storage to be located in one or more DB subnets 1130.

[0254] In some examples, the data plane mirroring application layer 1140 can facilitate direct communication between the control plane VCN 1116 and the data plane VCN 1118. For example, it may be desirable to apply configuration changes, updates, or other appropriate modifications to resources contained in the data plane VCN 1118. Through VNIC 1142, the control plane VCN 1116 can communicate directly with the resources contained in the data plane VCN 1118, and thus can perform configuration changes, updates, or other appropriate modifications.

[0255] In some embodiments, the control plane VCN 1116 and data plane VCN 1118 may be included in service lease 1119. In this case, the system's users or customers may not own or operate the control plane VCN 1116 or data plane VCN 1118. Alternatively, the IaaS provider may own or operate both the control plane VCN 1116 and data plane VCN 1118, and both planes may be included in service lease 1119. This embodiment can enable the isolation of networks that might prevent users or customers from interacting with resources of other users or customers. Furthermore, this embodiment can allow users or customers of the system to privately store databases without relying on the public Internet 1154, which may not have the desired level of security for storage.

[0256] In other embodiments, one or more LB subnets 1122 included in the control plane VCN 1116 may be configured to receive signals from the service gateway 1136. In this embodiment, the control plane VCN 1116 and the data plane VCN 1118 may be configured to be invoked by the IaaS provider's customers without invoking the public internet 1154. The IaaS provider's customers may expect this embodiment because the database(s) used by the customer can be controlled by the IaaS provider and can be stored on service lease 1119, which may be isolated from the public internet 1154.

[0257] Figure 12 This is a block diagram 1200 illustrating another example pattern of an IaaS architecture according to at least one embodiment. Service operator 1202 (e.g., Figure 11 Service provider 1102) can communicatively couple to secure host lease 1204 (e.g., Figure 11 Secure hosting lease 1104), the secure hosting lease 1204 may include a virtual cloud network (VCN) 1206 (e.g., Figure 11 VCN 1106) and Secure Host Subnet 1208 (e.g., Figure 11 The secure host subnet 1108). VCN 1206 may include a local peering gateway (LPG) 1210 (e.g., Figure 11 The LPG 1110, which can be communicatively coupled to the Secure Shell (SSH) VCN 1212 (e.g., LPG 1110 contained in the SSH VCN 1212) Figure 11 SSH VCN 1112). SSH VCN 1212 can include SSH subnet 1214 (e.g., Figure 11SSH subnet 1114), and SSH VCN 1212 can be communicatively coupled to control plane VCN 1216 via LPG 1210 included in control plane VCN 1216 (e.g., Figure 11 Control plane VCN 1116). Control plane VCN 1216 may be included in service lease 1219 (e.g., Figure 11 In the service lease 1119), and the data plane VCN 1218 (e.g., Figure 11 The data plane VCN 1118 may be included in a customer lease 1221 that may be owned or operated by the system’s users or customers.

[0258] Control plane VCN 1216 may include control plane DMZ layer 1220 (e.g., Figure 11 The control plane DMZ layer 1120), which may include one or more LB subnets 1222 (e.g., Figure 11 (One or more) LB subnets 1122), may include (one or more) application (app) subnets 1226 (e.g., Figure 11 The control plane application (app) layer 1224 of (one or more) application subnets 1126 (e.g., Figure 11 The control plane application layer 1124) may include one or more database (DB) subnets 1230 (e.g., similar to...). Figure 11 The control plane data layer 1228 of (one or more) DB subnets 1130 (e.g., Figure 11 The control plane data layer 1128). One or more LB subnets 1222 contained in the control plane DMZ layer 1220 can be communicatively coupled to one or more application subnets 1226 contained in the control plane application layer 1224 and an Internet gateway 1234 that can be contained in the control plane VCN 1216 (e.g., Figure 11 Internet gateway 1134), and application subnet(s) 1226 can communicatively couple to DB subnet(s) 1230 contained in control plane data layer 1228 and service gateway 1236 (e.g., Figure 11 The service gateway) and Network Address Translation (NAT) gateway 1238 (e.g., Figure 11 (NAT gateway 1138). The control plane VCN 1216 may include the service gateway 1236 and the NAT gateway 1238.

[0259] The control plane VCN 1216 may include a data plane mirror application (app) layer 1240 that may include one or more application subnets 1226 (e.g., Figure 11The data plane mirror application layer 1140). One or more application subnets 1226 contained in the data plane mirror application layer 1240 may include computational instances 1244 (e.g., similar to...). Figure 11 The virtual network interface controller (VNIC) 1242 (e.g., the VNIC of 1142) of the computing instance 1144. The computing instance 1244 may facilitate the mirroring of the data plane application layer 1240 with one or more application subnets 1226 and may be included in the data plane application (app) layer 1246 (e.g., Figure 11 Communication between one or more application subnets 1226 in the data plane application layer 1146 via VNIC 1242 contained in the data plane mirror application layer 1240 and VNIC 1242 contained in the data plane application layer 1246.

[0260] The Internet gateway 1234 included in the control plane VCN 1216 can be communicatively coupled to the metadata management service 1252 (e.g., Figure 11 Metadata management service 1252), which can communicatively couple to public Internet 1254 (e.g., Figure 11 The public internet 1254 can communicatively couple to a NAT gateway 1238 contained in a control plane VCN 1216. The service gateway 1236 contained in the control plane VCN 1216 can communicatively couple to a cloud service 1256 (e.g., ...). Figure 11 Cloud services (1156).

