Re: ZFS and 'traditional' nfs-export

2009-10-27 Thread Kris Kennaway
Arno J. Klaassen wrote: hello, "Larry Rosenman" writes: ZFS makes its own version of the exports file. Just do it that way, and be safe. You can pass the full set of NFS options in the sharenfs parameter ah ok, I see. Thanks for answering. I got fooled by the man zfs(1M) example :

panic from ifconfig in IFAREF

2008-11-30 Thread Kris Kennaway
I got this panic on HEAD when trying to configure an IP address on an interface immediately after boot: > Fatal trap 9: general protection fault while in kernel mode > ccpuid = 4; xapic id = 04 > ginstruction pointer= 0x8:0x80494b42 > bstack pointer = 0x10:0x20938490

Re: kern/129074: [ppp] [panic] kernel panic with pppoe_server

2008-11-29 Thread Kris Kennaway
KES wrote: Здравствуйте, Kris. Вы писали 29 ноября 2008 г., 4:00:05: kFo> Synopsis: [ppp] [panic] kernel panic with pppoe_server kFo> State-Changed-From-To: open->feedback kFo> State-Changed-By: kris kFo> State-Changed-When: Sat Nov 29 01:59:30 UTC 2008 kFo> State-Changed-Why: kFo> Please pro

Re: kernel profiling: spinlock_exit consumes 36% CPU time.

2008-10-11 Thread Kris Kennaway
邱剑 wrote: > Many thanks for the information. > > Could we say that interrupt handlers consumed ~36% execution time? > > Is this number too high? Is it possible that we abuse the use of critical > sections in kernel? Also note that profiling itself is using ~40% of CPU. That means you need to wo

Re: What's the status of parallel netisr?

2008-09-21 Thread Kris Kennaway
Jian Qiu wrote: Hi, Kris, In our application-level tests FreeBSD significantly out-performs Linux, so either you have found a different workload, or something is not configured equally. One important thing I can think of off the top of my head is that Linux has a larger socket buffer size by d

Re: What's the status of parallel netisr?

2008-09-18 Thread Kris Kennaway
Jian Qiu wrote: Thanks again for the info. As you suggested, I did test on the most recent 7.0-stable-200807 kernel. The SMP throughout on the new kernel was improved to around 90MB/s. However, SMP kernel still had no advantage over UP, at least for this kind of single threaded applications.

Re: What's the status of parallel netisr?

2008-09-16 Thread Kris Kennaway
Jian Qiu wrote: Interesting. I did a test on local UDP throughput. I was surprised to find out the performance with a SMP kernel was worse than UP. (~74MB/s v.s. 96 MB/s). I had though parallel netisr might be a solution. Make sure you are testing with either 8.0 or 7.1 (or late 7.0-STABLE),

Re: too many open file descriptors messages since bind 9.4.2-P1 (port dns94)

2008-07-15 Thread Kris Kennaway
JINMEI Tatuya / 神明達哉 wrote: At Tue, 15 Jul 2008 23:09:30 +0200, Kris Kennaway <[EMAIL PROTECTED]> wrote: If that's regularly happening, I'm afraid recent P1 versions don't handle that well, and recommend you try 9.4.3b2 ore 9.5.1b1. Or increase the number of file descri

Re: too many open file descriptors messages since bind 9.4.2-P1 (port dns94)

2008-07-15 Thread Kris Kennaway
JINMEI Tatuya / 神明達哉 wrote: At Tue, 15 Jul 2008 22:54:11 +0200, Thomas Vogt <[EMAIL PROTECTED]> wrote: Since i updated my FreeBSD 6.3 dns server with the latest bind version in the ports (dns/bind94) my system is flooding my log with "too many open file descriptors" messages. Is there someth

Re: too many open file descriptors messages since bind 9.4.2-P1 (port dns94)

2008-07-15 Thread Kris Kennaway
Thomas Vogt wrote: Hello Since i updated my FreeBSD 6.3 dns server with the latest bind version in the ports (dns/bind94) my system is flooding my log with "too many open file descriptors" messages. Is there something i can do? Example: Jul 15 12:08:38 intern named[50840]: socket: too many

Re: Freebsd IP Forwarding performance (question, and some info) [7-stable, current, em, smp]

2008-07-07 Thread Kris Kennaway
Andre Oppermann wrote: Robert Watson wrote: Experience suggests that forwarding workloads see significant lock contention in the routing and transmit queue code. The former needs some kernel hacking to address in order to improve parallelism for routing lookups. The latter is harder to addre

Re: NAT crashing FreeBSD 7.x

2008-06-18 Thread Kris Kennaway
Dave Robison wrote: Hiya, I posted this to -questions but didn't get any responses so I'm posting it again here. I'm having problems with NAT crashing my FreeBSD box. This never happened in 6.x but in 7.x it's predictable for me. Any time I use either of my two NICs for my internal net my F

Re: ssh window

2008-06-13 Thread Kris Kennaway
Brooks Davis wrote: It is worth noting that over most people's WAN's the none cipher is pretty pointless since you can do nearly 200Mbps with arcfour and a decent CPU (IIRC the graphs are several years old). In my case I'm CPU bound from other processes, so reducing SSH overhead will have a n

