VMFS-5 Enhancements
The following is a complete list of enhancements made in VMFS-5.
New Unified 1MB File Block Size
Earlier versions of VMFS used 1, 2, 4 or 8MB file blocks. These larger blocks were needed to create large files (>256GB). These different file blocks sizes are no longer needed to create large files on VMFS-5. Very large files can now be created on VMFS-5 using the new unified 1MB file blocks. Earlier versions of VMFS will still have to use larger file blocks to create large files.
Large Single Extent Volumes
In earlier versions of VMFS, the largest single extent was 2TB - 512 bytes. An extent is a partition on which one can place a VMFS. To create a 64TB VMFS-5, one needed to create 32 x 2TB extents /partitions and join them together. With VMFS-5, this limit for a single extent/partition has been increased to 64TB. This significantly reduces the management overhead when using very large VMFS volumes.
Smaller Sub-Blocks
VMFS-5 introduces smaller sub-blocks. Sub-blocks are now 8KB rather than 64KB as used in the earlier versions. With VMFS-5, small files (< 8KB, but > 1KB) in size will consume only 8KB rather than 64KB. This will reduce the amount of disk space stranded by small files. Also, there are many more sub-blocks in VMFS-5 than there were in VMFS-3 (32,000 on VMFS-5 compared to approximately 4,000 on VMFS-3).
Small File Support
VMFS-5 introduces support for very small files. For files less than or equal to 1KB, VMFS-5 uses the file descriptor location in the metadata for storage rather than file blocks. When these files grow beyond 1KB, they will then start to use the new 8KB sub-blocks. This will again reduce the amount of disk space stranded by very small files.
Increased File Count
VMFS-5 introduces support for greater than 120,000 files, a four-fold increase when compared to the number of files supported on VMFS-3, which was approximately 30,000.
ATS Enhancement
The Atomic Test & Set (ATS) Hardware Acceleration primitive is now used throughout VMFS-5 for file locking. ATS is a part of VAAI (vSphere Storage APIs for Array Integration). This enhancement improves the file locking performance over earlier versions of VMFS.
GPT
To handle much larger partition sizes, the GUID Partition Table (GPT) format will now be used to create VMFS-5 volumes. Historically, Master Boot Record (MBR) was used; however, this was limited to a maximum partition size of approximately 2TB. GPT overcomes this limitation and allows for much larger partitions to handle single extents up to 64TB (using VMFS-5).
New Starting Sector
VMFS-5 partitions will now have a starting sector of 2048. This is different from VMFS-3 which had a starting sector of 128. Moving to a starting sector of 2048 helps avoid alignment issues.
For more details you can see the link below:-
http://www.vmware.com/files/pdf/techpaper/VMFS-5_Upgrade_Considerations.pdf
The following is a complete list of enhancements made in VMFS-5.
New Unified 1MB File Block Size
Earlier versions of VMFS used 1, 2, 4 or 8MB file blocks. These larger blocks were needed to create large files (>256GB). These different file blocks sizes are no longer needed to create large files on VMFS-5. Very large files can now be created on VMFS-5 using the new unified 1MB file blocks. Earlier versions of VMFS will still have to use larger file blocks to create large files.
Large Single Extent Volumes
In earlier versions of VMFS, the largest single extent was 2TB - 512 bytes. An extent is a partition on which one can place a VMFS. To create a 64TB VMFS-5, one needed to create 32 x 2TB extents /partitions and join them together. With VMFS-5, this limit for a single extent/partition has been increased to 64TB. This significantly reduces the management overhead when using very large VMFS volumes.
Smaller Sub-Blocks
VMFS-5 introduces smaller sub-blocks. Sub-blocks are now 8KB rather than 64KB as used in the earlier versions. With VMFS-5, small files (< 8KB, but > 1KB) in size will consume only 8KB rather than 64KB. This will reduce the amount of disk space stranded by small files. Also, there are many more sub-blocks in VMFS-5 than there were in VMFS-3 (32,000 on VMFS-5 compared to approximately 4,000 on VMFS-3).
Small File Support
VMFS-5 introduces support for very small files. For files less than or equal to 1KB, VMFS-5 uses the file descriptor location in the metadata for storage rather than file blocks. When these files grow beyond 1KB, they will then start to use the new 8KB sub-blocks. This will again reduce the amount of disk space stranded by very small files.
Increased File Count
VMFS-5 introduces support for greater than 120,000 files, a four-fold increase when compared to the number of files supported on VMFS-3, which was approximately 30,000.
ATS Enhancement
The Atomic Test & Set (ATS) Hardware Acceleration primitive is now used throughout VMFS-5 for file locking. ATS is a part of VAAI (vSphere Storage APIs for Array Integration). This enhancement improves the file locking performance over earlier versions of VMFS.
GPT
To handle much larger partition sizes, the GUID Partition Table (GPT) format will now be used to create VMFS-5 volumes. Historically, Master Boot Record (MBR) was used; however, this was limited to a maximum partition size of approximately 2TB. GPT overcomes this limitation and allows for much larger partitions to handle single extents up to 64TB (using VMFS-5).
New Starting Sector
VMFS-5 partitions will now have a starting sector of 2048. This is different from VMFS-3 which had a starting sector of 128. Moving to a starting sector of 2048 helps avoid alignment issues.
For more details you can see the link below:-
http://www.vmware.com/files/pdf/techpaper/VMFS-5_Upgrade_Considerations.pdf
No comments:
Post a Comment