On 7/30/21 4:46 PM, Charan Teja Kalla wrote: > Thanks Vlastimil!! > > On 7/30/2021 7:36 PM, Vlastimil Babka wrote: >>> The proactive compaction[1] gets triggered for every 500msec and run >>> compaction on the node for COMPACTION_HPAGE_ORDER (usually order-9) >>> pages based on the value set to sysctl.compaction_proactiveness. >>> Triggering the compaction for every 500msec in search of >>> COMPACTION_HPAGE_ORDER pages is not needed for all applications, >>> especially on the embedded system usecases which may have few MB's of >>> RAM. Enabling the proactive compaction in its state will endup in >>> running almost always on such systems. >>> >>> Other side, proactive compaction can still be very much useful for >>> getting a set of higher order pages in some controllable >>> manner(controlled by using the sysctl.compaction_proactiveness). So, on >>> systems where enabling the proactive compaction always may proove not >>> required, can trigger the same from user space on write to its sysctl >>> interface. As an example, say app launcher decide to launch the memory >>> heavy application which can be launched fast if it gets more higher >>> order pages thus launcher can prepare the system in advance by >>> triggering the proactive compaction from userspace. >>> >>> This triggering of proactive compaction is done on a write to >>> sysctl.compaction_proactiveness by user. >>> >>> [1]https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?id=facdaa917c4d5a376d09d25865f5a863f906234a >>> >>> Signed-off-by: Charan Teja Reddy <charante@xxxxxxxxxxxxxx> >> Acked-by: Vlastimil Babka <vbabka@xxxxxxx> > > Thanks for the tag here. Np. >> >>> @@ -2895,9 +2920,16 @@ static int kcompactd(void *p) >>> while (!kthread_should_stop()) { >>> unsigned long pflags; >>> >>> + /* >>> + * Avoid the unnecessary wakeup for proactive compaction >>> + * when it is disabled. >>> + */ >>> + if (!sysctl_compaction_proactiveness) >>> + timeout = MAX_SCHEDULE_TIMEOUT; >> Does this part actually logically belong more to your previous patch that >> optimized the deferred timeouts? > > IMO, it won't fit there. Reason is that when user writes > sysctl_compaction_proactiveness = 0, it will goes to sleep with > MAX_SCHEDULE_TIMEOUT. Say now user writes non-zero value to > sysctl_compaction_proactiveness then no condition is there to wake it up > for proactive compaction, means, it will still be in sleep with > MAX_SCHEDULE_TIMEOUT. Good point! > Thus this logic is put in this patch, where, proactive compaction work > will be scheduled immediately on switch of proactiveness value from zero > to a non-zero. Agreed. Thanks! >> >
