Re: [PATCH RESEND] mm: drop lruvec->lru_lock if contended when skipping folio

[Bharata B Rao]

On 20-Aug-24 12:16 AM, Usama Arif wrote:
> lruvec->lru_lock is highly contended and is held when calling
> isolate_lru_folios. If the lru has a large number of CMA folios
> consecutively, while the allocation type requested is not MIGRATE_MOVABLE,
> isolate_lru_folios can hold the lock for a very long time while it
> skips those. vmscan_lru_isolate tracepoint showed that skipped can go
> above 70k in production and lockstat shows that waittime-max is x1000
> higher without this patch.
> This can cause lockups [1] and high memory pressure for extended periods of
> time [2]. Hence release the lock if its contended when skipping a folio to
> give other tasks a chance to acquire it and not stall.
>
> [1] https://lore.kernel.org/all/CAOUHufbkhMZYz20aM_3rHZ3OcK4m2puji2FGpUpn_-DevGk3Kg@xxxxxxxxxxxxxx/
> [2] https://lore.kernel.org/all/ZrssOrcJIDy8hacI@xxxxxxxxx/

Though the above link[2] mentions it, can you explicitly include the 
specific condition that we saw in the patch description?

"isolate_lru_folios() can end up scanning through a huge number of 
folios with lruvec spinlock held. For FIO workload, ~150million order=0 
folios were skipped to isolate a few ZONE_DMA folios."

Regards,
Bharata.