remarkable-linux/kernel
Peter Zijlstra 0d66bf6d35 mutex: implement adaptive spinning
Change mutex contention behaviour such that it will sometimes busy wait on
acquisition - moving its behaviour closer to that of spinlocks.

This concept got ported to mainline from the -rt tree, where it was originally
implemented for rtmutexes by Steven Rostedt, based on work by Gregory Haskins.

Testing with Ingo's test-mutex application (http://lkml.org/lkml/2006/1/8/50)
gave a 345% boost for VFS scalability on my testbox:

 # ./test-mutex-shm V 16 10 | grep "^avg ops"
 avg ops/sec:               296604

 # ./test-mutex-shm V 16 10 | grep "^avg ops"
 avg ops/sec:               85870

The key criteria for the busy wait is that the lock owner has to be running on
a (different) cpu. The idea is that as long as the owner is running, there is a
fair chance it'll release the lock soon, and thus we'll be better off spinning
instead of blocking/scheduling.

Since regular mutexes (as opposed to rtmutexes) do not atomically track the
owner, we add the owner in a non-atomic fashion and deal with the races in
the slowpath.

Furthermore, to ease the testing of the performance impact of this new code,
there is means to disable this behaviour runtime (without having to reboot
the system), when scheduler debugging is enabled (CONFIG_SCHED_DEBUG=y),
by issuing the following command:

 # echo NO_OWNER_SPIN > /debug/sched_features

This command re-enables spinning again (this is also the default):

