On Thu, 9 Oct 2003, Evan Dower wrote:
I ran with SCHED_ULE for a couple days recently and had trouble beyond just
sluggishness. When doing really intensive tasks such as buildworld or
installworld, the computer would actually stall. The first time was
immediately after booting single user
On Thu, 9 Oct 2003, Sheldon Hearn wrote:
On (2003/10/09 00:28), Scott Sipe wrote:
Anything that seems disk intensive: bzip2 (unbzip2ing one big file makes
this happen), making world, building ports, etc makes my X environment
practically unusable. Mouse stutters, reaction times is very
On Wed, 1 Oct 2003, Garrett Wollman wrote:
I'm working on getting the AFS client to work under FreeBSD. I just
compiled a -current kernel with DEBUG_VFS_LOCKS, and before I could
even load the AFS module I had the system stop with the following
locking assertion:
getdirtybuf: 0xc2678000
On Tue, 30 Sep 2003, Aggelos Economopoulos wrote:
On Monday 29 September 2003 08:05, Jeff Roberson wrote:
On Sun, 28 Sep 2003, Arjan van Leeuwen wrote:
[...]
It happens when compiling stuff, when loading complicated pages in
Mozilla Firebird, and when logging out of GNOME 2.4
There seems to have been some regression in the interactivity of
SCHED_ULE since I was last measuring it. I'll send a follow up mail when
I have found and fixed the issue.
Thanks,
Jeff
___
[EMAIL PROTECTED] mailing list
On Sun, 28 Sep 2003, Morten Rodal wrote:
On Sat, Sep 27, 2003 at 11:31:25PM -0400, Jeff Roberson wrote:
On Sat, 27 Sep 2003, Morten Rodal wrote:
It has improved quite a bit lately, and is now also working with KSE.
However, the mouse will get sluggish whenever the computer is under
On Sun, 28 Sep 2003, Arjan van Leeuwen wrote:
On Sunday 28 September 2003 14:38, Matt wrote:
Morten Rodal wrote:
On Sun, Sep 28, 2003 at 01:26:24PM +0100, Matt wrote:
Morten Rodal wrote:
On Sat, Sep 27, 2003 at 11:31:25PM -0400, Jeff Roberson wrote:
On Sat, 27 Sep 2003, Morten Rodal
On Sat, 27 Sep 2003, Morten Rodal wrote:
On Sat, Sep 27, 2003 at 06:47:54PM +0200, Roderick van Domburg wrote:
Hello everyone,
I was wondering about the status of the ULE scheduler. Is it very
experimental still or is it reasonably suitable for everyday (i.e.
non-mission-critical) use?
On Wed, 17 Sep 2003, Florian C. Smeets wrote:
Hi.
I get this panic on a system with kernel/world from 03 September.
Usually i only run X and xawtv on that system but when i wanted to make
world today i got the panic:
This was fixed recently. Can you cvsup and rebuild?
Kris Kennaway
On Tue, 2 Sep 2003, Christian Brueffer wrote:
Hi,
got a panic with a kernel from sources around September 1st, 8pm.
Dump and debugging kernel available for further debugging.
cg@ got the same panic on his machine.
This is probably my fault. I will look into it tonight. Until then you
On Tue, 2 Sep 2003, Kevin Oberman wrote:
Date: Tue, 2 Sep 2003 10:53:43 +0200
From: Jan Srzednicki [EMAIL PROTECTED]
Sender: [EMAIL PROTECTED]
On Mon, Sep 01, 2003 at 07:53:48PM +0300, Lefteris Chatzibarbas wrote:
Hello,
I have a problem with kernels, built the last couple of
I found the bug that I introduced around the 29th of august. It is fixed
in ffs_softdep.c rev 1.143. Truely, most of the leg work was done by
tegge. I just produced and tested a patch. This completes a buildworld
with 128M of memory now, whereas before it just completed with 64m and
512m.
