Date: Wed, 18 Jan 2006 12:40:01 -0500 From: John Baldwin <jhb@freebsd.org> To: freebsd-amd64@freebsd.org Cc: amd64@freebsd.org, Josef Pojsl <jp@tns.cz> Subject: Re: 5.4/amd64 not stable Message-ID: <200601181240.03366.jhb@freebsd.org> In-Reply-To: <20060118071323.GB795@bertik.tns.cz> References: <20060118071323.GB795@bertik.tns.cz>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wednesday 18 January 2006 02:13, Josef Pojsl wrote: > Hello list, > > I am observing panics of FreeBSD 5.4/amd64 > on a web server. We tested it heavily with > Apache bench. Load was over 250, without problems. > However, when we put the server in production, > it crashes time after time. It takes some time > between 1 and 8 hours. The panics look like this: > > Fatal trap 12: page fault while in kernel mode > cpuid = 0; apic id = 00 > fault virtual address = 0x48 > fault code = supervisor read, page not present > instruction pointer = 0x8:0xffffffff80271a83 > stack pointer = 0x10:0xffffffffc1043990 > frame pointer = 0x10:0x0 > code segment = base 0x0, limit 0xfffff, type 0x1b > = DPL 0, pres 1, long 1, def32 0, gran 1 > processor eflags = resume, IOPL = 0 > current process = 10567 (httpd) > trap number = 12 > panic: page fault > cpuid = 0 > boot() called on cpu#0 > > The instruction pointer is always the same, and process is always httpd. > Does it mean anything? It can. :) Can you compile DDB into your kernel to get a stack trace when it panics? Also, if you have a kernel.debug, you can run gdb on it and do a list of the instruction pointer to get the corresponding file:line. i.e.: # gdb kernel.debug gdb> l *0xffffffff80271a83 -- John Baldwin <jhb@FreeBSD.org> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve" = http://www.FreeBSD.org
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200601181240.03366.jhb>