Re: [PATCH 1/2] mm/pageblock: mitigation cmpxchg false sharing in pageblock flags

[Alex Shi]

在 2020/8/16 下午8:16, David Hildenbrand 写道:
> On 16.08.20 05:47, Alex Shi wrote:
>> pageblock_flags is used as long, since every pageblock_flags is just 4
>> bits, 'long' size will include 8(32bit machine) or 16 pageblocks' flags,
>> that flag setting has to sync in cmpxchg with 7 or 15 other pageblock
>> flags. It would cause long waiting for sync.
>>
>> If we could change the pageblock_flags variable as char, we could use
>> char size cmpxchg, which just sync up with 2 pageblock flags. it could
>> relief much false sharing in cmpxchg.
> 
> Do you have any performance numbers to back your claims? IOW, do we care
> at all?
> 
> 

Hi David,

Thanks for comments!

Not yet, I trace the following commit here, with this commit this hot path
looks be resolved.

Thanks
Alex

e380bebe4771548  mm, compaction: keep migration source private to a single compaction instance
                if (!locked) {
                        locked = compact_trylock_irqsave(zone_lru_lock(zone),
                                                                &flags, cc);
-                       if (!locked)
+
+                       /* Allow future scanning if the lock is contended */
+                       if (!locked) {
+                               clear_pageblock_skip(page);
                                break;
+                       }
+
+                       /* Try get exclusive access under lock */
+                       if (!skip_updated) {
+                               skip_updated = true;
+                               if (test_and_set_skip(cc, page, low_pfn))
+                                       goto isolate_abort;
+                       }