Re: SCHED_ULE should not be the default

On Sun, Dec 18, 2011 at 05:51:47PM +1100, Ian Smith wrote: > On Sun, 18 Dec 2011 02:37:52 +, Bruce Cran wrote: > > On 13/12/2011 09:00, Andrey Chernov wrote: > > > I observe ULE interactivity slowness even on single core machine (Pentium > > > 4) in very visible places, like 'ps ax' output s

Re: SCHED_ULE should not be the default

On Sun, 18 Dec 2011 02:37:52 +, Bruce Cran wrote: > On 13/12/2011 09:00, Andrey Chernov wrote: > > I observe ULE interactivity slowness even on single core machine (Pentium > > 4) in very visible places, like 'ps ax' output stucks in the middle by ~1 > > second. When I switch back to SHED_4

Re: fsck_ufs out of swapspace

On Dec 17, 2011, at 3:36 PM, Michiel Boland wrote: > FreeBSD 9.0-PRERELEASE locked up while into some heavy I/O and failed to shut > down properly, so I had to power-cycle. After it came back up it said > > Starting file system checks: > ** SU+J Recovering /dev/ada0a > ** Reading 33554432 byte j

Re: SCHED_ULE should not be the default

On 17 December 2011 14:00, Andriy Gapon wrote: > on 17/12/2011 23:20 Adrian Chadd said the following: >> This may -not- be a userland specific problem.. > That's an interesting idea.  From the recent discussion about USB I can > conclude > that USB threads run at higher priority than GEOM thread

Re: SCHED_ULE should not be the default

On 13/12/2011 09:00, Andrey Chernov wrote: I observe ULE interactivity slowness even on single core machine (Pentium 4) in very visible places, like 'ps ax' output stucks in the middle by ~1 second. When I switch back to SHED_4BSD, all slowness is gone. I'm also seeing problems with ULE on a

Re: SCHED_ULE should not be the default

on 17/12/2011 23:20 Adrian Chadd said the following: > Erm, just as a random question - since device drivers (and GEOM) run > as separate threads, has anyone looked into what kind of effects the > scheduler has on these? > > I definitely have measurable throughput/responsiveness differences > betw

Re: SCHED_ULE should not be the default

Erm, just as a random question - since device drivers (and GEOM) run as separate threads, has anyone looked into what kind of effects the scheduler has on these? I definitely have measurable throughput/responsiveness differences between ULE and 4BSD (and preempt/non-preempt on 4BSD) on my MIPS boa

Re: SCHED_ULE should not be the default

on 17/12/2011 19:33 George Mitchell said the following: > Summing up for the record, in my original test: > 1. It doesn't matter whether X is running or not. > 2. The problem is not limited to two or fewer CPUs. (It also happens >for me on a six-CPU system.) > 3. It doesn't require nCPU + 1 co

fsck_ufs out of swapspace

FreeBSD 9.0-PRERELEASE locked up while into some heavy I/O and failed to shut down properly, so I had to power-cycle. After it came back up it said Starting file system checks: ** SU+J Recovering /dev/ada0a ** Reading 33554432 byte journal from inode 4. swap_pager: out of swap space swap_pager_g

Re: 8.2->9.prerel: gmirror failed with error 19

>> FreeBSD 9.0-PRERELEASE #18: Tue Dec 13 12:20:57 GMT 2011 >> r...@work0.psg.com:/usr/obj/usr/src/sys/WORK0 amd64 > Could you also show your kernel config? cpu HAMMER ident WORK0 makeoptions DEBUG=-g# Build kernel with gdb(1) debug symbols options

Re: SCHED_ULE should not be the default

On 12/14/11 21:05, Oliver Pinter wrote: [...] Hi! Can you try with this settings: op@opn ~> sysctl kern.sched. kern.sched.cpusetsize: 8 kern.sched.preemption: 0 kern.sched.name: ULE kern.sched.slice: 13 kern.sched.interact: 30 kern.sched.preempt_thresh: 224 kern.sched.static_boost: 152 kern.sc

Re: 8.2->9.prerel: gmirror failed with error 19

On 17.12.2011 19:30, Randy Bush wrote: > FreeBSD 9.0-PRERELEASE #18: Tue Dec 13 12:20:57 GMT 2011 > r...@work0.psg.com:/usr/obj/usr/src/sys/WORK0 amd64 Could you also show your kernel config? > pass0 at ata0 bus 0 scbus0 target 1 lun 0 > pass0: Removable CD-ROM SCSI-0 device > pass0: 33.300

Re: swi4: clock taking 40% cpu?!?

Should also mention the kern.sched may be playing a part in this too. On Sat, Dec 17, 2011 at 11:20:29AM -0500, Jason Hellenthal wrote: > > > On Thu, Dec 15, 2011 at 12:51:28PM -0800, Doug Barton wrote: > > Howdy, > > > > Web server under heavy'ish load (7 on a 2 cpu system) running > > 8.2-RE

Re: swi4: clock taking 40% cpu?!?

On Thu, Dec 15, 2011 at 12:51:28PM -0800, Doug Barton wrote: > Howdy, > > Web server under heavy'ish load (7 on a 2 cpu system) running > 8.2-RELEASE-p4 i386 I'm seeing this: > > PID USERNAME PRI NICE SIZERES STATE C TIME WCPU COMMAND > 12 root -32- 0K 112K WAIT0

Re: 8.2->9.prerel: gmirror failed with error 19

>> neither 9 nor 8 would boot without ending up here >> the only way out was via loader >> >> OK unload >> OK load boot/kernel.old/kernel >> OK load boot/kernel.old/geom_mirror.ko >> OK set kern.geom.part.check_integrity=0 >> OK set vfs.root.mountfrom.options=rw >> OK boot

Re: 8.2->9.prerel: gmirror failed with error 19

On 17.12.2011 14:57, Randy Bush wrote: > neither 9 nor 8 would boot without ending up here > the only way out was via loader > > OK unload > OK load boot/kernel.old/kernel > OK load boot/kernel.old/geom_mirror.ko > OK set kern.geom.part.check_integrity=0 > OK set vfs.root.mount

Re: Spinlock panic in FreeBSD 7

on 17/12/2011 00:38 Charlie Martin said the following: > (This was originally posted to freebsd-hackers, I'm reposting following email > suggestions.) > > We've observed a panic in FreeBSD 7 (7.2-PRERELEASE FreeBSD) several times > that > we've not been able to track down. Upgrading is not an op

8.2->9.prerel: gmirror failed with error 19

8.2 system fully updated as of 2011.12.14 it can reboot quite happily csup to RELENG_9 make buildworld make kernel boot single root mount waiting for: usbus4 uhub4: 8 ports with 8 removable, self powered Trying to mount root from ufs:/dev/mirror/boota [rw]... mountroot: waiting fo