From: Shawn Starr <shawn.starr@rogers.com> To: Thomas Gleixner <tglx@linutronix.de> Cc: "Rafael J. Wysocki" <rjw@sisk.pl>, Linux Kernel Mailing List <linux-kernel@vger.kernel.org>, Kernel Testers List <kernel-testers@vger.kernel.org> Subject: Re: [Bug #14859] System timer firing too much without cause Date: Mon, 25 Jan 2010 11:53:58 -0500 [thread overview] Message-ID: <201001251153.59084.shawn.starr@rogers.com> (raw) In-Reply-To: <alpine.LFD.2.00.1001251103200.2906@localhost.localdomain> On Monday 25 January 2010 05:35:50 Thomas Gleixner wrote: > On Sun, 24 Jan 2010, Shawn Starr wrote: > > On Sunday 24 January 2010 17:04:33 Rafael J. Wysocki wrote: > > > This message has been generated automatically as a part of a report > > > of recent regressions. > > > > > > The following bug entry is on the current list of known regressions > > > from 2.6.32. Please verify if it still should be listed and let me > > > know (either way). > > Why is this on the regression list at all ? The report says that this > is happening with 33-rcX, but there is no comparison to the behaviour > of 32 or earlier kernels on that machine. Instead we have a comparison > > of apples and oranges: > > As a comparsion my quad core box has no such issue: (Running 2.6.32-rc7) > > x86_64 > > > > 0: 42 4 1 1 IO-APIC-edge > > timer > > > > my Lenovo ThinkPad W500 (latest BIOS 3.11) laptop shows the system timer > > flooding the bus (Running 2.6.33-rc1) x86_64 > > > > 0: 66775 70429 IO-APIC-edge timer <-- keeps rising, > > rapidly > > So we look at a quad core desktop machine which probably has no deeper > power states and therefor does not use the broadcast timer and compare > it to a laptop which has deeper power states and needs to use the > broadcast timer, which of course increases the number of IRQ0 > events. What a surprise. > > Can we please remove this from the regression list unless Shawn > confirms that 32 or earlier kernels do not show that behaviour on the > laptop? > > > > Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=14859 > > > Subject : System timer firing too much without cause > > > Submitter : Shawn Starr <shawn.starr@rogers.com> > > > Date : 2009-12-21 19:16 (35 days old) > > > > Continues with -rc5, I really cannot use Dynamic ticks at all, it has to > > be disabled. > > Shawn, why can't you use dynamic ticks ? In the bugzilla I just see > that you worry about the IRQ0 interrupts (which are correct and > necessary when the system is in nohz mode) and the extra rescheduling > interrupts. How is the system misbehaving ? > Well, this all stems from trying to use Radeon KMS with IRQs on. Doing so I see system stalls and this is quite noticeable however, I am able to show this same stall on the quad core with the same GPU. Right now, it is unclear to me if there is a underlying irq issue or a bug in the radeon driver code that is showing these stalls. Since the radeon folks - at the moment - do not think it is a coding problem in their driver My impression was using dynamic ticks meant ticks were on demand and not continuous. On the quad core box, with dynamic ticks on, the broadcasts are not increasing IRQ 0 events this only happens on the laptop. Thanks, Shawn. > Thanks, > > tglx
WARNING: multiple messages have this Message-ID (diff)
From: Shawn Starr <shawn.starr-bJEeYj9oJeDQT0dZR+AlfA@public.gmane.org> To: Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org> Cc: "Rafael J. Wysocki" <rjw-KKrjLPT3xs0@public.gmane.org>, Linux Kernel Mailing List <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>, Kernel Testers List <kernel-testers-u79uwXL29TY76Z2rM5mHXA@public.gmane.org> Subject: Re: [Bug #14859] System timer firing too much without cause Date: Mon, 25 Jan 2010 11:53:58 -0500 [thread overview] Message-ID: <201001251153.59084.shawn.starr@rogers.com> (raw) In-Reply-To: <alpine.LFD.2.00.1001251103200.2906-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org> On Monday 25 January 2010 05:35:50 Thomas