Re: ssh window

2008-06-13 Thread Kris Kennaway
Garrett Wollman wrote: In article <[EMAIL PROTECTED]>, Brooks Davis writes: On Thu, Jun 12, 2008 at 06:30:05PM -0700, Peter Losher wrote: FYI - HPN is already a build option in the openssh-portable port. I do think we should strongly consider adding the rest of it to the base. Am I the only

Re: ssh window

2008-06-13 Thread Kris Kennaway
Brooks Davis wrote: On Thu, Jun 12, 2008 at 06:30:05PM -0700, Peter Losher wrote: Randy Bush wrote: this has been a cause of great pain for a lng time. http://www.psc.edu/networking/projects/hpn-ssh/ as openssh seems not to be fixing it (and i do not consider a 2mb fixed buffer to be f

Re: kern/122875: "rstatd: Can't get namelist. 1" - fbsd 7.0-stable (works ok in 7.0-release)

2008-05-01 Thread Kris Kennaway
The following reply was made to PR kern/122875; it has been noted by GNATS. From: Kris Kennaway <[EMAIL PROTECTED]> To: hotlips Internet admin <[EMAIL PROTECTED]> Cc: [EMAIL PROTECTED] Subject: Re: kern/122875: "rstatd: Can't get namelist. 1" - fbsd 7.0-stable (works o

Re: kern/122875: "rstatd: Can't get namelist. 1" - fbsd 7.0-stable (works ok in 7.0-release)

2008-04-28 Thread Kris Kennaway
hotlips Internet admin wrote: The following reply was made to PR kern/122875; it has been noted by GNATS. From: hotlips Internet admin <[EMAIL PROTECTED]> To: [EMAIL PROTECTED], [EMAIL PROTECTED] Cc: [EMAIL PROTECTED] Subject: Re: kern/122875: "rstatd: Can't get namelist. 1" - fbsd 7.0-stable (

Re: misc/123066: kernel trap with ipsec

2008-04-26 Thread Kris Kennaway
On Fri, Apr 25, 2008 at 07:20:03AM +, misha saf wrote: > The following reply was made to PR kern/123066; it has been noted by GNATS. > > From: misha saf <[EMAIL PROTECTED]> > To: Kris Kennaway <[EMAIL PROTECTED]> > Cc: <[EMAIL PROTECTED]> > Subject: Re:

Re: misc/123066: kernel trap with ipsec

2008-04-24 Thread Kris Kennaway
The following reply was made to PR kern/123066; it has been noted by GNATS. From: Kris Kennaway <[EMAIL PROTECTED]> To: Mihail <[EMAIL PROTECTED]> Cc: [EMAIL PROTECTED] Subject: Re: misc/123066: kernel trap with ipsec Date: Fri, 25 Apr 2008 05:46:54 + On Fri, Apr 25, 2008 a

Re: nfs-server silent data corruption

2008-04-21 Thread Kris Kennaway
On Mon, Apr 21, 2008 at 01:02:33AM +0200, Arno J. Klaassen wrote: > I didn't stress-test this MB for a while, but last time I did was > with 7-PRELEASE/RC?/CANTremember-exactly-but-close-to-release > and all worked great > > I did add 2G ECC to the 2nd CPU since, though I doubt that interferes >

Re: kern/122331: [panic] 7.0-RELEASE && panic in Wifi area with WPA mode (not in WEP mode)

2008-04-02 Thread Kris Kennaway
2 00:24:15 UTC 2008 State-Changed-Why: See kern/122286 from same submitter. http://www.freebsd.org/cgi/query-pr.cgi?pr=122331 hmmm :-) Kris Kennaway <[EMAIL PROTECTED]> asked me to file this new bug report kern/122331 because the kgdb backtrace in kern/122286 looks for him more like a p

Lock order reversals with dummynet (Re: FreeBSD 7.0 Beta, RC, RELEASE (amd64) freezes with dummynet enabled)

2008-02-29 Thread Kris Kennaway
Adding back the mailing list so others can help. matthew wrote: Kris Kennaway wrote: matthew wrote: I have posted before that i have a stability issue with the 7.0 branch on my servers. Tested on BETA2,BETA4,RC1,RC2,RELEASE The original thread and my post with details is at: http

Re: i386/120264: double fault in freebsd 7.0

2008-02-05 Thread Kris Kennaway
The following reply was made to PR i386/120264; it has been noted by GNATS. From: Kris Kennaway <[EMAIL PROTECTED]> To: [EMAIL PROTECTED], [EMAIL PROTECTED] Cc: Subject: Re: i386/120264: double fault in freebsd 7.0 Date: Tue, 05 Feb 2008 11:58:26 +0100 Submitter forgot to give us any

Re: Routing SMP benefit

2008-01-03 Thread Kris Kennaway
H.fazaeli wrote: Hi all Where are 'those numbers' you are referring to? have I missed some message in the thread? Check the date below, Tiffany replied to an old message from 2 years ago for some reason. Kris Thanks, Tiffany. On 12/29/05, Andre Oppermann <[EMAIL PROTECTED] > wrote: _

Re: Packet loss every 30.999 seconds

2007-12-26 Thread Kris Kennaway
Mark Fullmer wrote: On Dec 25, 2007, at 12:27 AM, Kostik Belousov wrote: What fs do you use ? If FFS, are softupdates turned on ? Please, show the total time spent in the softdepflush process. Also, try to add the FULL_PREEMPTION kernel config option and report whether it helps. FFS with s

