talos-op-linux/kernel/time/tick-sched.c, branch v3.7

nohz: Fix one jiffy count too far in idle cputime

2012-10-05T08:22:20+00:00

When we stop the tick in idle, we save the current jiffies value in ts->idle_jiffies. This snapshot is substracted from the later value of jiffies when the tick is restarted and the resulting delta is accounted as idle cputime. This is how we handle the idle cputime accounting without the tick. But sometimes we need to schedule the next tick to some time in the future instead of completely stopping it. In this case, a tick may happen before we restart the periodic behaviour and from that tick we account one jiffy to idle cputime as usual but we also increment the ts->idle_jiffies snapshot by one so that when we compute the delta to account, we substract the one jiffy we just accounted. To prepare for stopping the tick outside idle, we introduced a check that prevents from fixing up that ts->idle_jiffies if we are not running the idle task. But we use idle_cpu() for that and this is a problem if we run the tick while another CPU remotely enqueues a ttwu to our runqueue: CPU 0: CPU 1: tick_sched_timer() { ttwu_queue_remote() if (idle_cpu(CPU 0)) ts->idle_jiffies++; } Here, idle_cpu() notes that &rq->wake_list is not empty and hence won't consider the CPU as idle. As a result, ts->idle_jiffies won't be incremented. But this is wrong because we actually account the current jiffy to idle cputime. And that jiffy won't get substracted from the nohz time delta. So in the end, this jiffy is accounted twice. Fix this by changing idle_cpu(smp_processor_id()) with is_idle_task(current). This way the jiffy is substracted correctly even if a ttwu operation is enqueued on the CPU. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: # 3.5+ Link: http://lkml.kernel.org/r/1349308004-3482-1-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar

Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2012-10-01T17:43:39+00:00

Pull scheduler changes from Ingo Molnar: "Continued quest to clean up and enhance the cputime code by Frederic Weisbecker, in preparation for future tickless kernel features. Other than that, smallish changes." Fix up trivial conflicts due to additions next to each other in arch/{x86/}Kconfig * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits) cputime: Make finegrained irqtime accounting generally available cputime: Gather time/stats accounting config options into a single menu ia64: Reuse system and user vtime accounting functions on task switch ia64: Consolidate user vtime accounting vtime: Consolidate system/idle context detection cputime: Use a proper subsystem naming for vtime related APIs sched: cpu_power: enable ARCH_POWER sched/nohz: Clean up select_nohz_load_balancer() sched: Fix load avg vs. cpu-hotplug sched: Remove __ARCH_WANT_INTERRUPTS_ON_CTXSW sched: Fix nohz_idle_balance() sched: Remove useless code in yield_to() sched: Add time unit suffix to sched sysctl knobs sched/debug: Limit sd->*_idx range on sysctl sched: Remove AFFINE_WAKEUPS feature flag s390: Remove leftover account_tick_vtime() header cputime: Consolidate vtime handling on context switch sched: Move cputime code to its own file cputime: Generalize CONFIG_VIRT_CPU_ACCOUNTING tile: Remove SD_PREFER_LOCAL leftover ...

Merge remote-tracking branch 'tip/core/rcu' into next.2012.09.25b

2012-09-25T17:03:56+00:00

Resolved conflict in kernel/sched/core.c using Peter Zijlstra's approach from https://lkml.org/lkml/2012/9/5/585.

time: RCU permitted to stop idle entry via softirq

2012-09-23T14:42:52+00:00

The can_stop_idle_tick() function complains if a softirq vector is raised too late in the idle-entry process, presumably in order to prevent dangling softirq invocations from being delayed across the full idle period, which might be indefinitely long -- and if softirq was asserted any later than the call to this function, such a delay might well happen. However, RCU needs to be able to use softirq to stop idle entry in order to be able to drain RCU callbacks from the current CPU, which in turn enables faster entry into dyntick-idle mode, which in turn reduces power consumption. Because RCU takes this action at a well-defined point in the idle-entry path, it is safe for RCU to take this approach. This commit therefore silences the error message that is sometimes produced when the going-idle CPU suddenly finds that it has an RCU_SOFTIRQ to process. The error message will continue to be issued for other softirq vectors. Reported-by: Sedat Dilek Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Tested-by: Sedat Dilek Reviewed-by: Josh Triplett

sched/nohz: Clean up select_nohz_load_balancer()

2012-09-13T14:52:05+00:00

There is no load_balancer to be selected now. It just sets the state of the nohz tick to stop. So rename the function, pass the 'cpu' as a parameter and then remove the useless call from tick_nohz_restart_sched_tick(). [ s/set_nohz_tick_stopped/nohz_balance_enter_idle/g s/clear_nohz_tick_stopped/nohz_balance_exit_idle/g ] Signed-off-by: Alex Shi Acked-by: Suresh Siddha Cc: Venkatesh Pallipadi Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1347261059-24747-1-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar

sched: Add missing call to calc_load_exit_idle()