Gleixner wrote: > On Sun, 24 Jan 2010, Shawn Starr wrote: > > On Sunday 24 January 2010 17:04:33 Rafael J. Wysocki wrote: > > > This message has been generated automatically as a part of a report > > > of recent regressions. > > > > > > The following bug entry is on the current list of known regressions > > > from 2.6.32. Please verify if it still should be listed and let me > > > know (either way). > > Why is this on the regression list at all ? The report says that this > is happening with 33-rcX, but there is no comparison to the behaviour > of 32 or earlier kernels on that machine. Instead we have a comparison > > of apples and oranges: > > As a comparsion my quad core box has no such issue: (Running 2.6.32-rc7) > > x86_64 > > > > 0: 42 4 1 1 IO-APIC-edge > > timer > > > > my Lenovo ThinkPad W500 (latest BIOS 3.11) laptop shows the system timer > > flooding the bus (Running 2.6.33-rc1) x86_64 > > > > 0: 66775 70429 IO-APIC-edge timer <-- keeps rising, > > rapidly > > So we look at a quad core desktop machine which probably has no deeper > power states and therefor does not use the broadcast timer and compare > it to a laptop which has deeper power states and needs to use the > broadcast timer, which of course increases the number of IRQ0 > events. What a surprise. > > Can we please remove this from the regression list unless Shawn > confirms that 32 or earlier kernels do not show that behaviour on the > laptop? > > > > Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=14859 > > > Subject : System timer firing too much without cause > > > Submitter : Shawn Starr <shawn.starr-bJEeYj9oJeDQT0dZR+AlfA@public.gmane.org> > > > Date : 2009-12-21 19:16 (35 days old) > > > > Continues with -rc5, I really cannot use Dynamic ticks at all, it has to > > be disabled. > > Shawn, why can't you use dynamic ticks ? In the bugzilla I just see > that you worry about the IRQ0 interrupts (which are correct and > necessary when the system is in nohz mode) and the extra rescheduling > interrupts. How is the system misbehaving ? > Well, this all stems from trying to use Radeon KMS with IRQs on. Doing so I see system stalls and this is quite noticeable however, I am able to show this same stall on the quad core with the same GPU. Right now, it is unclear to me if there is a underlying irq issue or a bug in the radeon driver code that is showing these stalls. Since the radeon folks - at the moment - do not think it is a coding problem in their driver My impression was using dynamic ticks meant ticks were on demand and not continuous. On the quad core box, with dynamic ticks on, the broadcasts are not increasing IRQ 0 events this only happens on the laptop. Thanks, Shawn. > Thanks, > > tglx
next prev parent reply other threads:[~2010-01-25 16:54 UTC|newest] Thread overview: 201+ messages / expand[flat|nested] mbox.gz Atom feed top 2010-01-24 21:54 2.6.33-rc5: Reported regressions from 2.6.32 Rafael J. Wysocki 2010-01-24 21:54 ` Rafael J. Wysocki 2010-01-24 21:54 ` Rafael J. Wysocki 2010-01-24 21:54 ` [Bug #14791] Something has been broken in the network stack this week Rafael J. Wysocki 2010-01-24 22:18 ` Ben Hutchings 2010-01-24 22:30 ` Rafael J. Wysocki 2010-01-24 22:30 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #14859] System timer firing too much without cause Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:34 ` Shawn Starr 2010-01-24 23:07 ` Rafael J. Wysocki 2010-01-24 23:07 ` Rafael J. Wysocki 2010-01-25 10:35 ` Thomas Gleixner 2010-01-25 10:35 ` Thomas Gleixner 2010-01-25 16:53 ` Shawn Starr [this message] 2010-01-25 16:53 ` Shawn Starr 2010-01-25 17:20 ` Thomas Gleixner 2010-01-25 17:20 ` Thomas Gleixner 2010-01-25 17:30 ` Shawn Starr 2010-01-25 17:30 ` Shawn Starr 2010-01-25 20:59 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #14937] WARNING: at kernel/lockdep.c:2830 Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #14946] All kernels after 2.6.32-git10 show only 1 