Re: why the swapping
Thanks for the tips, all who responded (including a few who responded via email-only --- Kris, thanks for not just calling me an idiot outright. -; BTW, thanks for your BSDCan presentation ... really motivated me to try to get the 5.x boxes I have in production upgraded! I'll say no more...). This was a false alarm. The box in question is being monitored fairly closely with some home-brew rrdtool graphs, and there was a definite corelation between the load and the paging graphs. The problem was confusion regarding the *scale* of the graph. The rrdtool graphs add an m to indicate the numbers are in the millis, when the frequency scale is less than 1 (per second), rather than using decimal places. This was not noticed. So the massive swapping was actually miniscule. Sorry about that. (-: The real slow down is probably simply due to just too many heavy parallel database queries. -- Tim Middleton | Vex.Net| There is a wisdom that is woe; but there [EMAIL PROTECTED] | VexTech.ca | is a woe that is madness. --Melville (MD) ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
possible tcp problem
Hi, I'm using freebsd 6.1 and _sometimes_ (one for every ~30-40 minutes) I get mysql connect errors with permission denied. The mysql_connect returns error code 1, which is permission denied. The same happed to me when i tried to open a tcp connection between jails and it wasn't mysql related. The same happened sometimes this dawn with a sendmail host lookup. On the console I got the permission denied. I don't really know what could cause this, but it's like a buffer gets full. I use pf for filtering and nat. I checked pfctl -si which says there are ~800-1000 states, so it's well below the max 1. The question is that what could cause this thing and what should we try to solve this. Errors: sendmail[37085]: gethostbyaddr(IP) failed: 1 Can't connect to MySQL server on 'IP' (1) netstat -m 298/812/1110 mbufs in use (current/cache/total) 286/396/682/25600 mbuf clusters in use (current/cache/total/max) 286/322 mbuf+clusters out of packet secondary zone in use (current/cache) 0/0/0/0 4k (page size) jumbo clusters in use (current/cache/total/max) 0/0/0/0 9k jumbo clusters in use (current/cache/total/max) 0/0/0/0 16k jumbo clusters in use (current/cache/total/max) 646K/995K/1641K bytes allocated to network (current/cache/total) 65610/107271/98848 requests for mbufs denied (mbufs/clusters/mbuf+clusters) 0/0/0 requests for jumbo clusters denied (4k/9k/16k) 0/0/0 sfbufs in use (current/peak/max) 0 requests for sfbufs denied 0 requests for sfbufs delayed 45726 requests for I/O initiated by sendfile 118 calls to protocol drain routines Regards, Andras ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
5.4=6.1 regression: nforce2 vs. APIC [+fix]
[Disclaimer, just in case: I do mean APIC, not ACPI] This is a good lesson for me for not trying any RCs or BETAs in due time. Short description of my system: nforce2 based motherboard NF-7 v2 with the latest BIOS (v2.7), CPU is Athlon XP. After upgrading from 5.4 to 6.1 I started to experience complete system freezes after some (short) time after each boot. 100% reproducible, time before lockup varied from several seconds to several minutes. I already had freezes but with different symptoms on this system with 5.2.1 and APIC enabled: http://lists.freebsd.org/pipermail/freebsd-questions/2004-September/058392.html These freezes were fixed either in 5.3 or in 5.4, I don't remember now precisely, but I had APIC enabled in kernel and BIOS for a long time. (Just in case: I did have interrupts 15 all that time). So I went and disabled APIC in BIOS and freezes went away. I am not sure exactly why, but I wanted my APIC back. So I googled up a lot of information about nforce2+APIC, nforce2+Linux and APIC+FreeBSD. Here's a brief summary of my findings: 1. apparently on FreeBSD 5.4 APIC works in mixed mode, system uses IRQ0 timer and everything is OK (for reasons not clear to me). 2. apparently linux 2.4.* works similarly but had or has some problems with nforce2 because almost all BIOSes (MADTs) on almost all nforce2-based MBs (save for some Shuttles) have bogus IRQ0-PIN2 override and that screwed something in linux. This might be (have been) causing problems for some FreeBSD users, but not for me, not my MB. 3. apparently linux 2.6.