Re: drm-current-kmod panics

On Thu, 19 Dec 2019, Hans Petter Selasky wrote: On 2019-12-19 19:40, Cy Schubert wrote: In message , Hans Petter Sela sky writes: On 2019-12-19 17:50, Cy Schubert wrote: Has anyone else had these since Dec 9? <4>WARN_ON(!mutex_is_locked(>lock))WARN_ON(!mutex_is_locked(> lock)) panic: page

object locking patch series going into current later today

Hello, As part of the NUMA and VM concurrency work I have refactored the way page busy state works in order to improve vm object concurrency. This is a six patch series that has been tested more in totality than in parts. I will be committing them back to back after a final universe build

Re: Strange ARC/Swap/CPU on yesterday's -CURRENT

On Sun, 11 Mar 2018, Matthew D. Fuller wrote: On Sun, Mar 11, 2018 at 10:43:58AM -1000 I heard the voice of Jeff Roberson, and lo! it spake thus: First, I would like to identify whether the wired memory is in the buffer cache. Can those of you that have a repro look at sysctl vfs.bufspace

Re: Strange ARC/Swap/CPU on yesterday's -CURRENT

On Sun, 11 Mar 2018, Mark Millard wrote: As I understand, O. Hartmann's report ( ohartmann at walstatt.org ) in: https://lists.freebsd.org/pipermail/freebsd-current/2018-March/068806.html includes a system with a completely non-ZFS context: UFS only. Quoting that part: This is from a APU,

Re: Strange ARC/Swap/CPU on yesterday's -CURRENT

On Sun, 11 Mar 2018, O. Hartmann wrote: Am Wed, 7 Mar 2018 14:39:13 +0400 Roman Bogorodskiy schrieb: Danilo G. Baio wrote: On Tue, Mar 06, 2018 at 01:36:45PM -0600, Larry Rosenman wrote: On Tue, Mar 06, 2018 at 10:16:36AM -0800, Rodney W. Grimes wrote: On Tue, Mar

Re: FreeBSD has a politics problem

Hi John, First of all this is really not an appropriate forum for this discussion. It is really unfortunate that these emails were leaked. However, I think if you take a careful look at them, you will find a couple examples of hostility but the great preponderance of them are quite

Re: New NUMA support coming to CURRENT

involved feature. Thanks, Jeff On Tue, 9 Jan 2018, Jeff Roberson wrote: Hello folks, I am working on merging improved NUMA support with policy implemented by cpuset(2) over the next week. This work has been supported by Dell/EMC's Isilon product division and Netflix. You can see some

New NUMA support coming to CURRENT

Hello folks, I am working on merging improved NUMA support with policy implemented by cpuset(2) over the next week. This work has been supported by Dell/EMC's Isilon product division and Netflix. You can see some discussion of these changes here: https://reviews.freebsd.org/D13403

Re: UMA cache back pressure

On Mon, 18 Nov 2013, Alexander Motin wrote: Hi. I've created patch, based on earlier work of avg@, to add back pressure to UMA allocation caches. The problem of physical memory or KVA exhaustion existed there for many years and it is quite critical now for improving systems performance

Re: UMA cache back pressure

On Mon, 18 Nov 2013, Alexander Motin wrote: On 18.11.2013 21:11, Jeff Roberson wrote: On Mon, 18 Nov 2013, Alexander Motin wrote: I've created patch, based on earlier work of avg@, to add back pressure to UMA allocation caches. The problem of physical memory or KVA exhaustion existed

Re: UMA cache back pressure

in a different way. Thanks, -adrian On 18 November 2013 11:55, Alexander Motin m...@freebsd.org wrote: On 18.11.2013 21:11, Jeff Roberson wrote: On Mon, 18 Nov 2013, Alexander Motin wrote: I've created patch, based on earlier work of avg@, to add back pressure to UMA allocation caches. The problem

Re: Early drop to debugger with DEBUG_MEMGUARD

On Mon, 12 Aug 2013, David Wolfskill wrote: On Tue, Aug 13, 2013 at 08:29:44AM +0300, Konstantin Belousov wrote: ... The r254025 indeed introduced the problem, and Davide pointed out you a workaround for the assertion triggering. Right; I tried one of those -- I hope I got it right...

