search for: nohz

...d wherin it calls the VCPUOP_down hypercall which offlines the vCPU. However, when the vCPU is onlined back, it resumes execution right after VCPUOP_down hypercall. That was OK (albeit the API for play_dead assumes that the CPU stays dead and never returns) but with commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down) that is no longer safe as said commit resets the ts->inidle which at the start of the cpu_idle loop was set. The net effect is that we get this warn: Broke affinity for irq 16 installing Xen timer for CPU 1 cpu 1 spinlock event irq 48 ------------[ cut here ]---------...

More goo from hrtimers integration. We do compile and run properly with NO_HZ enabled. There was a period when we didn't because of a missing export, but that was since fixed. And with the clocksource code now firmly in place, we can get rid of code that fixes up the wallclock, since this is done in the common infrastructure. This actually fixes a timer bug as well, that was caused by

At http://namei.org/misc/lguest/patches/time/v02/ Current status: - Resync to recent upstream lguest patch queue - Rudimentary clock event device is working, but with a significant performance hit - Old TSC code included, still needs to be modified to handle freq change Next: - Check for pending interrupts after they're enabled again per suggestion from Rusty. -- James Morris

More goo from hrtimers integration. We do compile and run properly with NO_HZ enabled. There was a period when we didn't because of a missing export, but that was since fixed. And with the clocksource code now firmly in place, we can get rid of code that fixes up the wallclock, since this is done in the common infrastructure. This actually fixes a timer bug as well, that was caused by

At http://namei.org/misc/lguest/patches/time/v02/ Current status: - Resync to recent upstream lguest patch queue - Rudimentary clock event device is working, but with a significant performance hit - Old TSC code included, still needs to be modified to handle freq change Next: - Check for pending interrupts after they're enabled again per suggestion from Rusty. -- James Morris

__napi_schedule might raise softirq but nothing causes do_softirq to trigger, so it does not in fact run. As a result, the error message "NOHZ: local_softirq_pending 08" sometimes occurs during boot of a KVM guest when the network service is started and we are oom: ... Bringing up loopback interface: [ OK ] Bringing up interface eth0: Determining IP information for eth0...NOHZ: local_softirq_pending 08 done. [ OK ]...

__napi_schedule might raise softirq but nothing causes do_softirq to trigger, so it does not in fact run. As a result, the error message "NOHZ: local_softirq_pending 08" sometimes occurs during boot of a KVM guest when the network service is started and we are oom: ... Bringing up loopback interface: [ OK ] Bringing up interface eth0: Determining IP information for eth0...NOHZ: local_softirq_pending 08 done. [ OK ]...

...0000 nsec (...) CE: xen increased min_delta_ns to 4000000 nsec CE: Reprogramming failure. Giving up This messages doesn''t exists in successful boot. I''ve also tried some options to xen and domU kernel, but without success (all combinations): xen: tsc=unstable, cpufreq=none domU: nohz=off, clocksource=tsc Some combination of above options lowered frequency of problem (ex tsc=unstable + nohz=off), but it happens quite often - like 1 of 15 boots fails. Have you idea what is the cause and what can help? Attached all relevant logs and configs: xl-dmesg: xl dmesg after failed domU...

...m does not support PCI [ 0.160322] NetLabel: Initializing [ 0.160322] NetLabel: domain hash size = 128 [ 0.160322] NetLabel: protocols = UNLABELED CIPSOv4 [ 0.160322] NetLabel: unlabeled traffic allowed by default [ 0.160322] Switching to clocksource xen [ 0.160805] Switched to NOHz mode on CPU #0 [ 0.162490] AppArmor: AppArmor Filesystem Enabled [ 0.162490] pnp: PnP ACPI: disabled [ 0.162668] NET: Registered protocol family 2 [ 0.162767] IP route cache hash table entries: 131072 (order: 8, 1048576 bytes) [ 0.163243] Switched to NOHz mode on CPU #1 [ 0.16325...

With the ATI bug I was hitting earlier fixed, only my btrfs partition continues to show high cpu usage for some operations. Rsync, git pull, git checkout and svn up are typicall operations which trigger the high cpu usage. As an example, this perf report is from using git checkout to change to a new branch; the change needed to checkout 208 files out of about 1600 total files. du(1) reports

...metal. Add a generic idle poll before enter >>> real idle path. When a reschedule event is pending, we can bypass >>> the real idle path. >> Why not do a HV specific idle driver? > If I understand the problem correctly then he wants to avoid the heavy > lifting in tick_nohz_idle_enter() in the first place, but there is already > an interesting quirk there which makes it exit early. See commit > 3c5d92a0cfb5 ("nohz: Introduce arch_needs_cpu"). The reason for this commit > looks similar. But lets not proliferate that. I'd rather see that go away....