[0261] In some examples, data plane VCN 1218 may be included in customer lease 1221. In this case, the IaaS provider may provide control plane VCN 1216 for each customer, and the IaaS provider may set up a unique compute instance 1244 for each customer, included in service lease 1219. Each compute instance 1244 may allow communication between control plane VCN 1216 included in service lease 1219 and data plane VCN 1218 included in customer lease 1221. Compute instance 1244 may allow resources provisioned in control plane VCN 1216 included in service lease 1219 to be deployed or otherwise used in data plane VCN 1218 included in customer lease 1221.

[0262] In other examples, an IaaS provider's customer may have a database residing in customer lease 1221. In this example, control plane VCN 1216 may include data plane mirror application layer 1240, which may include one or more application subnets 1226. Data plane mirror application layer 1240 may reside in data plane VCN 1218, but may not reside in data plane VCN 1218. That is, data plane mirror application layer 1240 may have access to customer lease 1221, but may not reside in data plane VCN 1218 or be owned or operated by an IaaS provider's customer. Data plane mirror application layer 1240 may be configured to invoke data plane VCN 1218, but may not be configured to invoke any entity contained in control plane VCN 1216. Customers may expect to deploy or otherwise use resources provided in the control plane VCN 1216 in the data plane VCN 1218, and the data plane mirroring application layer 1240 can facilitate the customer's expected deployment or other use of resources.

[0263] In some embodiments, an IaaS provider's customer may apply filters to data plane VCN 1218. In this embodiment, the customer may determine what data plane VCN 1218 can access, and the customer may restrict access from data plane VCN 1218 to the public Internet 1254. The IaaS provider may not be able to apply filters or otherwise control data plane VCN 1218's access to any external networks or databases. Applying filters and controls to data plane VCN 1218 contained in customer lease 1221 can help isolate data plane VCN 1218 from other customers and the public Internet 1254.

[0264] In some embodiments, cloud service 1256 may be invoked by service gateway 1236 to access services that may not exist on public internet 1254, control plane VCN 1216, or data plane VCN 1218. The connection between cloud service 1256 and control plane VCN 1216 or data plane VCN 1218 may not be real-time or continuous. Cloud service 1256 may reside on different networks owned or operated by an IaaS provider. Cloud service 1256 may be configured to receive calls from service gateway 1236 and may be configured not to receive calls from public internet 1254. Some cloud services 1256 may be isolated from other cloud services 1256, and control plane VCN 1216 may be isolated from cloud services 1256 that may not be in the same region as control plane VCN 1216. For example, control plane VCN 1216 may be located in "Region 1," and cloud service "Deployment 11" may be located in both "Region 1" and "Region 2." If the service gateway 1236, contained in the control plane VCN 1216 located in region 1, makes a call to deployment 11, then that call can be transmitted to deployment 11 in region 1. In this example, the control plane VCN 1216 or deployment 11 in region 1 may not be communicatively coupled to or otherwise communicate with deployment 11 in region 2.

[0265] Figure 13 This is a block diagram 1300 illustrating another example pattern of an IaaS architecture according to at least one embodiment. Service operator 1302 (e.g., Figure 11 Service provider 1102) can communicatively couple to secure host lease 1304 (e.g., Figure 11 Secure hosting lease 1104), the secure hosting lease 1304 may include a virtual cloud network (VCN) 1306 (e.g., Figure 11 VCN 1106) and Secure Host Subnet 1308 (e.g., Figure 11 The secure host subnet 1108). VCN 1306 may include LPG 1310 (e.g., Figure 11 The LPG 1110), which can be communicatively coupled to the SSH VCN 1312 via the LPG 1310 included in the SSH VCN 1312 (e.g., Figure 11 SSH VCN 1112). SSH VCN 1312 can include SSH subnet 1314 (e.g., Figure 11 SSH subnet 1114), and SSH VCN 1312 can be communicatively coupled to control plane VCN 1316 via LPG 1310 contained in control plane VCN 1316 (e.g., Figure 11The control plane VCN 1116) and coupled to the data plane VCN 1318 via the LPG 1310 contained in the data plane VCN 1318 (e.g., Figure 11 Data plane 1118). Control plane VCN 1316 and data plane VCN 1318 may be included in service lease 1319 (e.g., Figure 11 In the service rental (1119).

[0266] The control plane VCN 1316 may include a load balancer (LB) subnet 1322 (e.g., Figure 11 The control plane DMZ layer 1320 of (one or more) LB subnets 1122) (e.g., Figure 11 The control plane DMZ layer 1120 may include one or more application (app) subnets 1326 (e.g., similar to...). Figure 11 The control plane application (app) layer 1324 of (one or more) application subnets 1126 (e.g., Figure 11 The control plane application layer 1124), and the control plane data layer 1328, which may include (one or more) DB subnets 1330, for example, Figure 11 The control plane data layer 1128). One or more LB subnets 1322 contained in the control plane DMZ layer 1320 can be communicatively coupled to one or more application subnets 1326 contained in the control plane application layer 1324 and an Internet gateway 1334 that can be contained in the control plane VCN 1316 (e.g., Figure 11 Internet gateway 1134), and application subnet(s) 1326 can communicatively couple to DB subnet(s) 1330 contained in control plane data layer 1328 and service gateway 1336 (e.g., Figure 11 The service gateway) and Network Address Translation (NAT) gateway 1338 (e.g., Figure 11 (NAT gateway 1138). The control plane VCN 1316 may include service gateway 1336 and NAT gateway 1338.