On Sun, 31 Aug 2003, Christian Brueffer wrote:
On Sun, Aug 31, 2003 at 05:28:10AM -0400, Jeff Roberson wrote:
On Sun, 31 Aug 2003, Christian Brueffer wrote:
Hi,
got a panic on my server tonight. Coredump available for further debuggung.
FreeBSD haakonia.hitnet.rwth-aachen.de
On Sun, 31 Aug 2003, Christian Brueffer wrote:
Hi,
got a panic on my server tonight. Coredump available for further debuggung.
FreeBSD haakonia.hitnet.rwth-aachen.de 5.1-CURRENT FreeBSD 5.1-CURRENT #6: Thu Aug
28 00:16:19 CEST 2003
[EMAIL PROTECTED]:/usr/obj/usr/src/sys/LORIEN i386
On Thu, 14 Aug 2003, Adam Migus wrote:
Andrew Gallatin wrote:
Adam Migus writes:
Folks,
While doing some performance analysis (doing make -j5 buildkernel)
on a set of 14 kernels I've hit one using the SCHED_ULE scheduler
that hangs. It happens every time but not necessarily in
On Wed, 30 Jul 2003 [EMAIL PROTECTED] wrote:
The indication of this is that the g_bio zone does not return to
zero USED as it should.
It looks like z-uz_cachefree is slightly out of date (updated in
zone_timout() every 20th second) and often too low (not taking the
z-uz_full_bucket list
On Wed, 9 Jul 2003, Kenneth Culver wrote:
AH so it's direct DSL with either a fixed IP or DHCP or similar?
Yep, basically I don't have a DSL modem, I have an Ethernet to ATM bridge
(using AAL5 encapsulation I believe) running over the DSL. I have 2 fixed
IP's, and in my normal
Squashed the bug that was causing panics with nice processes on SMP ULE.
Thanks,
Jeff
-- Forwarded message --
Date: Mon, 7 Jul 2003 23:19:40 -0700 (PDT)
From: Jeff Roberson [EMAIL PROTECTED]
To: [EMAIL PROTECTED], [EMAIL PROTECTED], [EMAIL PROTECTED]
Subject: cvs commit: src/sys
Excellent debugging. Can you tell me whats in kseq_cpu[0] and
kseq_cpu[1]? I think I may know what the problem is. Do you have some
negative niced processes or some positive nice processes?
On Thu, 3 Jul 2003, Richard Todd wrote:
Hi. Last night I upgraded to the most recent -current source
On Mon, 30 Jun 2003, Andrew Gallatin wrote:
Jeff Roberson writes:
On Fri, 27 Jun 2003, John Baldwin wrote:
On 27-Jun-2003 Andrew Gallatin wrote:
Jeff Roberson writes:
Can you call kseq_print(0) and kseq_print(1) from ddb?
I found
On Fri, 27 Jun 2003, John Baldwin wrote:
On 27-Jun-2003 Andrew Gallatin wrote:
Jeff Roberson writes:
Can you call kseq_print(0) and kseq_print(1) from ddb?
I found a different problem which is nearly as interesting.
Note that ps thinks sysctl is on cpu 255...
#define
On Fri, 27 Jun 2003, Andrew Gallatin wrote:
Jeff,
On an SMP box I have, which is really a p4 box with one physical
CPU, and 2 HTT cores, I've seen some strange behaviour with ULE.
With ULE enabled, I've see jobs wedge for no apparent reason.
Some examples are fsck, dhclient and gcc.
