| Message ID | 20240206175251.3364296-1-tjmercier@google.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [v4] mm: memcg: Use larger batches for proactive reclaim | expand |
On Tue 06-02-24 17:52:50, T.J. Mercier wrote: > Before 388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive > reclaim") we passed the number of pages for the reclaim request directly > to try_to_free_mem_cgroup_pages, which could lead to significant > overreclaim. After 0388536ac291 the number of pages was limited to a > maximum 32 (SWAP_CLUSTER_MAX) to reduce the amount of overreclaim. > However such a small batch size caused a regression in reclaim > performance due to many more reclaim start/stop cycles inside > memory_reclaim. The restart cost is amortized over more pages with > larger batch sizes, and becomes a significant component of the runtime > if the batch size is too small. > > Reclaim tries to balance nr_to_reclaim fidelity with fairness across > nodes and cgroups over which the pages are spread. As such, the bigger > the request, the bigger the absolute overreclaim error. Historic > in-kernel users of reclaim have used fixed, small sized requests to > approach an appropriate reclaim rate over time. When we reclaim a user > request of arbitrary size, use decaying batch sizes to manage error while > maintaining reasonable throughput. > > MGLRU enabled - memcg LRU used > root - full reclaim pages/sec time (sec) > pre-0388536ac291 : 68047 10.46 > post-0388536ac291 : 13742 inf > (reclaim-reclaimed)/4 : 67352 10.51 > > MGLRU enabled - memcg LRU not used > /uid_0 - 1G reclaim pages/sec time (sec) overreclaim (MiB) > pre-0388536ac291 : 258822 1.12 107.8 > post-0388536ac291 : 105174 2.49 3.5 > (reclaim-reclaimed)/4 : 233396 1.12 -7.4 > > MGLRU enabled - memcg LRU not used > /uid_0 - full reclaim pages/sec time (sec) > pre-0388536ac291 : 72334 7.09 > post-0388536ac291 : 38105 14.45 > (reclaim-reclaimed)/4 : 72914 6.96 > > Fixes: 0388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive reclaim") > Signed-off-by: T.J. Mercier <tjmercier@google.com> > Reviewed-by: Yosry Ahmed <yosryahmed@google.com> > Acked-by: Johannes Weiner <hannes@cmpxchg.org> > Acked-by: Shakeel Butt <shakeelb@google.com> > Reviewed-by: Michal Koutný <mkoutny@suse.com> Acked-by: Michal Hocko <mhocko@suse.com> Sorry, I've missed this version
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 46d8d02114cf..02b054a316d3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6963,6 +6963,8 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; while (nr_reclaimed < nr_to_reclaim) { + /* Will converge on zero, but reclaim enforces a minimum */ + unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4; unsigned long reclaimed; if (signal_pending(current)) @@ -6977,8 +6979,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, lru_add_drain_all(); reclaimed = try_to_free_mem_cgroup_pages(memcg, - min(nr_to_reclaim - nr_reclaimed, SWAP_CLUSTER_MAX), - GFP_KERNEL, reclaim_options); + batch_size, GFP_KERNEL, reclaim_options); if (!reclaimed && !nr_retries--) return -EAGAIN;
Before 388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive reclaim") we passed the number of pages for the reclaim request directly to try_to_free_mem_cgroup_pages, which could lead to significant overreclaim. After 0388536ac291 the number of pages was limited to a maximum 32 (SWAP_CLUSTER_MAX) to reduce the amount of overreclaim. However such a small batch size caused a regression in reclaim performance due to many more reclaim start/stop cycles inside memory_reclaim. The restart cost is amortized over more pages with larger batch sizes, and becomes a significant component of the runtime if the batch size is too small. Reclaim tries to balance nr_to_reclaim fidelity with fairness across nodes and cgroups over which the pages are spread. As such, the bigger the request, the bigger the absolute overreclaim error. Historic in-kernel users of reclaim have used fixed, small sized requests to approach an appropriate reclaim rate over time. When we reclaim a user request of arbitrary size, use decaying batch sizes to manage error while maintaining reasonable throughput. MGLRU enabled - memcg LRU used root - full reclaim pages/sec time (sec) pre-0388536ac291 : 68047 10.46 post-0388536ac291 : 13742 inf (reclaim-reclaimed)/4 : 67352 10.51 MGLRU enabled - memcg LRU not used /uid_0 - 1G reclaim pages/sec time (sec) overreclaim (MiB) pre-0388536ac291 : 258822 1.12 107.8 post-0388536ac291 : 105174 2.49 3.5 (reclaim-reclaimed)/4 : 233396 1.12 -7.4 MGLRU enabled - memcg LRU not used /uid_0 - full reclaim pages/sec time (sec) pre-0388536ac291 : 72334 7.09 post-0388536ac291 : 38105 14.45 (reclaim-reclaimed)/4 : 72914 6.96 Fixes: 0388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive reclaim") Signed-off-by: T.J. Mercier <tjmercier@google.com> Reviewed-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Michal Koutný <mkoutny@suse.com> --- v4: Add additional info to commit message and move definition of batch_size per Michal Hocko. No functional changes. v3: Formatting fixes per Yosry Ahmed and Johannes Weiner. No functional changes. v2: Simplify the request size calculation per Johannes Weiner and Michal Koutný mm/memcontrol.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)