[0267] Data plane VCN 1318 may include data plane application (app) layer 1346 (e.g., Figure 11 Data plane application layer 1146), data plane DMZ layer 1348 (e.g., Figure 11 Data plane DMZ layer 1148), and data plane data layer 1350 (e.g., Figure 11The data plane data layer 1150. The data plane DMZ layer 1348 may include one or more trusted application (app) subnets 1360 and one or more untrusted application (app) subnets 1362 that are communicatively coupled to the data plane application layer 1346, and one or more LB subnets 1322 of the Internet gateway 1334 contained in the data plane VCN 1318. The one or more trusted application subnets 1360 may be communicatively coupled to the service gateway 1336 contained in the data plane VCN 1318, the NAT gateway 1338 contained in the data plane VCN 1318, and one or more DB subnets 1330 contained in the data plane data layer 1350. The one or more untrusted application subnets 1362 may be communicatively coupled to the service gateway 1336 contained in the data plane VCN 1318 and the one or more DB subnets 1330 contained in the data plane data layer 1350. The data plane data layer 1350 may include one or more DB subnets 1330 that can be communicatively coupled to the service gateway 1336 contained in the data plane VCN 1318.

[0268] One or more untrusted application subnets 1362 may include one or more primary VNICs 1364(1)-(N) that can be communicatively coupled to tenant virtual machines (VMs) 1366(1)-(N). Each tenant VM 1366(1)-(N) may be communicatively coupled to a corresponding application (app) subnet 1367(1)-(N) that may be contained in a corresponding container egress VCN 1368(1)-(N), which may be contained in a corresponding customer lease 1370(1)-(N). A corresponding secondary VNIC 1372(1)-(N) may facilitate communication between one or more untrusted application subnets 1362 contained in data plane VCN 1318 and application subnets contained in container egress VCN 1368(1)-(N). Each container exit VCN 1368(1)-(N) may include a NAT gateway 1338, which can communicatively couple to the public Internet 1354 (e.g., Figure 11 The public internet (1154).

[0269] Internet gateway 1334, contained in control plane VCN 1316 and data plane VCN 1318, can communicatively couple to metadata management service 1352 (e.g., Figure 11A metadata management system 1152, which is communicatively coupled to the public internet 1354, is also communicatively coupled to a NAT gateway 1338 contained in a control plane VCN 1316 and a data plane VCN 1318. A service gateway 1336 contained in both the control plane VCN 1316 and the data plane VCN 1318 is communicatively coupled to a cloud service 1356.

[0270] In some embodiments, the data plane VCN 1318 may be integrated with the customer lease 1370. Such integration may be useful or desired by the IaaS provider's customers in certain situations, such as when support may be expected during code execution. Customers may provide code that could be destructive, might communicate with other customer resources, or might otherwise cause undesirable effects. In response, the IaaS provider may determine whether to run the code provided by the customer to the IaaS provider.

[0271] In some examples, an IaaS provider's customer may grant the IaaS provider temporary network access and request functionality to be attached to data plane layer application 1346. The code running this functionality may execute in VMs 1366(1)-(N) and may not be configured to run anywhere else on data plane VCN 1318. Each VM 1366(1)-(N) may be connected to a customer lease 1370. The corresponding container 1371(1)-(N) contained in VMs 1366(1)-(N) may be configured to run the code. In this case, there may be dual isolation (e.g., container 1371(1)-(N) running the code, where container 1371(1)-(N) may be contained in at least one or more untrusted application subnets 1362 containing VMs 1366(1)-(N)), which can help prevent incorrect or otherwise unintended code from corrupting the IaaS provider's network or the networks of different customers. Containers 1371(1)-(N) may be communicatively coupled to customer lease 1370 and may be configured to transmit or receive data from customer lease 1370. Containers 1371(1)-(N) may not be configured to transmit or receive data from any other entity in the data plane VCN 1318. After the code execution is complete, the IaaS provider may terminate or otherwise dispose of containers 1371(1)-(N).

[0272] In some embodiments, one or more trusted application subnets 1360 may run code that can be owned or operated by an IaaS provider. In this embodiment, one or more trusted application subnets 1360 may be communicatively coupled to one or more database subnets 1330 and configured to perform CRUD operations in one or more database subnets 1330. One or more untrusted application subnets 1362 may be communicatively coupled to one or more database subnets 1330, but in this embodiment, one or more untrusted application subnets may be configured to perform read operations in one or more database subnets 1330. Containers 1371(1)-(N) that may be contained in each customer's VM 1366(1)-(N) and may run code from the customer may not be communicatively coupled to one or more database subnets 1330.

[0273] In other embodiments, the control plane VCN 1316 and the data plane VCN 1318 may be coupled without direct communication. In this embodiment, there may be no direct communication between the control plane VCN 1316 and the data plane VCN 1318. However, communication can occur indirectly through at least one method. The LPG 1310 may be established by an IaaS provider, which can facilitate communication between the control plane VCN 1316 and the data plane VCN 1318. In another example, either the control plane VCN 1316 or the data plane VCN 1318 may invoke the cloud service 1356 via the service gateway 1336. For example, an invocation of the cloud service 1356 from the control plane VCN 1316 may include a request for a service that can communicate with the data plane VCN 1318.

[0274] Figure 14 This is a block diagram 1400 illustrating another example pattern of an IaaS architecture according to at least one embodiment. Service operator 1402 (e.g., Figure 11 Service provider 1102) can communicatively couple to secure host lease 1404 (e.g., Figure 11 Secure hosting lease 1104), the secure hosting lease 1404 may include a virtual cloud network (VCN) 1406 (e.g., Figure 11 VCN 1106) and Secure Host Subnet 1408 (e.g., Figure 11 The secure host subnet 1108). VCN 1406 may include LPG 1410 (e.g., Figure 11 The LPG 1110), the LPG 1410 can be accessed via SSH VCN 1412 (e.g., LPG 1110), Figure 11The LPG 1410 in SSH VCN 1112 is communicatively coupled to SSH VCN 1412. SSH VCN 1412 may include SSH subnet 1414 (e.g., Figure 11 SSH subnet 1114), and SSH VCN 1412 can be communicatively coupled to control plane VCN 1416 via LPG 1410 contained in control plane VCN 1416 (e.g., Figure 11 The control plane VCN 1116) and coupled to the data plane VCN 1418 via the LPG 1410 contained in the data plane VCN 1418 (e.g., Figure 11 Data plane 1118). Control plane VCN 1416 and data plane VCN 1418 may be contained in service lease 1419 (e.g., Figure 11 In the service rental (1119).