Re: Switch pfil(9) to rmlocks

2007-11-24 Thread Kris Kennaway
Max Laier wrote: On Friday 23 November 2007, Robert Watson wrote: On Fri, 23 Nov 2007, Max Laier wrote: attached is a diff to switch the pfil(9) subsystem to rmlocks, which are more suited for the task. I'd like some exposure before doing the switch, but I don't expect any fallout. This email

Re: accept filters and zero copy sockets

2007-10-20 Thread Kris Kennaway
Vlad GALU wrote: On 10/19/07, Jonathan Noack <[EMAIL PROTECTED]> wrote: I'm in the process of upgrading my web/database/nfs/jack-of-all-trades box from 6.2 to RELENG_7. I figured now would be a good time to clean up my kernel config files. I have the following in my old kernel config: # Stati

Re: em driver sending bad packet lengths

2007-10-14 Thread Kris Kennaway
Kris Kennaway wrote: I am seeing the em driver on 7.0 sending packets with bad UDP (and apparently sometimes IP) packet length fields. This is from UDP NFS traffic (90MB/sec over gige). These packets are dropped on reception by the kernel and counted. I think this is due to rollover of the

Re: cvs commit: src/sys/nfsclient nfs.h nfs_socket.c nfs_subs.c nfsmount.h

2007-10-13 Thread Kris Kennaway
Jim Rees wrote: Kris Kennaway wrote: Mohan's previous commit that increases the nfs server socket buffer size is also very important for NFS performance. Without it I was only getting 1-2MB/sec throughput over 10Gb ethernet with UDP mounts You're trying to use nfs/udp

Re: cvs commit: src/sys/nfsclient nfs.h nfs_socket.c nfs_subs.c nfsmount.h

2007-10-12 Thread Kris Kennaway
than over loading the nfs request lock for this purpose. - Fix some of the locking in nfs_request. Many thanks to Kris Kennaway for his help with this and for initiating the MP scaling analysis and work. Kris also tested this patch thorougly. Approved by: re@ (Ken Smith) For the

Re: em driver sending bad packet lengths

2007-10-12 Thread Kris Kennaway
Jack Vogel wrote: You should a couple different adapters below, are you saying that its just one of them, can you try different ones to see if its specific. They're both showing the problem. Also, would you be able to test my latest driver to see if it still happens? Where is it? Kris ___

em driver sending bad packet lengths

2007-10-12 Thread Kris Kennaway
I am seeing the em driver on 7.0 sending packets with bad UDP (and apparently sometimes IP) packet length fields. This is from UDP NFS traffic (90MB/sec over gige). These packets are dropped on reception by the kernel and counted. Here is a tcpdump trace showing some bad packets: 17:50:27.9

Re: Panic in rt_check

2007-10-07 Thread Kris Kennaway
Ivan Voras wrote: Ivan Voras wrote: Ivan Voras wrote: Apparently, this was patched 4 days ago so I'll try two things: 1) build with the new (patched) version and Interesting development - the machine is stable now for 5 days (before this, it would panic within 48 hours). It looks like the pr

Re: localhost connections showing source address 0.0.0.0

2007-10-01 Thread Kris Kennaway
Peter Jeremy wrote: On 2007-Sep-29 22:24:02 +0200, Kris Kennaway <[EMAIL PROTECTED]> wrote: Going back at least as far as January 2007 some of the package build machines have occasionally experienced a problem where a fetch(1) via a localhost:3128 squid proxy are denied because squid se

localhost connections showing source address 0.0.0.0

2007-09-29 Thread Kris Kennaway
Going back at least as far as January 2007 some of the package build machines have occasionally experienced a problem where a fetch(1) via a localhost:3128 squid proxy are denied because squid sees the connection as having a source address of 0.0.0.0 instead of 127.0.0.1. I thought this had st

Re: Panic in rt_check

2007-09-27 Thread Kris Kennaway
Ivan Voras wrote: On 27/09/2007, Kris Kennaway <[EMAIL PROTECTED]> wrote: You will need to evaluate based on other evidence. e.g. if you've noticed other network flakiness on this machine to do with the gateway. No, I don't think there's anything like that. The panics

Re: Panic in rt_check

2007-09-27 Thread Kris Kennaway
Ivan Voras wrote: On 27/09/2007, Kris Kennaway <[EMAIL PROTECTED]> wrote: Ivan Voras wrote: Hi, I have a machine that panics almost daily in route.c, in rt_check(). This panic has been reported by several users, including Marcel Moolenaar for a machine in freebsd.org. The problem is p

Re: Panic in rt_check

2007-09-27 Thread Kris Kennaway
Ivan Voras wrote: Hi, I have a machine that panics almost daily in route.c, in rt_check(). This panic has been reported by several users, including Marcel Moolenaar for a machine in freebsd.org. The problem is present in both 6-STABLE and 7-CURRENT, and apparently it manifests on SMP machin

Re: Attention pf/ipfw users with uid/gid/jail rules (Re: Reminder: NET_NEEDS_GIANT, debug.mpsafenet going away in 7.0)

