[Ocfs2-devel] Ocfs2 performance
Daniel Phillips
phillips at google.com
Fri Mar 10 15:13:03 CST 2006
Going back to that mysterious idle time fluctuation problem, I just noticed
something interesting here:
> With hashvec, (64K buckets)
>
> real user sys
> 29.62 23.87 3.02
> 28.80 24.16 3.07
> 50.95 24.11 3.04
> 28.17 23.95 3.20
> 61.21 23.89 3.16
> 28.61 23.88 3.30
>
> With vmalloc (64K buckets)
>
> real user sys
> 29.67 23.98 2.88
> 28.35 23.96 3.13
> 52.29 24.16 2.89
> 28.39 24.07 2.97
> 65.13 24.08 3.01
> 28.08 24.02 3.16
Look, the real time artifacts show up in the same places in the two
different runs. There was a reboot before each run. There is a sync
before and after each trial. Each trial was initiated by hand, so this
isn't about something else going on in the machine at the same time.
Got to be a clue in there somewhere.
Regards,
Daniel
More information about the Ocfs2-devel
mailing list