[0275] The control plane VCN 1416 may include one or more LB subnets 1422 (e.g., Figure 11 The control plane DMZ layer 1420 of (one or more) LB subnets 1122) (e.g., Figure 11 The control plane DMZ layer 1120 may include one or more application (app) subnets 1426 (e.g., Figure 11 The control plane application (app) layer 1424 of (one or more) application subnets 1126 (e.g., Figure 11 The control plane application layer 1124) may include (one or more) DB subnets 1430 (e.g., Figure 13 The control plane data layer 1428 of (one or more) DB subnets 1330 (e.g., Figure 11 The control plane data layer 1128). One or more LB subnets 1422 contained in the control plane DMZ layer 1420 can be communicatively coupled to one or more application subnets 1426 contained in the control plane application layer 1424 and an Internet gateway 1434 that can be contained in the control plane VCN 1416 (e.g., Figure 11 Internet gateway 1134), and application subnet(s) 1426 can communicatively couple to DB subnet(s) 1430 contained in control plane data layer 1428 and service gateway 1436 (e.g., Figure 11 The service gateway) and Network Address Translation (NAT) gateway 1438 (e.g., Figure 11 (NAT gateway 138). The control plane VCN 1416 may include the service gateway 1436 and the NAT gateway 1438.

[0276] Data plane VCN 1418 may include data plane application (app) layer 1446 (e.g., Figure 11 Data plane application layer 1146), data plane DMZ layer 1448 (e.g., Figure 11 Data plane DMZ layer 1148), and data plane data layer 1450 (e.g., Figure 11 The data plane data layer 1150). The data plane DMZ layer 1448 may include one or more trusted application (app) subnets 1460 that can be communicatively coupled to the data plane application layer 1446 (e.g., Figure 13 The trusted application subnet 1360 and the untrusted application subnet 1462 (e.g., Figure 13 The data plane VCN 1418 may include one or more untrusted application subnets 1362 and one or more LB subnets 1422 of Internet gateway 1434. One or more trusted application subnets 1460 may communicatively couple to service gateway 1436, NAT gateway 1438, and DB subnets 1430 in data plane VCN 1450. One or more untrusted application subnets 1462 may communicatively couple to service gateway 1436 and DB subnets 1430 in data plane VCN 1418. Data plane VCN 1450 may include one or more DB subnets 1430 that may communicatively couple to service gateway 1436 in data plane VCN 1418.

[0277] One or more untrusted application subnets 1462 may include a primary VNIC 1464(1)-(N) communicatively coupled to tenant virtual machines (VMs) 1466(1)-(N) residing within one or more untrusted application subnets 1462. Each tenant VM 1466(1)-(N) may run code in a corresponding container 1467(1)-(N) and is communicatively coupled to an application subnet 1426 that may be contained in a data plane application layer 1446 contained in a container egress VCN 1468. A corresponding secondary VNIC 1472(1)-(N) may facilitate communication between one or more untrusted application subnets 1462 contained in a data plane VCN 1418 and the application subnets contained in a container egress VCN 1468. The container egress VCN may include a public internet 1454 (e.g., Figure 11 The public internet (1154) uses NAT gateway 1438.

[0278] Internet gateway 1434, contained in control plane VCN 1416 and data plane VCN 1418, can be communicatively coupled to metadata management service 1452 (e.g., Figure 11 A metadata management system 1452 (the metadata management service 1452) can be communicatively coupled to the public internet 1454. The public internet 1454 can be communicatively coupled to a NAT gateway 1438 contained in a control plane VCN 1416 and a data plane VCN 1418. A service gateway 1436 contained in a control plane VCN 1416 and a data plane VCN 1418 can be communicatively coupled to a cloud service 1456.

[0279] In some examples, Figure 14 The architecture shown in block diagram 1400 can be considered as... Figure 13 This is an exception to the pattern shown in the architecture of block diagram 1300, and this pattern may be what the IaaS provider's customers would expect if the IaaS provider cannot communicate directly with the customer (e.g., in a disconnected region). The customer can access in real time the corresponding container 1467(1)-(N) contained in each customer's VM 1466(1)-(N). Container 1467(1)-(N) can be configured to invoke the corresponding auxiliary VNIC 1472(1)-(N) contained in one or more application subnets 1426 of the data plane application layer 1446, which may be contained in the container egress VCN 1468. The auxiliary VNIC 1472(1)-(N) can transmit the call to NAT gateway 1438, which can then transmit the call to the public internet 1454. In this example, containers 1467(1)-(N), which can be accessed by clients in real time, can be isolated from the control plane VCN 1416 and from other entities contained in the data plane VCN 1418. Containers 1467(1)-(N) can also be isolated from resources from other clients.

[0280] In other examples, a client can use containers 1467(1)-(N) to invoke cloud service 1456. In this example, the client can run code within containers 1467(1)-(N) requesting a service from cloud service 1456. Container 1467(1)-(N) can then forward the request to a secondary VNIC 1472(1)-(N), which can then forward the request to a NAT gateway, which can forward the request to the public internet 1454. The public internet 1454 can then forward the request via internet gateway 1434 to one or more LB subnets 1422 contained in control plane VCN 1416. In response to determining that the request is valid, the one or more LB subnets can forward the request to one or more application subnets 1426, which can then forward the request to cloud service 1456 via service gateway 1436.