 # echo OWNER_SPIN > /debug/sched_features

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-14 18:09:02 +01:00
..
irq async: Asynchronous function calls to speed up kernel boot 2009-01-07 08:45:46 -08:00
power Merge branch 'linus' into release 2009-01-09 03:39:43 -05:00
time Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial 2009-01-07 11:31:52 -08:00
trace Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile 2009-01-09 12:43:06 -08:00
.gitignore
acct.c CRED: Wrap task credential accesses in the core kernel 2008-11-14 10:39:12 +11:00
async.c async: fix __lowest_in_progress() 2009-01-12 16:39:58 -08:00
audit.c [PATCH] fix broken timestamps in AVC generated by kernel threads 2008-12-09 02:27:41 -05:00
audit.h fixing audit rule ordering mess, part 1 2009-01-04 15:14:41 -05:00
audit_tree.c audit: validate comparison operations, store them in sane form 2009-01-04 15:14:42 -05:00
auditfilter.c audit: validate comparison operations, store them in sane form 2009-01-04 15:14:42 -05:00
auditsc.c make sure that filterkey of task,always rules is reported 2009-01-04 15:14:42 -05:00
backtracetest.c backtrace: replace timer with tasklet + completions 2008-06-27 18:09:16 +02:00
bounds.c
capability.c Merge branch 'next' into for-linus 2009-01-07 09:58:22 +11:00
cgroup.c cgroups: add css_tryget() 2009-01-08 08:31:10 -08:00
cgroup_debug.c cgroups: fix probable race with put_css_set[_taskexit] and find_css_set 2008-10-20 08:52:38 -07:00
cgroup_freezer.c freezer_cg: disable writing freezer.state of root cgroup 2008-11-12 17:17:16 -08:00
compat.c Allow times and time system calls to return small negative values 2009-01-06 15:59:13 -08:00
configs.c kernel/configs.c: remove useless comments 2008-10-20 08:52:34 -07:00
cpu.c stop_machine/cpu hotplug: fix disable_nonboot_cpus 2009-01-07 11:36:14 -08:00
cpuset.c cpuset: remove remaining pointers to cpumask_t 2009-01-08 08:31:11 -08:00
cred-internals.h CRED: Inaugurate COW credentials 2008-11-14 10:39:23 +11:00
cred.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6 2009-01-09 13:59:25 -08:00
delayacct.c schedstat: consolidate per-task cpu runtime stats 2008-12-18 13:54:01 +01:00
dma-coherent.c dma-coherent: catch oversized requests to dma_alloc_from_coherent() 2009-01-06 15:59:31 -08:00
dma.c kernel/dma.c: remove a CVS keyword 2008-10-16 11:21:30 -07:00
exec_domain.c proc: move /proc/execdomains to kernel/exec_domain.c 2008-10-23 14:30:41 +04:00
exit.c mm: introduce get_mm_hiwater_xxx(), fix taskstats->hiwater_xxx accounting 2009-01-06 15:59:09 -08:00
extable.c Merge branch 'core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2008-12-30 16:10:19 -08:00
fork.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-2.6-nommu 2009-01-09 14:00:58 -08:00
freezer.c freezer_cg: use thaw_process() in unfreeze_cgroup() 2008-10-30 11:38:45 -07:00
futex.c Merge branches 'core/futexes', 'core/locking', 'core/rcu' and 'linus' into core/urgent 2009-01-06 09:32:11 +01:00
futex_compat.c CRED: Use RCU to access another task's creds and to release a task's own creds 2008-11-14 10:39:19 +11:00
hrtimer.c hrtimer: splitout peek ahead functionality, fix 2009-01-05 14:11:10 +01:00
itimer.c timers: fix itimer/many thread hang 2008-09-14 16:25:35 +02:00
kallsyms.c allow stripping of generated symbols under CONFIG_KALLSYMS_ALL 2008-12-19 22:47:10 +01:00
Kconfig.freezer container freezer: implement freezer cgroup subsystem 2008-10-20 08:52:34 -07:00
Kconfig.hz sched: fix SCHED_HRTICK dependency 2008-07-28 14:37:38 +02:00
Kconfig.preempt rcu: provide RCU options on non-preempt architectures too 2008-12-25 09:31:28 +01:00
kexec.c cpumask: prepare for iterators to only go to nr_cpu_ids/nr_cpumask_bits.: core 2009-01-01 10:12:15 +10:30
kfifo.c
kgdb.c kgdb: call touch_softlockup_watchdog on resume 2008-10-06 13:50:59 -05:00
kmod.c kmod: fix varargs kernel-doc 2009-01-06 15:59:27 -08:00
kprobes.c kprobes: support probing module __init function 2009-01-06 15:59:21 -08:00
ksysfs.c kernel/ksysfs.c:fix dependence on CONFIG_NET 2009-01-06 10:44:31 -08:00
kthread.c tracepoints: add DECLARE_TRACE() and DEFINE_TRACE() 2008-11-16 09:01:36 +01:00
latencytop.c KSYM_SYMBOL_LEN fixes 2008-12-10 08:01:54 -08:00
lockdep.c Merge branch 'core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2008-12-30 16:10:19 -08:00
lockdep_internals.h lockdep: build fix 2008-08-13 12:55:10 +02:00
lockdep_proc.c lockstat: contend with points 2008-10-20 15:43:10 +02:00
Makefile smp_call_function_single(): be slightly less stupid 2009-01-11 03:41:58 +01:00
marker.c markers/tracpoints: fix non-modular build 2008-11-16 09:52:03 +01:00
module.c async: Asynchronous function calls to speed up kernel boot 2009-01-07 08:45:46 -08:00
mutex-debug.c mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
mutex-debug.h mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
mutex.c mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
mutex.h mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
notifier.c Merge commit 'v2.6.28-rc6' into core/debug 2008-11-26 08:22:50 +01:00
ns_cgroup.c ns_cgroup: remove unused spinlock 2009-01-08 08:31:02 -08:00
nsproxy.c User namespaces: set of cleanups (v2) 2008-11-24 18:57:41 -05:00
panic.c oops: increment the oops UUID every time we oops 2009-01-06 15:59:12 -08:00
