Messages in this thread | | | Date | Tue, 22 Nov 2022 14:08:19 +0800 | From | Aaron Lu <> | Subject | Re: [PATCH v3] sched: async unthrottling for cfs bandwidth |
| |
On Fri, Nov 18, 2022 at 11:25:09AM -0800, Josh Don wrote: > On Fri, Nov 18, 2022 at 4:47 AM Peter Zijlstra <peterz@infradead.org> wrote: > > > > preempt_disable() -- through rq->lock -- also holds off rcu. Strictly > > speaking this here is superfluous. But if you want it as an annotation, > > that's fine I suppose. > > Yep, I purely added this as extra annotation for future readers. > > > Ideally we'd first queue all the remotes and then process local, but > > given how all this is organized that doesn't seem trivial to arrange. > > > > Maybe have this function return false when local and save that cfs_rq in > > a local var to process again later, dunno, that might turn messy. > > Maybe something like this? Apologies for inline diff formatting. > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > index 012ec9d03811..100dae6023da 100644 > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -5520,12 +5520,15 @@ static bool distribute_cfs_runtime(struct > cfs_bandwidth *cfs_b) > struct cfs_rq *cfs_rq; > u64 runtime, remaining = 1; > bool throttled = false; > + int this_cpu = smp_processor_id(); > + struct cfs_rq *local_unthrottle = NULL; > + struct rq *rq; > + struct rq_flags rf; > > rcu_read_lock(); > list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, > throttled_list) { > - struct rq *rq = rq_of(cfs_rq); > - struct rq_flags rf; > + rq = rq_of(cfs_rq); > > if (!remaining) { > throttled = true; > @@ -5556,14 +5559,36 @@ static bool distribute_cfs_runtime(struct > cfs_bandwidth *cfs_b) > cfs_rq->runtime_remaining += runtime; > > /* we check whether we're throttled above */ > - if (cfs_rq->runtime_remaining > 0) > - unthrottle_cfs_rq_async(cfs_rq); > + if (cfs_rq->runtime_remaining > 0) { > + if (cpu_of(rq) != this_cpu || > + SCHED_WARN_ON(local_unthrottle)) { > + unthrottle_cfs_rq_async(cfs_rq); > + } else { > + local_unthrottle = cfs_rq; > + } > + } else { > + throttled = true; > + } > > next: > rq_unlock_irqrestore(rq, &rf); > } > rcu_read_unlock(); > > + /* > + * We prefer to stage the async unthrottles of all the remote cpus > + * before we do the inline unthrottle locally. Note that > + * unthrottle_cfs_rq_async() on the local cpu is actually synchronous, > + * but it includes extra WARNs to make sure the cfs_rq really is > + * still throttled.
With this said ->
> + */ > + if (local_unthrottle) { > + rq = cpu_rq(this_cpu); > + rq_lock_irqsave(rq, &rf);
Should we add: if (cfs_rq_throttled(local_unthrottle))
before calling into unthrottle_cfs_rq_async(local_unthrottle) to avoid a potential WARN?
As for whether the local cfs_rq can be unthrottled now after rq lock is re-acquired, I suppose it can be. e.g. another user sets a new quota to this task group during the window of rq lock gets dropped in the above loop and re-acquired here IIUC.
> + unthrottle_cfs_rq_async(local_unthrottle); > + rq_unlock_irqrestore(rq, &rf); > + } > + > return throttled; > } >
| |