Venkatesh Pallipadi
2f36825b17
sched: Next buddy hint on sleep and preempt path
...
When a task in a taskgroup sleeps, pick_next_task starts all the way back at
the root and picks the task/taskgroup with the min vruntime across all
runnable tasks.
But when there are many frequently sleeping tasks across different taskgroups,
it makes better sense to stay with same taskgroup for its slice period (or
until all tasks in the taskgroup sleeps) instead of switching cross taskgroup
on each sleep after a short runtime.
This helps specifically where taskgroups corresponds to a process with
multiple threads. The change reduces the number of CR3 switches in this case.
Example:
Two taskgroups with 2 threads each which are running for 2ms and
sleeping for 1ms. Looking at sched:sched_switch shows:
BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017]
cpu-soaker-5004 [003] 3683.391089
cpu-soaker-5016 [003] 3683.393106
cpu-soaker-5005 [003] 3683.395119
cpu-soaker-5017 [003] 3683.397130
cpu-soaker-5004 [003] 3683.399143
cpu-soaker-5016 [003] 3683.401155
cpu-soaker-5005 [003] 3683.403168
cpu-soaker-5017 [003] 3683.405170
AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935]
cpu-soaker-21890 [003] 865.895494
cpu-soaker-21935 [003] 865.897506
cpu-soaker-21934 [003] 865.899520
cpu-soaker-21935 [003] 865.901532
cpu-soaker-21934 [003] 865.903543
cpu-soaker-21935 [003] 865.905546
cpu-soaker-21891 [003] 865.907548
cpu-soaker-21890 [003] 865.909560
cpu-soaker-21891 [003] 865.911571
cpu-soaker-21890 [003] 865.913582
cpu-soaker-21891 [003] 865.915594
cpu-soaker-21934 [003] 865.917606
Similar problem is there when there are multiple taskgroups and say a task A
preempts currently running task B of taskgroup_1. On schedule, pick_next_task
can pick an unrelated task on taskgroup_2. Here it would be better to give some
preference to task B on pick_next_task.
A simple (may be extreme case) benchmark I tried was tbench with 2 tbench
client processes with 2 threads each running on a single CPU. Avg throughput
across 5 50 sec runs was:
BEFORE: 105.84 MB/sec
AFTER: 112.42 MB/sec
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-19 10:08:38 +02:00
..
debug
Fix common misspellings
2011-03-31 11:26:23 -03:00
gcov
Merge branch 'trivial' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6
2011-03-20 18:14:55 -07:00
irq
Merge branches 'x86-fixes-for-linus', 'sched-fixes-for-linus', 'timers-fixes-for-linus', 'irq-fixes-for-linus' and 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
2011-04-07 12:12:58 -07:00
power
fix XEN_SAVE_RESTORE Kconfig dependencies
2011-04-11 22:54:48 +02:00
time
Merge branch 'for-linus2' of git://git.profusion.mobi/users/lucas/linux-2.6
2011-04-07 11:14:49 -07:00
trace
Fix common misspellings
2011-03-31 11:26:23 -03:00
.gitignore
acct.c
async.c
audit.c
netlink: kill loginuid/sessionid/sid members from struct netlink_skb_parms
2011-03-03 10:55:40 -08:00
audit.h
audit_tree.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
audit_watch.c
kill path_lookup()
2011-03-14 09:15:23 -04:00
auditfilter.c
netlink: kill loginuid/sessionid/sid members from struct netlink_skb_parms
2011-03-03 10:55:40 -08:00
auditsc.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
backtracetest.c
bounds.c
memcg: remove direct page_cgroup-to-page pointer
2011-03-23 19:46:28 -07:00
capability.c
userns: make has_capability* into real functions
2011-03-23 19:47:06 -07:00
cgroup.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
cgroup_freezer.c
compat.c
posix-timers: Introduce a syscall for clock tuning.
