From: Vladimir Davydov <vdavydov@parallels.com> To: Christoph Lameter <cl@gentwo.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>, <akpm@linux-foundation.org>, <rientjes@google.com>, <penberg@kernel.org>, <hannes@cmpxchg.org>, <mhocko@suse.cz>, <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org> Subject: Re: [PATCH -mm v2 8/8] slab: make dead memcg caches discard free slabs immediately Date: Thu, 12 Jun 2014 01:24:34 +0400 [thread overview] Message-ID: <20140611212431.GA16589@esperanza> (raw) In-Reply-To: <20140610151830.GA8692@esperanza> On Tue, Jun 10, 2014 at 07:18:34PM +0400, Vladimir Davydov wrote: > On Tue, Jun 10, 2014 at 09:26:19AM -0500, Christoph Lameter wrote: > > On Tue, 10 Jun 2014, Vladimir Davydov wrote: > > > > > Frankly, I incline to shrinking dead SLAB caches periodically from > > > cache_reap too, because it looks neater and less intrusive to me. Also > > > it has zero performance impact, which is nice. > > > > > > However, Christoph proposed to disable per cpu arrays for dead caches, > > > similarly to SLUB, and I decided to give it a try, just to see the end > > > code we'd have with it. > > > > > > I'm still not quite sure which way we should choose though... > > > > Which one is cleaner? > > To shrink dead caches aggressively, we only need to modify cache_reap > (see https://lkml.org/lkml/2014/5/30/271). Hmm, reap_alien, which is called from cache_reap to shrink per node alien object arrays, only processes one node at a time. That means with the patch I gave a link to above it will take up to (REAPTIMEOUT_AC*nr_online_nodes) seconds to destroy a virtually empty dead cache, which may be quite long on large machines. Of course, we can make reap_alien walk over all alien caches of the current node, but that will probably hurt performance... > > To zap object arrays for dead caches (this is what this patch does), we > have to: > - set array_cache->limit to 0 for each per cpu, shared, and alien array > caches on kmem_cache_shrink; > - make cpu/node hotplug paths init new array cache sizes to 0; > - make free paths (__cache_free, cache_free_alien) handle zero array > cache size properly, because currently they doesn't. > > So IMO the first one (reaping dead caches periodically) requires less > modifications and therefore is cleaner.
WARNING: multiple messages have this Message-ID (diff)
From: Vladimir Davydov <vdavydov@parallels.com> To: Christoph Lameter <cl@gentwo.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>, akpm@linux-foundation.org, rientjes@google.com, penberg@kernel.org, hannes@cmpxchg.org, mhocko@suse.cz, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH -mm v2 8/8] slab: make dead memcg caches discard free slabs immediately Date: Thu, 12 Jun 2014 01:24:34 +0400 [thread overview] Message-ID: <20140611212431.GA16589@esperanza> (raw) In-Reply-To: <20140610151830.GA8692@esperanza> On Tue, Jun 10, 2014 at 07:18:34PM +0400, Vladimir Davydov wrote: > On Tue, Jun 10, 2014 at 09:26:19AM -0500, Christoph Lameter wrote: > > On Tue, 10 Jun 2014, Vladimir Davydov wrote: > > > > > Frankly, I incline to shrinking dead SLAB caches periodically from > > > cache_reap too, because it looks neater and less intrusive to me. Also > > > it has zero performance impact, which is nice. > > > > > > However, Christoph proposed to disable per cpu arrays for dead caches, > > > similarly to SLUB, and I decided to give it a try, just to see the end > > > code we'd have with it. > > > > > > I'm still not quite sure which way we should choose though... > > > > Which one is cleaner? > > To shrink dead caches aggressively, we only need to modify cache_reap > (see https://lkml.org/lkml/2014/5/30/271). Hmm, reap_alien, which is called from cache_reap to shrink per node alien object arrays, only processes one node at a time. That means with the patch I gave a