On Tue, 2009-10-06 at 11:53 -0700, Simon Kirby wrote: > Hello, > > I was just testing out blktrace/blkparse/btrace on a box that is hitting > some performance walls, and noticed that there are a fair amonut of "UT" > events (unplug by timer). Is this normal/expected? For example: > > [sroot@nas04:/root]# btrace /dev/etherd/e7.0 | grep T > 152,32 4 1379 3.582513494 0 UT N [swapper] 8 > 152,32 1 1289 4.329760067 0 UT N [swapper] 1 > 152,32 3 1132 4.362257911 0 UT N [swapper] 3 > 152,32 7 1070 4.375258374 0 UT N [swapper] 1 > 152,32 3 1146 4.382260172 0 UT N [swapper] 5 > 152,32 1 1318 4.417759727 2830 UT N [nfsd] 3 > 152,32 5 1003 4.498757105 0 UT N [swapper] 1 > 152,32 1 1368 4.517761127 0 UT N [swapper] 1 > 152,32 0 1133 4.585522116 0 UT N [swapper] 5 > > This is on 2.6.30.5 with the 2.6.30.6 XFS patches. > > Cheers, > > Simon- Hello Simon- This looks pretty bad - could you tell me what distro you are running on as a base? And did this happen before 2.6.30.5 (the poor performance)? And could you provide a more complete snippet of blktrace output (showing a handful of complete ops)? Thanks, Alan D. Brunelle Hewlett-Packard -- To unsubscribe from this list: send the line "unsubscribe linux-btrace" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
