Flash optimized, log-structured layer of a file system

• US 9,448,924 B2
• Filed: 01/08/2014
• Issued: 09/20/2016
• Est. Priority Date: 01/08/2014
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Sundaram, Rajesh, Daniel, Stephen, Kimmel, Jeffrey S., Lewis, Blake H.
• Primary Examiner(s): Bradley, Matthew
• Application Number:
  US14/150,717
• Publication Number:
  US 20150193338A1
• Time in Patent Office: 986 Days
• Field of Search: 711/103
• US Class Current: 1/1
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 16/1727 Details of free space management performed by the file system saving storage space on storage systems G06F3/0608; management of blocks in storage devices G06F3/064
• CPC Class Codes: G06F 16/1805 Append-only file systems, e.g. using logs or journals to store data
• CPC Class Codes: G06F 16/1847 specifically adapted to static storage, e.g. adapted to flash memory or SSD
• CPC Class Codes: G06F 2212/2022 Flash memory
• CPC Class Codes: G06F 2212/7208 Multiple device management, e.g. distributing data over multiple flash devices
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0616 in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0643 Management of files
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/0679 Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays
• CPC Class Codes: G06F 3/0689 : Disk arrays, e.g. RAID, JBOD

Abstract

In one embodiment, storage arrays of solid state drives (SSDs) coupled to a node are organized as redundant array of independent disks (RAID) groups. Each storage array includes one or more segments. Each segment has contiguous free space on the SSDs. Data and metadata is organized on the SSDs with a sequential log-structured layout, with the data organized as variable-length extents of one or more logical units (LUNs). Segment cleaning is performed to clean a selected segment by moving the extents of the selected segment that contain valid data to one or more different segments so as to free the selected segment. Additional extents are written as a sequence of contiguous range write operations to the entire free segment with temporal locality to reduce data relocation within the SSDs as a result of the write operations.

Claims

1. A system comprising:

a central processing unit (CPU) of a node;

one or more storage arrays of solid state drives (SSDs) coupled to the node, each storage array including a first set of segments and a second set of segments, each segment having a contiguous free space on the SSDs, the SSDs organized as one or more redundant array of independent disks (RAID) groups; and

a memory coupled to the CPU and configured to store a layered file system of a storage input/output (I/O) stack, the layered file system including a log-structured layer configured to provide sequential log-structured layout of data and metadata on the SSDs, the data organized as variable-length extents of one or more logical units (LUNs) served by the node, the log-structured layer configured to perform segment cleaning to clean a selected segment from the first set of segments by reading the extents of the selected segment that contain valid data and writing the read extents to one or more different segments so as to maintain a first fraction of free space in the selected segment to enable writing of additional extents as a sequence of contiguous range write operations to the selected segment with temporal locality to reduce data relocation within the SSDs as a result of the write operations, wherein the second set of segments is maintained at a second fraction of free space different from the first fraction of free space.

2. The system of claim 1 wherein the log structured layer is further configured to perform gathering of the extents to form one or more full stripes written to the selected segment such that a single stripe write operation spans all SSDs in a RAID group.

3. The system of claim 1 wherein the first set of segments has a greater rate of data change than the second set of segments.

4. The system of claim 1 wherein the second fraction of free space is lower than the first fraction of free space.

5. The system of claim 1 wherein writing a full stripe to the selected segment avoids a cost of parity updates and spreads a read operation load across the SSDs.

6. The system of claim 1 wherein segment cleaning comprises garbage collection and wherein the storage I/O stack implements the garbage collection to bypass performance impacts of flash translation layer functionality in the SSDs.

7. The system of claim 1 wherein the log-structured layer operates as a data layout engine using the segment cleaning to replace a portion of flash translation layer functionality in the SSDs.

8. A method comprising:

organizing one or more storage arrays of solid state drives (SSDs) coupled to a node as one or more redundant array of independent disks (RAID) groups, each storage array including a first set of segments and a second set segments, each segment having a contiguous free space on the SSDs;

organizing, by the node, data and metadata on the SSDs with a sequential log-structured layout, the data organized as variable-length extents of one or more logical units (LUNs) served by the node;

mapping LUN offsets to keys associated with the extents;

performing segment cleaning to clean a selected segment by reading the extents of the selected segment from the first set of segments that contain valid data and writing the read extents to one or more different segments so as to maintain a first fraction of free space in the selected segment; and

writing additional extents as a sequence of contiguous range write operations to the selected segment with temporal locality, wherein the second set of segments is maintained at a second fraction of free space different from the first fraction of free space.

9. The method of claim 8 further comprising:

gathering the extents to form one or more full stripes written to the selected segment such that a single stripe write operation spans all SSDs in a RAID group.

10. The method of claim 8 wherein the first set of segments has a greater rate of data change than the second set of segments.

11. The method of claim 8 wherein the second fraction of free space is lower than the first fraction of free space.

12. The method of claim 8 wherein the writing further comprises:

spreading a read operation load across the SSDs.

13. The method of claim 8 wherein the performing further comprises:

performing garbage collection to bypass performance impacts of flash translation layer functionality in the SSDs.

14. The method of claim 8 wherein the segment cleaning replaces a portion of flash translation layer functionality in the SSDs.

15. A non-transitory computer readable medium including program instructions for execution on one or more processors, the program instructions when executed operable to:

organize one or more storage arrays of solid state drives (SSDs) as one or more redundant array of independent disks (RAID) groups, each storage array including a first set of segments and a second set of segments, each segment having a contiguous free space on the SSDs;

organize data and metadata on the SSDs with a sequential log-structured layout, the data organized as variable-length extents of one or more logical units (LUNs);

perform segment cleaning to clean a selected segment from the first set of segments by reading the extents of the selected segment that contain valid data and writing the read extents to one or more different segments so as to maintain a first fraction of free space in the selected segment;

maintain the second set of segments at a second fraction of free space different from the first fraction of free space; and

write additional extents as a sequence of contiguous range write operations to the selected segment with temporal locality.

16. The non-transitory computer readable medium of claim 15 wherein the program instructions when executed are further operable to:

gather the extents to form one or more full stripes written to the selected segment such that a single stripe write operation spans all SSDs in a RAID group.

17. The non-transitory computer readable medium of claim 15 wherein the program instructions include program instructions for a log-structured layer of a layered file system of a storage input/output (I/O) stack.

18. The non-transitory computer readable medium of claim 15 wherein the second fraction of free space is lower than the first fraction of free space.

19. The non-transitory computer readable medium of claim 15 wherein the write of additional extents as a sequence of contiguous range write operations spreads a read operation load across the SSDs.

20. The non-transitory computer readable medium of claim 15 wherein segment cleaning uses garbage collection to bypass performance impacts of flash translation layer functionality in the SSDs.