CPU Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-25 1:41 ` Sid Boyce 2010-01-25 1:41 ` Sid Boyce 2010-01-25 21:04 ` Rafael J. Wysocki 2010-01-25 21:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #14924] Weird hard hangs when rendering 'some' web-sites in Firefox Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-25 13:55 ` Américo Wang 2010-01-25 13:55 ` Américo Wang 2010-01-25 19:26 ` David 2010-01-25 21:02 ` Rafael J. Wysocki 2010-01-25 21:02 ` Rafael J. Wysocki 2010-01-26 3:06 ` Américo Wang 2010-01-24 22:04 ` [Bug #14949] drm_vm.c:drm_mmap: possible circular locking dependency detected Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-25 8:28 ` Borislav Petkov 2010-01-25 8:28 ` Borislav Petkov 2010-01-24 22:04 ` [Bug #14792] Misdetection of the TV output Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #14950] tbench regression with 2.6.33-rc1 Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #14999] possible circular locking dependency detected in rfkill at suspend Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15000] Thinkpad dock button no longer works Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15032] Oops in uart_resume_port() on resume Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15017] kexec regression, radeon/kms irq related (bisected) Rafael J. Wysocki 2010-01-25 3:26 ` Alex Deucher 2010-01-25 3:26 ` Alex Deucher 2010-01-25 6:28 ` Dave Airlie 2010-01-25 6:28 ` Dave Airlie 2010-01-24 22:04 ` [Bug #15025] Oops in ext4 driver Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:43 ` Steinar H. Gunderson 2010-01-24 22:43 ` Steinar H. Gunderson 2010-01-24 23:09 ` Rafael J. Wysocki 2010-01-24 23:09 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15036] soft lockup in dmesg after suspend/resume Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15038] drm/ksm: fbdev blanking regression Rafael J. Wysocki 2010-01-24 22:45 ` Johan Hovold 2010-01-24 22:45 ` Johan Hovold 2010-01-24 23:13 ` Rafael J. Wysocki 2010-01-24 23:13 ` Rafael J. Wysocki 2010-01-25 6:28 ` Dave Airlie 2010-01-25 6:28 ` Dave Airlie 2010-01-25 21:07 ` Rafael J. Wysocki 2010-01-25 21:07 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15039] leds_alix2: can't allocate I/O for GPIO Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15043] Display goes off with i915.powersave=1 Rafael J. Wysocki 2010-01-27 17:57 ` Jesse Barnes 2010-01-28 5:05 ` Soeren Sonnenburg 2010-01-28 5:05 ` Soeren Sonnenburg 2010-02-04 20:09 ` Soeren Sonnenburg 2010-02-04 20:09 ` Soeren Sonnenburg 2010-01-24 22:04 ` [Bug #15076] System panic under load with clockevents_program_event Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15124] PCI host bridge windows ignored (works with pci=use_crs) Rafael J. Wysocki 2010-01-26 7:19 ` Jeff Garrett 2010-01-26 12:48 ` Rafael J. Wysocki 2010-01-26 17:32 ` Bjorn Helgaas 2010-01-26 18:02 ` Rafael J. Wysocki 2010-01-26 18:02 ` Rafael J. Wysocki 2010-01-26 18:17 ` Jesse Barnes 2010-01-26 18:22 ` Yinghai Lu 2010-01-26 22:57 ` Yinghai Lu 2010-01-27 16:45 ` Bjorn Helgaas 2010-01-27 16:45 ` Bjorn Helgaas 2010-01-27 16:53 ` Jesse Barnes 2010-01-27 20:45 ` Bjorn Helgaas 2010-01-27 20:45 ` Bjorn Helgaas 2010-01-27 20:50 ` Linus Torvalds 2010-01-27 20:50 ` Linus Torvalds 2010-01-27 20:59 ` Jesse Barnes 2010-01-27 20:59 ` Jesse Barnes 2010-01-27 21:02 ` Jesse Barnes 2010-01-28 1:32 ` Yinghai Lu 2010-01-27 21:03 ` Bjorn Helgaas 2010-01-27 23:34 ` Yinghai Lu 2010-01-27 23:34 ` Yinghai Lu 2010-01-28 4:26 ` Bjorn Helgaas 2010-01-28 5:53 ` Yinghai Lu 2010-01-28 5:53 ` Yinghai Lu 2010-01-28 10:45 ` Rafael J. Wysocki 2010-01-28 10:45 ` Rafael J. Wysocki 2010-01-28 16:09 ` Bjorn Helgaas 2010-01-28 18:20 ` Yinghai Lu 2010-01-28 18:20 ` Yinghai Lu 2010-01-28 19:03 ` Jesse Barnes 2010-01-28 20:28 ` Rafael J. Wysocki [not found] ` <201001282128.33389.rjw-KKrjLPT3xs0@public.gmane.org> 2010-01-28 20:35 ` Jesse Barnes 2010-01-28 20:35 ` Jesse Barnes 2010-01-29 2:44 ` Zhang Rui 2010-01-28 20:20 ` Bjorn