[0281] It should be recognized that the IaaS architectures 1100, 1200, 1300, and 1400 depicted in the figures may have other components besides those depicted. Furthermore, the embodiments shown in the figures are merely some examples of cloud infrastructure systems that can be incorporated into embodiments of this disclosure. In some other embodiments, the IaaS system may have more or fewer components than shown in the figures, may combine two or more components, or may have different configurations or component arrangements.

[0282] In some embodiments, the IaaS system described herein may include application suites, middleware, and database service offerings delivered to customers in a self-service, subscription-based, elastically scalable, reliable, highly available, and secure manner. An example of such an IaaS system is the Oracle Cloud Infrastructure (OCI) provided by this assignee.

[0283] Figure 15 An example computer system 1500, in which various embodiments can be implemented, is illustrated. System 1500 can be used to implement any of the computer systems described above. As shown, computer system 1500 includes a processing unit 1504 that communicates with a plurality of peripheral subsystems via a bus subsystem 1502. These peripheral subsystems may include a processing acceleration unit 1506, an I / O subsystem 1508, a storage subsystem 1518, and a communication subsystem 1524. Storage subsystem 1518 includes a tangible computer-readable storage medium 1522 and system memory 1510.

[0284] Bus subsystem 1502 provides a mechanism for allowing various components and subsystems of computer system 1500 to communicate with each other as intended. While bus subsystem 1502 is schematically shown as a single bus, alternative embodiments of the bus subsystem may utilize multiple buses. Bus subsystem 1502 can be any of several types of bus architectures, including memory buses or memory controllers, peripheral buses, and local buses using any of the various bus architectures. For example, such architectures may include Industry Standard Architecture (ISA) buses, Microchannel Architecture (MCA) buses, Enhanced ISA (EISA) buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses, which may be implemented as Mezzanine buses manufactured according to the IEEE P1386.1 standard.

[0285] A processing unit 1504, which may be implemented as one or more integrated circuits (e.g., a conventional microprocessor or microcontroller), controls the operation of the computer system 1500. One or more processors may be included in the processing unit 1504. These processors may include single-core or multi-core processors. In some embodiments, the processing unit 1504 may be implemented as one or more independent processing units 1532 and / or 1534, each including a single-core or multi-core processor. In other embodiments, the processing unit 1504 may also be implemented as a quad-core processing unit formed by integrating two dual-core processors into a single chip.

[0286] In various embodiments, processing unit 1504 can execute various programs in response to program code and can maintain multiple concurrently executing programs or processes. At any given time, some or all of the program code to be executed can reside in processor(s) 1504 and / or storage subsystem 1518. With appropriate programming, processor(s) 1504 can provide the various functions described above. Computer system 1500 may additionally include processing acceleration unit 1506, which may include digital signal processor (DSP), dedicated processor, etc.

[0287] I / O subsystem 1508 may include user interface input devices and user interface output devices. User interface input devices may include keyboards, pointing devices such as mice or trackballs, touchpads or touchscreens integrated into a display, scroll wheels, click wheels, dials, buttons, switches, keyboards, audio input devices with voice command recognition systems, microphones, and other types of input devices. User interface input devices may include, for example, motion sensing and / or gesture recognition devices, such as the Microsoft Kinect® motion sensor, which enables users to control and interact with input devices such as the Microsoft Xbox® 360 game controller via a natural user interface using gestures and voice commands. User interface input devices may also include eye posture recognition devices, such as the Google Glass® blink detector, which detects eye activity from the user (e.g., “blinking” when taking a photo and / or making menu selections) and translates the eye posture into input in an input device (e.g., Google Glass®). Furthermore, user interface input devices may include voice recognition sensing devices that enable users to interact with a voice recognition system (e.g., the Siri® navigator) via voice commands.

[0288] User interface input devices may also include, but are not limited to, 3D mice, joysticks or pointing sticks, game panels and drawing tablets, as well as audio / video devices such as speakers, digital cameras, digital camcorders, portable media players, webcams, image scanners, fingerprint scanners, barcode readers, 3D scanners, 3D printers, laser rangefinders, and eye-tracking devices. Furthermore, user interface input devices may include, for example, medical imaging input devices such as computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and medical ultrasound equipment. User interface input devices may also include, for example, audio input devices such as MIDI keyboards, digital musical instruments, etc.

[0289] User interface output devices may include display subsystems, indicator lights, or non-visual displays such as audio output devices, etc. Display subsystems may be cathode ray tubes (CRTs), flat panel devices such as those using liquid crystal displays (LCDs) or plasma displays, projection devices, touchscreens, etc. Generally, the term "output device" is intended to include all possible types of devices and mechanisms for outputting information from computer system 1500 to a user or other computer. For example, user interface output devices may include, but are not limited to, various display devices that visually convey text, graphics, and audio / video information, such as monitors, printers, speakers, headphones, car navigation systems, plotters, voice output devices, and modems.

[0290] Computer system 1500 may include a storage subsystem 1518 containing software elements, shown as currently located in system memory 1510. System memory 1510 may store program instructions that can be loaded and executed on processing unit 1504, as well as data generated during the execution of these programs.

[0291] Depending on the configuration and type of computer system 1500, system memory 1510 may be volatile (such as random access memory (RAM)) and / or non-volatile (such as read-only memory (ROM), flash memory, etc.). RAM typically contains data and / or program modules that can be immediately accessed by processing unit 1504 and / or are currently being operated and executed by processing unit 1504. In some implementations, system memory 1510 may include various different types of memory, such as static random access memory (SRAM) or dynamic random access memory (DRAM). In some implementations, a basic input / output system (BIOS), which contains basic routines that facilitate the transfer of information between elements of computer system 1500 during startup, may typically be stored in ROM. As an example, but not a limitation, system memory 1510 also includes application programs 1512, program data 1514, and an operating system 1516, which may include client applications, web browsers, middleware applications, relational database management systems (RDBMS), etc. As an example, operating system 1516 may include various versions of Microsoft Windows®, Apple Macintosh® and / or Linux operating systems, various commercially available UNIX® or UNIX-like operating systems (including but not limited to various GNU / Linux operating systems, Google Chrome® OS, etc.) and / or mobile operating systems such as iOS, Windows® Phone, Android® OS, BlackBerry® 15 OS and Palm® OS.

