Messages in this thread | | | Subject | Re: [PATCH 00/14] per memcg lru_lock | From | Konstantin Khlebnikov <> | Date | Mon, 26 Aug 2019 11:39:49 +0300 |
| |
On 22/08/2019 18.20, Daniel Jordan wrote: > On 8/22/19 7:56 AM, Alex Shi wrote: >> 在 2019/8/22 上午2:00, Daniel Jordan 写道: >>> https://git.kernel.org/pub/scm/linux/kernel/git/wfg/vm-scalability.git/tree/case-lru-file-readtwice> >>> It's also synthetic but it stresses lru_lock more than just anon alloc/free. It hits the page activate path, which is where we see this >>> lock in our database, and if enough memory is configured lru_lock also gets stressed during reclaim, similar to [1]. >> >> Thanks for the sharing, this patchset can not help the [1] case, since it's just relief the per container lock contention now. > > I should've been clearer. [1] is meant as an example of someone suffering from lru_lock during reclaim. Wouldn't your series help > per-memcg reclaim? > >> Yes, readtwice case could be more sensitive for this lru_lock changes in containers. I may try to use it in container with some tuning. >> But anyway, aim9 is also pretty good to show the problem and solutions. :) >>> >>> It'd be better though, as Michal suggests, to use the real workload that's causing problems. Where are you seeing contention? >> >> We repeatly create or delete a lot of different containers according to servers load/usage, so normal workload could cause lots of pages >> alloc/remove. > > I think numbers from that scenario would help your case. > >> aim9 could reflect part of scenarios. I don't know the DB scenario yet. > > We see it during DB shutdown when each DB process frees its memory (zap_pte_range -> mark_page_accessed). But that's a different thing, > clearly Not This Series. > >>>> With this patch series, lruvec->lru_lock show no contentions >>>> &(&lruvec->lru_l... 8 0 0 0 0 0 >>>> >>>> and aim9 page_test/brk_test performance increased 5%~50%. >>> >>> Where does the 50% number come in? The numbers below seem to only show ~4% boost. >>After splitting lru-locks present per-cpu page-vectors works no so well because they mixes pages from different cgroups.
pagevec_lru_move_fn and friends need better implementation: either sorting pages or splitting vectores in per-lruvec basis. >> the Setddev/CoeffVar case has about 50% performance increase. one of container's mmtests result as following: >> >> Stddev page_test 245.15 ( 0.00%) 189.29 ( 22.79%) >> Stddev brk_test 1258.60 ( 0.00%) 629.16 ( 50.01%) >> CoeffVar page_test 0.71 ( 0.00%) 0.53 ( 26.05%) >> CoeffVar brk_test 1.32 ( 0.00%) 0.64 ( 51.14%) > > Aha. 50% decrease in stdev. >
After splitting lru-locks present per-cpu page-vectors works no so well because they mix pages from different cgroups.
pagevec_lru_move_fn and friends need better implementation: either sorting pages or splitting vectores in per-lruvec basis.
| |