[Csync2] linux kernel cpu optimization
Ask Bjørn Hansen
ask at develooper.com
Thu Sep 11 21:48:32 CEST 2008
On Sep 11, 2008, at 6:03, Vincent Régnard wrote:
> I forced all disk interrupt on CPU1 using the /proc/irq/IRQ/
> smp_affinity trick, but I observe that CPU1 remains in waiting state
> too much as shown by the top above (about 50% on average) when csync
> is checking the whole file system tree.
If only a few files are changing, why are you checking the full tree?
Basically doing stat on a million files is going to incur a bunch of
disk i/o (and thus iowait state).
- ask
--
http://develooper.com/ - http://askask.com/
More information about the Csync2
mailing list