2011-02-02 15:28:19 +01:00
configs.c
cpu.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
cpuset.c
sched: Dynamic sched_domain::level
2011-04-11 14:09:32 +02:00
crash_dump.c
crash_dump: export is_kdump_kernel to modules, consolidate elfcorehdr_addr, setup_elfcorehdr and saved_max_pfn
2011-03-23 19:47:19 -07:00
cred.c
userns: security: make capabilities relative to the user namespace
2011-03-23 19:47:02 -07:00
delayacct.c
dma.c
elfcore.c
exec_domain.c
exit.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
extable.c
fork.c
Merge branch 'for-2.6.39/core' of git://git.kernel.dk/linux-2.6-block
2011-03-24 10:16:26 -07:00
freezer.c
futex.c
Merge branch 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
2011-03-25 17:52:22 -07:00
futex_compat.c
userns: user namespaces: convert several capable() calls
2011-03-23 19:47:08 -07:00
groups.c
userns: user namespaces: convert several capable() calls
2011-03-23 19:47:08 -07:00
hrtimer.c
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
2011-03-15 18:53:35 -07:00
hung_task.c
hw_breakpoint.c
irq_work.c
itimer.c
jump_label.c
kallsyms.c
Merge branch 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
2011-03-25 17:52:22 -07:00
Kconfig.freezer
Kconfig.hz
Kconfig.locks
Kconfig.preempt
kexec.c
Merge branch 'for-linus2' of git://git.profusion.mobi/users/lucas/linux-2.6
2011-04-07 11:14:49 -07:00
kfifo.c
kmod.c
kprobes.c
ksysfs.c
kthread.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
latencytop.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
lockdep.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
lockdep_internals.h
lockdep_proc.c
lockdep: Remove unused 'factor' variable from lockdep_stats_show()
2011-03-23 13:54:47 +01:00
lockdep_states.h
Makefile
crash_dump: export is_kdump_kernel to modules, consolidate elfcorehdr_addr, setup_elfcorehdr and saved_max_pfn
2011-03-23 19:47:19 -07:00
module.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
mutex-debug.c
mutex: Use p->on_cpu for the adaptive spin
2011-04-14 08:52:33 +02:00
mutex-debug.h
mutex: Use p->on_cpu for the adaptive spin
2011-04-14 08:52:33 +02:00
mutex.c
mutex: Use p->on_cpu for the adaptive spin
2011-04-14 08:52:33 +02:00
mutex.h
mutex: Use p->on_cpu for the adaptive spin
2011-04-14 08:52:33 +02:00
notifier.c
ns_cgroup.c
nsproxy.c
userns: user namespaces: convert several capable() calls
2011-03-23 19:47:08 -07:00
padata.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
panic.c
move x86 specific oops=panic to generic code
2011-03-22 17:44:11 -07:00
params.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
perf_event.c
perf: Fix task_struct reference leak
2011-03-31 13:02:56 +02:00
pid.c
export pid symbols needed for kvm_vcpu_on_spin
2011-03-17 13:08:28 -03:00
pid_namespace.c
pidns: call pid_ns_prepare_proc() from create_pid_namespace()
2011-03-23 19:46:58 -07:00
pm_qos_params.c
PM QoS: Make pm_qos settings readable
2011-03-15 00:43:18 +01:00
posix-cpu-timers.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
posix-timers.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
printk.c
printk: allow setting DEFAULT_MESSAGE_LEVEL via Kconfig
2011-03-22 17:44:13 -07:00
profile.c
ptrace.c
userns: allow ptrace from non-init user namespaces
2011-03-23 19:47:05 -07:00
range.c
rcupdate.c
rcu: add comment saying why DEBUG_OBJECTS_RCU_HEAD depends on PREEMPT.