Re: panic: UMA: Increase vm.boot_pages with 32 CPUs

On Mon, 12 Aug 2013, Colin Percival wrote: Hi all, A HEAD@254238 kernel fails to boot in EC2 with panic: UMA: Increase vm.boot_pages on 32-CPU instances. Instances with up to 16 CPUs boot fine. I know there has been some mucking about with VM recently -- anyone want to claim this, or

Re: Early drop to debugger with DEBUG_MEMGUARD

On Tue, 13 Aug 2013, Jeff Roberson wrote: On Mon, 12 Aug 2013, David Wolfskill wrote: On Tue, Aug 13, 2013 at 08:29:44AM +0300, Konstantin Belousov wrote: ... The r254025 indeed introduced the problem, and Davide pointed out you a workaround for the assertion triggering. Right; I tried one

Re: panic: UMA: Increase vm.boot_pages with 32 CPUs

On Tue, 13 Aug 2013, Jim Harris wrote: On Tue, Aug 13, 2013 at 3:05 PM, Jeff Roberson jrober...@jroberson.net wrote: On Mon, 12 Aug 2013, Colin Percival wrote: Hi all, A HEAD@254238 kernel fails to boot in EC2 with panic: UMA: Increase

Re: Kernel build fails on ARM: Cannot fork: Cannot allocate memory

On Sun, 23 Jun 2013, Ruslan Bukin wrote: On Sun, Jun 23, 2013 at 07:50:40PM +0300, Konstantin Belousov wrote: On Sun, Jun 23, 2013 at 08:44:25PM +0400, Ruslan Bukin wrote: On Sun, Jun 23, 2013 at 07:16:17PM +0300, Konstantin Belousov wrote: On Sun, Jun 23, 2013 at 06:43:46PM +0400, Ruslan

Re: Kernel build fails on ARM: Cannot fork: Cannot allocate memory

On Fri, 21 Jun 2013, Zbyszek Bodek wrote: On 21.06.2013 01:56, Jeff Roberson wrote: On Thu, 20 Jun 2013, Jeff Roberson wrote: On Wed, 19 Jun 2013, Zbyszek Bodek wrote: Hello, I've been trying to compile the kernel on my ARMv7 platform using the sources from the current FreeBSD HEAD. make

Re: Kernel build fails on ARM: Cannot fork: Cannot allocate memory

On Wed, 19 Jun 2013, Zbyszek Bodek wrote: Hello, I've been trying to compile the kernel on my ARMv7 platform using the sources from the current FreeBSD HEAD. make buildkernel . -j5 1/2 builds fails in the way described below:

Re: Kernel build fails on ARM: Cannot fork: Cannot allocate memory

On Thu, 20 Jun 2013, Jeff Roberson wrote: On Wed, 19 Jun 2013, Zbyszek Bodek wrote: Hello, I've been trying to compile the kernel on my ARMv7 platform using the sources from the current FreeBSD HEAD. make buildkernel . -j5 1/2 builds fails in the way described below

Re: Panic @r251934: _mtx_lock_sleep: recursed on non-recursive mutex vm map (system) @ /usr/src/sys/vm/vm_kern.c:430

On Tue, 18 Jun 2013, David Wolfskill wrote: This is on my (i386) build machine; laptop (also i386) did not exhibit the symptom. I had hand-applied r251953 (to get through buildworld). After installworld, mergemaster -i, make delete-old, I rebooted, and this is what I saw: This is my fault.

Re: [head tinderbox] failure on i386/i386

On Sun, 12 May 2013, David Wolfskill wrote: It appears that the issue is i386- (or 32-bit-) specific. On Sun, May 12, 2013 at 07:16:48AM -0700, David Wolfskill wrote: On Sun, May 12, 2013 at 11:45:37AM +, FreeBSD Tinderbox wrote: TB --- 2013-05-12 05:50:18 - tinderbox 2.10 running on

Re: Call for testers, users with scsi cards

On Wed, 5 Dec 2012, Jim Harris wrote: On Tue, Dec 4, 2012 at 2:36 PM, Jeff Roberson jrober...@jroberson.net wrote: http://people.freebsd.org/~jeff/loadccb.diff This patch consolidates all of the functions that map cam control blocks for DMA into one central function

Call for testers, users with scsi cards

http://people.freebsd.org/~jeff/loadccb.diff This patch consolidates all of the functions that map cam control blocks for DMA into one central function. This change is a precursor to adding new features to the I/O stack. It is mostly mechanical. If you are running current on a raid or scsi

Re: Call for testers, users with scsi cards

On Tue, 4 Dec 2012, Ian Lepore wrote: On Tue, 2012-12-04 at 14:49 -0700, Warner Losh wrote: On Dec 4, 2012, at 2:36 PM, Jeff Roberson wrote: http://people.freebsd.org/~jeff/loadccb.diff This patch consolidates all of the functions that map cam control blocks for DMA into one central

