Re: [PATCH 0/1] mm/vmscan: reduce lru_lock contention via vmstat-derived scan-balance cost

[Usama Arif <usama.arif@linux.dev>]

On Mon,  6 Jul 2026 05:28:25 -0700 Usama Arif <usama.arif@linux.dev> wrote:

> The anon/file scan balance heuristic in get_scan_count() is fed by two
> scalars in struct lruvec (anon_cost, file_cost) that every reclaim
> producer updates under lruvec->lru_lock. The cost-recording work
> itself is trivial, but it both contends for and contributes to
> contention on lru_lock - which is often a contention point on
> memory-pressured workloads. Specifically:
> 
> - shrink_inactive_list() re-acquires lru_lock at function exit just
>   to call lru_note_cost_unlock_irq().
> - shrink_active_list() does the same after rotation accounting.
> - workingset_refault() takes folio_lruvec_lock_irq() purely to
>   record the refault cost.
> - prepare_scan_control() snapshots anon_cost/file_cost under
>   lru_lock.
> - lru_note_cost_unlock_irq() itself walks parent_lruvec() and
>   re-acquires lru_lock on every ancestor, multiplying the cost
>   of every update by memcg-hierarchy depth.
> 
> This patch removes those producer-side acquisitions entirely. The
> producer-local inputs (PGROTATE_*, PGRECLAIM_PAGEOUT_*) become
> per-LRU vmstat counters; WORKINGSET_RESTORE_* already captures the
> refault input. prepare_scan_control() reads the raw cost signal
> lock-free from those vmstats and folds the delta into a per-lruvec
> accumulator. A dedicated per-lruvec cost_lock, not touched by
> isolate_lru_folios(), move_folios_to_lru(), or folio_add_lru(),
> serialises the accumulator RMW and the lrusize/4 halving check.
> Hierarchy aggregation is implicit in rstat propagation, so the
> parent_lruvec() walk and the lru_reparent_memcg() cost-splice both
> disappear.

Another update on this, I was profiling another Meta workload that suffers
from very heavy reclaim and has a lot of cgroups. I ran:

bpftrace -q -e 'profile:hz:99 { @[kstack, comm] = count(); }'

The biggest entry was below:
@[
        lru_note_cost_unlock_irq+146
        shrink_lruvec+1913
        shrink_node+869
        do_try_to_free_pages+197
        try_to_free_mem_cgroup_pages+311
        __mem_cgroup_charge+1832
        filemap_add_folio+127
        page_cache_ra_unbounded+347
        filemap_fault+956
        __do_fault+40
        handle_mm_fault+4034
        do_user_addr_fault+406
        exc_page_fault+105
        asm_exc_page_fault+34
, Func___]: 5354

5354 represents 51.42% of all kernel samples collected.

A very signifcant amount of time was being spent just in lru_note_cost_unlock_irq