2402 results about "Garbage collection" patented technology

Changes in performance in a Java program are deduced from information related to garbage collection events of the program. Assumptions are made about the system, the application and garbage collection, and changes in performance that will result from modifying the program are deduced.

An efficient write-watch mechanism and process. A bitmap is associated with the virtual address descriptor (VAD) for a process, one bit for each virtual page address allocated to a process having write-watch enabled. As part of the write-watch mechanism, if a virtual address is trimmed to disk and that virtual address page is marked as modified, then the corresponding bit in the VAD is set for that virtual address page. In response to an API call (e.g., from a garbage collection mechanism) seeking to know which virtual addresses in a process have been modified since last checked, the memory manager walks the bitmap in the relevant VAD for the specified virtual address range for the requested process. If a bit is set, then the page corresponding to that bit is known to have been modified since last asked. If specified by the API, the bit is cleared in the VAD bitmap so that it will reflect the state since this time of asking. If the bit is not set, to determine if the page was modified, the page table entry (PTE) is checked for that page, and if the PTE indicates the page was modified, the page is known to be modified, otherwise that page is known to be unmodified since the last call. One enhancement uses page directory tables to locate a series of trimmed pages, sometimes avoiding the need to access the PTE.

Disclosed herein is a controller architecture that pairs a controller with a NVM (non-volatile memory) storage system over a high-level, high speed interface such as PCIe. In one embodiment, the NVM storage system includes a bridge that communicates with the controller via the high-level interface, and controls the NVM via an interface (e.g., ONFI). The controller is provided a rich set of physical level of controls over individual elements of the NVM. In one embodiment, the controller is implemented in a higher powered processor that supports advanced functions such as mapping, garbage collection, wear leveling, etc. In one embodiment, the bridge is implemented in a lower powered processor and performs basic signal processing, channel management, basic error correction functions, etc. This labor division provides the controller physical control of the NVM over a fast, high-level interface, resulting in the controller managing the NVM at both the page and block level.

A flash memory controller connected to multiple flash memory groups performs independent garbage collection operations in each group. For each group, the controller independently determines the amount of free space and performs garbage collection operations if the amount falls below a threshold.

Certain example embodiments relate to a highly-concurrent, predictable, fast, self-managed, in-process space for storing data that is hidden away from the garbage collector and its related pauses. More particularly, certain example embodiments relate to improved memory management techniques for computer systems that leverage an off-heap direct-memory data store that is massively scalable and highly efficient. The off-heap store may be provided in connection with a Java-based environment, and garbage collection may be completely or nearly completely avoided for the off-heap store. The off-heap store may be integrated into a tiered storage solution in certain example embodiments.

Disclosed herein is a controller architecture that pairs a controller with a NVM (non-volatile memory) storage system over a high-level, high speed interface such as PCIe. In one embodiment, the NVM storage system includes a bridge that communicates with the controller via the high-level interface, and controls the NVM via an interface (e.g., ONFI). The controller is provided a rich set of physical level of controls over individual elements of the NVM. In one embodiment, the controller is implemented in a higher powered processor that supports advanced functions such as mapping, garbage collection, wear leveling, etc. In one embodiment, the bridge is implemented in a lower powered processor and performs basic signal processing, channel management, basic error correction functions, etc. This labor division provides the controller physical control of the NVM over a fast, high-level interface, resulting in the controller managing the NVM at both the page and block level.

An apparatus includes a non-volatile memory and a controller. The controller is coupled to the non-volatile memory and configured to (i) measure a rate of free space consumption in the non-volatile memory, (ii) measure a rate of free space production in the non-volatile memory, and (iii) adjust a rate of a recycling process in response to the measured rate of free space consumption and the measured rate of free space production.

A method, system, and computer program product for managing a heap of memory allocated to a program being executed on a data processing system is disclosed. A limited amount of memory is allocated to a program being executed by a mutator on a data processing system. The memory comprises memory objects. The disclosed method identifies memory objects, which are allocated to the program but are not referenced anymore. These dead memory objects are freed and made available for further allocation in the program. The memory objects that are still referenced are organized in compact contiguous blocks. Thus, the disclosed method recycles memory allocated to the program. The disclosed method is executed iteratively and concurrently with the execution of the program. The disclosed method does not interfere with program execution. Amount of memory required is specified before the commencement of the disclosed method and the same amount is freed without any surplus.

A method and system are disclosed for improved block erase cycle life prediction and block management in a non-volatile memory. The method includes the storage device tracking information relating to a first erase cycle count at which the block erase time exceeded a predetermined threshold relative to a first erase cycle at which this occurred in other blocks. Blocks having a later relative erase cycle at which the erase time threshold is exceeded are assumed to have a greater erase cycle life than those that need to exceed the erase time threshold at an earlier erase cycle. This information is used to adjust wear leveling in the form of free block selection, garbage collection block selection and other block management processes. Alternatively or in combination, the predicted erase cycle life information is used to adjust program and / or erase parameters such as erase voltage and time.

