On 08/06, Jason Low wrote:
>
> On Thu, 2015-08-06 at 16:18 +0200, Oleg Nesterov wrote:
> > > + /*
> > > + * Check for the special case process timers.
> > > + */
> > > + check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
> > > + SIGPROF);
> > > + check_cpu_itime
On Thu, 2015-08-06 at 16:18 +0200, Oleg Nesterov wrote:
> On 08/04, Jason Low wrote:
> >
> > @@ -973,13 +981,6 @@ static void check_process_timers(struct task_struct
> > *tsk,
> > virt_expires = check_timers_list(++timers, firing, utime);
> > sched_expires = check_timers_list(++timers, fir
On 08/04, Jason Low wrote:
>
> @@ -973,13 +981,6 @@ static void check_process_timers(struct task_struct *tsk,
> virt_expires = check_timers_list(++timers, firing, utime);
> sched_expires = check_timers_list(++timers, firing, sum_sched_runtime);
>
> - /*
> - * Check for the sp
On Wed, 2015-08-05 at 11:37 +0200, Peter Zijlstra wrote:
> On Tue, Aug 04, 2015 at 05:29:44PM -0700, Jason Low wrote:
>
> > @@ -1137,6 +1148,13 @@ static inline int fastpath_timer_check(struct
> > task_struct *tsk)
> > if (READ_ONCE(sig->cputimer.running)) {
>
> Maybe make that:
>
> i
On Tue, Aug 04, 2015 at 05:29:44PM -0700, Jason Low wrote:
> @@ -1137,6 +1148,13 @@ static inline int fastpath_timer_check(struct
> task_struct *tsk)
> if (READ_ONCE(sig->cputimer.running)) {
Maybe make that:
if (READ_ONCE(sig->cputimer.running) &&
!READ_ONCE(sig->cput
On Tue, Aug 04, 2015 at 05:29:44PM -0700, Jason Low wrote:
> When running a database workload on a 16 socket machine, there were
> scalability issues related to itimers.
I very much hope you're also trying to convince the relevant database
people that using process wide timers on something they ex
When running a database workload on a 16 socket machine, there were
scalability issues related to itimers.
Commit 1018016c706f addressed the issue with the thread_group_cputimer
spinlock taking up a significant portion of total run time.
This patch addresses the other issue where a lot of time is
7 matches
Mail list logo
