Date: Mon, 19 Apr 2004 20:38:35 +0400 From: "Artem Koutchine" <matrix@itlegion.ru> To: "Hiroharu Tamaru" <tamaru@myn.rcast.u-tokyo.ac.jp> Cc: freebsd-hardware@freebsd.org Subject: Re: Escalde 7506-4LP PCI parity error on Asustek p2b-ds Message-ID: <014501c4262c$c4535a70$0c00a8c0@artem> References: <sa68z5e8f78.wl@gin.myn.rcast.u-tokyo.ac.jp><001801c425e5$9f3a19a0$0c00a8c0@artem><sa63c70e133.wl@gin.myn.rcast.u-tokyo.ac.jp><003c01c425f7$3a3d6b30$0c00a8c0@artem><sa61xmkdypx.wl@gin.myn.rcast.u-tokyo.ac.jp><00c201c4260c$6acf2580$0c00a8c0@artem> <sa61xmkx70t.wl@amulet.amuletic.net>
next in thread | previous in thread | raw e-mail | index | archive | help
> > > > > > twe0: PCI parity error: Reseat card, move card or buggy device present. > > > > > > (this line is repeated many times). > > > > > This is the original message I wrote back then: > > > > > > > > > > http://docs.freebsd.org/cgi/getmsg.cgi?fetch=0+0+archive/2002/freebsd-hardware/20020623.freebsd-hardware > > > > > > > > > > I couldn't confirm if it were safe to ignore the message or > > > > > not, but I never had any trouble with it for the 1+ year > > > > > that I ran the system. That includes mail alarting and > > > > > rebuilding the array through the 3dmd utility. I use to run > > > > > JBOD, mirroring and RAID5 on that card. > > > > > > > > Thank you for replying. I just installed FreeBSD on > > > > that dual P2B-DS MB with 2 P3 550Mhz CPUs and > > > > run top. What i saw scred me. I saw 50% CPU LOAD on > > > > interupts. Nothing really was running, The system is just > > > > installed and it was my first login (as root). I thinj this > > > > 50% interupts load is somehow related to the error message. > > > > But this is just a guess. Is there any way to be make it sure? > > > > > > I can't remember well, but PRINTING warnings could well had > > > been the reason. Try my patch, and see if suppressing the > > > printf's themselves could save the CPU. If not, well, it > > > could be scheduler related, and you might want to try > > > 4-stable instead. > > > > Did the patch. The message are gone now. However, i still have > > about 50% of cpu power wasted on interupts and i have not idea > > what is going on and how to figure out what is geenrated so many > > interupts and why. Maybe i should first do CVSup to 5-CURRENT > > (i am running 5.2-RC2). > > > > And which BIOS version have you? > I'd try differrent BIOS versions before cvsup'ing, > since BIOS did change the interrupt rates in my case. > > Have a look at the counter and see how fast you are > getting the PE interrupts. > > sysctl hw.twe.twe_pe ; sleep 10 ; sysctl hw.twe.twe_pe > > Then flash some other BIOS (maybe the latest one :) ), and > see if the rates change. Since, in my case, it was 20/sec > -> 0.9/sec, that certainly would give you more CPU cycles > to spare... I am using the latest BIOS which i could get from www.asus.com.tw (version 1013). The rate is actyally well below 20/sec. I think (i didn't measure) it is about 3 to 5 errors per second. But error rate and interupts rate are different things and it may or maynot be related. Artem
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?014501c4262c$c4535a70$0c00a8c0>