From: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> To: Minchan Kim <minchan@kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>, Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Subject: Re: [PATCH v6 11/12] zsmalloc: page migration support Date: Thu, 26 May 2016 00:23:45 +0900 [thread overview] Message-ID: <20160525152345.GA515@swordfish> (raw) In-Reply-To: <20160525051438.GA14786@bbox> Hello Minchan, On (05/25/16 14:14), Minchan Kim wrote: [..] > > > do you also want to kick the deferred page release from the shrinker > > > callback, for example? > > > > Yeb, it can be. I will do it at next revision. :) > > Thanks! > > > > I tried it now but I feel strongly we want to fix shrinker first. > Now, shrinker doesn't consider VM's request(i.e., sc->nr_to_scan) but > shrink all objects which could make latency huge. hm... may be. I only briefly thought about it a while ago; and have no real data on hands. it was something as follows: between zs_shrinker_count() and zs_shrinker_scan() a lot can change; and _theoretically_ attempting to zs_shrinker_scan() even a smaller sc->nr_to_scan still may result in a "full" pool scan, taking all of the classes ->locks one by one just because classes are not the same as a moment ago. which is even more probable, I think, once the system is getting low on memory and begins to swap out, for instance. because in the latter case we increase the number of writes to zspool and, thus, reduce its chances to be compacted. if the system would still demand free memory, then it'd keep calling zs_shrinker_count() and zs_shrinker_scan() on us; at some point, I think, zs_shrinker_count() would start returning 0. ...if some of the classes would have huge fragmentation then we'd keep these class' ->locks for some time, moving objects. other than that we probably would just iterate the classes. purely theoretical. do you have any numbers? hm, probably it makes sense to change it. but if the change will replace "1 full pool scan" to "2 scans of 1/2 of pool's classes", then I'm less sure. > I want to fix it as another issue and then adding ZS_EMPTY pool pages > purging logic based on it because many works for zsmalloc stucked > with this patchset now which churns old code heavily. :( -ss
WARNING: multiple messages have this Message-ID (diff)
From: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> To: Minchan Kim <minchan@kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>, Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Subject: Re: [PATCH v6 11/12] zsmalloc: page migration support Date: Thu, 26 May 2016 00:23:45 +0900 [thread overview] Message-ID: <20160525152345.GA515@swordfish> (raw) In-Reply-To: <20160525051438.GA14786@bbox> Hello Minchan, On (05/25/16 14:14), Minchan Kim wrote: [..] > > > do you also want to kick the deferred page release from the shrinker > > > callback, for example? > > > > Yeb, it can be. I will do it at next revision. :) > > Thanks! > > > > I tried it now but I feel strongly we want to fix shrinker first. > Now, shrinker doesn't consider VM's request(i.e., sc->nr_to_scan) but > shrink all objects which could make latency huge. hm... may be. I only briefly thought about it a while ago; and have no real data on hands. it was something as follows: between zs_shrinker_count() and zs_shrinker_scan() a lot can change; and _theoretically_ attempting to zs_shrinker_scan() even a smaller sc->nr_to_scan still may result in a "full" pool scan, taking all of the classes ->locks one by one just because classes are not the same as a moment ago. which is even more probable, I think, once the system is getting low on memory and begins to swap out, for instance. because in the latter case we increase the number of writes to zspool and, thus, reduce its chances to be compacted. if the system would still demand free memory, then it'd keep calling zs_shrinker_count() and zs_shrinker_scan() on us; at some point, I think, zs_shrinker_count() would start returning 0. ...if some of the classes would have huge fragmentation then we'd keep these class' ->locks for some time, moving objects. other than that we probably would just iterate the classes. purely theoretical. do you have any numbers? hm, probably it makes sense to change it. but if the change will replace "1 full pool scan" to "2 scans of 1/2 of pool's classes", then I'm less sure. > I want to fix it as another issue and then adding ZS_EMPTY pool pages > purging logic based on it because many works for zsmalloc stucked > with this patchset now which churns old code heavily. :( -ss -- 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:[~2016-05-25 14:26 UTC|newest] Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-05-20 