Experimental SUJ feature; cache synchronization

Hello, As of rev 242815 current has a feature to issue a synchronize cache command to the drive in between journal records and the metadata they modify. This should make SUJ more safe in the face of power failure. This should be considered experimental at this phase. If you wish to try it

Re: DragonFly vs FreeBSD scheduler

On Sat, 3 Nov 2012, O. Hartmann wrote: Am 11/03/12 15:17, schrieb Mark Felder: On Sat, 3 Nov 2012 21:18:55 +0800 Alie Tan a...@affle.com wrote: Hi, No offence, just curious about scheduler and its functionality. What is the different between this two that makes FreeBSD performance far

ULE patch, call for testers

I have a small patch to the ULE scheduler that makes a fairly large change to the way timeshare threads are handled. http://people.freebsd.org/~jeff/schedslice.diff Previously ULE used a fixed slice size for all timeshare threads. Now it scales the slice size down based on load. This should

Re: ULE patch, call for testers

On Fri, 2 Nov 2012, Eitan Adler wrote: On 2 November 2012 14:26, Jeff Roberson jrober...@jroberson.net wrote: I have a small patch to the ULE scheduler that makes a fairly large change to the way timeshare threads are handled. http://people.freebsd.org/~jeff/schedslice.diff Previously ULE

Re: Increase the degree of interactivity ULE scheduler

On Sat, 22 Oct 2011, Ivan Klymenko wrote: Hello people! I have: CPU: Intel(R) Core(TM)2 Duo CPU T7250 @ 2.00GHz (1994.48-MHz K8-class CPU) FreeBSD 10.0-CURRENT r226607 amd64 For example during the building of the port lang/gcc46 in four streams (-j 4) with a heavy load on the processor

Re: couple of sched_ule issues

On Thu, 15 Sep 2011, Andriy Gapon wrote: This is more of a just for the record email. I think I've already stated the following observations, but I suspect that they drowned in the noise of a thread in which I mentioned them. 1. Incorrect topology is built for single-package SMP systems. That

Re: Increase the degree of interactivity ULE scheduler

On Thu, 3 Nov 2011, Ivan Klymenko wrote: Thank you for taking the time to answer me. ? Thu, 3 Nov 2011 10:21:48 -1000 (HST) Jeff Roberson jrober...@jroberson.net ?: On Sat, 22 Oct 2011, Ivan Klymenko wrote: Hello people! I have: CPU: Intel(R) Core(TM)2 Duo CPU T7250 @ 2.00GHz

SUJ progress report

Hi Folks, Kirk, Peter and I have been working hard on SUJ. We still have a few bugs related to snapshots but we fixed the couple of potential corruption problems that came up over the last year. If you are not currently using SUJ I implore you to do so and report any problems you may find..

Re: [head tinderbox] failure on sparc64/sun4v

I did not notice this was still failing. I didn't realize this make universe would pull in my modules. I will fix this now. Thanks, Jeff On Wed, 23 Mar 2011, FreeBSD Tinderbox wrote: TB --- 2011-03-23 05:47:53 - tinderbox 2.6 running on freebsd-current.sentex.ca TB --- 2011-03-23 05:47:53

Re: HEADS UP: OFED stack merge tonight.

On Wed, 23 Mar 2011, Mattia Rossi wrote: On 21/03/11 18:36, Jeff Roberson wrote: [..] I would not expect any instability in non ofed systems from this import. Hi Jeff, I've tried to compile netstat, and it bails out immediately if I try to make obj: /usr/src/usr.bin/netstat/Makefile

HEADS UP: OFED stack merge tonight.

Hi Folks, Just a notice that the 1.5.3 OFED Infiniband stack will be committed as soon as a fresh buildworld/installworld completes on my test machine. This brings in new drivers and user code and a very small number of changes to system sources. OFED will not be built by default and

SUJ Bugs

Hello, I have lost track of what bugs are pesently outstanding in SUJ. If you have experienced a problem that prevented you from using SUJ please try again and report your issue to me directly. I don't always have the time to read current@ so mails sent without cc will get more attention.