...sions about probabilistic polling I really need to write up which data needs to considerd to make decisions about probabilistic polling. At last several months, I always focused on the data _from idle to reschedule_, then to bypass the idle loops. unfortunately, this makes me touch scheduler/idle/nohz code inevitably. with tglx's suggestion, the data which is necessary to make power/idle state decisions, is the last idle state's residency time. IIUC this data is duration from idle to wakeup, which maybe by reschedule irq or other irq. I also test that the reschedule irq overlap by more...

...sions about probabilistic polling I really need to write up which data needs to considerd to make decisions about probabilistic polling. At last several months, I always focused on the data _from idle to reschedule_, then to bypass the idle loops. unfortunately, this makes me touch scheduler/idle/nohz code inevitably. with tglx's suggestion, the data which is necessary to make power/idle state decisions, is the last idle state's residency time. IIUC this data is duration from idle to wakeup, which maybe by reschedule irq or other irq. I also test that the reschedule irq overlap by more...

...ve than bare metal. Add a generic idle poll before enter > > real idle path. When a reschedule event is pending, we can bypass > > the real idle path. > > Why not do a HV specific idle driver? If I understand the problem correctly then he wants to avoid the heavy lifting in tick_nohz_idle_enter() in the first place, but there is already an interesting quirk there which makes it exit early. See commit 3c5d92a0cfb5 ("nohz: Introduce arch_needs_cpu"). The reason for this commit looks similar. But lets not proliferate that. I'd rather see that go away. But the irq_t...

...ve than bare metal. Add a generic idle poll before enter > > real idle path. When a reschedule event is pending, we can bypass > > the real idle path. > > Why not do a HV specific idle driver? If I understand the problem correctly then he wants to avoid the heavy lifting in tick_nohz_idle_enter() in the first place, but there is already an interesting quirk there which makes it exit early. See commit 3c5d92a0cfb5 ("nohz: Introduce arch_needs_cpu"). The reason for this commit looks similar. But lets not proliferate that. I'd rather see that go away. But the irq_t...

...idle poll before enter >>>> real idle path. When a reschedule event is pending, we can bypass >>>> the real idle path. >>> Why not do a HV specific idle driver? >> If I understand the problem correctly then he wants to avoid the heavy >> lifting in tick_nohz_idle_enter() in the first place, but there is >> already >> an interesting quirk there which makes it exit early.? See commit >> 3c5d92a0cfb5 ("nohz: Introduce arch_needs_cpu"). The reason for this >> commit >> looks similar. But lets not proliferate that. I&...

...idle poll before enter >>>> real idle path. When a reschedule event is pending, we can bypass >>>> the real idle path. >>> Why not do a HV specific idle driver? >> If I understand the problem correctly then he wants to avoid the heavy >> lifting in tick_nohz_idle_enter() in the first place, but there is >> already >> an interesting quirk there which makes it exit early.? See commit >> 3c5d92a0cfb5 ("nohz: Introduce arch_needs_cpu"). The reason for this >> commit >> looks similar. But lets not proliferate that. I&...

...us git tree from: > > git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-core-for-linus > > HEAD: eec19d1a0d04c80e66eef634f7b8f460f2ca5643 Merge branch ''linus'' into timers/core > > Continued cleanups of the core time and NTP code, plus more nohz > work preparing for tick-less userspace execution. > > Thanks, > > Ingo > > ------------------> > Frederic Weisbecker (5): > nohz: Separate idle sleeping time accounting from nohz logic > nohz: Make nohz API agnostic against idle ticks cputime acc...

...ter >>>>> real idle path. When a reschedule event is pending, we can bypass >>>>> the real idle path. >>>> Why not do a HV specific idle driver? >>> If I understand the problem correctly then he wants to avoid the heavy >>> lifting in tick_nohz_idle_enter() in the first place, but there is >>> already >>> an interesting quirk there which makes it exit early.? See commit >>> 3c5d92a0cfb5 ("nohz: Introduce arch_needs_cpu"). The reason for this >>> commit >>> looks similar. But lets not...

...c polling > > I really need to write up which data needs to considerd to make > decisions about probabilistic polling. At last several months, > I always focused on the data _from idle to reschedule_, then to bypass > the idle loops. unfortunately, this makes me touch scheduler/idle/nohz > code inevitably. > > with tglx's suggestion, the data which is necessary to make power/idle > state decisions, is the last idle state's residency time. IIUC this data > is duration from idle to wakeup, which maybe by reschedule irq or other irq. That's part of the pic...