link to above it will take up to (REAPTIMEOUT_AC*nr_online_nodes) seconds to destroy a virtually empty dead cache, which may be quite long on large machines. Of course, we can make reap_alien walk over all alien caches of the current node, but that will probably hurt performance... > > To zap object arrays for dead caches (this is what this patch does), we > have to: > - set array_cache->limit to 0 for each per cpu, shared, and alien array > caches on kmem_cache_shrink; > - make cpu/node hotplug paths init new array cache sizes to 0; > - make free paths (__cache_free, cache_free_alien) handle zero array > cache size properly, because currently they doesn't. > > So IMO the first one (reaping dead caches periodically) requires less > modifications and therefore is cleaner. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2014-06-11 21:24 UTC|newest] Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top 2014-06-06 13:22 [PATCH -mm v2 0/8] memcg/slab: reintroduce dead cache self-destruction Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 1/8] memcg: cleanup memcg_cache_params refcnt usage Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 2/8] memcg: destroy kmem caches when last slab is freed Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 3/8] memcg: mark caches that belong to offline memcgs as dead Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-10 7:48 ` Joonsoo Kim 2014-06-10 7:48 ` Joonsoo Kim 2014-06-10 10:06 ` Vladimir Davydov 2014-06-10 10:06 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 4/8] slub: don't fail kmem_cache_shrink if slab placement optimization fails Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 5/8] slub: make slab_free non-preemptable Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 14:46 ` Christoph Lameter 2014-06-06 14:46 ` Christoph Lameter 2014-06-09 12:52 ` Vladimir Davydov 2014-06-09 12:52 ` Vladimir Davydov 2014-06-09 13:52 ` Christoph Lameter 2014-06-09 13:52 ` Christoph Lameter 2014-06-12 6:58 ` Joonsoo Kim 2014-06-12 6:58 ` Joonsoo Kim 2014-06-12 10:03 ` Vladimir Davydov 2014-06-12 10:03 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 6/8] memcg: wait for kfree's to finish before destroying cache Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 7/8] slub: make dead memcg caches discard free slabs immediately Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 14:48 ` Christoph Lameter 2014-06-06 14:48 ` Christoph Lameter 2014-06-10 8:09 ` Joonsoo Kim 2014-06-10 8:09 ` Joonsoo Kim 2014-06-10 10:09 ` Vladimir Davydov 2014-06-10 10:09 ` Vladimir Davydov 2014-06-06 13:22 ` [PATCH -mm v2 8/8] slab: " Vladimir Davydov 2014-06-06 13:22 ` Vladimir Davydov 2014-06-06 14:52 ` Christoph Lameter 2014-06-06 14:52 ` Christoph Lameter 2014-06-09 13:04 ` Vladimir Davydov 2014-06-09 13:04 ` Vladimir Davydov 2014-06-10 7:43 ` Joonsoo Kim 2014-06-10 7:43 ` Joonsoo Kim 2014-06-10 10:03 ` Vladimir Davydov 2014-06-10 10:03 ` Vladimir Davydov 2014-06-10 14:26 ` Christoph Lameter 2014-06-10 14:26 ` Christoph Lameter 2014-06-10 15:18 ` Vladimir Davydov 2014-06-10 15:18 ` Vladimir Davydov 2014-06-11 8:11 ` Joonsoo Kim 2014-06-11 8:11 ` Joonsoo Kim 2014-06-11 21:24 ` Vladimir Davydov [this message] 2014-06-11 21:24 ` Vladimir Davydov 2014-06-12 6:53 ` Joonsoo Kim 2014-06-12 6:53 ` Joonsoo Kim 2014-06-12 10:02 ` Vladimir Davydov 2014-06-12 10:02 ` Vladimir Davydov 2014-06-13 16:34 ` Christoph Lameter 2014-06-13 16:34 ` Christoph Lameter
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20140611212431.GA16589@esperanza \ --to=vdavydov@parallels.com \ --cc=akpm@linux-foundation.org \ --cc=cl@gentwo.org \ --cc=hannes@cmpxchg.org \ --cc=iamjoonsoo.kim@lge.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mhocko@suse.cz \ --cc=penberg@kernel.org \ --cc=rientjes@google.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.