A modified JAVA(™) execution environment is described. The modified environment supports multiple JAVA(™) applications on a single JAVA(™) virtual machine (JVM). This modified environment provides significant memory and performance improvements when running multiple applications on a single computer system. Notably, no changes are needed to the source code of an application to take advantage of the modified environment. Further, embodiments of the invention may support shared access to base classes through the use of overlays. Additionally, system resource permissions can be enforced based upon the user permissions associated with a running application. Notably, embodiments of the invention allow multiple applications to share the abstract window toolkit (AWT) on a per display basis. Since only a single garbage collection routine is necessary, applications see improved performance relative to running in different JVMs. Further, the shared base classes eliminate significant memory overhead.

Described embodiments provide a method of recovering storage space on a solid state disk (SSD). An index and valid page count are determined for each block of a segment of an SSD. If the valid page count of at least one block in the segment is zero, a quick clean is performed. A quick clean deallocates blocks having zero valid pages and places them in a queue for erasure. Otherwise, a deep clean is performed. A deep clean determines a compaction ratio, N-M, wherein N is a number of partially valid blocks and M is a number of free blocks required to compact the valid data from the N partially valid blocks into M entirely valid blocks. At least one data structure of the SSD is modified to refer to the M entirely valid blocks, and the N partially valid blocks are placed in the queue for erasure.

A method and system are disclosed for improved block erase cycle life prediction and block management in a non-volatile memory. The method includes the storage device tracking information relating to a first erase cycle count at which the block erase time exceeded a predetermined threshold relative to a first erase cycle at which this occurred in other blocks. Blocks having a later relative erase cycle at which the erase time threshold is exceeded are assumed to have a greater erase cycle life than those that need to exceed the erase time threshold at an earlier erase cycle. This information is used to adjust wear leveling in the form of free block selection, garbage collection block selection and other block management processes. Alternatively or in combination, the predicted erase cycle life information is used to adjust program and / or erase parameters such as erase voltage and time.

A method, system and computer program product for optimizing memory usage of an application running on a virtual machine. A virtual machine memory block is pre-allocated and the average memory usage of the virtual machine is periodically computed using statistics collected from the virtual machine through an API. If the memory usage average becomes higher than a maximum threshold, then a recovery mode is entered by releasing the virtual machine memory block and forcing the running application to reduce its processing activity; optionally, a garbage collector cycle can be forced. If the computed memory usage average becomes lower than a minimum threshold value, which is lower than the maximum threshold value, then a normal mode is entered by re-allocating the virtual machine memory block and forcing the running application to resumes its normal processing activity. Optionally, when the virtual machine is idle, a deep garbage collection is forced.

Handling garbage collection and exceptions in hardware assisted transactions. Embodiments are practiced in a computing environment including a hardware assisted transaction system. Embodiments includes acts for writing to a card table outside of a transaction; handling garbage collection compaction occurring when a hardware transaction is active by using a common global variable and instructing one or more agents to write to the common global variable any time an operation is performed which may change an object's virtual address; acts for managing a thread-local allocation context; acts for handling exceptions while in a hardware assisted transaction. A method includes beginning a hardware assisted transaction, raising an exception while in the hardware assisted transaction, including creating an exception object, determining that the transaction should be rolled back, and as a result of determining that the transaction should be rolled back, marshaling the exception object out of the hardware assisted transaction.

A garbage collection (GC) process within a deduplication backup network comprising a GC component identifying metadata stored in file system (FS) segments, storing the metadata in a metadata container locally on the server as well as on cloud storage, and reading the locally stored metadata container through the GC process to obtain metadata of the FS containers and determine live data regions of the FS containers, wherein the metadata contains fingerprints of all segments of the file system containers; and a copy forward component forwarding the live data regions to new containers written both locally on the server and on the cloud storage, writing live portions of the metadata container to a new metadata container written both locally on the server and on the cloud storage, and deleting dead compression regions from the cloud storage and deleting the original metadata container from local storage and the cloud storage.

This document describes a protocol for reliably synchronizing states of nodes in a distributed environment through use of a Scalable Atomic Multicast (SAM) Service that ensures both atomicity and total order among messages sent to a multicast group. In addition to possessing good scalability property, this fault-tolerant protocol does not require explicit knowledge of multicast group membership, allows for non-disturbing state synchronization, and supports asynchronous non-blocking communications. According to one aspect of this invention, a dedicated sequencer is responsible solely for assigning sequence numbers to the multicast messages. The sequencer does not multicast the messages. Another aspect of the invention is the use of receiver-driven negative acknowledgments. According to third aspect, the invention supports message consolidation and garbage collection.

