Associating a processing thread and memory section to a memory device

• US 10,324,855 B2
• Filed: 06/23/2017
• Issued: 06/18/2019
• Est. Priority Date: 06/23/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Baptist, Andrew D., Vedpathak, Yogesh R.
• Primary Examiner(s): Bataille, Pierre Miche
• Application Number:
  US15/631,453
• Publication Number:
  US 20180373640A1
• Time in Patent Office: 725 Days
• Field of Search: 711170, 711171, 711202
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 12/10 Address translation
• CPC Class Codes: G06F 12/1072 Decentralised address translation, e.g. in distributed shared memory systems
• CPC Class Codes: G06F 12/1081 for peripheral access to main memory, e.g. direct memory access [DMA]
• CPC Class Codes: G06F 12/109 for multiple virtual address spaces, e.g. segmentation G06F12/1036 takes precedence
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/154 Networked environment
• CPC Class Codes: G06F 2212/263 Network storage, e.g. SAN or NAS
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A method begins by a storage unit of a dispersed storage network (DSN) receiving access requests which include a logical DSN address and a storage function. The method continues with a first processing module of the storage unit performing logical to physical address conversions of logical DSN addresses of the access requests to physical addresses of a plurality of main memories. For a first access request of the access requests, the method continues with the first processing module identifying a first main memory based on the physical address resulting from the physical address conversion. The method continues with the first processing module identifying a first processing thread of a plurality of processing threads based on allocation of the plurality of processing threads to the plurality of main memories. The method continues with the first processing thread executing tasks of the first access request to fulfill the first access request.

Claims

1. A storage unit of a dispersed storage network (DSN), the storage unit comprises:

a network interface;

a plurality of main memories; and

a plurality of processing modules, wherein the plurality of processing modules are operably coupled to the network interface and the plurality of main memories, wherein a first processing module of the plurality of processing modules is operable to;

receive access requests, wherein an access request of the access requests includes a logical DSN address and a storage function;

perform logical to physical address conversions of logical DSN addresses of the access requests to produce physical addresses of a plurality of main memories of the storage unit;

for a first access request of the access requests;

identify a first main memory from the plurality of main memories based on the logical to physical address resulting from the physical address conversion of a first logical DSN address of the first access request;

identify a first processing thread of a plurality of processing threads based on an allocation of the plurality of processing threads to the plurality of main memories, wherein the allocation of the plurality of processing threads to the plurality of main memories includes;

allocating the first processing thread to a first main memory of the plurality of main memories, wherein the first main memory is paired with a first subset of memory devices of a plurality of memory devices;

allocating a second processing thread to the first main memory of the plurality of main memories wherein the first main memory is paired with a second subset of memory devices of the plurality of memory devices; and

allocating a third processing thread to a second main memory of the plurality of main memories wherein the second main memory is paired with a third subset of memory devices of the plurality of memory devices; and

instruct the first processing thread to execute a plurality of tasks of the first access request to fulfill the first access request.

2. The storage unit of claim 1, wherein the storage function includes one of:

a read request;

a write request;

list request;

digest request; and

rebuild request.

3. The storage unit of claim 1, wherein the first processing module is further operable to:

for a second access request of the access requests;

identify the second main memory from the plurality of main memories based on the logical to physical address resulting from the physical address conversion of a second logical DSN address of the second access request;

identifying the second processing thread of the plurality of processing threads based on allocation of the plurality of processing threads to the plurality of main memories; and

instruct the second processing thread to execute a plurality of tasks of the second access request to fulfill the second access request.

4. The storage unit of claim 3, wherein a second processing module of the plurality of processing modules is operable to execute the first and second processing threads.

5. The storage unit of claim 3, wherein a second processing module of the plurality of processing modules is operable to execute the first processing thread and a third processing module of the plurality of processing modules is operable to execute the second processing thread.

6. The storage unit of claim 1 further comprises:

one or more of the plurality of memory devices being a non-uniform memory access (NUMA) memory device.

7. The storage unit of claim 1, wherein the first processing module is further operable to:

for a second access request of the access requests;

identify the second main memory from the plurality of main memories based on the logical to physical address resulting from the physical address conversion of a first logical DSN address of the first access request;

identify the first processing thread based on the allocation of the plurality of processing threads to the plurality of main memories; and

instruct the first processing thread to execute a second plurality of tasks of the second access request to fulfill the second access request.

8. A method comprises:

receiving, by a storage unit of a dispersed storage network (DSN), access requests, wherein an access request of the access requests includes a logical DSN address and a storage function;

performing, by a first processing module of a plurality of processing modules of the storage unit, logical to physical address conversions of logical DSN addresses of the access requests to produce physical addresses of a plurality of main memories of the storage unit;

for a first access request of the access requests;

identifying, by the first processing module, a first main memory from the plurality of main memories based on the physical address resulting from the logical to physical address conversion of a first logical DSN address of the first access request;

identifying, by the first processing module, a first processing thread of a plurality of processing threads based on an allocation of the plurality of processing threads to the plurality of main memories, wherein the allocation of the plurality of processing threads to the plurality of main memories includes;

allocating the first processing thread to a first main memory of the plurality of main memories, wherein the first main memory is paired with a first subset of memory devices of a plurality of memory devices;

allocating a second processing thread to the first main memory of the plurality of main memories wherein the first main memory is paired with a second subset of memory devices of the plurality of memory devices; and

allocating a third processing thread to a second main memory of the plurality of main memories wherein the second main memory is paired with a third subset of memory devices of the plurality of memory devices; and

executing, by the first processing thread, a plurality of tasks of the first access request to fulfill the first access request.

9. The method of claim 8, wherein the storage function includes one of:

a read request;

a write request;

list request;

digest request; and

rebuild request.

10. The method of claim 8 further comprises:

for a second access request of the access requests;

identifying, by the first processing module, a main memory from the plurality of main memories based on the physical address resulting from the logical to physical address conversion of a second logical DSN address of the second access request;

identifying, by the first processing module, the second processing thread of the plurality of processing threads based on allocation of the plurality of processing threads to the plurality of main memories; and

executing, by the second processing thread, a plurality of tasks of the second access request to fulfill the second access request.

11. The method of claim 10, wherein the first and second processing threads are executed by a second processing module of the plurality of processing modules.

12. The method of claim 10, wherein the first processing thread is executed by a second processing module of the plurality of processing modules and the second processing thread is executed by a third processing module of the plurality of processing modules.

13. The method of claim 8 further comprises:

one or more of the plurality of memory devices being a non-uniform memory access (NUMA) memory device.

14. The method of claim 8 further comprises:

for a second access request of the access requests;

identifying, by the first processing module, the second main memory from the plurality of main memories based on the physical address resulting from the logical to physical address conversion of a first logical DSN address of the first access request;

identifying, by the first processing module, the first processing thread based on the allocation of the plurality of processing threads to the plurality of main memories; and

executing, by the first processing thread, a second plurality of tasks of the second access request to fulfill the second access request.