Can
On Wed, 25 Jun 2003, Ian Freislich wrote:
Hi
About 4.5 minutes after rebooting with a SCHED_ULE kernel (I give
ULE a go every few months), top started looking really wierd (the
CPU % just kept on accumulating for each process). Before dnetc
started, httpd showed 17% CPU, but the system was
On Wed, 18 Jun 2003, Wiktor Niesiobedzki wrote:
On Tue, Jun 17, 2003 at 03:51:32PM -0400, Jeff Roberson wrote:
I am still not able to reproduce this. Can you update your sources? I
commited some code just now that removed an external dependency from
sched_nice(). This should make
--
Date: Mon, 16 Jun 2003 23:39:51 -0700 (PDT)
From: Jeff Roberson [EMAIL PROTECTED]
To: [EMAIL PROTECTED], [EMAIL PROTECTED], [EMAIL PROTECTED]
Subject: cvs commit: src/sys/kern sched_ule.c
jeff2003/06/16 23:39:51 PDT
FreeBSD src repository
Modified files:
sys/kern
On Mon, 16 Jun 2003, Wiktor Niesiobedzki wrote:
On Fri, Apr 11, 2003 at 04:40:17PM -0400, Jeff Roberson wrote:
On Fri, 11 Apr 2003, Steve Kargl wrote:
I started to recompile the kernel and while sitting here decided
to load linux-mozilla. The system rebooted before linux-mozilla
On Mon, 16 Jun 2003, Wiktor Niesiobedzki wrote:
I'm seeing quite similar panic, when I do renice to lower (negative) value:
(Negative nice count.)
(kgdb) bt
#0 doadump () at ../../../kern/kern_shutdown.c:240
#1 0xc018b374 in boot (howto=260) at ../../../kern/kern_shutdown.c:372
#2
On Tue, 17 Jun 2003, Wiktor Niesiobedzki wrote:
On Tue, Jun 17, 2003 at 02:53:36AM -0400, Jeff Roberson wrote:
The sources are from today. I also noticed, that 5.1-BETA (build around 9th of
May) is working correctly.
Also: I've noticed a strange behaviour - if I do nice -n -15
On Fri, 13 Jun 2003, Terry Lambert wrote:
John Hay wrote:
On a 5.1-RELEASE machine I have been able to cause a panic like this:
panic: kmem_malloc(4096): kmem_map too small: 28610560 total allocated
Manually tune your system. This panic results from the fact
that zone allocations with
I found the culprit. It was an off by one error. rev 1.35 has the fix.
Thanks,
Jeff
___
[EMAIL PROTECTED] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-current
To unsubscribe, send any mail to [EMAIL PROTECTED]
I'm currently debugging ULE issues. I heard reports of panics on SMP
which I am not able to reproduce. If any one knows of panics with recent
kernels on SMP or any other ULE issues please mail me privately.
Thanks!
Jeff
___
[EMAIL PROTECTED] mailing
On Tue, 3 Jun 2003, Terry Lambert wrote:
Scott Long wrote:
Bryan Liesner wrote:
It's very hard to imagine Jeff's patches causing a problem at the point
that the PR mentions. Have you confirmed the problem in a kernel that
was build in a totally clean environment?
The changed code is
If you have had issues with libthr on SMP or umtx panics, the following
patch may solve these issues.
http://www.chesapeake.net/~jroberson/umtxlocks.diff
This patch fixes several race conditions and other issues with umtx.
Thanks,
Jeff
___
[EMAIL
On Wed, 2 Apr 2003, Terry Lambert wrote:
Robert Watson wrote:
You should notice marked interactivity and UI latency improvements with
threaded GUI apps over libc_r because GUI threads will generally no longer
be blocked when disk I/O and blocking I/O occurs. For example,
applications
On Wed, 2 Apr 2003, Juli Mallett wrote:
* De: Jeff Roberson [EMAIL PROTECTED] [ Data: 2003-04-02 ]
[ Subjecte: Re: libthr and 1:1 threading. ]
On Wed, 2 Apr 2003, Terry Lambert wrote:
Also, any ETA on the per process signal mask handing bug in
libthr? Might not be safe to convert
On Wed, 2 Apr 2003, Julian Elischer wrote:
On Wed, 2 Apr 2003, Juli Mallett wrote:
* De: Jeff Roberson [EMAIL PROTECTED] [ Data: 2003-04-02 ]
[ Subjecte: Re: libthr and 1:1 threading. ]
On Wed, 2 Apr 2003, Terry Lambert wrote:
Also, any ETA on the per process signal mask
On Wed, 2 Apr 2003, Daniel Eischen wrote:
On Wed, 2 Apr 2003, Jeff Roberson wrote:
On Wed, 2 Apr 2003, Julian Elischer wrote:
On Wed, 2 Apr 2003, Juli Mallett wrote:
* De: Jeff Roberson [EMAIL PROTECTED] [ Data: 2003-04-02 ]
[ Subjecte: Re: libthr and 1:1
On Wed, 2 Apr 2003, Daniel Eischen wrote:
[ CC list trimmed somewhat ]
On Wed, 2 Apr 2003, Jeff Roberson wrote:
On Wed, 2 Apr 2003, Daniel Eischen wrote:
On Wed, 2 Apr 2003, Jeff Roberson wrote:
Then set the mask to be the same on all threads in the process. The mask
is set
On Wed, 2 Apr 2003, Gordon Tetlow wrote:
I think it was a libthr linked app after I killed it:
Yeah, this is a problem with the thread single exit and suspend code. I
haven't fixed it yet. Thanks for the report.