The operation of a pool of solid state drives is orchestrated to manage garbage collection and wear leveling. Each individual solid state drive is operated in either an Active Mode in which I / O commands are processed or in a Maintenance Mode in which garbage collection is performed and no I / O commands are processed. The selection of solid state drives in the Active Mode is further selected to achieve wear leveling over the pool of solid state drives. A virtualization layer provides dynamic mapping of virtual volume addresses to physical solid state drives.

The present invention relates to an NAND Flash memory garbage collection method. The NAND Flash memory garbage collection method comprises the following steps of (1) if write-in data are the first page of data of the write request, obtaining to-be-write-in data bulk size Pwr of the current write request, and if not, going to a step (4) for execution; (2) pre-searching the flash memory, and determining the minimum average collection times [mu]=Bgc / Pwr of the write-in data; (3) selecting a collection strategy according to garbage collection overhead determined by pre-searching; and (4) setting size of idle space to be Perased and size of residual space except flash memory space occupied by valid data to be Pfree, if Perased / Pfree>1 / 4, ending collection; and if not, determining a collection target block Bvictim according to the collection strategy selected in the step (3), migrating valid pages of data in the Bvictim to other clean pages, and erasing the Bvictim to complete the collection. According to the NAND Flash memory garbage collection method, collection efficiency can be improved, write operation overhead of a memory management system can be reduced, and system I / O performance can be improved.

The invention relates to a garbage recovery method for a solid-state storage device and a system for the garbage recovery method and belongs to the field of solid-state storage. The garbage recovery method is applicable to the solid-state storage device based on flash memory and is used for solving the problem that the existing garbage recovery method cannot effectively utilize the system idle time to carry out garbage recycling or the garbage recycling consumes a longer time and the reading and writing response delay of a system is increased. The method provided by the invention comprises the steps of generating garbage recovery requests, judging, executing uninterruptible requests and executing interruptible requests. The system provided by the invention comprises corresponding modules. According to the method and the system, the garbage recovery requests are divided into interruptible garbage recovery requests and uninterruptible garbage recovery requests, an interruptible garbage recovery step and an uninterruptible garbage recovery step are respectively called through dynamically adjusting a garbage recovery trigger threshold, the garbage recovery is carried out by making full use of the idle time of the solid-state storage device, and meanwhile, unnecessary garbage recovery is avoided; and the reading / writing performance loss caused by the garbage recovery is reduced effectively under the condition that garbage recovery efficiency is not affected.

The invention provides a cleaning device 1. The device comprises a rolling brush 2 which is arranged on a shell and can be in rolling contact with the ground, a garbage collection area is integrally or separately arranged in the shell, a collection inlet 31 corresponding to the rolling brush 2 is formed in the garbage collection area, and garbage brought up through rolling contact is collected into the garbage collection area under the rotating action of the rolling brush 2; the shell is provided with one or more scraping guiders connected with the collecting inlet 31, and the scraping guidersare in flexible pressure contact with the rolling brush 2 or the ground and used for scraping and transferring residual garbage absorbed by the rolling brush 2 or residual garbage on the ground intothe garbage collecting area so as to reduce or avoid garbage omission.

One embodiment of the present invention provides a system that facilitates performing generational garbage collection on a heap. The system operates by dividing an old generation of the heap into segments. Next, the system divides each segment into a series of cards and associates a separate card table with each segment. This card table has an entry for each card in the segment. In a variation on this embodiment, while updating a pointer within an object in the old generation, the system locates the segment containing the object and accesses the card table for the segment. The system then marks the entry in the card table associated with the card containing the object.

The invention relates to the technical field of garbage classifying, in particular to a smart community garbage classifying system and method. An account number is established for each community userand correlated to the garbage classifying system. The garbage classifying system comprises a server, a community garbage classifying management client side and garbage classifying terminal equipment.The server achieves user data storage and supports data reading and writing through various access ends. The community garbage classifying management client side mainly comprises a garbage classifyingtreatment management module, a garbage paid recycling management module, a garbage bag getting management module, a user management module, a user garbage classifying grade management module and other community equipment management modules. The garbage classifying terminal equipment comprises a garbage classifying treatment module and a garbage bag getting module. According to the provided garbage classifying system, the garbage classifying effect can be better guaranteed, and garbage recycling and treatment are benefited.