* uses LAPIC timer similarly to FreeBSD 6.1, but people still experienced or experience hard freezes when they have all of the following 3 enabled: LAPIC timer, APIC and Disconnect CPU on C1 chipset feature. The latter is done through either BOIS setting or through programs like fvcool. I indeed verified that if I disable C1 disconnect, then 6.1 with APIC enabled works well. But the CPU temperature went up as well, so I wanted my C1 disconnect back :) After fruitlessly trying to hack sources to disable LAPIC timer and go back to IRQ0 timer and make this portion of kernel behave similarly to 5.4 (this is a long and uninteresting story), I finally found a very useful piece of information from within nVidia itself: http://lkml.org/lkml/2004/5/3/157 Based on that info and the linux patch in that thread I came up with the following PCI fixup. Now I am running 6.1 with both APIC and C1 disconnect enabled for 2 days without any problems. --- sys/dev/pci/fixup_pci.c.origWed May 17 21:08:47 2006 +++ sys/dev/pci/fixup_pci.c Thu May 18 16:42:53 2006 @@ -51,6 +51,7 @@ static int fixup_pci_probe(device_t dev); static voidfixwsc_natoma(device_t dev); +static voidfixc1_nforce2(device_t dev); static device_method_t fixup_pci_methods[] = { /* Device interface */ @@ -76,6 +77,9 @@ case 0x12378086: /* Intel 82440FX (Natoma) */ fixwsc_natoma(dev); break; +case 0x01e010de: /* nVidia nforce2 */ + fixc1_nforce2(dev); + break; } return(ENXIO); } @@ -99,4 +103,18 @@ pci_write_config(dev, 0x50, pmccfg, 2); } #endif +} + +/* + * See: http://lkml.org/lkml/2004/5/3/157 + */ +static void +fixc1_nforce2(device_t dev) +{ +uint32_t val; + +val = pci_read_config(dev, 0x6c, 4); +val = 0xfff1; +pci_write_config(dev, 0x6c, val, 4); +printf(fixup from nforce2 C1 CPU disconnect hangs\n); } -- Andriy Gapon ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 5.4=6.1 regression: nforce2 vs. APIC [+fix]
Andriy Gapon wrote: [Disclaimer, just in case: I do mean APIC, not ACPI] Based on that info and the linux patch in that thread I came up with the following PCI fixup. Now I am running 6.1 with both APIC and C1 disconnect enabled for 2 days without any problems. Did you file a PR with your fix? ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 5.4=6.1 regression: nforce2 vs. APIC [+fix]
On Friday 19 May 2006 10:27, Andriy Gapon wrote: [Disclaimer, just in case: I do mean APIC, not ACPI] This is a good lesson for me for not trying any RCs or BETAs in due time. Short description of my system: nforce2 based motherboard NF-7 v2 with the latest BIOS (v2.7), CPU is Athlon XP. ... Based on that info and the linux patch in that thread I came up with the following PCI fixup. Now I am running 6.1 with both APIC and C1 disconnect enabled for 2 days without any problems. Good find! The patch looks good. I've modified it slight to expand the comment and to make it more paranoid and only trigger for bus/slot/function 0/0/0 like the post mentions along with a minor tweak to the printf. Can you test to make sure I didn't break anything in the process? -- John Baldwin [EMAIL PROTECTED]http://www.FreeBSD.org/~jhb/ Power Users Use the Power to Serve = http://www.FreeBSD.org ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 5.4=6.1 regression: nforce2 vs. APIC [+fix]
on 19/05/2006 18:16 John Baldwin said the following: On Friday 19 May 2006 10:27, Andriy Gapon wrote: [Disclaimer, just in case: I do mean APIC, not ACPI] This is a good lesson for me for not trying any RCs or BETAs in due time. Short description of my system: nforce2 based motherboard NF-7 v2 with the latest BIOS (v2.7), CPU is Athlon XP. ... Based on that info and the linux patch in that thread I came up with the following PCI fixup. Now I am running 6.1 with both APIC and C1 disconnect enabled for 2 days without any problems. Good find! The patch looks good. I've modified it slight to expand the comment and to make it more paranoid and only trigger for bus/slot/function 0/0/0 like the post mentions along with a minor tweak to the printf. Can you test to make sure I didn't break anything in the process? Jon, sure, where can I find your version of the patch ? :-) -- Andriy Gapon ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 5.4=6.1 regression: nforce2 vs. APIC [+fix]
