Date: Tue, 21 Aug 2001 15:54:15 -0700 (PDT) From: Matt Dillon <dillon@earth.backplane.com> To: Dag-Erling Smorgrav <des@ofug.org> Cc: Alfred Perlstein <bright@mu.org>, John Baldwin <jhb@FreeBSD.ORG>, cvs-committers@FreeBSD.ORG, cvs-all@FreeBSD.ORG Subject: Re: cvs commit: src/sys/kern kern_condvar.c kern_synch.c src/sys/sys proc.h Message-ID: <200108212254.f7LMsFQ68740@earth.backplane.com> References: <200108211842.f7LIgkp03186@freefall.freebsd.org> <20010821134601.J81307@elvis.mu.org> <xzppu9p1b29.fsf@flood.ping.uio.no> <xzpy9od11uv.fsf@flood.ping.uio.no> <xzpu1z111mi.fsf@flood.ping.uio.no>
next in thread | previous in thread | raw e-mail | index | archive | help
:Dag-Erling Smorgrav <des@ofug.org> writes:
:> Interesting Fact Of The Day: I just noticed that the syncer process is
:> eating up heaps of CPU
:
:8% averaged over the machine's uptime, in fact:
:
:root@des /sys/kern# uptime
:12:31AM up 5 days, 10:27, 7 users, load averages: 1.94, 1.57, 1.69
:root@des /sys/kern# ps -axlp 5
: UID PID PPID CPU PRI NI VSZ RSS WCHAN STAT TT TIME COMMAND
: 0 5 0 142 20 0 0 0 syncer DL ?? 629:49.14 (syncer)
:
:DES
:--
:Dag-Erling Smorgrav - des@ofug.org
vm_mtx could not be responsible for a constant 8% cpu utilization by
the syncer on an idle machine. Something is seriously whacked.
I might be able to diagnose it with root access (and a kernel.debug) to
the machine in question, or if you have a way of reproducing it I can
try to reproduce it on one of my boxes.
The syncer is not typically fragile. The only thing I can think of
that could cause something like this to happen is if 'rushjob'
(aka speedup_syncer()) is being called continuously.
-Matt
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200108212254.f7LMsFQ68740>