The invention discloses a writing, reading and garbage collection method of a solid-state memory system having an online repeated data deleting function. The writing method comprises the steps of receiving a request for writing a logic page through the solid-state memory system; calculating a characteristic value (i.e. fingerprint) of data of the logic page; judging whether the characteristic value of the data of the logic page exists in a fingerprint mapping table or not; recording a mapped address of the logic page in the address mapping table as a physical page address corresponding to the characteristic value of the data of the logic page in the mapping table if the characteristic value of the data of the logic page exists in the fingerprint mapping table; and enabling a valid page count of the corresponding physical page address in a valid page count table plus one. Due to the adoption of the writing, reading and garbage collection method of the solid-state memory system having the online repeated data deleting function, repeated data which is written into the solid-state memory system can be eliminated online, so that the memory efficiency and performance of the solid-state memory system can be improved, and the power consumption can be reduced.

Methods and apparatus for controlling garbage collection in solid state devices (SSDs) are provided. Once such apparatus includes a non-volatile memory (NVM), and a controller communicatively coupled to a host device and the NVM, and configured to calculate an invalidation factor for each of a plurality of blocks in the NVM, wherein the invalidation factor is determined based on a percentage of invalid pages in a respective block of the plurality of blocks and a most recent time of invalidation of one or more pages in the respective block; classify each block of the plurality of blocks into one of three categories based on the calculated invalidation factor; and perform a garbage collection operation for the NVM, wherein the garbage collection operation includes selecting a source block for the garbage collection operation based on the classifications of the plurality of blocks.

The invention belongs to the technical field of network storage, and discloses a method for creating an allocation-on-demand incremental volume. The volume has a two-layer volume structure, and realizes separation of a physical space and a logical space. The creating method comprises that: a user state interface participates in a new parameter (N) in a user state command lvcreate of a logical volume manger (LVM). The real volume of the bottom layer is a common logical volume, and the virtual volume of the upper layer is a data structure in a Linux kernel. The physical space of the real volume is allocated according to the actual requirement, so the utilization rate of a disk space is improved. Real-time monitoring of the physical space of the real volume and automatic capacity expansion of the actual space effectively avoid overflow of the spaces. A user can randomly designate capacity expansion increment magnitude as required to perform capacity expansion of the virtual volume. The volume processes the write request by adopting a mode of additional write. Moreover, the volume processes garbage fragments by adopting a quick and effective garbage reclamation algorithm.

The invention discloses a shell mounting structure of cleaning equipment, which comprises a mounting shell 11 for mounting a rolling brush 2, one end of the rolling brush 2 is mounted on the mountingshell 11 in a relatively rotatable manner, the other end of the rolling brush 2 is in driving connection with a rolling brush driver 7, a garbage collection area is provided with a collection inlet 31corresponding to the rolling brush 2, the rolling brush 2 and the mounting shell 11 are correspondingly matched to form a ground scraping guider 5 connected with the collecting inlet 31, and the ground scraping guider 5 is used for scraping residual garbage on the ground and transferring the residual garbage into a garbage collecting area through the rotating motion of the rolling brush 2, wherein the ground scraping guider 5 comprises a ground scraping strip 51 and a guide surface 52 which are respectively positioned on the mounting shell 11, the ground scraping strip 51 is in flexible pressure contact with the ground, and the guide surface 52 is connected with the collecting inlet 31. Garbage omission can be remarkably reduced or avoided, and the cleaning effect of the composite sweeping and mopping function is effectively improved.

In processor architectures that support allocation of register windows to called procedures, functions or methods, register windowing mechanisms can be used to facilitate suspension of a mutator thread (or mutator threads) while imposing negligible overhead on the mutator computation during periods when thread suspension is not requested. Reduced Instruction Set Computer-(RISC)-oriented processor architectures often employ register windows (typically partially-overlapped register windows) and can therefore benefit from the technique. Variations can be employed even in processors (RISC or otherwise) that do not employ register windowing as long as the processor (by itself or in cooperation with software) provides facilities for allocating and reclaiming resources in correspondence with calls to, and returns from, procedures, functions or methods. Mechanisms are provided to spill values from the fixed set of resources to a secondary store and to fill values from the secondary store into the fixed set in correspondence with function call triggered overflows and function return triggered underflows. In some configurations, modified spill and / or fill mechanism(s) are used to suspend threads at safe points coinciding with call and / or return sites. Because the modified spill and / or fill mechanism(s) impose negligible overhead when not employed and can be engaged in response to an event (e.g., a start garbage collection event), safe points can be defined at call and / or return points throughout mutator code to reduce the latency between the event and suspension of threads.

Disclosed is a method of operating a memory system which executes a plurality of commands including a write command and a trim command. The memory system includes a memory device, which includes a plurality of blocks. The method further includes performing garbage collection for generating a free block, calculating a workload level in performing the garbage collection, and changing a command schedule based on the workload level.