params.c Fix compile warning in kernel/params.c 2008-10-23 12:09:00 -07:00
pid.c pid: generalize task_active_pid_ns 2009-01-08 08:31:12 -08:00
pid_namespace.c pid_ns: (BUG 11391) change ->child_reaper when init->group_leader exits 2008-09-02 19:21:38 -07:00
pm_qos_params.c pm_qos_requirement might sleep 2008-09-02 19:21:40 -07:00
posix-cpu-timers.c Merge commit 'v2.6.28' into core/core 2008-12-25 13:51:46 +01:00
posix-timers.c Merge branches 'timers/clocksource', 'timers/hpet', 'timers/hrtimers', 'timers/nohz', 'timers/ntp', 'timers/posixtimers' and 'timers/rtc' into timers/core 2008-12-25 18:02:25 +01:00
printk.c trivial: printk: fix indentation of new_text_line declaration 2009-01-06 11:28:06 +01:00
profile.c profile: don't include <asm/ptrace.h> twice. 2009-01-06 15:59:14 -08:00
ptrace.c Merge branch 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2008-12-28 12:21:10 -08:00
rcuclassic.c cpumask: convert RCU implementations, fix 2009-01-03 18:59:25 +01:00
rcupdate.c rcu: eliminate synchronize_rcu_xxx macro 2009-01-05 10:18:08 +01:00
rcupreempt.c rcu: eliminate synchronize_rcu_xxx macro 2009-01-05 10:18:08 +01:00
rcupreempt_trace.c "Tree RCU": scalable classic RCU implementation 2008-12-18 21:56:04 +01:00
rcutorture.c rcu: fix bug in rcutorture system-shutdown code 2009-01-07 23:36:25 +01:00
rcutree.c rcu: make treercu safe for suspend and resume 2009-01-05 10:12:33 +01:00
rcutree_trace.c "Tree RCU": scalable classic RCU implementation 2008-12-18 21:56:04 +01:00
relay.c relayfs: fix infinite loop with splice() 2008-12-10 08:01:52 -08:00
res_counter.c memcg: memory cgroup resource counters for hierarchy 2009-01-08 08:31:05 -08:00
resource.c resource: allow MMIO exclusivity for device drivers 2009-01-07 11:12:32 -08:00
rtmutex-debug.c
rtmutex-debug.h
rtmutex-tester.c sysdev: Pass the attribute to the low level sysdev show/store function 2008-07-21 21:55:02 -07:00
rtmutex.c hrtimer: convert kernel/* to the new hrtimer apis 2008-09-05 21:35:13 -07:00
rtmutex.h
rtmutex_common.h
rwsem.c
sched.c mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
sched_clock.c sched_clock: prevent scd->clock from moving backwards, take #2 2008-12-31 09:53:21 +01:00
sched_cpupri.c sched: fix section mismatch 2009-01-06 11:07:15 +01:00
sched_cpupri.h sched: convert struct cpupri_vec cpumask_var_t. 2008-11-24 17:52:22 +01:00
sched_debug.c sched: partly revert "sched debug: remove NULL checking in print_cfs_rt_rq()" 2009-01-11 02:40:32 +01:00
sched_fair.c generic swap(): sched: remove local swap() macro 2009-01-08 08:31:15 -08:00
sched_features.h mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
sched_idletask.c sched: add CONFIG_SMP consistency 2008-10-22 10:01:52 +02:00
sched_rt.c sched: put back some stack hog changes that were undone in kernel/sched.c 2009-01-03 19:00:09 +01:00
sched_stats.h Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-cpumask into merge-rr-cpumask 2009-01-03 18:53:31 +01:00
seccomp.c
semaphore.c semaphore: __down_common: use signal_pending_state() 2008-08-05 14:33:47 -07:00
signal.c SEND_SIG_NOINFO: set si_pid to tgid instead of pid 2009-01-06 15:59:29 -08:00
smp.c cpumask: prepare for iterators to only go to nr_cpu_ids/nr_cpumask_bits.: core 2009-01-01 10:12:15 +10:30
softirq.c Merge branch 'cpus4096-for-linus-3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-01-03 12:04:39 -08:00
softlockup.c cpumask: convert rest of files in kernel/ 2009-01-01 10:12:28 +10:30
spinlock.c lockdep: spin_lock_nest_lock(), checkpatch fixes 2008-08-13 13:56:51 +02:00
srcu.c
stacktrace.c stacktrace: provide save_stack_trace_tsk() weak alias 2008-12-25 11:44:43 +01:00
stop_machine.c stop_machine: introduce stop_machine_create/destroy. 2009-01-05 08:40:14 +10:30
sys.c Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-01-06 17:10:33 -08:00
sys_ni.c reintroduce accept4 2008-11-19 18:49:57 -08:00
sysctl.c NOMMU: Make mmap allocation page trimming behaviour configurable. 2009-01-08 12:04:47 +00:00
sysctl_check.c [XFS] remove restricted chown parameter from xfs linux 2008-10-30 18:30:09 +11:00
taskstats.c cpumask: convert rest of files in kernel/ 2009-01-01 10:12:28 +10:30
test_kprobes.c kprobes: add tests for register_kprobes 2009-01-06 15:59:20 -08:00
time.c Allow times and time system calls to return small negative values 2009-01-06 15:59:13 -08:00
timeconst.pl Make constants in kernel/timeconst.h fixed 64 bits 2008-05-02 16:18:42 -07:00
timer.c [PATCH] idle cputime accounting 2008-12-31 15:11:46 +01:00
tracepoint.c markers/tracpoints: fix non-modular build 2008-11-16 09:52:03 +01:00
tsacct.c mm: introduce get_mm_hiwater_xxx(), fix taskstats->hiwater_xxx accounting 2009-01-06 15:59:09 -08:00
uid16.c CRED: Wrap current->cred and a few other accessors 2008-11-14 10:39:18 +11:00
up.c smp_call_function_single(): be slightly less stupid, fix #2 2009-01-12 16:04:37 +01:00
user.c Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2008-12-28 12:27:58 -08:00
user_namespace.c User namespaces: set of cleanups (v2) 2008-11-24 18:57:41 -05:00
utsname.c removed unused #include <linux/version.h>'s 2008-08-23 12:14:12 -07:00
utsname_sysctl.c sysctl: simplify ->strategy 2008-10-16 11:21:47 -07:00
wait.c wait: kill is_sync_wait() 2008-10-16 11:21:31 -07:00
workqueue.c cpumask: convert kernel/workqueue.c 2009-01-01 10:12:25 +10:30