Comments like that really don't help. Moreover, this is a kernel issue that is affecting all distributions across the board; I recently came to Ubuntu from Fedora where it was just as bad.
However, things are looking pretty good for getting this fixed by 2.6.31, which as it stands will be in Karmic. Last month there was a set of patches[1] posted to the LKML reworking the page eviction code to give executable code priority over streaming pages, which should help the thrashing situation quite a bit.
Secondly, there is the Jens Axboe's per-bdi flusher threads which seem to be kicking some serious ass in initial testing[2].
Lastly, there was very recently a breakthrough on the kernel.org incarnation of this bug where Thomas Pilarski's tireless efforts in bisecting the issue finally resulted in some measurably regressing commits. Jens has already looked at the commits in question and it looks very promising that we'll see at least some improvement come of this.
All in all, don't fret, things are looking up. It's certainly a frustrating bug for users and developers alike, but I think the efforts of the community may about to pay off.
@cornbread
Comments like that really don't help. Moreover, this is a kernel issue that is affecting all distributions across the board; I recently came to Ubuntu from Fedora where it was just as bad.
However, things are looking pretty good for getting this fixed by 2.6.31, which as it stands will be in Karmic. Last month there was a set of patches[1] posted to the LKML reworking the page eviction code to give executable code priority over streaming pages, which should help the thrashing situation quite a bit.
Secondly, there is the Jens Axboe's per-bdi flusher threads which seem to be kicking some serious ass in initial testing[2].
Lastly, there was very recently a breakthrough on the kernel.org incarnation of this bug where Thomas Pilarski's tireless efforts in bisecting the issue finally resulted in some measurably regressing commits. Jens has already looked at the commits in question and it looks very promising that we'll see at least some improvement come of this.
All in all, don't fret, things are looking up. It's certainly a frustrating bug for users and developers alike, but I think the efforts of the community may about to pay off.
- Ben
[1] http:// thread. gmane.org/ gmane.linux. kernel. mm/33818 lkml.org/ lkml/2009/ 5/28/164 bugzilla. kernel. org/show_ bug.cgi? id=12309# c360
[2] http://
[3] http://