2007-07-26 Thread Kris Kennaway
On Fri, Jul 20, 2007 at 11:36:50AM -0700, Julian Elischer wrote: > Robert Watson wrote: > > > >On Tue, 17 Jul 2007, Max Laier wrote: > > > >So far I have had 0 (zero) reports of problems since this thread began. > >Could people using uid/gid/jail rules with ipfw or pf on 7.x *please* > >try runni

panic: mtx_lock() of destroyed mutex @ ../../../net/route.c:1306

2007-05-02 Thread Kris Kennaway
One of my 7.0 systems has a flaky gateway, and when it goes down the node often goes down with this panic: panic: mtx_lock() of destroyed mutex @ ../../../net/route.c:1306 cpuid = 0 KDB: enter: panic [thread pid 28619 tid 100074 ] Stopped at kdb_enter+0x68: ta %xcc, 1 db> wh Trac

Page fault in syncache_drop

2007-04-16 Thread Kris Kennaway
8-core amd64, up-to-date CVS sources Fatal trap 12: page fault while in kernel mode cpuid = 0; apic id = 00 fault virtual address = 0x0 fault code = supervisor read data, page not present instruction pointer = 0x8:0x803134b4 stack pointer = 0x10:0xabe09

Re: GPF in ether_output -> m_tag_locate

2007-04-15 Thread Kris Kennaway
On Sun, Apr 15, 2007 at 11:30:47PM -0400, Kris Kennaway wrote: > On an 8-core amd64 running up-to-date CVS sources: > > > Fatal trap 9: general protection fault while in kernel mode > > cpuid = 7; apic id = 07 > > instruction pointer = 0x8:0x802a7800 > >

GPF in ether_output -> m_tag_locate

2007-04-15 Thread Kris Kennaway
On an 8-core amd64 running up-to-date CVS sources: > Fatal trap 9: general protection fault while in kernel mode > cpuid = 7; apic id = 07 > instruction pointer = 0x8:0x802a7800 > stack pointer = 0x10:0xabc61960 > frame pointer = 0x10:0xabc61970 > co

Re: A radical restructuring of IPsec...

2007-04-06 Thread Kris Kennaway
On Fri, Apr 06, 2007 at 04:49:01PM +0200, Ivan Voras wrote: > [EMAIL PROTECTED] wrote: > > >The patch removes Kame derived IPsec from the tree, and adds v6 > >support to FAST_IPSEC. The IPSEC kernel option is removed, but the > >FAST_IPSEC option remains. This is a test patch and has a known > >p

Re: Scalability problem from route refcounting

2007-03-14 Thread Kris Kennaway
On Wed, Mar 14, 2007 at 06:45:20PM -0700, Kip Macy wrote: > Apologies in advance if you have already answered this question > elsewhere - can you point me to a HOWTO for replicating the test in my > local environment? Well it's not completely spelled out...but most of the steps are documented in h

Scalability problem from route refcounting

2007-03-14 Thread Kris Kennaway
I have recently started looking at database performance over gigabit ethernet, and there seems to be a bottleneck coming from the way route reference counting is implemented. On an 8-core system it looks like we spend a lot of time waiting for the rtentry mutex: maxtotal wait_total

Re: 6.2 becomes unresponsive under high traffic

2006-10-21 Thread Kris Kennaway
On Sat, Oct 21, 2006 at 10:06:16AM -0400, Mikhail Teterin wrote: > Hello! > > The system is a dual Opteron 244 running today's FreeBSD-6.2/amd64. > > em-interface connects it to the switch (in gigabit mode). > > When I direct 2 database dumps at the machine in parallel (the arriving data > is g

Re: em network issues

2006-10-18 Thread Kris Kennaway
On Wed, Oct 18, 2006 at 03:31:53PM -0700, Jack Vogel wrote: > On 10/18/06, Kip Macy <[EMAIL PROTECTED]> wrote: > >I have a Sun T2000 that I generally run with the em driver from as of > >July in order to avoid watchdog timeouts. One trivial scenario that > >reproduces the problem with 100% consiste

Panic from osendmsg() (Re: panic: m_prepend: MH_ALIGN not PKTHDR mbuf)

2006-06-04 Thread Kris Kennaway
On Tue, May 23, 2006 at 09:58:26PM -0400, Kris Kennaway wrote: > I got this panic as a non-privileged user running the stress2 test > component that does random syscalls: > > panic: m_prepend: MH_ALIGN not PKTHDR mbuf > cpuid = 1 > KDB: enter: panic > [thread pid 15370 tid

Re: nfsd and CPU/performance problem

2006-05-24 Thread Kris Kennaway
On Wed, May 24, 2006 at 03:15:42PM +0200, Marko Lerota wrote: > Nash Nipples <[EMAIL PROTECTED]> writes: > > >Hi Marko, > > > > Actually i dont find that load critical. I think those lines well tell that > > actually the process is running 581m42s and now it utilizes 13.48% > > Sometimes it

panic: m_prepend: MH_ALIGN not PKTHDR mbuf

2006-05-23 Thread Kris Kennaway
I got this panic as a non-privileged user running the stress2 test component that does random syscalls: panic: m_prepend: MH_ALIGN not PKTHDR mbuf cpuid = 1 KDB: enter: panic [thread pid 15370 tid 100536 ] Stopped at kdb_enter+0x32: leave db> wh Tracing pid 15370 tid 100536 td 0xc5561000 kdb_