lock order reversal
1st 0xc679d248 process lock (process lock) @
On Wed, 2 Apr 2003, Terry Lambert wrote:
Peter Wemm wrote:
No. It gives the ability for a thread to block on a syscall without
stalling the entire system. Just try using mysqld on a system using libc_r
and heavy disk IO. You can't select() on a read() from disk. Thats the
ultimate
On Thu, 3 Apr 2003, Daniel O'Connor wrote:
On Wed, 2 Apr 2003 16:24, Jeff Roberson wrote:
It probably still needs some tweaking but it seems to be MUCH better now.
New algorithm entirely.
nice +20 processes will not run if anything else wants to.
idleprio is still not working
On Wed, 2 Apr 2003, Bruce Evans wrote:
On Wed, 2 Apr 2003, Sheldon Hearn wrote:
On (2003/04/02 01:54), Jeff Roberson wrote:
It probably still needs some tweaking but it seems to be MUCH better now.
New algorithm entirely.
nice +20 processes will not run if anything else wants
I'm letting you all know since I wont be able to look at thr bugs for a
week.
Also, I'm very interested in hearing comments on ULE when I get back.
Cheers,
Jeff
___
[EMAIL PROTECTED] mailing list
On Thu, 3 Apr 2003, Bruce Evans wrote:
On Wed, 2 Apr 2003, Jeff Roberson wrote:
On Wed, 2 Apr 2003, Bruce Evans wrote:
... The scaling of niceness was re-broken in -current about 3
years ago to fix the priority inversion problems. This is with
SCHED_4BSD. SCHED_ULE has larger
On Thu, 3 Apr 2003, Bruce Evans wrote:
On Thu, 3 Apr 2003, Daniel O'Connor wrote:
On Wed, 2 Apr 2003 16:24, Jeff Roberson wrote:
It probably still needs some tweaking but it seems to be MUCH better now.
New algorithm entirely.
nice +20 processes will not run if anything else
On Thu, 3 Apr 2003, Vallo Kallaste wrote:
On Wed, Apr 02, 2003 at 07:35:59PM -0500, Jeff Roberson
[EMAIL PROTECTED] wrote:
Do you know of any problem other than idlepri breakage? I just fixed
that. I'm about to get on a plane so I don't have time to benchmark it.
If you have a chance
On Tue, 1 Apr 2003, Scott Long wrote:
Jeff Roberson wrote:
I have commited libthr. To try this out you'll need to do the following
Excellent job Jeff and Jon, thanks a lot!
Is anyone working on getting full Apache2 support for this? Also,
linking the Java 1.3 and 1.4 ports
It probably still needs some tweaking but it seems to be MUCH better now.
New algorithm entirely.
nice +20 processes will not run if anything else wants to.
idleprio is still not working correctly. bde reports that this causes a
3% perf degradation for buildworld.
I'd appreciate feedback from
The kernel components for the 1:1 threading implementation are in the
tree. This includes the thr system calls, the umtx implementation, and
all of the signal changes.
