ext4 is faster with LVM than without, and other filesystem benchmarks
in [Kernel]
|
From: Bernd Eckenfels on 7 May 2010 12:20 In article <20100507142310.GF13143(a)lh.kyla.fi> you wrote: > I think the most surprising result of the benchmarks is that ext4 > seems to be significantly faster under LVM than on the raw /dev/sdd1 > partition. Without LVM the variance in run times is much larger. Sounds like the syncs/barriers never reach the disk with LVM. What mount journal/sync options did you use? default? Is dmesg telling you that barriers have been turned off for the lvm case? IF yo uwant it fast and dirty try nobarrier,data=writeback :) Greetings Bernd -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Eric Sandeen on 7 May 2010 13:50 Bernd Eckenfels wrote: > In article <20100507142310.GF13143(a)lh.kyla.fi> you wrote: >> I think the most surprising result of the benchmarks is that ext4 >> seems to be significantly faster under LVM than on the raw /dev/sdd1 >> partition. Without LVM the variance in run times is much larger. > > Sounds like the syncs/barriers never reach the disk with LVM. What mount > journal/sync options did you use? default? Is dmesg telling you that > barriers have been turned off for the lvm case? IF yo uwant it fast and > dirty try nobarrier,data=writeback :) LVM barriers should be working in that kernel, though... still, comparing mount -o nobarrier on each might yield a clue there. -Eric -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
|
Pages: 1 Prev: Device driver for DA9052 PMIC IC Next: ext2/ext3:useless code for return value |