2.5.21 IDE 91
Quoted 6 lines
Quoted 3 lines
Recently, 2.5.20-dj[34] completed all my tests, whereas
2.5.{19,20,21} haven't. I realize breakage in the development series
is expected and sometimes good. Nonetheless, "two thumbs up" for -dj.That's interesting. What exactly was failing ? It'd be in everyones interests to get those bits pushed to Linus sooner.
tiobench.pl --size 2048 --numruns 3 --threads 128 # 384 MB ram in machine
The ssh session running vmstat no longer updates. Console won't give a new "login" prompt with <Enter>. <sysrq T> prints a trace (which I haven't captured - it's really long with > 128 processes).
Does <sysrq T> need any post processing to convert addresses to something more useful? I'll save it on 2.5.22 if it happens.
Signature · 1 line
Randy Hron
Quoted 8 lines · [email protected] wrote:
Quoted 7 lines
Quoted 4 lines
Recently, 2.5.20-dj[34] completed all my tests, whereas
2.5.{19,20,21} haven't. I realize breakage in the development series
is expected and sometimes good. Nonetheless, "two thumbs up" for -dj.That's interesting. What exactly was failing ? It'd be in everyones interests to get those bits pushed to Linus sooner.
Quoted 8 lines
tiobench.pl --size 2048 --numruns 3 --threads 128 # 384 MB ram in machine
The ssh session running vmstat no longer updates. Console won't give a new "login" prompt with <Enter>. <sysrq T> prints a trace (which I haven't captured - it's really long with > 128 processes).
Does <sysrq T> need any post processing to convert addresses to something more useful? I'll save it on 2.5.22 if it happens.
Well I dunno, Randy. Works fine here, on aic7xxx SCSI and hpt366 IDE.
Quoted 1 line
From your trace it would seem that writeout completion has not
occurred against one or more pages. Could be that the device driver lost an interrupt, or it failed to deliver completion for one or more BIO segments, or something screwed up at the VFS level.
I am (of course ;)) disinclined to believe the latter, mainly because of the amount of testing I do here. Eight-hour Cerberus runs on quad CPU, five IDE disks and six SCSI disks all chugging along, no probs.
Is it reproducible? Are you able to try it on a different machine?
On other disks in the same machine?
-