I will commit the library shortly. This is all 'beta' quality. It runs
mozilla and openoffice without issue. There are known
I have commited libthr. To try this out you'll need to do the following
1. cvsup
2. rebuild world and kernel
3. install world and kernel
4. build libthr from src/lib/libthr
5. Either replace /usr/lib/libc_r.so.5 with /usr/lib/libthr.so.1 or
relink your applications against libthr.so.1
This
I'm looking for some poeple to try out my threading patches. I'm only
looking for people to make sure that there have been no reversions in
signal handling. I'm not ready for people to test out the actual
threading interfaces.
You should notice no changes in application behavior or system
I pooched the patch. It's updated now.
On Tue, 25 Mar 2003, Jeff Roberson wrote:
I'm looking for some poeple to try out my threading patches. I'm only
looking for people to make sure that there have been no reversions in
signal handling. I'm not ready for people to test out the actual
Got that crash again, with sync-on-panic disabled. The interesting thing
is that the stack trace might be corrupted or inaccurate (maybe some tail
recursion optimisation or inlining is going on around): although it seems
to indicate that the panic is the one from bwrite: need chained iodone
On Mon, 17 Mar 2003, Brooks Davis wrote:
On Mon, Mar 17, 2003 at 12:45:15PM -0800, Julian Elischer wrote:
I might add that the test filesystem was 95% full with about 8,000,000
directories on it. It was populated with multiple copies of /bin
and /etc as a test set :-)
How much like
On Mon, 17 Mar 2003, Andrew Gallatin wrote:
I'm seeing the following panic under heavy NFS client usage on an SMP
w/kernel sources from Weds. evening. Has this been fixed?
Thanks,
Drew
I believe that is fixed in nfs_vnops.c 1.200.
panic: lockmgr: locking against myself
cpuid = 0;
On Mon, 17 Mar 2003, Terry Lambert wrote:
Jeff Roberson wrote:
On Mon, 17 Mar 2003, Brooks Davis wrote:
I am still intrested in improvements to fsck since I'm planning to buy
several systems with two 1.4TB IDE RAID5 arrays in them soon.
For these types of systems doing a block
disable sync on panic? The buf must have been modified. That
section of code is never entered with b_xflags == 0. The contents of the
buf just dont make sense with the panic..
Cheers,
Jeff
On Sun, 16 Mar 2003, Morten Rodal wrote:
On Sun, Mar 16, 2003 at 02:46:13AM -0500, Jeff Roberson wrote
On Sat, 15 Mar 2003, Morten Rodal wrote:
On Fri, Mar 14, 2003 at 06:47:27PM +0100, Morten Rodal wrote:
[snip the parent post]
I just got another one of these. This time it didn't double panic
while syncing the disks. I've been getting this quite often now,
almost daily. If there is
On Tue, 11 Mar 2003, Doug Barton wrote:
FYI, -bugs is not a discussion list.
On Tue, 11 Mar 2003, Attila Nagy wrote:
The following reply was made to PR kern/49079; it has been noted by GNATS.
From: Attila Nagy [EMAIL PROTECTED]
To: Martin Machacek [EMAIL PROTECTED]
Cc: [EMAIL
On Thu, 13 Mar 2003, Norikatsu Shigemura wrote:
On Thu, 13 Mar 2003 01:23:00 -0500 (EST)
Jeff Roberson [EMAIL PROTECTED] wrote:
How much memory is in your machine? Can you go back to an earlier date
and see if this is still a problem? Are you doing anything else with the
machine while
On Thu, 13 Mar 2003, Julian Elischer wrote:
I got this today on a kernel checked out on the 10th.
Can you please disable sync on panic and get a dump from the first panic?
Then print out the contents of the buf in that stack for me? A couple of
people have seen this now but I have not been
On Fri, 14 Mar 2003, Donn Miller wrote:
Can you please disable sync on panic and get a dump from the first panic?
Then print out the contents of the buf in that stack for me? A couple of
people have seen this now but I have not been able to repro it.
