* [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) @ 2017-09-19 15:12 Yanko Kaneti 2017-09-19 15:33 ` Marc Zyngier 0 siblings, 1 reply; 8+ messages in thread From: Yanko Kaneti @ 2017-09-19 15:12 UTC (permalink / raw) To: Marc Zyngier; +Cc: LKML, Thomas Gleixner Hello, Fedora rawhide config here. AMD FX-8370E Bisected a problem to: 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) It seems to be causing stalls, short lived or long lived lockups very shortly after boot. Everything becomes jerky. The only visible in the log indication is something like : .... [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking clocksource 'tsc' as unstable because the skew is too large: [ 59.802134] clocksource: 'hpet' wd_now: 3326e7aa wd_last: 329956f8 mask: ffffffff [ 59.802137] clocksource: 'tsc' cs_now: 423662bc6f cs_last: 41dfc91650 mask: ffffffffffffffff [ 59.802140] tsc: Marking TSC unstable due to clocksource watchdog [ 59.802158] TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'. [ 59.802161] sched_clock: Marking unstable (59802142067, 15510)<-(59920871789, -118714277) [ 60.015604] clocksource: Switched to clocksource hpet [ 89.015994] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 209.660 msecs [ 89.016003] perf: interrupt took too long (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to 1000 .... Just reverting that commit on top of linus mainline cures all the symptoms Regards - Yanko ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) 2017-09-19 15:12 [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) Yanko Kaneti @ 2017-09-19 15:33 ` Marc Zyngier 2017-09-19 15:40 ` Yanko Kaneti 0 siblings, 1 reply; 8+ messages in thread From: Marc Zyngier @ 2017-09-19 15:33 UTC (permalink / raw) To: Yanko Kaneti; +Cc: LKML, Thomas Gleixner On 19/09/17 16:12, Yanko Kaneti wrote: > Hello, > > Fedora rawhide config here. > AMD FX-8370E > > Bisected a problem to: > 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) > > It seems to be causing stalls, short lived or long lived lockups very shortly after boot. > Everything becomes jerky. > > The only visible in the log indication is something like : > .... > [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking clocksource 'tsc' as unstable because the skew is too large: > [ 59.802134] clocksource: 'hpet' wd_now: 3326e7aa wd_last: 329956f8 mask: ffffffff > [ 59.802137] clocksource: 'tsc' cs_now: 423662bc6f cs_last: 41dfc91650 mask: ffffffffffffffff > [ 59.802140] tsc: Marking TSC unstable due to clocksource watchdog > [ 59.802158] TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'. > [ 59.802161] sched_clock: Marking unstable (59802142067, 15510)<-(59920871789, -118714277) > [ 60.015604] clocksource: Switched to clocksource hpet > [ 89.015994] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 209.660 msecs > [ 89.016003] perf: interrupt took too long (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to 1000 > .... > > Just reverting that commit on top of linus mainline cures all the symptoms Interesting. Do you still get HPET interrupts? Thanks, M. -- Jazz is not dead. It just smells funny... ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) 2017-09-19 15:33 ` Marc Zyngier @ 2017-09-19 15:40 ` Yanko Kaneti 2017-09-19 15:51 ` Marc Zyngier 0 siblings, 1 reply; 8+ messages in thread From: Yanko Kaneti @ 2017-09-19 15:40 UTC (permalink / raw) To: Marc Zyngier; +Cc: LKML, Thomas Gleixner On Tue, 2017-09-19 at 16:33 +0100, Marc Zyngier wrote: > On 19/09/17 16:12, Yanko Kaneti wrote: > > Hello, > > > > Fedora rawhide config here. > > AMD FX-8370E > > > > Bisected a problem to: > > 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) > > > > It