Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On Mon, Feb 09, 2009 at 07:18:46PM +0100, Matteo Tescione wrote: > It's a long time since i've been using the no-disk-barrier, no-disk-flushes > and no drain to optimize the performance of our datastores (3ware 9650 w/ > BBU cache) but it has no apparent correlations btw the 2 mentioned drbd > version (8.2.7 vs 8.3.0) > > We are using Centos5.2 x86_64 with a custom kernel and the read performance > lost (about 20%) is only seen running 8.3.0 (same config&setup) works for me. and, if its READ you have that problem on, maybe you need to adjust your read ahead settings. drbd does nothing funny on reads but just keeps a stub of housekeeping information to be able to retry in case of read error, then passes it on to the lower level device. there is nothing I can see right now that would impact performance. > If you don't believe me I can produce logs and iostats during some IO test. I doubt that the "iostats" statistics would help here in any way. but I may be wrong. so yes, go ahead. > In the btw, iostats accounting for drbd devices is still crazy, even > reverting back to 8.2.7 can you be more specific? -- : Lars Ellenberg : LINBIT | Your Way to High Availability : DRBD/HA support and consulting http://www.linbit.com DRBD® and LINBIT® are registered trademarks of LINBIT, Austria. __ please don't Cc me, but send to list -- I'm subscribed