Date: Mon, 18 Nov 2002 22:09:04 -0700 From: <soralx@cydem.zp.ua> To: freebsd-hackers@FreeBSD.ORG Subject: Re: Memory corruption in -STABLE on P4/2GHz Message-ID: <200211182209.04459.soralx@cydem.zp.ua> In-Reply-To: <20021117211654.GE6115@vega.vega.com> References: <20021117211654.GE6115@vega.vega.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> SoboMax > I'm observing very strange memory corruption problems with 2GHz P4 > system running 4.7 (security branch as of today). Under the load > (make -j20 buildworld) the compiler or make(1) often die with signal > 11. I found in mailing lists that there is similarly looking problem > with -current, any chances that -stable is affected as well? What CPU core you have? I tested my system several times and found no problems: FreeBSD 4.6.2-RELEASE NO 'options DISABLE_PSE' CPU: Intel P4 2.0A Ghz, NW core, overclocked to 2.5Ghz MBoard: Gigabyte GA-8IHXP, i850E chipset RAM: 512Mb RDRAM 800Mhz Run /usr/ports/sysutils/cpuburn, `burnP6` for a night. If it doesn't coredump, run memtest86 for another night. This is how I tested my overclocked system. With FSB frequency more than 125Mhz (+25Mhz), `burnP6` dies with sig?? after some time, and 'memtest86' reports errors. The same result is when I increase the frequency and don't increase Vcc (CPU core voltage). Seems like the CPU doesn't get enough power (check the 12V 4-pin power connector and the power supply) or the memory is no-brand/overclocked. >Robert Withrow <witr@rwwa.com> >I had similar problems. Terry Lambert reports that there is a bug >in the P4. not likely. why? 18.11.2002; 21:42:59 [SorAlx] http://cydem.zp.ua/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200211182209.04459.soralx>