STORAGE CONTROLLER CACHE MEMORY OPERATIONS THAT FOREGO REGION LOCKING

• US 20170097909A1
• Filed: 10/05/2015
• Published: 04/06/2017
• Est. Priority Date: 10/05/2015
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Avago Technologies General IP PTE Limited (Broadcom, Inc.)
• Inventors: Simionescu, Horia Cristian, Hoglund, Timothy E., Veerla, Sridhar Rao, Pandit, Panthini, Radhakrishnan, Gowrisankar
• Granted Patent: US 9,910,798 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 12/0864 using pseudo-associative means, e.g. set-associative or hashing
• CPC Class Codes: G06F 12/0871 Allocation or management of cache space
• CPC Class Codes: G06F 12/0893 Caches characterised by their organisation or structure
• CPC Class Codes: G06F 13/28 using burst mode transfer, e.g. direct memory access DMA, cycle steal G06F13/32 takes precedence
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/262 configured as RAID
• CPC Class Codes: G06F 2212/312 In storage controller
• CPC Class Codes: G06F 2212/60 Details of cache memory
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

Methods and structure for managing cache memory for a storage controller. One exemplary embodiment a Redundant Array of Independent Disks (RAID) storage controller. The storage controller includes an interface operable to receive Input/Output (I/O) requests from a host, a Direct Memory Access (DMA) module, a memory comprising cache data for a logical volume, and a control unit. The control unit is able to generate Scatter Gather Lists (SGLs) that indicate the location of cache data for incoming read requests. Each SGL is stored in the memory, and at least one SGL points to cache data that is no longer indexed by the cache. The control unit is also able to service an incoming read request based on the SGL, by directing the DMA module to transfer the cache data that is no longer indexed to the host.

Claims

1. A Redundant Array of Independent Disks (RAID) storage controller comprising:

an interface operable to receive Input/Output (I/O) requests from a host;

a Direct Memory Access (DMA) module;

a memory comprising buffer segments that store data for a logical volume, and further comprising cache entries that correlate buffer segments with Logical Block Addresses (LBAs) of the logical volume; and

a control unit operable to detect an incoming read request, to query the cache entries to identify buffer segments storing data for the read request, to generate a Scatter Gather List (SGL) indicating the identified buffer segments, and to direct the DMA module to transfer data to the host based on the SGL,

wherein the control unit is further operable to detect an incoming write request that updates LBAs referenced by the read request, to update a cache entry by eliminating a reference to one of the identified buffer segments and adding a new reference to a new buffer segment, and after the cache entry has been updated, to prevent the identified buffer segment from being overwritten before the DMA module has finished reading data from the identified buffer segment.

2. The system of claim 1, wherein:

the SGL comprises multiple Scatter Gather Entries (SGEs) that each indicate a buffer segment storing data for the read request.

3. The system of claim 1, wherein:

the cache manager is operable to utilize a hash table to index the cache entries.

4. The system of claim 3, wherein:

entries in the hash table are ordered by a combination of logical volume identifier and strip number for a logical volume.

5. The system of claim 1, wherein:

the control unit is further operable to generate multiple SGLs for the read request, and to link the SGLs together via chain Scatter Gather Entries (SGEs) within the SGLs.

6. The system of claim 1, wherein:

the control unit is further operable to populate the new buffer segment with data for the incoming write request.

7. The system of claim 1, wherein:

the control unit is further operable to enable overwriting of the identified buffer segment by deallocating the identified buffer segment.

8. A method for operating a Redundant Array of Independent Disks (RAID) storage controller, the method comprising:

receiving a read request directed to Logical Block Addresses (LBAs) of a logical volume;

querying cache entries in memory that identify buffer segments in the memory which are correlated with the LBAs, wherein the buffer segments store data for the logical volume;

generating a Scatter Gather List (SGL) indicating the identified buffer segments;

directing a Direct Memory Access (DMA) module to transfer data to the host based on the SGL;

detecting an incoming write request that updates LBAs referenced by the read request;

updating a cache entry based on the write request by eliminating a reference to one of the identified buffer segments and adding a reference for a new buffer segment storing the updated LBAs; and

in response to updating the cache entry, preventing the identified buffer segment from being overwritten before the DMA module has finished reading data from the identified buffer segment.

9. The method of claim 8, wherein:

the SGL comprises multiple Scatter Gather Entries (SGEs) that each indicate a buffer segment storing data for the read request.

10. The method of claim 8, further comprising:

utilizing a hash table to index the cache entries.

11. The method of claim 8, wherein:

entries in the hash table are ordered by a combination of logical volume identifier and strip number for a logical volume.

12. The method of claim 8, further comprising:

generating multiple SGLs for the read request; and

linking the SGLs together via chain Scatter Gather Entries (SGEs) within the SGLs.

13. The method of claim 8, further comprising:

populating the new buffer segment with data for the incoming write request.

14. The method of claim 8, further comprising:

enabling overwriting of the identified buffer segment by deallocating the identified buffer segment.

15. A non-transitory computer readable medium embodying programmed instructions which, when executed by a processor, are operable for directing the processor to:

receive a read request directed to Logical Block Addresses (LBAs) of a logical volume;

querying cache entries in memory that identify buffer segments in the memory which are correlated with the LBAs, wherein the buffer segments store data for the logical volume;

generate a Scatter Gather List (SGL) indicating the identified buffer segments;

direct a Direct Memory Access (DMA) module to transfer data to the host based on the SGL;

detect an incoming write request that updates LBAs referenced by the read request;

update a cache entry based on the write request by eliminating a reference to one of the identified buffer segments and adding a reference for a new buffer segment storing the updated LBAs; and

in response to updating the cache entry, prevent the identified buffer segment from being overwritten before the DMA module has finished reading data from the identified buffer segment.

16. The medium of claim 15, wherein:

the SGL comprises multiple Scatter Gather Entries (SGEs) that each indicate a buffer segment storing data for the read request.

17. The medium of claim 15, wherein the instructions further direct the processor to:

utilize a hash table to index the cache entries.

18. The medium of claim 15, wherein:

entries in the hash table are ordered by a combination of logical volume identifier and strip number for a logical volume.

19. The medium of claim 15, wherein the instructions further direct the processor to:

generate multiple SGLs for the read request; and

link the SGLs together via chain Scatter Gather Entries (SGEs) within the SGLs.

20. The method of claim 15, wherein the instructions further direct the processor to:

populate the new buffer segment with data for the incoming write request.