Date: Mon, 23 Jun 2014 09:27:46 -0600 From: Ian Lepore <ian@FreeBSD.org> To: "O. Hartmann" <ohartman@zedat.fu-berlin.de> Cc: Adrian Chadd <adrian@FreeBSD.org>, FreeBSD CURRENT <freebsd-current@FreeBSD.org> Subject: Re: [CURRENT]: weird memory/linker problem? Message-ID: <1403537266.20883.296.camel@revolution.hippie.lan> In-Reply-To: <20140623163115.03bdd675.ohartman@zedat.fu-berlin.de> References: <20140622165639.17a1ba1e.ohartman@zedat.fu-berlin.de> <CAJ-Vmok0Oh6XGe62acXE-82pTmEaouibd1GqDT0pCo8P6x6Hog@mail.gmail.com> <20140623163115.03bdd675.ohartman@zedat.fu-berlin.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 2014-06-23 at 16:31 +0200, O. Hartmann wrote:
>
> I'm out of ideas. Is there a way to stress test the CPU and memory
> system to check
> whether RAM, the CPU itself and, as an additional possibility, the
> disk i/o controller
> (Intel ICH10)?
>
> Thanks for your patience,
A really good tool for stress-testing a system is ports/math/mprime. It
will find memory and cpu errors that memtest86 and other tools
completely overlook. Run one copy per cpu, something like this:
for i in $(jot $(sysctl -n hw.ncpu) 0) ; do
sleep $((i * 2)) && mprime -t -a$i >/tmp/mprime$i.log &
done
Many overclockers use this to ensure the system is stable with the OC
settings. If your system can run a copy of mprime per cpu continuously
for 24 hours the hardware is fine.
-- Ian
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1403537266.20883.296.camel>