Thanks for the report. Please
On Wed, 12 Mar 2003, Thomas Quinot wrote:
Le 2003-03-12, Jeff Roberson écrivait :
Can you please print bp? I'd like to know what all of the members are. A
cluster buf should NEVER have BX_BKGRDWRITE set. This is totally bogus.
(kgdb) fr
#11 0xc0232072 in bwrite (bp=0xce5313e0
On Thu, 13 Mar 2003, Norikatsu Shigemura wrote:
Big file like OOo_1.0.2_source.tar.bz2 became broken with making
openoffice in my environment.
How much memory is in your machine? Can you go back to an earlier date
and see if this is still a problem? Are you doing anything else
On Thu, 13 Mar 2003, Jeff Roberson wrote:
On Thu, 13 Mar 2003, Norikatsu Shigemura wrote:
Big file like OOo_1.0.2_source.tar.bz2 became broken with making
openoffice in my environment.
How much memory is in your machine? Can you go back to an earlier date
and see
On Thu, 13 Mar 2003, Jeff Roberson wrote:
On Thu, 13 Mar 2003, Norikatsu Shigemura wrote:
Big file like OOo_1.0.2_source.tar.bz2 became broken with making
openoffice in my environment.
How much memory is in your machine? Can you go back to an earlier date
and see
I've trimmed to the relavent part of the stack.
On Tue, 11 Mar 2003, Thomas Quinot wrote:
#11 0xc0232072 in bwrite (bp=0xce5313e0) at /usr/src/sys/kern/vfs_bio.c:795
#12 0xc0232a7c in bawrite (bp=0x0) at /usr/src/sys/kern/vfs_bio.c:1138
#13 0xc023a02b in cluster_wbuild (vp=0xc4a21124,
Found a bug. Please update your source from the same location if you
previously applied this patch.
On Sun, 2 Mar 2003, Jeff Roberson wrote:
I have a patch that should clear up buf locking issues and race conditions
in vfs_cluster.c. Since this code is so tricky I'd like to have a few
I'm using SCHED_ULE on my laptop now. My recent round of fixes seems to
have helped out. I'm getting good interactive performance. I'm doing the
following:
nice -5'd for (;;) {} process.
make -j4 buildworld
Mozilla, pine, irc, screen, vi, etc.
All interactive tasks are very responsive. My
I have a patch that should clear up buf locking issues and race conditions
in vfs_cluster.c. Since this code is so tricky I'd like to have a few
people test it. You should notice no difference in your system
performance or behavior.
Please see: http://www.chesapeake.net/~jroberson/cluster.diff
Please try this:
Index: nfs_vnops.c
===
RCS file: /home/ncvs/src/sys/nfsclient/nfs_vnops.c,v
retrieving revision 1.195
diff -u -r1.195 nfs_vnops.c
--- nfs_vnops.c 25 Feb 2003 03:37:47 - 1.195
+++ nfs_vnops.c 25 Feb 2003
This patch worked.
On Tue, 25 Feb 2003, Jeff Roberson wrote:
Please try this:
Index: nfs_vnops.c
===
RCS file: /home/ncvs/src/sys/nfsclient/nfs_vnops.c,v
retrieving revision 1.195
diff -u -r1.195 nfs_vnops.c
--- nfs_vnops.c 25
On Mon, 10 Feb 2003, Kris Kennaway wrote:
*Grump* I can't get my boxes to stay up more than a few
minutes..evidently this code was not tested prior to commit.
So much for getting work done on the package cluster today.
It was tested. I ran it on my desktop and did several buildworlds on an
On Mon, 10 Feb 2003, Kris Kennaway wrote:
It was tested. I ran it on my desktop and did several buildworlds on an
smp machine. I should have let it kick around for a bit longer than a few
days, I agree. I will commit the fix in just a moment.
Thanks!