Re: Panic on current when enabling SUJ

On Thu, 3 Jun 2010, John Doe wrote: Boot into single user-mode # tunefs -j enable / # tunefs -j enable /usr # tunefs -j enable /tmp # tunefs -j enable /var # reboot The machine then panics. Looks like the machine is trying to write to a read-only filesystem. Can you please give me

Re: ffs_copyonwrite panics

On Sun, 23 May 2010, Roman Bogorodskiy wrote: Jeff Roberson wrote: On Tue, 18 May 2010, Roman Bogorodskiy wrote: Hi, I've been using -CURRENT last update in February for quite a long time and few weeks ago decided to finally update it. The update was quite unfortunate as system became

Re: LOR: ufs vs bufwait

On Fri, 21 May 2010, Erik Cederstrand wrote: Den 12/05/2010 kl. 22.44 skrev Jeff Roberson: I think Peter Holm also saw this once while we were testing SUJ and reproduced ~30 second hangs with stock sources. At this point we need to brainstorm ideas for adding debugging instrumentation

Re: ffs_copyonwrite panics

On Tue, 18 May 2010, Roman Bogorodskiy wrote: Hi, I've been using -CURRENT last update in February for quite a long time and few weeks ago decided to finally update it. The update was quite unfortunate as system became very unstable: it just hangs few times a day and panics sometimes. Some

SUJ Changes

-- Forwarded message -- Date: Tue, 18 May 2010 01:45:28 + (UTC) From: Jeff Roberson j...@freebsd.org To: src-committ...@freebsd.org, svn-src-...@freebsd.org, svn-src-h...@freebsd.org Subject: svn commit: r208241 - head/sbin/tunefs Author: jeff Date: Tue May 18 01:45:28 2010 New

Re: LOR: ufs vs bufwait

On Wed, 12 May 2010, Ulrich Sp?rlein wrote: On Mon, 10.05.2010 at 22:53:32 +0200, Attilio Rao wrote: 2010/5/10 Peter Jeremy peterjer...@acm.org: On 2010-May-08 12:20:05 +0200, Ulrich Sp?rlein u...@spoerlein.net wrote: This LOR also is not yet listed on the LOR page, so I guess it's rather

Re: LOR: ufs vs bufwait

On Sat, 8 May 2010, Ulrich Sp?rlein wrote: On Sat, 08.05.2010 at 18:00:50 +0200, Attilio Rao wrote: 2010/5/8 Ulrich Sp?rlein u...@spoerlein.net: On Sat, 08.05.2010 at 12:20:05 +0200, Ulrich Sp?rlein wrote: This LOR also is not yet listed on the LOR page, so I guess it's rather new. I do use

Re: SUJ update - new panic - ffs_copyonwrite: recursive call

On Sun, 2 May 2010, Vladimir Grebenschikov wrote: Hi While 'make buildworld' kgdb /boot/kernel/kernel /var/crash/vmcore.13 GNU gdb 6.1.1 [FreeBSD] Hi Vladimir, I checked in a fix for this at revision 207742. If you can verify that it works for you it would be appreciated. Thanks! Jeff

Re: SUJ deadlock

for tunefs. Thanks, Jeff Applied and restarted portupgrade. Will tell you tomorrow. Fabien Le 6 mai 2010 ? 00:54, Jeff Roberson a ?crit : On Mon, 3 May 2010, Fabien Thomas wrote: Hi Jeff, I'm with r207548 now and since some days i've system deadlock. It seems related to SUJ with process

Re: SUJ deadlock

On Mon, 3 May 2010, Fabien Thomas wrote: Hi Jeff, I'm with r207548 now and since some days i've system deadlock. It seems related to SUJ with process waiting on suspfs or ppwait. I've also seen it stalled in suspfs, but this information is way better than what I was able to garner. I was

Re: SUJ update

On Mon, 3 May 2010, Ed Maste wrote: On Mon, May 03, 2010 at 04:32:37PM -0700, Doug Barton wrote: I also don't want to bikeshed this to death. I imagine that once the feature is stable that users will just twiddle it once and then leave it alone, or it will be set at install time and then not

Re: SUJ deadlock

On Mon, 3 May 2010, Fabien Thomas wrote: Hi Jeff, I'm with r207548 now and since some days i've system deadlock. It seems related to SUJ with process waiting on suspfs or ppwait. I've also seen it stalled in suspfs, but this information is way better than what I was able to garner. I was

Re: SUJ update

On Sun, 2 May 2010, Fabien Thomas wrote: Hi Jeff, Before sending the 'bad' part i would like to say that it is very useful and save me a lot of time after a crash. I've updated the ports and there was no more space on the FS. It end up with this backtrace (After one reboot the kernel

Re: SUJ update - new panic - ffs_copyonwrite: recursive call

On Sun, 2 May 2010, Vladimir Grebenschikov wrote: Hi While 'make buildworld' This is a problem with snapshots and the journal full condition. I will address it shortly. Thanks, Jeff kgdb /boot/kernel/kernel /var/crash/vmcore.13 GNU gdb 6.1.1 [FreeBSD] ... #0 0xc056b93c in doadump ()