Re: Low network performance after upgrade from FreeBSD 4.8 to 6.0

2006-03-20 Thread Kris Kennaway
On Mon, Mar 20, 2006 at 03:33:33PM +0100, OxY wrote: > > - Original Message - > From: "Bohuslav Plucinsky" <[EMAIL PROTECTED]> > To: > Cc: > Sent: Monday, March 20, 2006 2:10 PM > Subject: Low network performance after upgrade from FreeBSD 4.8 to 6.0 > > > >Hello, > > > >I use the Fre

Re: Low network performance after upgrade from FreeBSD 4.8 to 6.0

2006-03-20 Thread Kris Kennaway
On Mon, Mar 20, 2006 at 02:10:20PM +0100, Bohuslav Plucinsky wrote: > The "top" utility shows 100% CPU load: What about top -S to show the kernel threads (since that's what's using 90% of your CPU)? > last pid: 771; load averages: 0.25, 0.06, 0.02 >

Re: ipv6 panic in 6.0 ([EMAIL PROTECTED]: kern/85780: 'panic: bogus refcnt 0' in routing/ipv6])

2006-03-10 Thread Kris Kennaway
On Mon, Mar 06, 2006 at 06:15:56PM -0500, Kris Kennaway wrote: > I've been adding KTR debugging to try and track down the cause of this > recurring problem (FYI: debug.mpsafenet=0 is no longer working around > it). To refresh your memory, here is the panic: > > db> wh >

Re: ipv6 panic in 6.0 ([EMAIL PROTECTED]: kern/85780: 'panic: bogus refcnt 0' in routing/ipv6])

2006-03-06 Thread Kris Kennaway
I've been adding KTR debugging to try and track down the cause of this recurring problem (FYI: debug.mpsafenet=0 is no longer working around it). To refresh your memory, here is the panic: db> wh Tracing pid 24 tid 100012 td 0xf802be9fa560 panic() at panic+0x164 rtfree() at rtfree+0xb4 nd6_na

Double free in icmp6 processing?

2006-03-05 Thread Kris Kennaway
I've been doing a lot of ping6'ing trying to track down the cause of the nd6 panics on sparc64 SMP machines, and I'm also seeing the following panic: -- memory address not aligned sfar=0xdedeadc0de sfsr=0x40029 %o7=0xc031d8e4 -- m_tag_delete_chain() at m_tag_delete_chain+0x28 mb_dtor_mbuf() at mb_

Re: nfs locking broken

2006-02-26 Thread Kris Kennaway
On Sun, Feb 26, 2006 at 07:21:55PM +, Brian Candler wrote: > On Fri, Feb 24, 2006 at 03:58:09PM +0100, Palle Girgensohn wrote: > > It seems that NFS locking is broken for the combo of 4.11 or 5.4 server and > > 6.x client. Apps like eclipse and firefox fail to start with my home dir on > > a

Re: nfs locking broken

2006-02-24 Thread Kris Kennaway
On Fri, Feb 24, 2006 at 03:58:09PM +0100, Palle Girgensohn wrote: > Hi! > > It seems that NFS locking is broken for the combo of 4.11 or 5.4 server and > 6.x client. Apps like eclipse and firefox fail to start with my home dir on > a 4.11 server and a 6.x client. > > Problem shows in that firef

deadc0de panic in em driver (Re: deadc0de panic in fxp driver)

2006-02-23 Thread Kris Kennaway
On Thu, Feb 16, 2006 at 03:15:14PM -0500, Kris Kennaway wrote: > Peter Holm's stress test gave me this on an SMP machine running fresh > 7.0: > > Fatal trap 12: page fault while in kernel mode > cpuid = 0; apic id = 00 > fault virtual address = 0xdeadc0de > fault code

Re: bpf panic

2006-02-23 Thread Kris Kennaway
On Thu, Feb 23, 2006 at 03:19:46AM -0500, Kris Kennaway wrote: > I ran tcpdump and killall tcpdump in a loop on 7.0, and after a few > minutes it panicked with: > > Fatal trap 12: page fault while in kernel mode > cpuid = 0; apic id = 00 > fault virtual address

bpf panic

2006-02-23 Thread Kris Kennaway
I ran tcpdump and killall tcpdump in a loop on 7.0, and after a few minutes it panicked with: Fatal trap 12: page fault while in kernel mode cpuid = 0; apic id = 00 fault virtual address = 0x8 fault code = supervisor read, page not present instruction pointer = 0x20:0xc058d0fb stack poi

Re: deadc0de panic in fxp driver

2006-02-17 Thread Kris Kennaway
On Thu, Feb 16, 2006 at 03:15:14PM -0500, Kris Kennaway wrote: > Peter Holm's stress test gave me this on an SMP machine running fresh > 7.0: > > Fatal trap 12: page fault while in kernel mode > cpuid = 0; apic id = 00 > fault virtual address = 0xdeadc0de > fault code

deadc0de panic in fxp driver

2006-02-16 Thread Kris Kennaway
Peter Holm's stress test gave me this on an SMP machine running fresh 7.0: Fatal trap 12: page fault while in kernel mode cpuid = 0; apic id = 00 fault virtual address = 0xdeadc0de fault code = supervisor write, page not present instruction pointer = 0x20:0xc0681633 stack pointe

Re: NFS file locking problem, rpc.lockd seems to be leaking ports?

