Flash optimized, log-structured layer of a file system

• US 10,042,853 B2
• Filed: 08/17/2016
• Issued: 08/07/2018
• 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 A
• Application Number:
  US15/239,125
• Publication Number:
  US 20160357776A1
• Time in Patent Office: 720 Days
• Field of Search: 711103, 711114
• 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

A flash-optimized, log-structured layer of a file system of a storage input/output (I/O) stack executes on one or more nodes of a cluster. The log-structured layer of the file system provides sequential storage of data and metadata (i.e., a log-structured layout) on solid state drives (SSDs) of storage arrays in the cluster to reduce write amplification, while leveraging variable compression and variable length data features of the storage I/O stack. The data may be organized as an arbitrary number of variable-length extents of one or more host-visible logical units (LUNs) served by the nodes. The metadata may include mappings from host-visible logical block address ranges (i.e., offset ranges) of a LUN to extent keys, as well as mappings of the extent keys to SSD storage locations of the extents. The storage location of an extent on SSD is effectively “virtualized” by its mapped extent key (i.e., extent store layer mappings) such that relocation of the extent on SSD does require update to volume layer metadata (i.e., the extent key sufficiently identifies the extent).

Claims

1. A method comprising:

organizing a storage array of solid state drives (SSDs) coupled to a node as a redundant array of independent disks (RAID) group;

organizing data and metadata on the SSDs in a sequential log-structured layout, the data stored as extents of a logical unit (LUN) served by the node;

gathering the extents to form a stripe written as a write operation that spans all of the SSDs in the RAID group; and

controlling a frequency and a size of the write operation to sustain a streaming bandwidth to the SSDs and to override garbage collection in the SSDs.

2. The method of claim 1 wherein controlling the frequency and the size of the write operation further comprises varying the size of the write operation depending on a write load served by the node.

3. The method of claim 2 wherein the size of the write operation varies from a minimum size to a maximum size depending on the write load, wherein the maximum size is at least 10 times the minimum size.

4. The method of claim 2 wherein varying the size of the write operation comprises determining the size of the write operation based on pressure in a write-back cache of the node.

5. The method of claim 2 wherein controlling the frequency and the size of the write operation further comprises waiting until enough data is accumulated in a write-back cache of the node to form a sufficiently large write size to override garbage collection in the SSDs.

6. The method of claim 2 wherein controlling the frequency and the size of the write operation further comprises choosing a sufficiently small write size to ensure timely storage of the data on the SSDs.

7. The method of claim 1 wherein controlling the frequency and the size of the write operation comprises writing the extents of the write operation over a same SSD address range as previously written extents on the SSD to override the garbage collection in the SSDs.

8. A system comprising:

a processor connected to a memory;

a storage array connected to the processor and having solid state drives (SSDs);

a storage input/output (I/O) stack executing on the processor to;

organize the SSDs as a redundant array of independent disks (RAID) group;

organize data and metadata on the SSDs in a sequential log-structured layout, the data stored as extents of a logical unit (LUN) served by the storage I/O stack;

gather the extents to form a stripe written as a write operation that spans all of the SSDs in the RAID group; and

control a frequency and a size of the write operation to sustain a streaming bandwidth to the SSDs and to override garbage collection in the SSDs.

9. The system of claim 8 wherein the size of the write operation varies depending on a write load served the storage I/O stack.

10. The system of claim 9 wherein the size of the write operation varies from a minimum size to a maximum size depending on the write load, wherein the maximum size is at least 10 times the minimum size.

11. The system of claim 9 wherein the size of the write operation is determined based-on pressure in a write-back cache connected to the processor.

12. The system of claim 9 further comprising a write-back cache connected to the processor, the write-back cache configured to accumulate enough data to form a sufficiently large write size to override garbage collection in the SSDs.

13. The system of claim 8 wherein the extents of the write operation are written over a same SSD address range as previously written extents on the SSD to override the garbage collection in the SSDs.

14. A non-transitory computer readable medium including program instructions for execution on a processor, the program instructions configured to:

organize a storage array of solid state drives (SSDs) coupled to a node a redundant array of independent disks (RAID) group;

organize data and metadata on the SSDs in a sequential log-structured layout, the data stored as extents of a logical unit (LUN) served by the node;

gather the extents to form a stripe written as a write operation that spans all of the SSDs in the RAID group; and

control a frequency and a size of the write operation to sustain a streaming bandwidth to the SSDs and to override garbage collection in the SSDs.

15. The non-transitory computer readable medium of claim 14 wherein program instructions are further configured to:

vary the size of the write operation depending on a write load served by the node.

16. The non-transitory computer readable medium of claim 15 wherein the size of the write operation varies from a minimum size to a maximum size depending on the write load, wherein the maximum size is at least 10 times the minimum size.

17. The non-transitory computer readable medium of claim 15 wherein program instructions are further configured to:

determine the size of the write operation based-on pressure in a write-back cache of the node.

18. The non-transitory computer readable medium of claim 15 wherein program instructions are further configured to:

wait until enough data is accumulated in a write-back cache of the node to form a sufficiently large write size to override garbage collection in the SSDs.

19. The non-transitory computer readable medium of claim 15 wherein program instructions are further configured to:

choose a sufficiently small write size to ensure timely storage of the data on the SSDs.

20. The non-transitory computer readable medium of claim 14 wherein program instructions when executed are further configured to:

write the extents of the write operation over a same SSD address range as previously written extents on the SSD to override the garbage collection in the SSDs.