2012-09-04T12:30:29+00:00

Azat Khuzhin reported high loadavg in Linux v3.6 After checking the upstream scheduler code, I found Peter's commit: 5167e8d5417b sched/nohz: Rewrite and fix load-avg computation -- again not fully applied, missing the call to calc_load_exit_idle(). After that idle exit in sampling window will always be calculated to non-idle, and the load will be higher than normal. This patch adds the missing call to calc_load_exit_idle(). Signed-off-by: Charles Wang Cc: stable@kernel.org Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1345449754-27130-1-git-send-email-muming.wq@gmail.com Signed-off-by: Ingo Molnar

Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2012-07-22T18:35:46+00:00

Pull timer core changes from Ingo Molnar: "Continued cleanups of the core time and NTP code, plus more nohz work preparing for tick-less userspace execution." * 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: time: Rework timekeeping functions to take timekeeper ptr as argument time: Move xtime_nsec adjustment underflow handling timekeeping_adjust time: Move arch_gettimeoffset() usage into timekeeping_get_ns() time: Refactor accumulation of nsecs to secs time: Condense timekeeper.xtime into xtime_sec time: Explicitly use u32 instead of int for shift values time: Whitespace cleanups per Ingo%27s requests nohz: Move next idle expiry time record into idle logic area nohz: Move ts->idle_calls incrementation into strict idle logic nohz: Rename ts->idle_tick to ts->last_tick nohz: Make nohz API agnostic against idle ticks cputime accounting nohz: Separate idle sleeping time accounting from nohz logic timers: Improve get_next_timer_interrupt() timers: Add accounting of non deferrable timers timers: Consolidate base->next_timer update timers: Create detach_if_pending() and use it

Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2012-07-22T17:45:05+00:00

Pull RCU changes from Ingo Molnar: "Quoting from Paul, the major features of this series are: 1. Preventing latency spikes of more than 200 microseconds for kernels built with NR_CPUS=4096, which is reportedly becoming the default for some distros. This is a first step, as it does not help with systems that actually -have- 4096 CPUs (work on this case is in progress, but is not yet ready for mainline). This category also includes improving concurrency of rcu_barrier(), placed here due to conflicts. Posted to LKML at: https://lkml.org/lkml/2012/6/22/381 Note that patches 18-22 of that series have been defered to 3.7, as they have not yet proven themselves to be mainline-ready (and yes, these are the ones intended to get rid of RCU's latency spikes for systems that actually have 4096 CPUs). 2. Updates to documentation and rcutorture fixes, the latter category including improvements to rcu_barrier() testing. Posted to LKML at http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/04094.html. 3. Miscellaneous fixes posted to LKML at: https://lkml.org/lkml/2012/6/22/500 with the exception of the last commit, which was posted here: http://www.gossamer-threads.com/lists/linux/kernel/1561830 4. RCU_FAST_NO_HZ fixes and improvements. Posted to LKML at: http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/00006.html http://www.gossamer-threads.com/lists/linux/kernel/1561833 The first four patches of the first series went into 3.5 to fix a regression. 5. Code-style fixes. These were posted to LKML at http://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01180.html http://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01181.html" * 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits) rcu: Fix broken strings in RCU's source code. rcu: Fix code-style issues involving "else" rcu: Introduce check for callback list/count mismatch rcu: Make RCU_FAST_NO_HZ respect nohz= boot parameter rcu: Fix qlen_lazy breakage rcu: Round FAST_NO_HZ lazy timeout to nearest second rcu: The rcu_needs_cpu() function is not a quiescent state rcu: Dump only the current CPU's buffers for idle-entry/exit warnings rcu: Add check for CPUs going offline with callbacks queued rcu: Disable preemption in rcu_blocking_is_gp() rcu: Prevent uninitialized string in RCU CPU stall info rcu: Fix rcu_is_cpu_idle() #ifdef in TINY_RCU rcu: Split RCU core processing out of __call_rcu() rcu: Prevent __call_rcu() from invoking RCU core on offline CPUs rcu: Make __call_rcu() handle invocation from idle rcu: Remove function versions of __kfree_rcu and __is_kfree_rcu_offset rcu: Consolidate tree/tiny __rcu_read_{,un}lock() implementations rcu: Remove return value from rcu_assign_pointer() key: Remove extraneous parentheses from rcu_assign_keypointer() rcu: Remove return value from RCU_INIT_POINTER() ...

Merge branch 'timers/urgent' into timers/core

2012-07-15T08:24:53+00:00

Reason: Update to upstream changes to avoid further conflicts. Fixup a trivial merge conflict in kernel/time/tick-sched.c Signed-off-by: Thomas Gleixner

sched/nohz: Rewrite and fix load-avg computation -- again

2012-07-05T18:58:13+00:00

Thanks to Charles Wang for spotting the defects in the current code: - If we go idle during the sample window -- after sampling, we get a negative bias because we can negate our own sample. - If we wake up during the sample window we get a positive bias because we push the sample to a known active period. So rewrite the entire nohz load-avg muck once again, now adding copious documentation to the code. Reported-and-tested-by: Doug Smythies Reported-and-tested-by: Charles Wang Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1340373782.18025.74.camel@twins [ minor edits ] Signed-off-by: Ingo Molnar