Helgaas 2010-01-28 20:20 ` Bjorn Helgaas 2010-01-28 20:31 ` Bjorn Helgaas 2010-01-28 20:31 ` Bjorn Helgaas 2010-01-28 21:14 ` Yinghai Lu 2010-01-28 21:14 ` Yinghai Lu 2010-01-31 2:45 ` Matthew Garrett 2010-01-31 2:45 ` Matthew Garrett 2010-01-28 1:35 ` Jesse Barnes 2010-01-28 1:35 ` Jesse Barnes 2010-01-28 4:01 ` Jeff Garrett 2010-01-28 4:01 ` Jeff Garrett 2010-01-28 1:50 ` Linus Torvalds 2010-01-28 3:24 ` Jesse Barnes 2010-01-28 3:24 ` Jesse Barnes 2010-01-28 4:02 ` Jeff Garrett 2010-01-28 16:24 ` Jesse Barnes 2010-01-28 16:24 ` Jesse Barnes 2010-01-28 18:13 ` Yinghai Lu 2010-01-28 20:12 ` Jesse Barnes 2010-01-28 20:12 ` Jesse Barnes 2010-01-28 18:30 ` [PATCH] x86/pci: print ioh resources only Yinghai Lu 2010-01-28 18:30 ` Yinghai Lu 2010-01-28 18:54 ` Linus Torvalds 2010-01-28 18:54 ` Linus Torvalds 2010-01-28 19:10 ` [PATCH -v2] " Yinghai Lu 2010-01-28 19:30 ` Olivier Galibert 2010-01-28 19:30 ` Olivier Galibert 2010-01-28 21:06 ` Yinghai Lu 2010-01-28 21:06 ` Yinghai Lu 2010-01-26 18:21 ` [Bug #15124] PCI host bridge windows ignored (works with pci=use_crs) Linus Torvalds 2010-01-26 18:21 ` Linus Torvalds 2010-01-26 18:16 ` Linus Torvalds 2010-01-26 18:16 ` Linus Torvalds 2010-01-26 18:21 ` Yinghai Lu 2010-01-26 18:21 ` Yinghai Lu 2010-01-26 18:35 ` Jesse Barnes 2010-01-26 18:35 ` Jesse Barnes 2010-01-24 22:04 ` [Bug #15125] hung task - jbd2/dm-1-8 (during raid rebuild) Rafael J. Wysocki 2010-01-24 22:49 ` Michael Breuer 2010-01-24 23:14 ` Rafael J. Wysocki 2010-01-24 23:14 ` Rafael J. Wysocki 2010-01-30 19:21 ` Michael Breuer 2010-01-30 19:21 ` Michael Breuer 2010-01-24 22:04 ` [Bug #15126] REGRESSION for RT2561/RT61 in 2.6.33 Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:32 ` Alan Stern 2010-01-24 22:32 ` Alan Stern 2010-01-24 22:34 ` Rafael J. Wysocki 2010-01-24 22:34 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15128] Boot regression on AMD Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15129] [drm:i915_gem_execbuffer] *ERROR* i915_gem_do_execbuffer returns -512 Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-27 17:58 ` Jesse Barnes 2010-01-27 17:58 ` Jesse Barnes 2010-01-27 21:03 ` Rafael J. Wysocki 2010-01-27 21:03 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15131] [OOPS] radeon kms Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15132] OOPS's with large initramfs Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:55 ` Nigel Kukard 2010-01-24 22:55 ` Nigel Kukard 2010-01-24 23:15 ` Rafael J. Wysocki 2010-01-24 23:15 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15133] Wake on LAN doesn't work in sky2 Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15138] evdev regression on macbook Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15137] NULL pointer dereference in vlan_skb_recv Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki 2010-01-25 13:43 ` Américo Wang 2010-01-25 13:43 ` Américo Wang 2010-01-25 21:07 ` Rafael J. Wysocki 2010-01-25 21:30 ` David Miller 2010-01-25 21:30 ` David Miller 2010-01-25 21:58 ` Rafael J. Wysocki 2010-01-25 21:58 ` Rafael J. Wysocki 2010-01-24 22:04 ` [Bug #15139] e1000: transmit queue 0 timed out Rafael J. Wysocki 2010-01-24 22:04 ` Rafael J. Wysocki -- strict thread matches above, loose matches on Subject: below -- 2010-01-10 22:27 2.6.33-rc3-git3: Reported regressions from 2.6.32 Rafael J. Wysocki 2010-01-10 22:32 ` [Bug #14859] System timer firing too much without cause Rafael J. Wysocki 2010-01-10 22:32 ` Rafael J. Wysocki 2010-01-11 3:22 ` Shawn Starr [not found] ` <201001102222.19700.shawn.starr-bJEeYj9oJeDQT0dZR+AlfA@public.gmane.org> 2010-01-11 19:59 ` Rafael J. Wysocki 2010-01-11 3:28 ` Shawn Starr
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=201001251153.59084.shawn.starr@rogers.com \ --to=shawn.starr@rogers.com \ --cc=kernel-testers@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=rjw@sisk.pl \ --cc=tglx@linutronix.de \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.