Storage Adjuncts for In-Band RPC Data Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solutions for data-intensive operations in commercial environments face challenges in enabling application-specific processing near storage, maintaining data access security, preserving storage stability, and managing application-specific functionality, particularly in mainframe systems with CKD data formats, due to limitations in hardware and software support.
Innovation Solution
A method that places data-intensive subprocesses on a storage facility using adjuncts, which are invoked through an in-band RPC mechanism, allowing for secure and efficient data processing by binding to host applications and managing access control, while maintaining storage server stability and security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If custom operations are added to the storage server to enable data processing, then application-specific processing capability is improved, but storage server stability deteriorates due to code load and modification risks
Solution Approach 1:
The system segments the storage server functionality by introducing a separate adjunct program that runs in its own address space. The adjunct handles application-specific data processing operations while the storage server maintains its core functions. This segmentation allows custom operations to be added without compromising the stability of the storage server itself.
Solution Approach 2:
The adjunct acts as an intermediary between the host application and the storage server. It receives requests from the host, performs data-intensive operations locally, and returns results to the host. This intermediary approach enables application-specific processing while isolating the storage server from direct modification or instability risks.
2Productivity
If a dedicated application server is added to perform data-intensive computation, then processing capability is improved, but system cost increases due to additional hardware
Solution Approach 1:
The system merges the data processing capability directly into the storage server by loading adjunct programs onto it. This combination eliminates the need for separate dedicated application servers, reducing hardware costs while maintaining enhanced data processing capability. The storage server simultaneously performs both storage and computation functions.
Solution Approach 2:
The storage server is transformed into a multi-functional system that can perform both traditional storage operations and application-specific data processing through adjunct programs. This universality allows a single system to replace what would traditionally require multiple specialized components, reducing overall system cost.
3Ease of operation
If adjuncts are made invokable through host I/O channel with RPC mechanism, then ease of operation is improved, but communication overhead increases
Solution Approach 1:
The adjunct program automatically handles its own invocation and execution through the RPC mechanism initiated by host applications. The system provides self-service by allowing applications to directly invoke adjuncts through familiar I/O channel commands without requiring complex intermediary procedures, balancing ease of operation with acceptable communication overhead.
Data Source
AI summary
A method is disclosed that places data-intensive subprocesses in close physical and logical proximity to the facility responsible for storing the data, so that high efficiencies at reduced cost are achieved. In one specific example, new computer programs, termed adjuncts, are added and placed in a logical partition on a storage facility so that they can be invoked using appropriate commands issued on the I/O channel. Further, programs or changes are added to existing programs on the host machine, wherein such programs or changes discover the function extensions and invoke them to perform data processing.