Re: SUJ update

On Sat, 1 May 2010, Bruce Cran wrote: On Thu, Apr 29, 2010 at 06:37:00PM -1000, Jeff Roberson wrote: I fixed a few SUJ bugs. If those of you who reported one of the following bugs could re-test I would greatly appreciate it. I've started seeing a panic Sleeping thread owns a non-sleepable

SUJ update

Hello, I fixed a few SUJ bugs. If those of you who reported one of the following bugs could re-test I would greatly appreciate it. 1) panic on gnome start via softdep_cancel_link(). 2) Difficulty setting flags on /. This can only be done from a direct boot into single user but there were

Re: HEADS UP: SUJ Going in to head today

On Sun, 25 Apr 2010, Scott Long wrote: On Apr 24, 2010, at 8:57 PM, Jeff Roberson wrote: On Sun, 25 Apr 2010, Alex Keda wrote: try in single user mode: tunefs -j enable / tunefs: Insuffient free space for the journal tunefs: soft updates journaling can not be enabled tunefs -j enable /dev

Re: HEADS UP: SUJ Going in to head today

On Sun, 25 Apr 2010, Bruce Cran wrote: On Sunday 25 April 2010 19:47:00 Scott Long wrote: On Apr 24, 2010, at 8:57 PM, Jeff Roberson wrote: On Sun, 25 Apr 2010, Alex Keda wrote: try in single user mode: tunefs -j enable / tunefs: Insuffient free space for the journal tunefs: soft updates

Re: HEADS UP: SUJ Going in to head today

On Mon, 26 Apr 2010, pluknet wrote: On 26 April 2010 17:42, dikshie diks...@gmail.com wrote: Hi Jeff, thanks for SUJ. btw, why there is nan% utilization? and what does it mean? -- ** SU+J Recovering /dev/ad0s1g ** Reading 33554432 byte journal from inode 4. ** Building recovery

Re: HEADS UP: SUJ Going in to head today - panic on rename()

On Mon, 26 Apr 2010, Vladimir Grebenschikov wrote: Hi First, many thanks for this effort, it is really very appreciated, Panic on Gnome starting: Thank you for the report with stack. That was very helpful. I know how to fix this bug but it will take me a day or two as my primary test

Re: HEADS UP: SUJ Going in to head today

On Sun, 25 Apr 2010, Lucius Windschuh wrote: Hi Jeff, thank you for your effort in implementing the soft update journaling. I tried to test SUJ on a provider with 4 kB block size. My system runs 9-CURRENT r207195 (i386). Unfortunately, tunefs is unable to cope with the device. It can easily

Re: HEADS UP: SUJ Going in to head today

On Sun, 25 Apr 2010, Gary Jennejohn wrote: On Sat, 24 Apr 2010 16:57:59 -1000 (HST) Jeff Roberson jrober...@jroberson.net wrote: On Sun, 25 Apr 2010, Alex Keda wrote: try in single user mode: tunefs -j enable / tunefs: Insuffient free space for the journal tunefs: soft updates journaling

Re: HEADS UP: SUJ Going in to head today

On Sun, 25 Apr 2010, Alex Keda wrote: try in single user mode: tunefs -j enable / tunefs: Insuffient free space for the journal tunefs: soft updates journaling can not be enabled tunefs -j enable /dev/ad0s2a tunefs: Insuffient free space for the journal tunefs: soft updates journaling can not

Re: HEADS UP: SUJ Going in to head today

On Wed, 21 Apr 2010, Garrett Cooper wrote: On Wed, Apr 21, 2010 at 12:39 AM, Gary Jennejohn gary.jennej...@freenet.de wrote: On Tue, 20 Apr 2010 12:15:48 -1000 (HST) Jeff Roberson jrober...@jroberson.net wrote: Hi Folks, You may have seen my other Soft-updates journaling (SUJ) announcements

Re: HEADS UP: SUJ Going in to head today

On Tue, 20 Apr 2010, Patrick Tracanelli wrote: Jeff Roberson escreveu: Hi Folks, You may have seen my other Soft-updates journaling (SUJ) announcements. If not, it is a journaling system that works cooperatively with soft-updates to eliminate the full background filesystem check after

HEADS UP: SUJ Going in to head today

Hi Folks, You may have seen my other Soft-updates journaling (SUJ) announcements. If not, it is a journaling system that works cooperatively with soft-updates to eliminate the full background filesystem check after an unclean shutdown. SUJ may be enabled with tunefs -j enable and disabled

Re: amd64/SMP(/ata-raid ?) not happy...

