The patch titled
sched: cpuacct: use bigger percpu counter batch values for stats counters
has been added to the -mm tree. Its filename is
sched-cpuacct-use-bigger-percpu-counter-batch-values-for-stats-counters.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: sched: cpuacct: use bigger percpu counter batch values for stats counters
From: Anton Blanchard <anton@xxxxxxxxx>
When CONFIG_VIRT_CPU_ACCOUNTING and CONFIG_CGROUP_CPUACCT are enabled we
can call cpuacct_update_stats with values much larger than
percpu_counter_batch. This means the call to percpu_counter_add will
always add to the global count which is protected by a spinlock and we end
up with a global spinlock in the scheduler.
Based on an idea by KOSAKI Motohiro, this patch scales the batch value by
cputime_one_jiffy such that we have the same batch limit as we would if
CONFIG_VIRT_CPU_ACCOUNTING was disabled. His patch did this once at boot
but that initialisation happened too early on PowerPC (before time_init)
and it was never updated at runtime as a result of a hotplug cpu
add/remove.
This patch instead scales percpu_counter_batch by cputime_one_jiffy at
runtime, which keeps the batch correct even after cpu hotplug operations.
We cap it at INT_MAX in case of overflow.
For architectures that do not support CONFIG_VIRT_CPU_ACCOUNTING,
cputime_one_jiffy is the constant 1 and gcc is smart enough to optimise
min(s32 percpu_counter_batch, INT_MAX) to just percpu_counter_batch at
least on x86 and PowerPC. So there is no need to add an #ifdef.
On a 64 thread PowerPC box with CONFIG_VIRT_CPU_ACCOUNTING and
CONFIG_CGROUP_CPUACCT enabled, a context switch microbenchmark is 234x
faster and almost matches a CONFIG_CGROUP_CPUACCT disabled kernel:
CONFIG_CGROUP_CPUACCT disabled: 16906698 ctx switches/sec
CONFIG_CGROUP_CPUACCT enabled: 61720 ctx switches/sec
CONFIG_CGROUP_CPUACCT + patch: 16663217 ctx switches/sec
Tested with:
wget http://ozlabs.org/~anton/junkcode/context_switch.c
make context_switch
for i in `seq 0 63`; do taskset -c $i ./context_switch & done
vmstat 1
Signed-off-by: Anton Blanchard <anton@xxxxxxxxx>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: "Luck, Tony" <tony.luck@xxxxxxxxx>
Acked-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Tested-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/sched.c | 20 +++++++++++++++++++-
1 file changed, 19 insertions(+), 1 deletion(-)
diff -puN kernel/sched.c~sched-cpuacct-use-bigger-percpu-counter-batch-values-for-stats-counters kernel/sched.c
--- a/kernel/sched.c~sched-cpuacct-use-bigger-percpu-counter-batch-values-for-stats-counters
+++ a/kernel/sched.c
@@ -10898,12 +10898,30 @@ static void cpuacct_charge(struct task_s
}
/*
+ * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large
+ * in cputime_t units. As a result, cpuacct_update_stats calls
+ * percpu_counter_add with values large enough to always overflow the
+ * per cpu batch limit causing bad SMP scalability.
+ *
+ * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we
+ * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled
+ * and enabled. We cap it at INT_MAX which is the largest allowed batch value.
+ */
+#ifdef CONFIG_SMP
+#define CPUACCT_BATCH \
+ min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX)
+#else
+#define CPUACCT_BATCH 0
+#endif
+
+/*
* Charge the system/user time to the task's accounting group.
*/
static void cpuacct_update_stats(struct task_struct *tsk,
enum cpuacct_stat_index idx, cputime_t val)
{
struct cpuacct *ca;
+ int batch = CPUACCT_BATCH;
if (unlikely(!cpuacct_subsys.active))
return;
@@ -10912,7 +10930,7 @@ static void cpuacct_update_stats(struct
ca = task_ca(tsk);
do {
- percpu_counter_add(&ca->cpustat[idx], val);
+ __percpu_counter_add(&ca->cpustat[idx], val, batch);
ca = ca->parent;
} while (ca);
rcu_read_unlock();
_
Patches currently in -mm which might be from anton@xxxxxxxxx are
origin.patch
percpu_counter-make-__percpu_counter_add-an-inline-function-on-up.patch
sched-cpuacct-use-bigger-percpu-counter-batch-values-for-stats-counters.patch
zlib-make-new-optimized-inflate-endian-independent.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
