On Tue, Mar 19, 2024 at 05:00:24PM -0500, Yan Zhai wrote:
> Hi Paul,
>
> On Tue, Mar 19, 2024 at 4:31 PM Paul E. McKenney <paulmck@xxxxxxxxxx> wrote:
> >
> > On Tue, Mar 19, 2024 at 01:44:34PM -0700, Yan Zhai wrote:
> > > When under heavy load, network processing can run CPU-bound for many
> > > tens of seconds. Even in preemptible kernels (non-RT kernel), this can
> > > block RCU Tasks grace periods, which can cause trace-event removal to
> > > take more than a minute, which is unacceptably long.
> > >
> > > This commit therefore creates a new helper function that passes through
> > > both RCU and RCU-Tasks quiescent states every 100 milliseconds. This
> > > hard-coded value suffices for current workloads.
> > >
> > > Suggested-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
> > > Reviewed-by: Jesper Dangaard Brouer <hawk@xxxxxxxxxx>
> > > Signed-off-by: Yan Zhai <yan@xxxxxxxxxxxxxx>
> >
> > If you would like me to take this one via -rcu, I would be happy to take
> > it. If it would be easier for you to push these as a group though
> > networking:
> >
> > Reviewed-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
>
> Since the whole series aims at fixing net problems, going through net
> is probably more consistent.
Very good! I will let you push it along.
> Also, thank you for your help through the series!
No, thank you! I had just been asked to find this slowdown when you
posted the patch. So it worked out extremely well for me! ;-)
Thanx, Paul
> Yan
>
> > > ---
> > > v4->v5: adjusted kernel docs and commit message
> > > v3->v4: kernel docs error
> > >
> > > ---
> > > include/linux/rcupdate.h | 31 +++++++++++++++++++++++++++++++
> > > 1 file changed, 31 insertions(+)
> > >
> > > diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
> > > index 16f519914415..17d7ed5f3ae6 100644
> > > --- a/include/linux/rcupdate.h
> > > +++ b/include/linux/rcupdate.h
> > > @@ -247,6 +247,37 @@ do { \
> > > cond_resched(); \
> > > } while (0)
> > >
> > > +/**
> > > + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states
> > > + * @old_ts: jiffies at start of processing.
> > > + *
> > > + * This helper is for long-running softirq handlers, such as NAPI threads in
> > > + * networking. The caller should initialize the variable passed in as @old_ts
> > > + * at the beginning of the softirq handler. When invoked frequently, this macro
> > > + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will
> > > + * provide both RCU and RCU-Tasks quiescent states. Note that this macro
> > > + * modifies its old_ts argument.
> > > + *
> > > + * Because regions of code that have disabled softirq act as RCU read-side
> > > + * critical sections, this macro should be invoked with softirq (and
> > > + * preemption) enabled.
> > > + *
> > > + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would
> > > + * have more chance to invoke schedule() calls and provide necessary quiescent
> > > + * states. As a contrast, calling cond_resched() only won't achieve the same
> > > + * effect because cond_resched() does not provide RCU-Tasks quiescent states.
> > > + */
> > > +#define rcu_softirq_qs_periodic(old_ts) \
> > > +do { \
> > > + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \
> > > + time_after(jiffies, (old_ts) + HZ / 10)) { \
> > > + preempt_disable(); \
> > > + rcu_softirq_qs(); \
> > > + preempt_enable(); \
> > > + (old_ts) = jiffies; \
> > > + } \
> > > +} while (0)
> > > +
> > > /*
> > > * Infrastructure to implement the synchronize_() primitives in
> > > * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
> > > --
> > > 2.30.2
> > >
> > >
