Tom Sightler wrote:
write read ----- ---- ext2 81 180 ext3 34 222 XFS 109 213
This suggests to me you have a problem with the journal. Placing the journal on its own disk seems good to me.
I have a couple of questions, is access time important to you? If not, have you tried mounting with noatime? Also, have you tried increasing the size of the journal and the stride options (previous suggestion)? My guess is that your having journal contention and having an external journal might help. Another option, you could attempt to tweak the commit rate with the commit= mount option. The default is 5 seconds which seems too often for some disk arrays.
I'm completely unfamiliar with RAID devices and such, but it seems to me that the important point is the time before some Major Disaster (eg hardware failure the wrong side of the UPS) and the time it actually bites (eg the lights go out). That might be quite a long period (from the computer's perspective), and I'd not suggesting that whatever time that is it's the upper limit, not a good interval. Additionally, there may be some "lumpiness" in performance with longer intervals.
60 seconds seems to me a long interval, and if performance is still terrible I might test with longer intervals, but I'd not want to use them (or 60 seconds without some reassurance from someone who knows).
-- Cheers John -- spambait 1aaaaaaa computerdatasafe com au Z1aaaaaaa computerdatasafe com au Tourist pics http://portgeographe.environmentaldisasters.cds.merseine.nu/ do not reply off-list