2006-02-15 Thread Kris Kennaway
On Wed, Feb 15, 2006 at 10:15:03AM +0100, Palle Girgensohn wrote: > I have lived with this, planning an upgrade of the server to freebsd-6, > hoping it will fix it, but now I've upgraded one of the workstations to > freebsd-6, and nfs file locking does not work at all for this client. I Talk t

Re: Changing time causes ipv6 panics

2006-02-11 Thread Kris Kennaway
On Sat, Feb 11, 2006 at 04:31:23PM +0900, JINMEI Tatuya / [EMAIL PROTECTED]@C#:H wrote: > >>>>> On Sat, 11 Feb 2006 02:14:11 -0500, > >>>>> Kris Kennaway <[EMAIL PROTECTED]> said: > > >> >> Sorry, not really (we've not got a test

Re: Changing time causes ipv6 panics

2006-02-10 Thread Kris Kennaway
On Sat, Feb 11, 2006 at 03:38:56PM +0900, JINMEI Tatuya / [EMAIL PROTECTED]@C#:H wrote: > >>>>> On Fri, 10 Feb 2006 22:50:25 -0500, > >>>>> Kris Kennaway <[EMAIL PROTECTED]> said: > > >> Sorry, not really (we've not got a test environm

Re: Changing time causes ipv6 panics

2006-02-10 Thread Kris Kennaway
On Tue, Feb 07, 2006 at 07:16:09PM +0900, JINMEI Tatuya / [EMAIL PROTECTED]@C#:H wrote: > >>>>> On Tue, 7 Feb 2006 00:45:02 -0500, > >>>>> Kris Kennaway <[EMAIL PROTECTED]> said: > > >> I ran ntpdate on an amd64 system with ipv6 enabled and

Re: Changing time causes ipv6 panics

2006-02-06 Thread Kris Kennaway
On Sun, Jan 15, 2006 at 07:44:38PM -0500, Kris Kennaway wrote: > I ran ntpdate on an amd64 system with ipv6 enabled and a skewed clock > (ntpdate stepped it back by about an hour), and immediately got a > use-after-free panic in ifaddr. When I rebooted with memguard enabled > on this

Re: Changing time causes ipv6 panics

2006-01-30 Thread Kris Kennaway
On Mon, Jan 23, 2006 at 02:39:42PM -0500, Kris Kennaway wrote: > On Thu, Jan 19, 2006 at 02:30:35PM +0900, JINMEI Tatuya / [EMAIL > PROTECTED]@C#:H wrote: > > >>>>> On Sun, 15 Jan 2006 19:44:38 -0500, > > >>>>> Kris Kennaway <[EMAIL PROTECTED]

Re: Changing time causes ipv6 panics

2006-01-23 Thread Kris Kennaway
On Thu, Jan 19, 2006 at 02:30:35PM +0900, JINMEI Tatuya / [EMAIL PROTECTED]@C#:H wrote: > >>>>> On Sun, 15 Jan 2006 19:44:38 -0500, > >>>>> Kris Kennaway <[EMAIL PROTECTED]> said: > > > I ran ntpdate on an amd64 system with ipv6 enabled and a

Changing time causes ipv6 panics

2006-01-15 Thread Kris Kennaway
I ran ntpdate on an amd64 system with ipv6 enabled and a skewed clock (ntpdate stepped it back by about an hour), and immediately got a use-after-free panic in ifaddr. When I rebooted with memguard enabled on this malloc type and retried, I got this panic upon changing the date forward, then back,

Re: BUG: ip_output.c FreeBSD 4.11

2005-12-13 Thread Kris Kennaway
On Tue, Dec 13, 2005 at 04:32:10PM -0800, Jack Vogel wrote: > On 12/13/05, Kris Kennaway <[EMAIL PROTECTED]> wrote: > > On Tue, Dec 13, 2005 at 01:37:31PM -0800, Doug Barton wrote: > > > Mihail Balikov wrote: > > > > Hello, > > > > > > &g

Re: BUG: ip_output.c FreeBSD 4.11

2005-12-13 Thread Kris Kennaway
On Tue, Dec 13, 2005 at 01:37:31PM -0800, Doug Barton wrote: > Mihail Balikov wrote: > > Hello, > > > > In FreeBSD 4.x in ip_output.c in part for ipfw local forwarding there's typo > > that will cause kernel panic: > > If you haven't already, this should be filed as a problem report. I don't kno

Re: bad udp cksum 26ff!

2005-11-28 Thread Kris Kennaway
On Mon, Nov 28, 2005 at 10:46:38AM -0800, John Palmer wrote: > I am running FreeBSD 5.4 p8. I did a tcpdump -vv -i em0. The output > produced > a "bad udp cksum" with my DNS server. Does anyone know what it means? Or, > how I can > correct the problem? If your NIC is doing checksum offload,

Re: em interrupt storm

2005-11-23 Thread Kris Kennaway
On Thu, Nov 24, 2005 at 12:40:24PM +1100, Michael Vince wrote: > chipset in all their servers. > Luckily I haven't not seen the problem on any of my Dell servers (as > long as I am looking at this right). > > This server has been running for a long time. > vmstat -i > interrupt

