linux/kernel/hrtimer.c, branch mybooklive

hrtimer: Tune hrtimer_interrupt hang logic

2010-04-01T22:58:14Z

commit 41d2e494937715d3150e5c75d01f0e75ae899337 upstream. The hrtimer_interrupt hang logic adjusts min_delta_ns based on the execution time of the hrtimer callbacks. This is error-prone for virtual machines, where a guest vcpu can be scheduled out during the execution of the callbacks (and the callbacks themselves can do operations that translate to blocking operations in the hypervisor), which in can lead to large min_delta_ns rendering the system unusable. Replace the current heuristics with something more reliable. Allow the interrupt code to try 3 times to catch up with the lost time. If that fails use the total time spent in the interrupt handler to defer the next timer interrupt so the system can catch up with other things which got delayed. Limit that deferment to 100ms. The retry events and the maximum time spent in the interrupt handler are recorded and exposed via /proc/timer_list Inspired by a patch from Marcelo. Reported-by: Michael Tokarev Signed-off-by: Thomas Gleixner Tested-by: Marcelo Tosatti Cc: kvm@vger.kernel.org Cc: Jeremy Fitzhardinge Signed-off-by: Greg Kroah-Hartman

Merge branch 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

2009-10-05T19:04:16Z

* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: hrtimer: Remove overly verbose "switch to high res mode" message

Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

2009-09-27T17:39:04Z

* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: hrtimer: Eliminate needless reprogramming of clock events device

hrtimer: Remove overly verbose "switch to high res mode" message

2009-09-26T14:58:09Z

On big systems, printing copies of Switched to high resolution mode on CPU nnn clutters up the kernel log for minimal gain. Just get rid of them. Signed-off-by: Roland Dreier LKML-Reference: Signed-off-by: Ingo Molnar

Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

2009-09-23T16:46:15Z

* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: itimers: Add tracepoints for itimer hrtimer: Add tracepoint for hrtimers timers: Add tracepoints for timer_list timers cputime: Optimize jiffies_to_cputime(1) itimers: Simplify arm_timer() code a bit itimers: Fix periodic tics precision itimers: Merge ITIMER_VIRT and ITIMER_PROF Trivial header file include conflicts in kernel/fork.c

Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

2009-09-18T16:15:24Z

* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (34 commits) time: Prevent 32 bit overflow with set_normalized_timespec() clocksource: Delay clocksource down rating to late boot clocksource: clocksource_select must be called with mutex locked clocksource: Resolve cpu hotplug dead lock with TSC unstable, fix crash timers: Drop a function prototype clocksource: Resolve cpu hotplug dead lock with TSC unstable timer.c: Fix S/390 comments timekeeping: Fix invalid getboottime() value timekeeping: Fix up read_persistent_clock() breakage on sh timekeeping: Increase granularity of read_persistent_clock(), build fix time: Introduce CLOCK_REALTIME_COARSE x86: Do not unregister PIT clocksource on PIT oneshot setup/shutdown clocksource: Avoid clocksource watchdog circular locking dependency clocksource: Protect the watchdog rating changes with clocksource_mutex clocksource: Call clocksource_change_rating() outside of watchdog_lock timekeeping: Introduce read_boot_clock timekeeping: Increase granularity of read_persistent_clock() timekeeping: Update clocksource with stop_machine timekeeping: Add timekeeper read_clock helper functions timekeeping: Move NTP adjusted clock multiplier to struct timekeeper ... Fix trivial conflict due to MIPS lemote -> loongson renaming.

hrtimer: Eliminate needless reprogramming of clock events device

2009-09-15T15:09:44Z

On NOHZ systems the following timers, - tick_nohz_restart_sched_tick (tick_sched_timer) - hrtimer_start (tick_sched_timer) are reprogramming the clock events device far more often than needed. No specific test case was required to observe this effect. This occurres because there was no check to see if the currently removed or restarted hrtimer was: 1) the one which previously armed the clock events device. 2) going to be replaced by another timer which has the same expiry time. Avoid the reprogramming in hrtimer_force_reprogram when the new expiry value which is evaluated from the clock bases is equal to cpu_base->expires_next. This results in faster application startup time by ~4%. [ tglx: simplified initial solution ] Signed-off-by: Ashwin Chaugule LKML-Reference: <4AA00165.90609@codeaurora.org> Signed-off-by: Thomas Gleixner

hrtimer: Add tracepoint for hrtimers

2009-08-29T12:10:06Z

Add tracepoints which cover the life cycle of a hrtimer. The tracepoints are integrated with the already existing debug_object debug points as far as possible. [ tglx: Fixed comments, made output conistent, easier to read and parse. Fixed output for 32bit archs which do not use the scalar representation of ktime_t. Hand current time to trace_hrtimer_expiry_entry instead of calling get_time() inside of the trace assignment. ] Signed-off-by: Xiao Guangrong Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Mathieu Desnoyers Cc: Anton Blanchard Cc: Peter Zijlstra Cc: KOSAKI Motohiro Cc: Zhaolei LKML-Reference: <4A7F8B2B.5020908@cn.fujitsu.com> Signed-off-by: Thomas Gleixner

pktgen: spin using hrtimer

2009-08-29T06:41:29Z

This changes how the pktgen thread spins/waits between packets if delay is configured. It uses a high res timer to wait for time to arrive. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller

Merge branch 'linus' into timers/core

2009-08-14T13:59:30Z

Reason: Martin's timekeeping cleanup series depends on both timers/core and mainline changes. Signed-off-by: Thomas Gleixner