seems to be causing stalls, short lived or long lived lockups very shortly after boot. > > Everything becomes jerky. > > > > The only visible in the log indication is something like : > > .... > > [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking clocksource 'tsc' as unstable because the skew is too large: > > [ 59.802134] clocksource: 'hpet' wd_now: 3326e7aa wd_last: 329956f8 mask: ffffffff > > [ 59.802137] clocksource: 'tsc' cs_now: 423662bc6f cs_last: 41dfc91650 mask: ffffffffffffffff > > [ 59.802140] tsc: Marking TSC unstable due to clocksource watchdog > > [ 59.802158] TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'. > > [ 59.802161] sched_clock: Marking unstable (59802142067, 15510)<-(59920871789, -118714277) > > [ 60.015604] clocksource: Switched to clocksource hpet > > [ 89.015994] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 209.660 msecs > > [ 89.016003] perf: interrupt took too long (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to 1000 > > .... > > > > Just reverting that commit on top of linus mainline cures all the symptoms > > Interesting. Do you still get HPET interrupts? Sorry, I might need some basic help here (i.e where do I count them...) After the watchdog switches the clocksource to hpet the system is still somewhat alive, so I'll guess some clock is still ticking.... -Yanko ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) 2017-09-19 15:40 ` Yanko Kaneti @ 2017-09-19 15:51 ` Marc Zyngier 2017-09-20 0:30 ` Chuck Ebbert 0 siblings, 1 reply; 8+ messages in thread From: Marc Zyngier @ 2017-09-19 15:51 UTC (permalink / raw) To: Yanko Kaneti; +Cc: LKML, Thomas Gleixner On 19/09/17 16:40, Yanko Kaneti wrote: > On Tue, 2017-09-19 at 16:33 +0100, Marc Zyngier wrote: >> On 19/09/17 16:12, Yanko Kaneti wrote: >>> Hello, >>> >>> Fedora rawhide config here. >>> AMD FX-8370E >>> >>> Bisected a problem to: >>> 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) >>> >>> It seems to be causing stalls, short lived or long lived lockups very shortly after boot. >>> Everything becomes jerky. >>> >>> The only visible in the log indication is something like : >>> .... >>> [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking clocksource 'tsc' as unstable because the skew is too large: >>> [ 59.802134] clocksource: 'hpet' wd_now: 3326e7aa wd_last: 329956f8 mask: ffffffff >>> [ 59.802137] clocksource: 'tsc' cs_now: 423662bc6f cs_last: 41dfc91650 mask: ffffffffffffffff >>> [ 59.802140] tsc: Marking TSC unstable due to clocksource watchdog >>> [ 59.802158] TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'. >>> [ 59.802161] sched_clock: Marking unstable (59802142067, 15510)<-(59920871789, -118714277) >>> [ 60.015604] clocksource: Switched to clocksource hpet >>> [ 89.015994] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 209.660 msecs >>> [ 89.016003] perf: interrupt took too long (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to 1000 >>> .... >>> >>> Just reverting that commit on top of linus mainline cures all the symptoms >> >> Interesting. Do you still get HPET interrupts? > > Sorry, I might need some basic help here (i.e where do I count them...) /proc/interrupts should display them. > After the watchdog switches the clocksource to hpet the system is still > somewhat alive, so I'll guess some clock is still ticking.... Probably, but I suspect they're not hitting the right CPU, hence the lockups. Unfortunately, my x86-foo is pretty minimal, and I'm about to drop off the net for a few days. Thomas, any insight? Thanks, M. -- Jazz is not dead. It just smells funny... ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) 2017-09-19 15:51 ` Marc Zyngier @ 2017-09-20 0:30 ` Chuck Ebbert 2017-10-01 12:46 ` Thorsten Leemhuis 0 siblings, 1 reply; 8+ messages in thread From: Chuck Ebbert @ 2017-09-20 0:30 UTC (permalink / raw) To: Marc Zyngier; +Cc: Yanko Kaneti, LKML, Thomas Gleixner On Tue, 19 Sep 2017 16:51:06 +0100 Marc Zyngier <marc.zyngier@arm.com> wrote: > On 19/09/17 16:40, Yanko Kaneti wrote: > > On Tue, 2017-09-19 at 16:33 +0100, Marc Zyngier wrote: > >> On 19/09/17 16:12, Yanko Kaneti wrote: > >>> Hello, > >>> > >>> Fedora rawhide config here. > >>> AMD FX-8370E > >>> > >>> Bisected a problem to: > >>> 74def747bcd0 (genirq: Restrict effective affinity to interrupts > >>> actually using it) > >>> > >>> It seems to be causing stalls, short lived or long lived lockups > >>> very shortly after boot. Everything becomes jerky. > >>> > >>> The only visible in the log indication is something like : > >>> .... > >>> [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking > >>> clocksource 'tsc' as unstable because the skew is too large: > >>> [ 59.802134] clocksource: 'hpet' wd_now: > >>> 3326e7aa wd_last: 329956f8 mask: ffffffff [ 59.802137] > >>> clocksource: 'tsc' cs_now: 423662bc6f > >>> cs_last: 41dfc91650 mask: ffffffffffffffff [ 59.802140] tsc: > >>> Marking TSC unstable due to clocksource watchdog [ 59.802158] > >>> TSC found unstable after boot, most likely due to broken BIOS. > >>> Use 'tsc=unstable'. [ 59.802161] sched_clock: Marking unstable > >>> (59802142067, 15510)<-(59920871789, -118714277) [ 60.015604] > >>> clocksource: Switched to clocksource hpet [ 89.015994] INFO: > >>> NMI handler (perf_event_nmi_handler) took too long to run: > >>> 209.660 msecs [ 89.016003] perf: interrupt took too long > >>> (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to > >>> 1000 .... > >>> > >>> Just reverting that commit on top of linus mainline cures all the > >>> symptoms > >> > >> Interesting. Do you still get HPET interrupts? > > > > Sorry, I might need some basic help here (i.e where do I count > > them...) > > /proc/interrupts should display them. > > > After the watchdog switches the clocksource to hpet the system is > > still somewhat alive, so I'll guess some clock is still > > ticking.... > Probably, but I suspect they're not hitting the right CPU, hence the > lockups. > > Unfortunately, my x86-foo is pretty minimal, and I'm about to drop off > the net for a few days. > > Thomas, any insight? Looking at flat_cpu_mask_to_apicid(), I don't see how 74def747bcd0 can be correct: struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); unsigned long cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; if (!cpu_mask) return -EINVAL; *apicid = (unsigned int)cpu_mask; cpumask_bits(effmsk)[0] = cpu_mask; Before that patch, this function wrote to the effective mask unconditionally. After, it only writes to effective_mask if it is already non-zero. ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) 2017-09-20 0:30 ` Chuck Ebbert @ 2017-10-01 12:46 ` Thorsten Leemhuis 2017-10-01 13:06 ` Yanko Kaneti 0 siblings, 1 reply; 8+ messages in thread From: Thorsten Leemhuis @ 2017-10-01 12:46 UTC (permalink / raw) To: Chuck Ebbert, Marc Zyngier; +Cc: Yanko Kaneti, LKML, Thomas Gleixner Hi, the regression tracker here. What's the status of this issue? Was the problem fixed? It seems nothing happened for more than 10 days -- or did the discussion move somewhere else? Ciao, Thorsten On 20.09.2017 02:30, Chuck Ebbert wrote: > On Tue, 19 Sep 2017 16:51:06 +0100 > Marc Zyngier <marc.zyngier@arm.com> wrote: > >> On 19/09/17 16:40, Yanko Kaneti wrote: >>> On Tue, 2017-09-19 at 16:33 +0100, Marc Zyngier wrote: >>>> On 19/09/17 16:12, Yanko Kaneti wrote: >>>>> Hello, >>>>> >>>>> Fedora