On Sun, 30 Nov 2003, Poul-Henning Kamp wrote: Timecounters tick every 10.000 msec GEOM: create disk ad0 dp=0xff00eebfaca0 ad0: 35772MB IBM-DPTA-353750 [72680/16/63] at ata0-master UDMA66 GEOM: create disk ad4 dp=0xff00eebfa4a0 ad4: 35304MB WDC WD360GD-00FNA0 [71730/16/63] at

Re: user:sys time ratio

On Sun, 30 Nov 2003, Colin Percival wrote: Robert Watson suggested that I compare performance from UP and SMP kernels: # /usr/bin/time -hl sh -c 'make -s buildworld 21' /dev/null Real UserSys UP kernel 38m33.29s 27m10.09s 10m59.15s

Re: kernel compile fails in uma_core.c

On Sun, 30 Nov 2003, Paulius Bulotas wrote: Hello, when building kernel: ../../../vm/uma_core.c: In function `zone_timeout': ../../../vm/uma_core.c:345: error: `mp_maxid' undeclared (first use in this function) and so on. Anything I missed? I just fixed this, sorry. Paulius

Re: Frequent lockups with 5.2-BETA

On 27 Nov 2003, Christian Laursen wrote: Since upgrading from 5.1-RELEASE to 5.2-BETA, I've been experiencing hard lockups once or twice every day. I managed to get a trace by enabling the watchdog, which put me into the debugger. This is the trace: db trace

Re: zone(9) is broken on SMP?!

On Thu, 27 Nov 2003, Florian C. Smeets wrote: Max Laier wrote: If I build attached kmod and kldload/-unload it on a GENERIC kernel w/ SMP apic it'll error out: Zone was not empty (xx items). Lost X pages of memory. This is on a p4 HTT, but seems reproducible on proper SMP systems as

Re: LOR (swap_pager.c:1323, swap_pager.c:1838, uma_core.c:876) (current:Nov17)

On Tue, 18 Nov 2003, Cosmin Stroe wrote: Here is the stack backtrace: Thanks, this is known and is actually safe. We're pursuing ways to quiet these warnings. lock order reversal 1st 0xc1da318c vm object (vm object) @ /usr/src/sys/vm/swap_pager.c:1323 2nd 0xc0724900 swap_pager swhash

Re: ULE and very bad responsiveness

On Fri, 14 Nov 2003, Jonathan Fosburgh wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On Thursday 13 November 2003 06:01 pm, Harald Schmalzbauer wrote: I also could play quake(2) and have something compiling in the background but I see every new object file in form of a picture

Re: ULE and very bad responsiveness

On Fri, 14 Nov 2003, Jonathan Fosburgh wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On Friday 14 November 2003 01:52 pm, Jeff Roberson wrote: This does not happen with SCHED_4BSD? How fast is your system? Can you give me an example including what applications you're running

Re: ULE and very bad responsiveness

On Thu, 13 Nov 2003, Harald Schmalzbauer wrote: On Thursday 13 November 2003 07:17, Harald Schmalzbauer wrote: Hi, from comp.unix.bsd.freebsd.misc: Kris Kennaway wrote: On 2003-11-13, Harald Schmalzbauer [EMAIL PROTECTED] wrote: Well, I don't have any measurements but in my case

Re: SYSENTER in FreeBSD

On Wed, 5 Nov 2003, David Xu wrote: Jun Su wrote: I noticed that Jeff Roberson implement this already. Is whi will be commit? http://kerneltrap.org/node/view/1531 I google this because I found this feature is listed in the list of Kernel Improvement of WindowsXP. :-) Thanks, Jun Su

Re: More ULE bugs fixed.

On Tue, 4 Nov 2003, Sheldon Hearn wrote: On (2003/11/04 09:29), Eirik Oeverby wrote: The problem is two parts: The mouse tends to 'lock up' for brief moments when the system is under load, in particular during heavy UI operations or when doing compile jobs and such. The second part of

Re: Was: More ULE bugs fixed. Is: Mouse problem?

On Wed, 5 Nov 2003, Eirik Oeverby wrote: Alex Wilkinson wrote: On Wed, Nov 05, 2003 at 12:27:04AM +0100, Eirik Oeverby wrote: Just for those interested: I do *not* get any messages at all from the kernel (or elsewhere) when my mouse goes haywire. And it's an absolute

Re: Was: More ULE bugs fixed. Is: Mouse problem?