14:23 [PATCH v6 00/12] Support non-lru page migration Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 01/12] mm: use put_page to free page instead of putback_lru_page Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 02/12] mm: migrate: support non-lru movable page migration Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-27 14:26 ` Vlastimil Babka 2016-05-27 14:26 ` Vlastimil Babka 2016-05-27 14:26 ` Vlastimil Babka 2016-05-30 1:33 ` Minchan Kim 2016-05-30 1:33 ` Minchan Kim 2016-05-30 1:33 ` Minchan Kim 2016-05-30 9:01 ` Vlastimil Babka 2016-05-30 9:01 ` Vlastimil Babka 2016-05-30 9:01 ` Vlastimil Babka 2016-05-30 1:33 ` Minchan Kim 2016-05-27 14:26 ` Vlastimil Babka 2016-05-30 1:39 ` PATCH v6v2 " Minchan Kim 2016-05-30 1:39 ` Minchan Kim 2016-05-30 1:39 ` Minchan Kim 2016-05-30 1:39 ` Minchan Kim 2016-05-30 9:36 ` Vlastimil Babka 2016-05-30 9:36 ` Vlastimil Babka 2016-05-30 9:36 ` Vlastimil Babka 2016-05-30 16:25 ` Minchan Kim 2016-05-30 16:25 ` Minchan Kim 2016-05-30 16:25 ` Minchan Kim 2016-05-31 7:51 ` Vlastimil Babka 2016-05-31 7:51 ` Vlastimil Babka 2016-05-31 7:51 ` Vlastimil Babka 2016-05-31 0:01 ` [PATCH v6v3 " Minchan Kim 2016-05-31 0:01 ` Minchan Kim 2016-05-31 0:01 ` Minchan Kim 2016-05-31 0:01 ` Minchan Kim 2016-05-31 7:52 ` Vlastimil Babka 2016-05-31 7:52 ` Vlastimil Babka 2016-05-31 23:05 ` Minchan Kim 2016-05-31 23:05 ` Minchan Kim 2016-05-31 23:05 ` Minchan Kim 2016-05-31 7:52 ` Vlastimil Babka 2016-06-13 9:38 ` Anshuman Khandual 2016-06-13 9:38 ` Anshuman Khandual 2016-06-15 2:32 ` Minchan Kim 2016-06-15 2:32 ` Minchan Kim 2016-06-15 6:45 ` Anshuman Khandual 2016-06-15 6:45 ` Anshuman Khandual 2016-06-15 6:45 ` Anshuman Khandual 2016-06-16 0:26 ` Minchan Kim 2016-06-16 0:26 ` Minchan Kim 2016-06-16 0:26 ` Minchan Kim 2016-06-16 0:26 ` Minchan Kim 2016-06-16 3:42 ` Anshuman Khandual 2016-06-16 3:42 ` Anshuman Khandual 2016-06-16 3:42 ` Anshuman Khandual 2016-06-16 5:37 ` Minchan Kim 2016-06-16 5:37 ` Minchan Kim 2016-06-27 5:51 ` Anshuman Khandual 2016-06-27 5:51 ` Anshuman Khandual 2016-06-27 5:51 ` Anshuman Khandual 2016-06-28 6:39 ` Minchan Kim 2016-06-28 6:39 ` Minchan Kim 2016-06-28 6:39 ` Minchan Kim 2016-06-30 5:56 ` Anshuman Khandual 2016-06-30 5:56 ` Anshuman Khandual 2016-06-30 6:18 ` Minchan Kim 2016-06-30 6:18 ` Minchan Kim 2016-06-30 6:18 ` Minchan Kim 2016-06-30 6:18 ` Minchan Kim 2016-06-30 5:56 ` Anshuman Khandual 2016-06-16 5:37 ` Minchan Kim 2016-06-15 2:32 ` Minchan Kim 2016-06-13 9:38 ` Anshuman Khandual 2016-05-20 14:23 ` [PATCH v6 03/12] mm: balloon: use general non-lru movable page feature Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-30 12:16 ` Vlastimil Babka 2016-05-30 12:16 ` Vlastimil Babka 2016-05-30 12:16 ` Vlastimil Babka 2016-05-20 14:23 ` [PATCH v6 04/12] zsmalloc: keep max_object in size_class Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 05/12] zsmalloc: use bit_spin_lock Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 06/12] zsmalloc: use accessor Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 07/12] zsmalloc: factor page chain functionality out Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 08/12] zsmalloc: introduce zspage structure Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 09/12] zsmalloc: separate free_zspage from putback_zspage Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 10/12] zsmalloc: use freeobj for index Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 11/12] zsmalloc: page migration support Minchan Kim 2016-05-20 14:23 ` Minchan Kim 2016-05-24 5:28 ` Sergey Senozhatsky 2016-05-24 5:28 ` Sergey Senozhatsky 2016-05-24 6:28 ` Minchan Kim 2016-05-24 6:28 ` Minchan Kim 2016-05-24 8:05 ` Sergey Senozhatsky 2016-05-24 8:05 ` Sergey Senozhatsky 2016-05-24 8:17 ` Minchan Kim 2016-05-24 8:17 ` Minchan Kim 2016-05-25 5:14 ` Minchan Kim 2016-05-25 5:14 ` Minchan Kim 2016-05-25 15:23 ` Sergey Senozhatsky [this message] 2016-05-25 15:23 ` Sergey Senozhatsky 2016-05-26 0:32 ` Minchan Kim 2016-05-26 0:32 ` Minchan Kim 2016-05-26 0:59 ` Sergey Senozhatsky 2016-05-26 0:59 ` Sergey Senozhatsky 2016-05-26 4:37 ` Minchan Kim 2016-05-26 4:37 ` Minchan Kim 2016-05-26 21:50 ` [PATCH v6r2 " Minchan Kim 2016-05-26 21:50 ` Minchan Kim 2016-05-20 14:23 ` [PATCH v6 12/12] zram: use __GFP_MOVABLE for memory allocation Minchan Kim 2016-05-20 14:23 ` Minchan Kim
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=20160525152345.GA515@swordfish \ --to=sergey.senozhatsky@gmail.com \ --cc=akpm@linux-foundation.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=minchan@kernel.org \ --cc=sergey.senozhatsky.work@gmail.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.