rawhide config here. >>>>> AMD FX-8370E >>>>> >>>>> Bisected a problem to: >>>>> 74def747bcd0 (genirq: Restrict effective affinity to interrupts >>>>> actually using it) >>>>> >>>>> It seems to be causing stalls, short lived or long lived lockups >>>>> very shortly after boot. Everything becomes jerky. >>>>> >>>>> The only visible in the log indication is something like : >>>>> .... >>>>> [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking >>>>> clocksource 'tsc' as unstable because the skew is too large: >>>>> [ 59.802134] clocksource: 'hpet' wd_now: >>>>> 3326e7aa wd_last: 329956f8 mask: ffffffff [ 59.802137] >>>>> clocksource: 'tsc' cs_now: 423662bc6f >>>>> cs_last: 41dfc91650 mask: ffffffffffffffff [ 59.802140] tsc: >>>>> Marking TSC unstable due to clocksource watchdog [ 59.802158] >>>>> TSC found unstable after boot, most likely due to broken BIOS. >>>>> Use 'tsc=unstable'. [ 59.802161] sched_clock: Marking unstable >>>>> (59802142067, 15510)<-(59920871789, -118714277) [ 60.015604] >>>>> clocksource: Switched to clocksource hpet [ 89.015994] INFO: >>>>> NMI handler (perf_event_nmi_handler) took too long to run: >>>>> 209.660 msecs [ 89.016003] perf: interrupt took too long >>>>> (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to >>>>> 1000 .... >>>>> >>>>> Just reverting that commit on top of linus mainline cures all the >>>>> symptoms >>>> >>>> Interesting. Do you still get HPET interrupts? >>> >>> Sorry, I might need some basic help here (i.e where do I count >>> them...) >> >> /proc/interrupts should display them. >> >>> After the watchdog switches the clocksource to hpet the system is >>> still somewhat alive, so I'll guess some clock is still >>> ticking.... >> Probably, but I suspect they're not hitting the right CPU, hence the >> lockups. >> >> Unfortunately, my x86-foo is pretty minimal, and I'm about to drop off >> the net for a few days. >> >> Thomas, any insight? > > Looking at flat_cpu_mask_to_apicid(), I don't see how 74def747bcd0 > can be correct: > > struct cpumask *effmsk = > irq_data_get_effective_affinity_mask(irqdata); unsigned long > cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; > > if (!cpu_mask) > return -EINVAL; > *apicid = (unsigned int)cpu_mask; > cpumask_bits(effmsk)[0] = cpu_mask; > > Before that patch, this function wrote to the effective mask > unconditionally. After, it only writes to effective_mask if it is > already non-zero. > > > http://news.gmane.org/find-root.php?message_id=20170919203044.560cb9f1%40gmail.com > http://mid.gmane.org/20170919203044.560cb9f1%40gmail.com > ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) 2017-10-01 12:46 ` Thorsten Leemhuis @ 2017-10-01 13:06 ` Yanko Kaneti 2017-10-01 13:17 ` Thorsten Leemhuis 0 siblings, 1 reply; 8+ messages in thread From: Yanko Kaneti @ 2017-10-01 13:06 UTC (permalink / raw) To: Thorsten Leemhuis; +Cc: LKML, Thomas Gleixner, Chuck Ebbert, Marc Zyngier On Sun, 2017-10-01 at 14:46 +0200, Thorsten Leemhuis wrote: > Hi, the regression tracker here. What's the status of this issue? Was > the problem fixed? It seems nothing happened for more than 10 days -- or > did the discussion move somewhere else? Ciao, Thorsten The commit was reverted last week before rc2 https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=0551968add53777fddd18f4ffb4e3bbc1f646d79 Thanks for tracking it -Yanko > > On 20.09.2017 02:30, Chuck Ebbert wrote: > > On Tue, 19 Sep 2017 16:51:06 +0100 > > Marc Zyngier <marc.zyngier@arm.com> wrote: > > > > > On 19/09/17 16:40, Yanko Kaneti wrote: > > > > On Tue, 2017-09-19 at 16:33 +0100, Marc Zyngier wrote: > > > > > On 19/09/17 16:12, Yanko Kaneti wrote: > > > > > > Hello, > > > > > > > > > > > > Fedora