Sign in with
Sign up | Sign in

Benchmark Results: Iometer Workload Tests

Does Your SSD's File System Affect Performance?
By , Achim Roos

The database test is a completely random set of operations, of which 67% are reads. It works with 8 KB block sizes, on which NTFS can capitalize on the non-compressed Samsung architecture, while the SandForce-based drive performs similarly on NTFS and eFAT. FAT32 is barely worth noting here.

The Web server workload does not execute writes, so it delivers similar performance across all the file systems.

The workstation workload patterns split read and write operations 80/20% respectively, with random and sequential operations also split 80/20%. It involves block sizes of 64, 128, and 256 KB, which is why FAT32 shows performance limits again, since it does not support blocks that large.

Display all 5 comments.
This thread is closed for comments
  • 0 Hide
    jamesedgeuk2000 , 13 April 2012 15:56
    Could you not have benchmarked HPS too by doing the tests with a Mac setup to duel boot OSX and Windows 7? (thus letting the 7 install see the HPS file system)
  • 0 Hide
    djamorpheus , 14 April 2012 05:42
    What about linux filesystems?
  • 0 Hide
    audiovoodoo , 16 April 2012 08:09
    No mention of cluster size impact on performance?
  • 0 Hide
    audiovoodoo , 14 May 2012 18:04
    What are you talking about?
  • 0 Hide
    Anonymous , 16 August 2012 00:02
    Question is does the FAT32 partition was aligned? Data on FAT32 starts straight after two FAT tables (their size depends on amount of clusters). So even if volume for FAT32 partition is aligned after creating such partition the FAT32 clusters may not be aligned to SSD physical sectors.

    http://www.msfn.org/board/topic/151798-does-fat32-align-its-clusters/