In <[🔎] 201105011040.19169.bss@iguanasuicide.net>, Boyd Stephen Smith Jr. wrote: >In <[🔎] 4DBD0D23.1080903@hardwarefreak.com>, Stan Hoeppner wrote: >>http://btrfs.boxacle.net/repository/raid/2.6.35-rc5/2.6.35-rc5/2.6.35-rc5_L >>a rge_file_creates_num_threads=1.html >>http://btrfs.boxacle.net/repository/raid/2.6.35-rc5/2.6.35-rc5/2.6.35-rc5_L >>a rge_file_creates_num_threads=16.html >>http://btrfs.boxacle.net/repository/raid/2.6.35-rc5/2.6.35-rc5/2.6.35-rc5_L >>a rge_file_creates_num_threads=128.html This is clearly where XFS shines. I've used OpenSTV, and treated each graph as a preferential vote. That's a total of 12 "votes", and the aggregate ranking, based on Condorocet-SSD is: 1. ext4-nobarrier 1. xfs 1. xfs-nobarrier (3-way tie for 1st) 4. ext4 4. jfs (tie for next) 6. btrfs-nocow 7. ext3-barrier 8. ext3 9. btrfs (So, XFS, JFS, and Ext4 are all strong competitors, and I think XFS is likely the most well-tested on those.) This is only one way to aggregate the data on the graphs, and it is certainly flawed, but it can be reasonably be used for ranking the file systems. I think I'll extend this technique across all the benchmark graphs in that area and report back on that. -- Boyd Stephen Smith Jr. ,= ,-_-. =. bss@iguanasuicide.net ((_/)o o(\_)) ICQ: 514984 YM/AIM: DaTwinkDaddy `-'(. .)`-' http://iguanasuicide.net/ \_/
Attachment:
signature.asc
Description: This is a digitally signed message part.