Yeah, I really am sorry about
On Mon, 10 Feb 2003, Kris Kennaway wrote:
I gave ULE another try just now, following your recent commits, and
I'm seeing even worse problems:
At boot time when the X server is loading, disk activity occurs
briefly about once every 2 seconds; the mouse is active briefly at the
same time, and
On Tue, 4 Feb 2003, Kris Kennaway wrote:
On Tue, Feb 04, 2003 at 09:54:23PM -0800, Steve Kargl wrote:
On Tue, Feb 04, 2003 at 09:38:18PM -0800, Kris Kennaway wrote:
I just booted a kernel with SCHED_ULE. It looks like there's a pretty
serious bug:
PID USERNAME PRI NICE SIZE
I'm about to commit code that will make one of :
options SCHED_4BSD
or
options SCHED_ULE
mandatory. This will go in a few hours from now. I will update all of
the standard config files to account for this change. SCHED_4BSD selects
the old scheduler in case you're wondering. Failure to
Ok, this has been commited. Expect build breakage if you don't add one of
these options or use GENERIC.
Cheers,
Jeff
On Sun, 26 Jan 2003, Jeff Roberson wrote:
I'm about to commit code that will make one of :
options SCHED_4BSD
or
options SCHED_ULE
mandatory. This will go in a few
On Tue, 26 Nov 2002, Philip Paeps wrote:
I was also starting to think in the NFS direction. It's one of the reasons I
use Maildirs. My setup is a bit convoluted too. This machine (the one now
running -current and hanging) plays NFS server. The mailserver mounts the
maildir and writes
On Sat, 9 Nov 2002, Terry Lambert wrote:
Jeff Roberson wrote:
[ ... patch ... looks right to me, but I wonder if it opens a race
window in the vput() blocks case ...either way, it's no
worse than the code it replaces... ]
I'll look into it some more, but it looks like someone
On Fri, 8 Nov 2002, Andrea Campi wrote:
Hi all,
for months now I've been having a reproducible hang under load
(make -j4 buildworld on a uniprocessor with plenty of RAM). I transcribed
some info which might be useful to debug it; it seems to me this is a
deadlock (am I right?). I'll leave
On Mon, 28 Oct 2002, Terry Lambert wrote:
John Baldwin wrote:
Yes. This means that you don't need to even look at v_tag to see
if it is a UFS vnode or not. What does libgtop want with
device and inode numbers anways? Does it actually do anything
useful with them or does it just print
On Mon, 28 Oct 2002, John Baldwin wrote:
Terry is right. It needs to be the same inode number that is reported by
stat and getdirents. It's unfortunate that you can't do a getattr or stat
based on the address of the vnode. I have actually used and relied on this
behavior in the past.
On Wed, 23 Oct 2002, Seigo Tanimura wrote:
On Wed, 23 Oct 2002 16:44:06 +1000 (EST),
Bruce Evans [EMAIL PROTECTED] said:
Incidentally, Solaris 7 on sun4u reserves a space of 256MB in the KVM
according to Solaris Internals. On i386 (x86), the size is only 4MB.
Not sure whether they use
On Wed, 16 Oct 2002, Ben Stuyts wrote:
I just got the same panic without your patch. (I wanted to verify that it
was still panic-ing with the latest src tree.) I am now building a kernel
with your patch.
I'll also run your vmstat script that you posted in a similar thread. One
of the big
On Tue, 15 Oct 2002, Makoto Matsushita wrote:
I'm now trying Terry's patch (just rebuilding a kernel).
jroberson You are using 100mb of KVA for malloc(9)? Are you certain
jroberson that you don't have a memory leak?
Maybe there's a chance of a memory leakage by GLOBAL, but I don't sure.
On Mon, 14 Oct 2002, Makoto Matsushita wrote:
After upgrading my 5-current box (as of late September 2002), the
kernel panics periodically with following message:
panic: kmem_malloc(4096): kmem_map too small: 107651072 total allocated
The number '4096' and '107651072' is always the
On Sat, 12 Oct 2002, Kris Kennaway wrote:
I'm having a strange problem with my -current box: I am running the
bfbtester port on system utilities, which basically forks 100 copies
of the binary at once to test different options. The problem is that
sometimes the -current system becomes unable
On Fri, 11 Oct 2002, Terry Lambert wrote:
Ben Stuyts wrote:
Is there a way to check the free list of the kernel? Maybe I can find out
what action triggers eating al its memory.
