Re: ?Understanding metadata efficiency of btrfs

2012-03-06 Thread Hugo Mills
On Tue, Mar 06, 2012 at 05:30:23AM +, Duncan wrote: Kai Ren posted on Mon, 05 Mar 2012 21:16:34 -0500 as excerpted: I've run a little wired benchmark on comparing Btrfs v0.19 and XFS: [snip description of test] I monitor the number of disk read requests #WriteRq

Re: ?Understanding metadata efficiency of btrfs

2012-03-06 Thread Duncan
Hugo Mills posted on Tue, 06 Mar 2012 11:29:58 + as excerpted: The in-memory buffer is simply the standard Linux block layer and FS cache: When a piece of metadata is searched for, btrfs walks down the relevant tree, loading each tree node (a 4k page) in turn, until it finds the metadata.

Understanding metadata efficiency of btrfs

2012-03-05 Thread Kai Ren
I've run a little wired benchmark on comparing Btrfs v0.19 and XFS: There are 2000 directories and each directory contains 1000 files. The workload randomly stat a file or chmod a file for 200 times. And the number of stat and chmod are 50% and 50%. I monitor the number of disk read requests

Re: Understanding metadata efficiency of btrfs

2012-03-05 Thread Duncan
Kai Ren posted on Mon, 05 Mar 2012 21:16:34 -0500 as excerpted: I've run a little wired benchmark on comparing Btrfs v0.19 and XFS: [snip description of test] I monitor the number of disk read requests #WriteRq #ReadRq #WriteSect #ReadSect Btrfs 2403520 157118329249216