rawhide config here. > > > > > > AMD FX-8370E > > > > > > > > > > > > Bisected a problem to: > > > > > > 74def747bcd0 (genirq: Restrict effective affinity to interrupts > > > > > > actually using it) > > > > > > > > > > > > It seems to be causing stalls, short lived or long lived lockups > > > > > > very shortly after boot. Everything becomes jerky. > > > > > > > > > > > > The only visible in the log indication is something like : > > > > > > .... > > > > > > [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking > > > > > > clocksource 'tsc' as unstable because the skew is too large: > > > > > > [ 59.802134] clocksource: 'hpet' wd_now: > > > > > > 3326e7aa wd_last: 329956f8 mask: ffffffff [ 59.802137] > > > > > > clocksource: 'tsc' cs_now: 423662bc6f > > > > > > cs_last: 41dfc91650 mask: ffffffffffffffff [ 59.802140] tsc: > > > > > > Marking TSC unstable due to clocksource watchdog [ 59.802158] > > > > > > TSC found unstable after boot, most likely due to broken BIOS. > > > > > > Use 'tsc=unstable'. [ 59.802161] sched_clock: Marking unstable > > > > > > (59802142067, 15510)<-(59920871789, -118714277) [ 60.015604] > > > > > > clocksource: Switched to clocksource hpet [ 89.015994] INFO: > > > > > > NMI handler (perf_event_nmi_handler) took too long to run: > > > > > > 209.660 msecs [ 89.016003] perf: interrupt took too long > > > > > > (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to > > > > > > 1000 .... > > > > > > > > > > > > Just reverting that commit on top of linus mainline cures all the > > > > > > symptoms > > > > > > > > > > Interesting. Do you still get HPET interrupts? > > > > > > > > Sorry, I might need some basic help here (i.e where do I count > > > > them...) > > > > > > /proc/interrupts should display them. > > > > > > > After the watchdog switches the clocksource to hpet the system is > > > > still somewhat alive, so I'll guess some clock is still > > > > ticking.... > > > > > > Probably, but I suspect they're not hitting the right CPU, hence the > > > lockups. > > > > > > Unfortunately, my x86-foo is pretty minimal, and I'm about to drop off > > > the net for a few days. > > > > > > Thomas, any insight? > > > > Looking at flat_cpu_mask_to_apicid(), I don't see how 74def747bcd0 > > can be correct: > > > > struct cpumask *effmsk = > > irq_data_get_effective_affinity_mask(irqdata); unsigned long > > cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; > > > > if (!cpu_mask) > > return -EINVAL; > > *apicid = (unsigned int)cpu_mask; > > cpumask_bits(effmsk)[0] = cpu_mask; > > > > Before that patch, this function wrote to the effective mask > > unconditionally. After, it only writes to effective_mask if it is > > already non-zero. > > > > > > http://news.gmane.org/find-root.php?message_id=20170919203044.560cb9f1%40gmail.com > > http://mid.gmane.org/20170919203044.560cb9f1%40gmail.com > > ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) 2017-10-01 13:06 ` Yanko Kaneti @ 2017-10-01 13:17 ` Thorsten Leemhuis 0 siblings, 0 replies; 8+ messages in thread From: Thorsten Leemhuis @ 2017-10-01 13:17 UTC (permalink / raw) To: Yanko Kaneti; +Cc: LKML, Thomas Gleixner, Chuck Ebbert, Marc Zyngier On 01.10.2017 15:06, Yanko Kaneti wrote: > On Sun, 2017-10-01 at 14:46 +0200, Thorsten Leemhuis wrote: >> Hi, the regression tracker here. What's the status of this issue? Was >> the problem fixed? It seems nothing happened for more than 10 days -- or >> did the discussion move somewhere else? Ciao, Thorsten > The commit was reverted last week before rc2 > https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=0551968add53777fddd18f4ffb4e3bbc1f646d79 I could have sworn I checked that :-/ Thx for the hint and sorry for the noise! Ciao, Thorsten >> On 20.09.2017 02:30, Chuck Ebbert wrote: >>> On Tue, 19 Sep 2017 16:51:06 +0100 >>> Marc Zyngier <marc.zyngier@arm.com> wrote: >>> >>>> On 19/09/17 16:40, Yanko Kaneti wrote: >>>>> On Tue, 2017-09-19 at 16:33 +0100, Marc Zyngier wrote: >>>>>> On 19/09/17 16:12, Yanko Kaneti wrote: >>>>>>> Hello, >>>>>>> >>>>>>> Fedora rawhide config here. >>>>>>> AMD FX-8370E >>>>>>> >>>>>>> Bisected a problem to: >>>>>>> 74def747bcd0 (genirq: Restrict effective affinity to interrupts >>>>>>> actually using it) >>>>>>> >>>>>>> It seems to be causing stalls, short lived or long lived lockups >>>>>>> very shortly after boot. Everything becomes jerky. >>>>>>> >>>>>>> The only visible in the log indication is something like : >>>>>>> .... >>>>>>> [ 59.802129] clocksource: timekeeping watchdog on CPU3: Marking >>>>>>> clocksource 'tsc' as unstable because the skew is too large: >>>>>>> [ 59.802134] clocksource: 'hpet' wd_now: >>>>>>> 3326e7aa wd_last: 329956f8 mask: ffffffff [ 59.802137] >>>>>>> clocksource: 'tsc' cs_now: 423662bc6f >>>>>>> cs_last: 41dfc91650 mask: ffffffffffffffff [ 59.802140] tsc: >>>>>>> Marking TSC unstable due to clocksource watchdog [ 59.802158] >>>>>>> TSC found unstable after boot, most likely due to broken BIOS. >>>>>>> Use 'tsc=unstable'. [ 59.802161] sched_clock: Marking unstable >>>>>>> (59802142067, 15510)<-(59920871789, -118714277) [ 60.015604] >>>>>>> clocksource: Switched to clocksource hpet [ 89.015994] INFO: >>>>>>> NMI handler (perf_event_nmi_handler) took too long to run: >>>>>>> 209.660 msecs [ 89.016003] perf: interrupt took too long >>>>>>> (1638003 > 2500), lowering kernel.perf_event_max_sample_rate to >>>>>>> 1000 .... >>>>>>> >>>>>>> Just reverting that commit on top of linus mainline cures all the >>>>>>> symptoms >>>>>> >>>>>> Interesting. Do you still get HPET interrupts? >>>>> >>>>> Sorry, I might need some basic help here (i.e where do I count >>>>> them...) >>>> >>>> /proc/interrupts should display them. >>>> >>>>> After the watchdog switches the clocksource to hpet the system is >>>>> still somewhat alive, so I'll guess some clock is still >>>>> ticking.... >>>> >>>> Probably, but I suspect they're not hitting the right CPU, hence the >>>> lockups. >>>> >>>> Unfortunately, my x86-foo is pretty minimal, and I'm about to drop off >>>> the net for a few days. >>>> >>>> Thomas, any insight? >>> >>> Looking at flat_cpu_mask_to_apicid(), I don't see how 74def747bcd0 >>> can be correct: >>> >>> struct cpumask *effmsk = >>> irq_data_get_effective_affinity_mask(irqdata); unsigned long >>> cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; >>> >>> if (!cpu_mask) >>> return -EINVAL; >>> *apicid = (unsigned int)cpu_mask; >>> cpumask_bits(effmsk)[0] = cpu_mask; >>> >>> Before that patch, this function wrote to the effective mask >>> unconditionally. After, it only writes to effective_mask if it is >>> already non-zero. >>> >>> >>> http://news.gmane.org/find-root.php?message_id=20170919203044.560cb9f1%40gmail.com >>> http://mid.gmane.org/20170919203044.560cb9f1%40gmail.com >>> > ^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2017-10-01 13:17 UTC | newest] Thread overview: 8+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2017-09-19 15:12 [regression 4.14rc] 74def747bcd0 (genirq: Restrict effective affinity to interrupts actually using it) Yanko Kaneti 2017-09-19 15:33 ` Marc Zyngier 2017-09-19 15:40 ` Yanko Kaneti 2017-09-19 15:51 ` Marc Zyngier 2017-09-20 0:30 ` Chuck Ebbert 2017-10-01 12:46 ` Thorsten Leemhuis 2017-10-01 13:06 ` Yanko Kaneti 2017-10-01 13:17 ` Thorsten Leemhuis
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.