On Wed, 5 Nov 2003, Eirik Oeverby wrote: Eirik Oeverby wrote: Just for those interested: I do *not* get any messages at all from the kernel (or elsewhere) when my mouse goes haywire. And it's an absolute truth (just tested back and forth 8 times) that it *only* happens with SCHED_ULE

How nice should behave (was Re: More ULE bugs fixed.)

On Tue, 4 Nov 2003, Bruce Evans wrote: On Sun, 2 Nov 2003, Jeff Roberson wrote: You commented on the nice cutoff before. What do you believe the correct behavior is? In ULE I went to great lengths to be certain that I emulated the old behavior of denying nice +20 processes cpu time

Re: More ULE bugs fixed.

for the report. Cheers, Jeff If you need me to do anything to track this down, let me know. I am, and have always been, running with moused, on a uniprocessor box (ThinkPad T21 1ghz p3). Best regards, /Eirik Jeff Roberson wrote: On Fri, 31 Oct 2003, Bruno Van Den Bossche wrote: Jeff Roberson

Re: More ULE bugs fixed.

On Sat, 1 Nov 2003, Bruce Evans wrote: On Fri, 31 Oct 2003, Jeff Roberson wrote: I have commited my SMP fixes. I would appreciate it if you could post update results. ULE now outperforms 4BSD in a single threaded kernel compile and performs almost identically in a 16 way make. I still

Re: Sticky mouse with SCHED_ULE 10-30-03

On Sun, 2 Nov 2003, Schnoopay wrote: Are you using moused? Is this SMP or UP? What CPUs are you using? Thanks, Jeff I am having similar problems after my last cvsup (10-31-03) also using a USB MS Intellimouse. Mouse is slow to respond under ULE but fine under 4BSD. The

Re: More ULE bugs fixed.

On Wed, 29 Oct 2003, Jeff Roberson wrote: On Thu, 30 Oct 2003, Bruce Evans wrote: Test for scheduling buildworlds: cd /usr/src/usr.bin for i in obj depend all do MAKEOBJDIRPREFIX=/somewhere/obj time make -s -j16 $i done /tmp/zqz 21 (Run

Re: More ULE bugs fixed.

On Fri, 31 Oct 2003, Bruno Van Den Bossche wrote: Jeff Roberson [EMAIL PROTECTED] wrote: On Wed, 29 Oct 2003, Jeff Roberson wrote: On Thu, 30 Oct 2003, Bruce Evans wrote: Test for scheduling buildworlds: cd /usr/src/usr.bin for i in obj depend all

Re: Sticky mouse with SCHED_ULE 10-30-03

On Fri, 31 Oct 2003, Michal wrote: FreeBSD 5.1-CURRENT #0: Thu Oct 30 17:49:13 EST 2003 When kernel compiled with SCHED_ULE, USB mouse (MS USB Intellimouse) is almost unusable. Even if CPU is idle, mouse feels sticky. When loading mozilla or compiling comething mouse freezes for several

Re: More ULE bugs fixed.

On Thu, 30 Oct 2003, Bruce Evans wrote: Test for scheduling buildworlds: cd /usr/src/usr.bin for i in obj depend all do MAKEOBJDIRPREFIX=/somewhere/obj time make -s -j16 $i done /tmp/zqz 21 (Run this with an empty /somewhere/obj. The all stage

Re: More ULE bugs fixed.

On Fri, 17 Oct 2003, Bruce Evans wrote: On Fri, 17 Oct 2003, Jeff Roberson wrote: On Fri, 17 Oct 2003, Bruce Evans wrote: How would one test if it was an improvement on the 4BSD scheduler? It is not even competitive in my simple tests. ... At one point ULE was at least as fast

Re: ULE page fault with sched_ule.c 1.67

On Mon, 27 Oct 2003, Jonathan Fosburgh wrote: On Monday 27 October 2003 12:06 pm, Arjan van Leeuwen wrote: Hi, I just cvsupped and built a new kernel that includes sched_ule.c 1.67. I'm getting a page fault when working in Mozilla Firebird. It happens pretty soon, after opening one or

Re: More ULE bugs fixed.

On Fri, 17 Oct 2003, Bruce Evans wrote: How would one test if it was an improvement on the 4BSD scheduler? It is not even competitive in my simple tests. [scripts results deleted] Summary: SCHED_ULE was more than twice as slow as SCHED_4BSD for the obj and depend stages. These stages

Re: More ULE bugs fixed.

