DISTRIBUTED STORAGE NETWORK MEMORY ACCESS BASED ON MEMORY STATE

• US 20110078372A1
• Filed: 05/11/2010
• Published: 03/31/2011
• Est. Priority Date: 09/29/2009
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: LEGGETTE, WESLEY, GLADWIN, S. CHRISTOPHER
• Granted Patent: US 8,473,677 B2
• Time in Patent Office: Days
• US Class Current: 711/114
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 2211/1011 Clustered RAID, i.e. clustered or de-clustered RAID where data and parity are spread over more disks than blocks in a parity group
• CPC Class Codes: G06F 3/0617 in relation to availability
• 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 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 based on network conditions
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04N 21/231 Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion
• CPC Class Codes: H04N 21/2405 Monitoring of the internal components or processes of the server, e.g. server load allocation of resources in multiprogramming arrangements G06F9/50; performance measurement of computer activity G06F11/34
• CPC Class Codes: H04N 21/442 Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk arrangements for monitoring broadcast services or broadcast-related services H04H60/29; arrangements for identifying or recognising characteristics with a direct linkage to broadcast information H04H60/35; monitoring of user activities for profile generation for accessing a video database G06F16/739; monitoring in wireless networks H04W24/00

Abstract

A distributed storage unit determines how to handle a read or write request for a data slice based on a state of the memory the data slice is to be read from or written to. When receiving a request to retrieve a data slice, the distributed storage unit, determines a state of the memory in which the data slice is stored. Based on the memory state, one of multiple different methods for obtaining the data slice is selected. The methods include, among others, a direct read from the memory, and reconstructing the data slice using other memories and parity values. In response to a write request, the distributed storage unit can determine whether to use the currently selected memory for writing, or rotate the memory used for writing, based on a state of the memory.

Claims

1. A method comprising:

receiving, at a distributed storage unit, a first request to retrieve a first data slice from storage;

determining a first memory in which the first data slice is stored, and a state of the first memory; and

determining a selected method of a plurality of different methods of obtaining the first data slice based, at least in part, on the state of the first memory.

2. The method of claim 1, wherein the selected method includes reconstructing the first data slice from resources available to the distributed storage unit, the method further comprising:

obtaining the first data slice by reconstructing the first data slice using a second memory, different from the first memory, and a read parity memory.

3. The method of claim 1, wherein the selected method includes reconstructing the first data slice using a read threshold number of data slices from other distributed storage units, the method further comprising:

in response to the first request, sending a notification denying the request.

4. The method of claim 3, further comprising:

sending the notification denying the first request if the state of the first memory is WRITE ONLY, and the distributed storage unit does not have enough currently available resources to reconstruct the first data slice.

5. The method of claim 1, further comprising:

retrieving the first data slice from the first memory if the state of the first memory is one of READ ONLY and WRITE WITH READ PRIORITY.

6. The method of claim 1, further comprising:

in response to the first request, and if the state of the first memory is WRITE ONLY, responding to the first request by one of failing the request and sending a delayed response to the first request.

7. The method of claim 1, further comprising:

receiving, at the distributed storage unit, a second request to write a second data slice to storage;

selecting a second memory and a parity memory to be used for storage of the second data slice;

storing the second data slice using the second memory and the parity memory; and

determining if it the second memory and the parity memory should be rotated.

8. The method of claim 7, wherein determining if it the second memory and the parity memory should be rotated further comprising:

determining a number of write requests in a queue;

determining if read requests are pending for the second memory and the parity memory;

if the number of write requests is greater than an upper threshold, determining that the second memory and the parity memory should not be rotated, regardless of whether there are pending read requests; and

if there are pending read requests, and the number of write requests is less than the upper threshold limit, determining that the second memory and the parity memory should be rotated.

9. The method of claim 7, further comprising:

in response to the determining that the second memory and the parity memory should be rotated, selecting a next memory and a next parity memory; and

setting the second memory and the parity memory to a READ status.

10. A distributed storage unit comprising:

an interface to receive a request to retrieve a data slice from storage;

a control module to determine a memory in which the data slice is stored, and a state of the memory; and

the control module further to determine a selected method of obtaining the data slice based, at least in part, on the state of the memory.

11. The distributed storage unit of claim 10, further comprising:

the control module to obtain information from a second memory and a parity memory; and

the control module further to reconstruct the data slice using information from the second memory and the parity memory.

12. The distributed storage unit of claim 10, further comprising:

the interface further to send a notification denying the request in response to the control module determining the selected method includes reconstructing the first data slice using a read threshold number of data slices from other distributed storage units.

13. The distributed storage unit of claim 12, further comprising:

the interface further to send the notification denying the request in response to the control module determining that the state of the memory is WRITE ONLY, and the distributed storage unit does not have enough currently available resources to reconstruct the data slice.

14. The distributed storage unit of claim 10, further comprising:

the control module further to retrieve the data slice from the memory if the state of the memory is one of READ ONLY and WRITE WITH READ PRIORITY; and

the interface further to send the data slice to a requestor.

15. The distributed storage unit of claim 10, further comprising:

the control module further to, respond to the first request by one of failing the request and sending a delayed response to the first request, if the state of the first memory is WRITE ONLY.

16. The distributed storage unit of claim 10, further comprising:

a plurality of primary memories in which to store data slices; and

a plurality of parity memories to store parity information across the plurality of primary memories.

17. A distributed storage unit comprising:

an interface to receive a request to write a data slice to storage;

a control module to select a primary memory to be used for storage of the data slice, and a parity memory to store parity information associated with the data slice;

the control module to deliver the data slice to the primary memory and the parity memory; and

the control module further to determine if the primary memory and the parity memory should be rotated.

18. The distributed storage unit of claim 17, wherein the control module is further to:

determine a number of write requests in a queue;

determine if a read request is pending for the primary memory;

determine that the second memory and the parity memory should not be rotated, if the number of write requests is greater than an upper threshold, regardless of whether there are pending read requests; and

determine that the second memory and the parity memory should be rotated if the number of write requests is less than the upper threshold limit and there are pending read requests.

19. The distributed storage unit of claim 17, further comprising:

the control module further to select a next memory and a next parity memory to be used for subsequent write requests; and

the control module further to set a status of the second memory and the parity memory to READ.

20. The distributed storage unit of claim 17, further comprising:

a plurality of primary memories to store data slices; and

a plurality of parity memories to store parity information across the plurality of primary memories.

21. The distributed storage unit of claim 17, further comprising:

the interface further to receive a read request to retrieve a second data slice from storage;

a control module to determine a second memory in which the second data slice is stored, and a state of the second memory;

the control module further to determine a selected method of obtaining the second data slice based, at least in part, on the state of the second memory.

22. The distributed storage unit of claim 17, the control module further to:

determine that the second memory is in a WRITE ONLY state; and

reconstruct the data slice using information from an alternate memory and a parity memory.