Re: em interrupt storm

2005-11-23 Thread Kris Kennaway
On Tue, Nov 22, 2005 at 08:54:49PM -0800, John Polstra wrote: > > On 23-Nov-2005 Kris Kennaway wrote: > > I am seeing the em driver undergoing an interrupt storm whenever the > > amr driver receives interrupts. In this case I was running newfs on > > the amr arra

em interrupt storm

2005-11-22 Thread Kris Kennaway
I am seeing the em driver undergoing an interrupt storm whenever the amr driver receives interrupts. In this case I was running newfs on the amr array and em0 was not in use: 28 root1 -68 -187 0K 8K CPU1 1 0:32 53.98% irq16: em0 36 root1 -64 -183 0K 8K RU

Re: panic: receive: m == 0 so->so_rcv.sb_cc == 4294967295

2005-09-28 Thread Kris Kennaway
On Thu, Sep 08, 2005 at 11:04:12AM +0200, Marc Olzheim wrote: > On Thu, Sep 08, 2005 at 12:43:36AM -0400, Kris Kennaway wrote: > > db> wh > > Tracing pid 23098 tid 100263 td 0xc92e4af0 > > kdb_enter(c07060af,0,c070c9b3,f7d14bc8,c92e4af0) at kdb_enter+0x30 > > panic(c0

Re: ipv6 panic in 6.0 ([EMAIL PROTECTED]: kern/85780: 'panic: bogus refcnt 0' in routing/ipv6])

2005-09-28 Thread Kris Kennaway
On Wed, Sep 28, 2005 at 12:06:18PM +0900, SUZUKI Shinsuke wrote: > Hello kris, > > >>>>> On Tue, 27 Sep 2005 18:26:34 -0400 > >>>>> [EMAIL PROTECTED](Kris Kennaway) said: > > > Can someone please look into this ipv6 panic? It is now my #1 pani

ipv6 panic in 6.0 ([EMAIL PROTECTED]: kern/85780: 'panic: bogus refcnt 0' in routing/ipv6])

2005-09-27 Thread Kris Kennaway
Can someone please look into this ipv6 panic? It is now my #1 panic on 6.0 (every few days, and I hardly make any use of ipv6 except for light nfs and tcp traffic), so it would be good to get it fixed before the release. Kris - Forwarded message from Kris Kennaway <[EMAIL PROTEC

panic: receive: m == 0 so->so_rcv.sb_cc == 4294967295

2005-09-07 Thread Kris Kennaway
Got this on a SMP (up-to-date) 7.0 machine doing a buildworld loop and not much else: panic: receive: m == 0 so->so_rcv.sb_cc == 4294967295 cpuid = 0 KDB: enter: panic [thread pid 23098 tid 100263 ] Stopped at kdb_enter+0x30: leave db> wh Tracing pid 23098 tid 100263 td 0xc92e4af0 kdb_enter(c

'panic: bogus refcnt 0' from routing/ipv6 code.

2005-09-04 Thread Kris Kennaway
I got this on a quad sparc64 machine running 7.0 from a few days ago. Both IPv4 and IPv6 are in use on the machine. I will leave it in DDB for now in case you want something from it, but I should be able to obtain a core. Kris panic: bogus refcnt 0 cpuid = 0 KDB: enter: panic [thread pid 15 tid

Re: running out of mbufs?

2005-08-02 Thread Kris Kennaway
On Wed, Aug 03, 2005 at 03:55:39AM +, Kris Kennaway wrote: > On Wed, Aug 03, 2005 at 01:54:16PM +1000, Dave+Seddon wrote: > > So as for the system losing all network connectivity, do you have any > > suggestions? > > No, it must be some unrelated problem. P.S. Return

Re: running out of mbufs?

2005-08-02 Thread Kris Kennaway
On Wed, Aug 03, 2005 at 01:54:16PM +1000, Dave+Seddon wrote: > So as for the system losing all network connectivity, do you have any > suggestions? No, it must be some unrelated problem. Kris -- In God we Trust -- all others must submit an X.509 certificate. -- Charles Forsythe <[EMAIL PRO

Re: running out of mbufs?

2005-08-02 Thread Kris Kennaway
On Wed, Aug 03, 2005 at 01:49:32PM +1000, Dave+Seddon wrote: > Greetings, > > I'm trying to do some performance testing of a content filtering system, so > I'm trying to get very high HTTP throughput. I've got 4 * HP DL380s with > 3.4G Xeon processors (hyper threading) and 1 G RAM, 2 onboard BGEs

Re: SSL lib

2005-08-02 Thread Kris Kennaway
On Fri, Jul 29, 2005 at 03:45:15AM -0700, sibel kanmaz wrote: > hello I have some problems with openssl: > wclient2.o(.text+0x3a6): undefined reference to `SSL_new' > wclient2.o(.text+0x3b9): undefined reference to `BIO_new_socket' > wclient2.o(.text+0x3d0): undefined reference to `SSL_set_bio' > w

Re: mping

2005-05-30 Thread Kris Kennaway
On Thu, May 26, 2005 at 07:07:24PM +0200, Olivier Casasole wrote: > > Hi all, > > I would like to use mping under FreeBSD 5.3. > mping seems to be installed in /kame directory but it > doesn't work. > Do you know why? FreeBSD has no /kame directory. I'm guessing this is something you have insta

Re: FreeBSD 5.4 - TCP MD5

2005-05-26 Thread Kris Kennaway
On Thu, May 26, 2005 at 05:22:47PM +0100, Lee Johnston wrote: > Hi, > > I'm trying to configure a 5.4 box with Quagga to support TCP MD5 Passwords. > I've achieved this previously with 4.10, but when I try to add the > following kernel options, 5.4 doesn't like it: > > options FAST_IPSEC > opti