On Fri, 17 Oct 2003, Bruce Evans wrote: On Fri, 17 Oct 2003, Jeff Roberson wrote: On Fri, 17 Oct 2003, Bruce Evans wrote: How would one test if it was an improvement on the 4BSD scheduler? It is not even competitive in my simple tests. ... At one point ULE was at least

Re: More ULE bugs fixed.

On Fri, 17 Oct 2003, Sean Chittenden wrote: I think you cvsup'd at a bad time. I fixed a bug that would have caused the system to lock up in this case late last night. On my system it freezes for a few seconds and then returns. I can stop that by turning down the interactivity

Re: More ULE bugs fixed.

On Thu, 16 Oct 2003, Eirik Oeverby wrote: Jeff Roberson wrote: On Wed, 15 Oct 2003, Eirik Oeverby wrote: Eirik Oeverby wrote: Jeff Roberson wrote: I fixed two bugs that were exposed due to more of the kernel running outside of Giant. ULE had some issues with priority propagation

Re: Page faults with today's current

On Thu, 16 Oct 2003, Arjan van Leeuwen wrote: I just cvsupped and installed a new world and kernel (previous kernel was from October 13), and now my machine gets a page fault when I try to run any GTK2 application (Firebird, Gnome 2). Are others seeing this as well? Arjan If you're running

Re: sched_ule.c SMP error

On Thu, 16 Oct 2003, Valentin Chopov wrote: I'm getting an error in the sched_ule.c It looks that sched_add is called with struct kse arg. instead of struct thread Fixed, thanks. Thanks, Val cc -c -O -pipe -march=pentiumpro -Wall -Wredundant-decls -Wnested-externs -Wstri

More ULE bugs fixed.

I fixed two bugs that were exposed due to more of the kernel running outside of Giant. ULE had some issues with priority propagation that stopped it from working very well. Things should be much improved. Feedback, as always, is welcome. I'd like to look into making this the default scheduler

Re: More ULE bugs fixed.

On Wed, 15 Oct 2003, Eirik Oeverby wrote: Eirik Oeverby wrote: Jeff Roberson wrote: I fixed two bugs that were exposed due to more of the kernel running outside of Giant. ULE had some issues with priority propagation that stopped it from working very well. Things should be much

Re: More ULE bugs fixed.

On Wed, 15 Oct 2003, Daniel Eischen wrote: On Wed, 15 Oct 2003, Jeff Roberson wrote: I fixed two bugs that were exposed due to more of the kernel running outside of Giant. ULE had some issues with priority propagation that stopped it from working very well. Things should be much

Re: ULE status; interactivity fixed? nice uninvestigated, HTT broken

On Mon, 13 Oct 2003, Arjan van Leeuwen wrote: On Sunday 12 October 2003 23:21, Jeff Roberson wrote: I commited a fix that would have caused all of the jerky behaviors under some load. I was not able to reproduce this problem with kde running afterwards. Thanks for the fix! However

Re: ULE status; interactivity fixed? nice uninvestigated, HTT broken

On Tue, 14 Oct 2003, Arjan van Leeuwen wrote: On Monday 13 October 2003 21:27, Jeff Roberson wrote: On Mon, 13 Oct 2003, Arjan van Leeuwen wrote: On Sunday 12 October 2003 23:21, Jeff Roberson wrote: I commited a fix that would have caused all of the jerky behaviors under some load

ULE status; interactivity fixed? nice uninvestigated, HTT broken

I commited a fix that would have caused all of the jerky behaviors under some load. I was not able to reproduce this problem with kde running afterwards. I'm going to look into the reports of some problems with nice, although I suspect that they could have been caused by the same issues. HTT is

Re: panic: softdep_deallocate_dependencies: dangling deps

On Mon, 13 Oct 2003, Oliver Fischer wrote: My notebook was a little bit panic this night. After rebooting I found this message in my system log: panic: softdep_deallocate_dependencies: dangling deps ? When are your sources from? Regards, Oliver Fischer

Re: Interesting...sched_ule discussion

On Sat, 11 Oct 2003, Brendon and Wendy wrote: Hi, Just saw the talk about sched_ule, nvidia driver, moused and pauses... I was running -current up until about a month ago, using the nvidia driver, sched_bsd on a dual ht xeon, with htt disabled. Mouse interactivity with moused was terrible

ULE Update

I have reproduced the lagging mouse issue on my laptop. I tried moused to no effect. Eventually, I grudgingly installed kde and immediately started encountering problems with mouse lag. It would seem that twm was not stressing my machine in the same ways that kde is. ;-) I suspect a problem

  1   2   3   >