2011-03-04 08:05:41 -08:00
rcutiny.c
rcu: avoid pointless blocked-task warnings
2011-01-14 04:58:08 -08:00
rcutiny_plugin.h
rcu: call __rcu_read_unlock() in exit_rcu for tiny RCU
2011-03-04 08:05:08 -08:00
rcutorture.c
rcutorture: Get rid of duplicate sched.h include
2011-03-04 08:05:17 -08:00
rcutree.c
rcutree.h
rcutree_plugin.h
rcutree_trace.c
relay.c
res_counter.c
memcg: res_counter_read_u64(): fix potential races on 32-bit machines
2011-03-23 19:46:22 -07:00
resource.c
rtmutex-debug.c
rtmutex: Simplify PI algorithm and make highest prio task get lock
2011-01-27 21:13:51 -05:00
rtmutex-debug.h
rtmutex-tester.c
rtmutex: tester: Remove the remaining BKL leftovers
2011-02-22 22:07:22 +01:00
rtmutex.c
rtmutex: Simplify PI algorithm and make highest prio task get lock
2011-01-27 21:13:51 -05:00
rtmutex.h
rtmutex_common.h
rtmutex: Simplify PI algorithm and make highest prio task get lock
2011-01-27 21:13:51 -05:00
rwsem.c
sched.c
Merge branch 'sched/locking' into sched/core
2011-04-18 14:53:33 +02:00
sched_autogroup.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
sched_autogroup.h
sched, autogroup: Stop going ahead if autogroup is disabled
2011-02-23 11:33:59 +01:00
sched_clock.c
sched_cpupri.c
sched_cpupri.h
sched_debug.c
sched: Provide p->on_rq
2011-04-14 08:52:35 +02:00
sched_fair.c
sched: Next buddy hint on sleep and preempt path
2011-04-19 10:08:38 +02:00
sched_features.h
sched: Move the second half of ttwu() to the remote cpu
2011-04-14 08:52:41 +02:00
sched_idletask.c
sched: Drop the rq argument to sched_class::select_task_rq()
2011-04-14 08:52:36 +02:00
sched_rt.c
sched: Drop the rq argument to sched_class::select_task_rq()
2011-04-14 08:52:36 +02:00
sched_stats.h
sched_stoptask.c
sched: Drop the rq argument to sched_class::select_task_rq()
2011-04-14 08:52:36 +02:00
seccomp.c
semaphore.c
signal.c
signal.c: fix erroneous syscall kernel-doc
2011-04-08 11:05:24 -07:00
smp.c
smp: move smp setup functions to kernel/smp.c
2011-03-22 17:44:11 -07:00
softirq.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
spinlock.c
srcu.c
rcu: demote SRCU_SYNCHRONIZE_DELAY from kernel-parameter status
2011-01-14 04:56:49 -08:00
stacktrace.c
stop_machine.c
kthread: use kthread_create_on_node()
2011-03-22 17:44:01 -07:00
sys.c
userns: user namespaces: convert all capable checks in kernel/sys.c
2011-03-23 19:47:06 -07:00
sys_ni.c
vfs: Add open by file handle support
2011-03-15 02:21:44 -04:00
sysctl.c
sysctl: restrict write access to dmesg_restrict
2011-03-23 19:46:54 -07:00
sysctl_binary.c
open-style analog of vfs_path_lookup()
2011-03-14 09:15:28 -04:00
sysctl_check.c
sysctl_check: drop dead code
2011-03-23 19:46:51 -07:00
taskstats.c
taskstats: use appropriate printk priority level
2011-03-23 19:47:14 -07:00
test_kprobes.c
time.c
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
2011-03-15 18:53:35 -07:00
timeconst.pl
timer.c
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
2011-03-15 18:53:35 -07:00
tracepoint.c
tracepoints: Fix section alignment using pointer array
2011-02-03 09:28:46 -05:00
tsacct.c
uid16.c
userns: user namespaces: convert several capable() calls
2011-03-23 19:47:08 -07:00
up.c
user-return-notifier.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
user.c
userns: add a user_namespace as creator/owner of uts_namespace
2011-03-23 19:46:59 -07:00
user_namespace.c
utsname.c
userns: allow sethostname in a container
2011-03-23 19:47:03 -07:00
utsname_sysctl.c
wait.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
watchdog.c
kernel/watchdog.c: always return NOTIFY_OK during cpu up/down events
2011-03-22 17:44:12 -07:00
workqueue.c
Fix common misspellings
2011-03-31 11:26:23 -03:00
workqueue_sched.h