Maybe you should just increase the size of your kmem_map? I'll look into
a better fix but that should do it
On Wed, 2 Oct 2002, Don Lewis wrote:
Version 1.114 of nfs_bio.c added a call to ASSERT_VOP_LOCKED() to
nfs_doio(). I've been running a kernel with the DEBUG_VFS_LOCKS option
and I can consistently get this assertion to fail by running mozilla
with an nfs mounted home directory. The DDB
On Sat, 5 Oct 2002, Brian F. Feldman wrote:
Steven G. Kargl [EMAIL PROTECTED] wrote:
The source tree was retrieved by cvsup
at 21:47 (PST) on Oct 4.
This is a non-GEOM and non-acpi kernel.
I have the core and kernel.debug, so any
further postmortem is possible.
I think the
On Tue, 8 Oct 2002, Dag-Erling Smorgrav wrote:
Makefile, line 4194: warning: duplicate script for target geom_bsd.o ignored
cc1: warnings being treated as errors
/h/des/src/sys/dev/advansys/adv_pci.c: In function `adv_pci_attach':
/h/des/src/sys/dev/advansys/adv_pci.c:197: warning: overflow
On Thu, 26 Sep 2002, Danny Braniss wrote:
if this is of any help:
panic: vn_finished_write: neg cnt
Debugger(panic)
Stopped at Debugger+0x54: xchgl %ebx,in_Debugger.0
db trace
Debugger(c04b2d1c,c05664e0,c04bcd6b,cb4607d8,1) at Debugger+0x54
The next one will pass.
On Tue, 24 Sep 2002, Dag-Erling Smorgrav wrote:
--
Rebuilding the temporary build tree
--
stage 1: bootstrap tools
On Wed, 25 Sep 2002, Ollivier Robert wrote:
VAIO Z600TEK, PIII/700, 20 GB, 256 MB.
cvsup from three hours ago, whicle rebooting I get this:
panic: vrele: missed vn_close
Debugger(panic)
Stopped at Debugger+0x45:xchgl%ebx,in_Debugger.0
db trace
Debugger at Debugger+0x45
On Wed, 25 Sep 2002, walt wrote:
Michael Hostbaek wrote:
I just build latest -CURRENT on my laptop.
The error is:
panic: vrele: negative ref cnt
Debugger(panic)
Stopped at Debugger+0x54: xchgl %ebx,in_Debugger.0
I did the following:
After bootup - logged in as root.
On Wed, 25 Sep 2002, David Wolfskill wrote:
panic: vrele: missed vn_close
cpuid = 0; lapic.id =
Debugger(panic)
Stopped at Debugger+0x55: xchgl %ebx,in_Debugger.0
db tr
Debugger(c036903a,0,c0372831,d7b9cb70,1) at Debugger+0x55
panic(c0372831,0,c03724c2,810,c4439200) at
On Wed, 25 Sep 2002, Don Lewis wrote:
I tried booting a kernel with lock checking enabled and got the
following panic:
panic: mutex vnode interlock owned at vnode_if.h:24
Yeah, sorry, there was a bit of my patch that I forgot to commit. It's in
there now.
Thanks!
Jeff
To Unsubscribe:
The VFS panic that was introduced in my recent commits has been fixed. I
accidentally commited extra stuff from my tree that was not entirely
correct.
Thank you all for the error reports and debugging assistance.
Jeff
To Unsubscribe: send mail to [EMAIL PROTECTED]
with unsubscribe
cc1: warnings being treated as errors
/usr/src/sys/kern/vfs_mount.c: In function `checkdirs':
/usr/src/sys/kern/vfs_mount.c:1141: warning: implicit declaration of function
`vrefcnt'
Oops, I commited this file before I commited a dependency. Please cvsup
again. Specifically, you need the
101 - 200 of 223 matches
Mail list logo