Date: Wed, 04 Aug 2004 16:19:20 -0500 From: Jon Noack <noackjr@alumni.rice.edu> To: Jeremy Chadwick <freebsd@jdc.parodius.com> Cc: current@freebsd.org Subject: Re: Postgresql locks up server - no response at all Message-ID: <411152D8.2050305@alumni.rice.edu> In-Reply-To: <20040804203456.GA46377@parodius.com> References: <1091649533.29481.42.camel@lanshark.dmv.com> <20040804203456.GA46377@parodius.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 08/04/04 15:34, Jeremy Chadwick wrote: > I've seen this with our SuperMicro SuperServer 5013C-T, running mysqld. > Please note that the server is "heavily loaded" (note the quotes); usually > a load of around 0.50 to 1.00 at all times, with mysqld being the top > process. Server runs all latest -CURRENT builds. > > Many people over in freebsd-threads mentioned this problem, and recommended > all sorts-of different workarounds. I tried every one available to me, > except mucking with PREEMPTION (as I did not feel comfortable tinkering > with a random .h file on the box; seemed to be a kernel-related thing, > so I'd rather have just an "options" line for it -- I'm conditionally > lazy). The one you didn't try most likely was the culprit. Robert Watson showed that PREEMPTION and threading don't play well together right now: http://lists.freebsd.org/pipermail/freebsd-current/2004-July/031211.html The thought is that PREEMPTION uncovers scheduler bugs, but nobody's figured it out at the moment. > Wed Aug 4 13:28:35 PDT 2004 > * -CURRENT box is still alive and well. PREEMPTION was turned off on August 1st, so if you've updated since then things should have stabilized a bit: http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/i386/include/param.h#rev1.72 Jon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?411152D8.2050305>