on 19/05/2006 17:54 [LoN]Kamikaze said the following: Andriy Gapon wrote: [Disclaimer, just in case: I do mean APIC, not ACPI] Based on that info and the linux patch in that thread I came up with the following PCI fixup. Now I am running 6.1 with both APIC and C1 disconnect enabled for 2 days without any problems. Did you file a PR with your fix? Not yet. I wanted to receive some feedback and test results first (and kinda hoped that this will get included without a PR). -- Andriy Gapon ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
ipw(4) breaking under load
Hi guys, is it just me, or is no one actually using ipw(4) under 6.1? Anyway, I set up a FreeBSD based AP using an ural(4) device. I'm connecting to it via laptop and ipw(4). This works fine, as long as you don't push it. Transferring some files via NFS gives me a lousy 100kB/s transfer rate, which quickly stalls and the connection wedges. Syslog reports: May 19 17:29:48 roadrunner kernel: ipw0: fatal error May 19 17:34:43 roadrunner kernel: ipw0: fatal error May 19 17:35:54 roadrunner kernel: ipw0: fatal error May 19 17:37:43 roadrunner kernel: ipw0: fatal error After running 'ifconfig ipw0 up ssid FOO' it will quickly re-associate and resume transferring, but as you see from the timestamps above, it stalls rather quickly. The link quality can't be responsive, as I was within 2m of the AP. I wish I could try if_ndis(4) but it quickly panics too (there's a PR about it). Anything I could try? Ulrich Spoerlein -- PGP Key ID: 20FEE9DD Encrypted mail welcome! Fingerprint: AEC9 AF5E 01AC 4EE1 8F70 6CBD E76E 2227 20FE E9DD Which is worse: ignorance or apathy? Don't know. Don't care. pgpKYORmdvxdG.pgp Description: PGP signature
Re: ipw(4) breaking under load
Le Vendredi 19 Mai 2006 18:27, Ulrich Spoerlein a écrit : Hi guys, Hello, is it just me, or is no one actually using ipw(4) under 6.1? Anyway, I set up a FreeBSD based AP using an ural(4) device. I'm connecting to it via laptop and ipw(4). This works fine, as long as you don't push it. Transferring some files via NFS gives me a lousy 100kB/s transfer rate, which quickly stalls and the connection wedges. Syslog reports: May 19 17:29:48 roadrunner kernel: ipw0: fatal error I've got this error with the iwi driver too (Intel 2200 BG). But not often (one or two times a week). It seems not related to the network load for me. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 4.11 snapshots?
You could build your own snapshots It's not hard (hint 'man release'). Seth Brett Glass wrote: Is there a server currently furnishing snapshots of the FreeBSD 4.11 security branch? We have some servers running various 4.x versions that might not be happy with 6.x due to memory requirements. They also might have slower file access (The file system in FreeBSD 6.x still isn't as snappy as the one in 4.x, though I hope this will change). So, we'd like to upgrade them to a patch level that includes all recent security fixes. Are ISOs available? --Brett Glass ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED] ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: possible tcp problem
Hi, On Fri, 19 May 2006 15:49:25 +0200 Andras Got [EMAIL PROTECTED] wrote: The question is that what could cause this thing and what should we try to solve this. Errors: sendmail[37085]: gethostbyaddr(IP) failed: 1 Can't connect to MySQL server on 'IP' (1) Don't know about the second error, but I believe the first one is printed by following chunk of src/contrib/sendmail/src/conf.c start of the quote sm_syslog(LOG_WARNING, NOQID, gethostbyaddr(%.100s) failed: %d, anynet_ntoa(sa), #if NAMED_BIND h_errno #else /* NAMED_BIND */ -1 #endif /* NAMED_BIND */ ); end of the quote netdb.h has following description for that error number in h_errno: #define HOST_NOT_FOUND 1 /* Authoritative Answer Host not found */ So that specific error looks like a problem on your DNS. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]