Consistent unmapping of application data in presence of concurrent, unquiesced writers and readers

• US 9,448,728 B2
• Filed: 08/28/2015
• Issued: 09/20/2016
• Est. Priority Date: 06/22/2011
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: VMware, Inc. (Broadcom, Inc.)
• Inventors: Shaikh, Faraz, Vilayannur, Murali, Vaghani, Satyam B., Joshi, Kiran
• Primary Examiner(s): Birkhimer, Christopher D
• Application Number:
  US14/839,163
• Publication Number:
  US 20150370489A1
• Time in Patent Office: 389 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 12/0253 Garbage collection, i.e. reclamation of unreferenced memory
• CPC Class Codes: G06F 12/0261 using reference counting
• CPC Class Codes: G06F 12/0269 Incremental or concurrent garbage collection, e.g. in real-time systems G06F12/0261 takes precedence
• CPC Class Codes: G06F 12/0276 Generational garbage collection
• 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 16/182 Distributed file systems
• CPC Class Codes: G06F 16/188 Virtual file systems
• CPC Class Codes: G06F 2009/45579 I/O management, e.g. providing access to device drivers or storage
• CPC Class Codes: G06F 2212/1044 Space efficiency improvement
• CPC Class Codes: G06F 2212/154 Networked environment
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0652 Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• 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 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

Free storage blocks previously allocated to a logical block device are released back to an underlying storage system supporting the logical block device in a manner that does not conflict with write operations that may be issued to the free storage blocks at about the same time. According to a first technique, write operations on the same storage blocks to be released are paused until the underlying storage system has completed the releasing operation or, if the write operations are issued earlier than when the underlying storage system actually performs the releasing operation, such storage blocks are not released. According to a second technique, a special file is allocated the free storage blocks, which are then made available for safe releasing.

Claims

1. A method of releasing free blocks of a logical block device back to an underlying disk-based storage system supporting the logical block device, comprising:

identifying a set of the free blocks of the logical block device that are candidates to be released;

updating the set of free blocks to remove those free blocks that have already been released from the logical block device;

allocating the free blocks in the updated set to a file stored on the disk-based storage system; and

issuing a command to the logical block device to release the free blocks allocated to the file from the logical block device.

2. The method of claim 1, further comprising:

maintaining a data structure to track blocks for which the command to release has been issued; and

updating the data structure to include the free blocks allocated to the file.

3. The method of claim 1, wherein the command is issued to a thinly provisioned disk.

4. The method of claim 3, wherein the thinly provisioned disk is a thinly provisioned virtual disk of a virtual machine, and the file is a file of the virtual machine.

5. The method of claim 1, wherein the command comprises a SCSI UNMAP command.

6. The method of claim 1, wherein the step of identifying the set of free blocks comprises:

determining a number of free blocks in a file system of the logical block device;

determining an UNMAP latency;

wherein the set of free blocks is determined based on the number of free blocks and the UNMAP latency.

7. The method of claim 1, wherein the step of updating the set of free blocks comprises:

identifying blocks to be released by a previously issued SCSI UNMAP command as the free blocks that have already been released from the logical block device.

8. A non-transitory computer readable storage medium comprising instructions executable in a computer system to cause the computer system to carry out a method of releasing free blocks of a logical block device back to an underlying disk-based storage system supporting the logical block device, comprising:

identifying a set of the free blocks in a file system of the logical block device that are candidates to be released;

updating the set of free blocks to remove those free blocks that have already been released from the file system of the logical block device;

allocating the free blocks in the updated set to a file stored on the disk-based storage system; and

issuing a command to the logical block device to release the free blocks allocated to the file from the logical block device.

9. The non-transitory computer readable storage medium of claim 8, wherein the method further comprises:

maintaining a data structure to track blocks for which the command to release has been issued; and

updating the data structure to include the free blocks allocated to the file.

10. The non-transitory computer readable storage medium of claim 8, wherein the command is issued to a thinly provisioned disk.

11. The non-transitory computer readable storage medium of claim 10, wherein the thinly provisioned disk is a thinly provisioned virtual disk of a virtual machine, and the file is a file of the virtual machine.

12. The non-transitory computer readable storage medium of claim 8, wherein the command comprises a SCSI UNMAP command.

13. The non-transitory computer readable storage medium of claim 8, wherein the step of identifying the set of free blocks comprises:

determining a number of free blocks in the file system of the logical block device;

determining an UNMAP latency;

wherein the set of free blocks is determined based on the number of free blocks and the UNMAP latency.

14. The non-transitory computer readable storage medium of claim 8, wherein the step of updating the set of free blocks comprises:

identifying blocks to be released by a previously issued SCSI UNMAP command as the free blocks that have already been released from the logical block device.

15. A system, comprising:

a disk-based storage system supporting a logical block device; and

a hardware platform configured to execute a virtualization layer to release free blocks of the logical block device back to the disk-based storage system supporting the logical block device by;

identifying a set of the free blocks in a file system of the logical block device that are candidates to be released;

updating the set of free blocks to remove those free blocks that have already been released from the file system of the logical block device;

allocating the free blocks in the updated set to a file stored on the disk-based storage system; and

issuing a command to the logical block device to release the free blocks allocated to the file from the logical block device.

16. The system of claim 15, wherein the hardware platform is further configured to execute the virtualization layer to:

maintain a data structure to track blocks for which the command to release has been issued; and

update the data structure to include the free blocks allocated to the file.

17. The system of claim 15, wherein the command is issued to a thinly provisioned disk.

18. The system of claim 17, wherein the thinly provisioned disk is a thinly provisioned virtual disk of a virtual machine, and the file is a file of the virtual machine.

19. The system of claim 15, wherein the hardware platform is further configured to execute the virtualization layer to:

determine a number of free blocks in the file system of the logical block device;

determine an UNMAP latency;

wherein the set of free blocks is determined based on the number of free blocks and the UNMAP latency.

20. The system of claim 15, wherein the hardware platform is further configured to execute the virtualization layer to:

identify blocks to be released by a previously issued SCSI UNMAP command as the free blocks that have already been released from the logical block device.