From: Christoph Lameter <cl@linux.com> To: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Aruna Ramakrishna <aruna.ramakrishna@oracle.com>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Mike Kravetz <mike.kravetz@oracle.com>, Pekka Enberg <penberg@kernel.org>, David Rientjes <rientjes@google.com>, Andrew Morton <akpm@linux-foundation.org> Subject: Re: [PATCH] mm/slab: Improve performance of gathering slabinfo stats Date: Tue, 2 Aug 2016 09:59:26 -0500 (CDT) [thread overview] Message-ID: <alpine.DEB.2.20.1608020953160.24620@east.gentwo.org> (raw) In-Reply-To: <20160802024342.GA15062@js1304-P5Q-DELUXE> Hmm.... What SLUB does is: 1. Keep a count of the total number of allocated slab pages per node. This counter only needs to be updated when a slab page is allocated from the page allocator or when it is freed to the page allocator. At that point we already hold the per node lock, page allocator operations are extremely costly anyways and so that is ok. 2. Keep a count of the number of partially allocated slab pages per node. At that point we have to access the partial list and take a per node lock. Placing the counter into the same cacheline and the increment/decrement into the period when the lock has been taken avoids the overhead. The number of full pages is then total - partial If both allocators would use the same scheme here then the code to maintain the counter can be moved into mm/slab_common.c. Plus the per node structures could be mostly harmonized between both allocators. Maybe even the page allocator operations could become common code. Aruna: Could you work on a solution like that?
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Lameter <cl@linux.com> To: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Aruna Ramakrishna <aruna.ramakrishna@oracle.com>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Mike Kravetz <mike.kravetz@oracle.com>, Pekka Enberg <penberg@kernel.org>, David Rientjes <rientjes@google.com>, Andrew Morton <akpm@linux-foundation.org> Subject: Re: [PATCH] mm/slab: Improve performance of gathering slabinfo stats Date: Tue, 2 Aug 2016 09:59:26 -0500 (CDT) [thread overview] Message-ID: <alpine.DEB.2.20.1608020953160.24620@east.gentwo.org> (raw) In-Reply-To: <20160802024342.GA15062@js1304-P5Q-DELUXE> Hmm.... What SLUB does is: 1. Keep a count of the total number of allocated slab pages per node. This counter only needs to be updated when a slab page is allocated from the page allocator or when it is freed to the page allocator. At that point we already hold the per node lock, page allocator operations are extremely costly anyways and so that is ok. 2. Keep a count of the number of partially allocated slab pages per node. At that point we have to access the partial list and take a per node lock. Placing the counter into the same cacheline and the increment/decrement into the period when the lock has been taken avoids the overhead. The number of full pages is then total - partial If both allocators would use the same scheme here then the code to maintain the counter can be moved into mm/slab_common.c. Plus the per node structures could be mostly harmonized between both allocators. Maybe even the page allocator operations could become common code. Aruna: Could you work on a solution like that? -- 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:[~2016-08-02 15:01 UTC|newest] Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-08-02 0:09 [PATCH] mm/slab: Improve performance of gathering slabinfo stats Aruna Ramakrishna 2016-08-02 0:09 ` Aruna Ramakrishna 2016-08-02 0:55 ` Joonsoo Kim 2016-08-02 0:55 ` Joonsoo Kim 2016-08-02 1:43 ` Aruna Ramakrishna 2016-08-02 1:43 ` Aruna Ramakrishna 2016-08-02 2:43 ` Joonsoo Kim 2016-08-02 2:43 ` Joonsoo Kim 2016-08-02 14:59 ` Christoph Lameter [this message] 2016-08-02 14:59 ` Christoph Lameter 2016-08-02 17:39 ` Aruna Ramakrishna 2016-08-02 17:39 ` Aruna Ramakrishna
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=alpine.DEB.2.20.1608020953160.24620@east.gentwo.org \ --to=cl@linux.com \ --cc=akpm@linux-foundation.org \ --cc=aruna.ramakrishna@oracle.com \ --cc=iamjoonsoo.kim@lge.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mike.kravetz@oracle.com \ --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.