[0292] Storage subsystem 1518 may also provide a tangible computer-readable storage medium for storing basic programming and data structures that provide the functionality of some embodiments. Software (programs, code modules, instructions) that provides the above-described functionality when executed by a processor may be stored in storage subsystem 1518. These software modules or instructions may be executed by processing unit 1504. Storage subsystem 1518 may also provide a repository for storing data used according to this disclosure.

[0293] The storage subsystem 1500 may also include a computer-readable storage medium reader 1520 that can be further connected to the computer-readable storage medium 1522. Together with and optionally in conjunction with the system memory 1510, the computer-readable storage medium 1522 can comprehensively represent a remote, local, fixed, and / or removable storage device plus storage medium for temporarily and / or more persistently containing, storing, transmitting, and retrieving computer-readable information.

[0294] The computer-readable storage medium 1522 containing code or portions thereof may also include any suitable medium known or used in the art, including storage and communication media, such as, but not limited to, volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing and / or transmitting information. This may include tangible computer-readable storage media such as RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic tape cassettes, magnetic tape, disk storage or other magnetic storage devices, or other tangible computer-readable media. This may also include non-tangible computer-readable media such as data signals, data transmissions, or any other medium that can be used to transmit desired information and can be accessed by the computing system 1500.

[0295] For example, computer-readable storage medium 1522 may include hard disk drives that read from or write to non-removable non-volatile magnetic media, disk drives that read from or write to removable non-volatile magnetic disks, and optical disc drives that read from or write to removable non-volatile optical discs (such as CD ROMs, DVDs, and Blu-ray® discs or other optical media). Computer-readable storage medium 1522 may include, but is not limited to, Zip® drives, flash memory cards, Universal Serial Bus (USB) flash drives, Secure Digital (SD) cards, DVD discs, digital audio tapes, and so on. Computer-readable storage medium 1522 may also include solid-state drives (SSDs) based on non-volatile memory (such as flash memory-based SSDs, enterprise flash drives, solid-state ROMs, etc.), volatile memory-based SSDs (such as solid-state RAM, dynamic RAM, static RAM), DRAM-based SSDs, magnetoresistive RAM (MRAM) SSDs, and hybrid SSDs using a combination of DRAM-based and flash memory-based SSDs. Disk drives and their associated computer-readable media can provide non-volatile storage for computer-readable instructions, data structures, program modules and other data for computer system 1500.

[0296] The communication subsystem 1524 provides an interface to other computer systems and networks. The communication subsystem 1524 serves as an interface for receiving data from other systems and sending data from computer system 1500 to other systems. For example, the communication subsystem 1524 enables computer system 1500 to connect to one or more devices via the Internet. In some embodiments, the communication subsystem 1524 may include radio frequency (RF) transceiver components (e.g., advanced data network technologies using cellular telephone technology, such as 3G, 4G, or EDGE (Enhanced Data Rates for Global Evolution), WiFi (IEEE 802.11 series standards), or other mobile communication technologies, or any combination thereof), GPS receiver components, and / or other components for accessing wireless voice and / or data networks. In some embodiments, as an addition to or alternative to the wireless interface, the communication subsystem 1524 may provide a wired network connection (e.g., Ethernet).

[0297] In some embodiments, the communication subsystem 1524 may also represent one or more users who can use the computer system 1500 to receive input communications in the form of structured and / or unstructured data feeds 1526, event streams 1528, event updates 1530, etc.

[0298] For example, the communication subsystem 1524 can be configured to receive data feeds 1526 in real time from users of social networks and / or other communication services, such as Twitter® feeds, Facebook® updates, web feeds such as Rich Site Summary (RSS) feeds, and / or real-time updates from one or more third-party information sources.

[0299] Furthermore, the communication subsystem 1524 can also be configured to receive data in the form of a continuous data stream, which may include event streams 1528 and / or event updates 1530 that are essentially continuous or unbounded real-time events without a clearly defined termination. Examples of applications that generate continuous data may include, for example, sensor data applications, financial quote machines, network performance measurement tools (e.g., network monitoring and traffic management applications), clickstream analysis tools, vehicle traffic monitoring, and so on.

[0300] The communication subsystem 1524 can also be configured to output structured and / or unstructured data feeds 1526, event streams 1528, event updates 1530, etc. to one or more databases, which can communicate with one or more streaming data source computers coupled to the computer system 1500.

[0301] The computer system 1500 can be one of a variety of types, including handheld portable devices (e.g., iPhone® cellular phones, iPad® computing tablets, PDAs), wearable devices (e.g., Google® Glass head-mounted displays), PCs, workstations, mainframes, information stations, server racks, or any other data processing systems.

[0302] Due to the constantly evolving nature of computers and networks, the description of the computer system 1500 depicted in the figures is intended only as a specific example. Many other configurations with more or fewer components than the system depicted in the figures are possible. For example, custom hardware may also be used and / or specific elements may be implemented in hardware, firmware, software (including small applications), or a combination thereof. Additionally, connectivity with other computing devices, such as network input / output devices, may be employed. Based on the disclosure and teachings provided herein, those skilled in the art will recognize other ways and / or methods for implementing the various embodiments.