Re: SOLVED: Degraded TCP performace on Intel PRO/1000

2005-05-06 Thread Kris Kennaway
On Fri, May 06, 2005 at 08:59:50AM +0200, Marian Durkovic wrote: > Hi all, > > > seems we've found the problem. The performance degradation was happening > it the TX path, due to insufficient setting of TX packet buffer FIFO on the > chip. > > To achieve wirespeed performance, the TX FIFO mu

Re: mouse not working on FBSD5.0

2005-04-24 Thread Kris Kennaway
On Sat, Apr 23, 2005 at 05:45:14PM -0700, Grace Lin wrote: > Hi, > > I have reinstalled FBSD5.0 recently but the mouse happened not working right. > I have two buttons MS serial mouse and it was working fine on my previous > FBSD4.5. Any patch out there or anything I can do to fixed it? First,

Re: "panic: trap: fast data access mmu miss" in m_copym

2005-04-19 Thread Kris Kennaway
On Tue, Apr 19, 2005 at 08:36:28AM +0100, Robert Watson wrote: > On Mon, 18 Apr 2005, Kris Kennaway wrote: > > >This on an u10 running > > > >FreeBSD 5.3-STABLE (NETBOOT) #1: Sun Dec 12 18:38:35 JST 2004 > > > >It may already be fixed, but since this is clearl

Re: "panic: trap: fast data access mmu miss" in m_copym

2005-04-19 Thread Kris Kennaway
On Tue, Apr 19, 2005 at 08:36:28AM +0100, Robert Watson wrote: > On Mon, 18 Apr 2005, Kris Kennaway wrote: > > >This on an u10 running > > > >FreeBSD 5.3-STABLE (NETBOOT) #1: Sun Dec 12 18:38:35 JST 2004 > > > >It may already be fixed, but since this is clearl

"panic: trap: fast data access mmu miss" in m_copym

2005-04-18 Thread Kris Kennaway
This on an u10 running FreeBSD 5.3-STABLE (NETBOOT) #1: Sun Dec 12 18:38:35 JST 2004 It may already be fixed, but since this is clearly a very infrequent problem (the other 7 machines with the same kernel have been running for months) it will be hard to tell empirically. Unfortunately I don't se

Re: Race condition in mb_free_ext()?

2005-03-01 Thread Kris Kennaway
On Tue, Mar 01, 2005 at 06:04:27PM -0500, Bosko Milekic wrote: > This does not appear to explain the livelock. alc and dwhite tracked it down to a missing volatile causing gcc to mis-optimize the loop: - cnt = *(m->m_ext.ref_cnt); + cnt = *(volatile u_int *)(m->m_ext.

Race condition in mb_free_ext()?

2005-02-28 Thread Kris Kennaway
I'm seeing an easily-provoked livelock on quad-CPU sparc64 machines running RELENG_5. It's hard to get a good trace because the processes running on other CPUs cannot be traced from DDB, but I've been lucky a few times: db> show alllocks Process 15 (swi1: net) thread 0xf8001fb07480 (18) e

Re: ABI suggestions?

2005-02-20 Thread Kris Kennaway
On Sun, Feb 20, 2005 at 07:40:35PM -0600, Mike Silbersack wrote: > > On Sun, 20 Feb 2005, Julian Elischer wrote: > > >I'm looking at implementing a kernel module that implelemnts an ABI that > >allows a particular tcp session to be followed. > >I'm not terribly intereted in the data sent/receive

Re: SACK problems

2005-02-10 Thread Kris Kennaway
On Fri, Feb 11, 2005 at 10:15:35AM +1300, Sam Jansen wrote: > During some testing on an isolated network we have, I found some > interesting behaviour from a FreeBSD 5.3 host using TCP SACK. > > I've detailed this problem fully at: > >http://www.wand.net.nz/~stj2/nsc/emu_freebsd.html > > PC

Re: SMBFS with AMD64

2005-01-13 Thread Kris Kennaway
On Thu, Jan 13, 2005 at 03:31:22PM -0800, Thomas M. Skeren III wrote: > Kris Kennaway wrote: > > >On Thu, Jan 13, 2005 at 03:05:02PM -0800, Thomas M. Skeren III wrote: > > > > > >>Trying to compile AMD64 with smbfs. > >> > >>Added > >>

Re: SMBFS with AMD64

2005-01-13 Thread Kris Kennaway
On Thu, Jan 13, 2005 at 03:05:02PM -0800, Thomas M. Skeren III wrote: > Trying to compile AMD64 with smbfs. > > Added > > optionsSMBFS > options NETSMB > > got a lot of errors like this: > > > smb_usr.o(.text+0x5ae): In function `smb_usr_simplerequest': > : undefined reference to `md_g

Re: Infinite loop in tcp_output on RELENG_5

2004-10-09 Thread Kris Kennaway
On Sat, Oct 09, 2004 at 12:40:38PM +0400, Gleb Smirnoff wrote: > On Fri, Oct 08, 2004 at 08:39:00PM -0700, Kris Kennaway wrote: > K> This might be related to SACK, which is one of the situations where we > K> loop back to the again label, but that's just a guess. >

  1   2   >