[0303] While specific embodiments have been described, various modifications, alterations, alternative constructions, and equivalents are also included within the scope of this disclosure. The embodiments are not limited to operation within certain specific data processing environments, but can be freely operated within multiple data processing environments. Furthermore, although the embodiments have been described using a specific series of transactions and steps, those skilled in the art will understand that the scope of this disclosure is not limited to the described series of transactions and steps. Various features and aspects of the above embodiments can be used individually or in combination.

[0304] Furthermore, while embodiments have been described using specific combinations of hardware and software, it should be recognized that other combinations of hardware and software are also within the scope of this disclosure. Embodiments may be implemented using only hardware, or only software, or a combination thereof. The various processes described herein can be implemented in any combination on the same processor or on different processors. Thus, where a component or module is described as being configured to perform certain operations, such configuration can be accomplished, for example, by designing electronic circuits to perform operations, by programming programmable electronic circuits (such as microprocessors), or any combination thereof. Processes may communicate using various technologies, including but not limited to conventional technologies for inter-process communication, and different pairs of processes may use different technologies, or the same pair of processes may use different technologies at different times.

[0305] Therefore, the specification and drawings are to be considered illustrative rather than restrictive. However, it will be apparent that additions, omissions, deletions, and other modifications and changes can be made thereto without departing from the broader spirit and scope set forth in the claims. Thus, while specific disclosed embodiments have been described, they are not intended to be limiting. Various modifications and equivalents are within the scope of the following claims.

[0306] In the context of describing the disclosed embodiments (particularly in the context of the following claims), the terms “a,” “an,” and “the,” and similar designations, are to be interpreted as encompassing both singular and plural, unless otherwise indicated herein or clearly contradicted by the context. Unless otherwise stated, the terms “comprising,” “having,” “including,” and “containing” are to be interpreted as open-ended terms (i.e., meaning “including but not limited to”). The term “connected” should be interpreted as partially or wholly contained in, attached to, or joined together, even if something exists in between. Unless otherwise indicated herein, the enumeration of value ranges herein is intended only as a shorthand method for individually referencing each individual value falling within that range, and each individual value is incorporated into the specification as if it were individually enumerated herein. Unless otherwise indicated herein or clearly contradicted by the context, all methods described herein can be performed in any suitable order. The use of any and all examples or exemplary language (e.g., “such as”) provided herein is intended only to better illustrate the embodiments and does not constitute a limitation on the scope of this disclosure, unless otherwise stated. Nothing in the specification should be construed as indicating that any unclaimed element is essential to the practice of this disclosure.

[0307] Disjunctive language, such as the phrase “at least one of X, Y, or Z”, unless otherwise explicitly stated, is intended to be understood in the context generally used to represent items, terms, etc., and may be X, Y, or Z, or any combination thereof (e.g., X, Y, and / or Z). Therefore, such disjunctive language is generally not intended to, and should not, imply that some embodiments require the presence of at least one of X, at least one of Y, or at least one of Z, each individually.

[0308] This document describes preferred embodiments of the present disclosure, including the best modes known for carrying out the present disclosure. Variations of those preferred embodiments will become apparent to those skilled in the art upon reading the foregoing description. Those skilled in the art should be able to suitably employ such variations and may practice the present disclosure in ways other than those specifically described herein. Thus, the present disclosure includes all modifications and equivalents to the subject matter recited in the appended claims, where permitted by applicable law. Furthermore, unless otherwise indicated herein, the present disclosure includes any combination of the foregoing elements in all its possible variations.

[0309] All references cited in this article, including publications, patent applications and patents, are incorporated into this article by reference to the same extent as if each reference individually and specifically indicated to be incorporated by reference and elaborated in full in this article.

[0310] In the foregoing specification, various aspects of this disclosure have been described with reference to specific embodiments thereof; however, those skilled in the art will recognize that this disclosure is not limited thereto. The various features and aspects of the foregoing disclosure may be used individually or in combination. Furthermore, embodiments may be used in any number of settings and applications other than those described herein without departing from the broader spirit and scope of this specification. Therefore, this specification and the accompanying drawings should be considered illustrative rather than restrictive.

Claims

1. A method for queuing Remote Direct Memory Access (RDMA) packets, the method comprising: The network device receives a first RDMA packet containing a first Quality of Service (QoS) data field and a first Virtual Local Area Network (VLAN) identifier, wherein the first VLAN identifier indicates a first VLAN; Based on the quality of service value of the first QoS data field indicating the service category of the first RDMA packet, the first RDMA packet is queued into a first RDMA queue among multiple queues. The networked device receives a second RDMA packet containing a second QoS data field and a second VLAN identifier, the second VLAN identifier indicating the second VLAN; Based on the quality of service value of the second QoS data field indicating the service category of the second RDMA packet, the second RDMA packet is placed into a second RDMA queue among the plurality of queues. The second RDMA queue is different from the first RDMA queue. The networked device receives a third RDMA packet containing a third QoS data field and a third VLAN identifier, the third VLAN identifier indicating a third VLAN different from the first VLAN; as well as The third RDMA packet is queued into the first RDMA queue if the quality of service value of the third QoS data field indicating the service category of the third RDMA packet is the same as the quality of service value of the first QoS data field indicating the service category of the first RDMA packet.

2. The method of claim 1, further comprising retrieving a first RDMA packet from a first RDMA queue based on a first weight in the plurality of queues, and retrieving a second RDMA packet from a second RDMA queue.

3. The method of claim 1, further comprising retrieving a first RDMA packet from a first RDMA queue according to a weighted round-robin scheme, and retrieving a second RDMA packet from a second RDMA queue.

4. The method of claim 1, wherein the plurality of queues includes a control queue, and wherein the method further includes retrieving a plurality of control packets from the control queue by a networking device. The retrieval of the multiple control groups has a stricter priority than the retrieval of the first RDMA group and the retrieval of the second RDMA group.

5. The method of claim 4, wherein the plurality of queues comprises a plurality of RDMA queues, the plurality of RDMA queues comprising a first RDMA queue and a second RDMA queue, and The control queue is configured to have a lower bandwidth than any of the plurality of RDMA queues.

6. The method of claim 4, wherein the plurality of control packets includes at least one of network control protocol packets or congestion notification packets.

7. The method of any one of claims 1 to 6, wherein the first QoS data field is the Differential Service Code Point (DSCP) data field of the Internet Protocol IP header of the first RDMA packet.

8. The method of any one of claims 1 to 6, wherein each of the first RDMA packet and the second RDMA packet is a RoCEv2 packet.

9. The method of any one of claims 1 to 6, wherein each of the first RDMA packet and the second RDMA packet is a layer 3 encapsulated packet formatted according to an overlay encapsulation protocol.

10. The method of claim 9, wherein the overlay encapsulation protocol is one of VxLAN, NVGRE, GENEVE, STT, and MPLS.

11. The method of claim 9, wherein the method further comprises: Decapsulate the first RDMA packet to obtain the first decapsulated RDMA packet, and The congestion indication information is copied from at least one external header of the first RDMA packet to the first decapsulated RDMA packet.

12. The method of claim 1, wherein the method further comprises: Receive multiple RDMA packets, each of which has a corresponding QoS data field; For each of the plurality of RDMA packets, the RDMA packet is placed into an RDMA queue among the plurality of queues based on the value of the QoS data field indicating the priority of the RDMA packet. as well as Retrieve the multiple RDMA packets from the multiple queues. The plurality of RDMA packets comprise multiple packet streams, and The method further includes routing the plurality of packet flows according to a per-flow equivalent multipath scheme.

13. A networked device, comprising: A memory that stores multiple queues; as well as A processing circuit system, coupled to a memory, is used for: Receive a first Remote Direct Memory Access (RDMA) packet having a first Quality of Service (QoS) data field and a first Virtual Local Area Network (VLAN) identifier, wherein the first VLAN identifier indicates a first VLAN; Based on the quality of service value of the first QoS data field indicating the service category of the first RDMA packet, the first RDMA packet is queued into the first RDMA queue among the plurality of queues. Receive a second RDMA packet with a second QoS data field and a second VLAN identifier, the second VLAN identifier indicating the second VLAN; Based on the quality of service value of the second QoS data field indicating the service category of the second RDMA packet, the second RDMA packet is placed into a second RDMA queue among the plurality of queues. The second RDMA queue is different from the first RDMA queue. Receive a third RDMA packet with a third QoS data field and a third VLAN identifier, the third VLAN identifier indicating a third VLAN different from the first VLAN; as well as The third RDMA packet is queued into the first RDMA queue if the quality of service value of the third QoS data field indicating the service category of the third RDMA packet is the same as the quality of service value of the first QoS data field indicating the service category of the first RDMA packet.

14. The networking device of claim 13, wherein the plurality of queues includes a control queue, and The processing circuitry retrieves multiple control packets from the control queue based on a stricter priority than retrieving the first RDMA packet and retrieving the second RDMA packet.

15. The networking device of claim 14, wherein each of the first RDMA packet and the second RDMA packet is a layer 3 encapsulated packet formatted according to an overlay encapsulation protocol.

16. The networking device of any one of claims 13 to 15, wherein the processing circuitry is further configured to: Decapsulate the first RDMA packet to obtain the first decapsulated RDMA packet, and The congestion indication information is copied from at least one external header of the first RDMA packet to the first decapsulated RDMA packet.

17. The networking device of claim 16, wherein the networking device is a switch of a Clos network.

18. A non-transitory computer-readable medium storing a plurality of instructions executable by one or more processors, the plurality of instructions including instructions that, when executed by the one or more processors, cause the one or more processors to perform the following operations: Receive a first RDMA packet having a first Quality of Service (QoS) data field and a first Virtual Local Area Network (VLAN) identifier, wherein the first VLAN identifier indicates a first VLAN; Based on the quality of service value of the first QoS data field indicating the service category of the first RDMA packet, the first RDMA packet is queued into a first RDMA queue among multiple queues. Receive a second RDMA packet with a second QoS data field and a second VLAN identifier, the second VLAN identifier indicating the second VLAN; Based on the quality of service value of the second QoS data field indicating the service category of the second RDMA packet, the second RDMA packet is placed into a second RDMA queue among the plurality of queues. The second RDMA queue is different from the first RDMA queue. Receive a third RDMA packet with a third QoS data field and a third VLAN identifier, the third VLAN identifier indicating a third VLAN different from the first VLAN; as well as The third RDMA packet is queued into the first RDMA queue if the quality of service value of the third QoS data field indicating the service category of the third RDMA packet is the same as the quality of service value of the first QoS data field indicating the service category of the first RDMA packet.

19. The non-transitory computer-readable medium of claim 18, wherein the plurality of queues includes a control queue, and The plurality of instructions also include instructions that, when executed by the one or more processors, cause the one or more processors to retrieve a plurality of control packets from the control queue according to a stricter priority than retrieving the first RDMA packet and retrieving the second RDMA packet.

20. The non-transitory computer-readable medium of claim 18, wherein each of the first RDMA packet and the second RDMA packet is a layer 3 encapsulated packet formatted according to an overlay encapsulation protocol.

21. The non-transitory computer-readable medium of any one of claims 18 to 20, wherein the first RDMA packet is for a first tenant among a plurality of tenants and the second RDMA packet is for a second tenant among the plurality of tenants, and The first VLAN is the VLAN of the first computing instance among the multiple computing instances running on the host machine, and the second VLAN is the VLAN of the second computing instance among the multiple computing instances.

Images