From: "Huang\, Ying" <ying.huang@intel.com> To: Andrew Morton <akpm@linux-foundation.org> Cc: "Huang\, Ying" <ying.huang@intel.com>, <linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>, Hugh Dickins <hughd@google.com>, Shaohua Li <shli@kernel.org>, Minchan Kim <minchan@kernel.org>, Rik van Riel <riel@redhat.com> Subject: Re: [PATCH -mm -v3] mm, swap: Sort swap entries before free Date: Fri, 14 Apr 2017 09:36:18 +0800 [thread overview] Message-ID: <878tn3db3h.fsf@yhuang-dev.intel.com> (raw) In-Reply-To: <20170407144346.b2e5d3c8364767eb2b4118ed@linux-foundation.org> (Andrew Morton's message of "Fri, 7 Apr 2017 14:43:46 -0700") Andrew Morton <akpm@linux-foundation.org> writes: > On Fri, 7 Apr 2017 14:49:01 +0800 "Huang, Ying" <ying.huang@intel.com> wrote: > >> To reduce the lock contention of swap_info_struct->lock when freeing >> swap entry. The freed swap entries will be collected in a per-CPU >> buffer firstly, and be really freed later in batch. During the batch >> freeing, if the consecutive swap entries in the per-CPU buffer belongs >> to same swap device, the swap_info_struct->lock needs to be >> acquired/released only once, so that the lock contention could be >> reduced greatly. But if there are multiple swap devices, it is >> possible that the lock may be unnecessarily released/acquired because >> the swap entries belong to the same swap device are non-consecutive in >> the per-CPU buffer. >> >> To solve the issue, the per-CPU buffer is sorted according to the swap >> device before freeing the swap entries. Test shows that the time >> spent by swapcache_free_entries() could be reduced after the patch. >> >> Test the patch via measuring the run time of swap_cache_free_entries() >> during the exit phase of the applications use much swap space. The >> results shows that the average run time of swap_cache_free_entries() >> reduced about 20% after applying the patch. > > "20%" is useful info, but it is much better to present the absolute > numbers, please. If it's "20% of one nanosecond" then the patch isn't > very interesting. If it's "20% of 35 seconds" then we know we have > more work to do. I added memory freeing timing capability to vm-scalability test suite. The result shows the memory freeing time reduced from 2.64s to 2.31s (about -12.5%). Best Regards, Huang, Ying > If there is indeed still a significant problem here then perhaps it > would be better to move the percpu swp_entry_t buffer into the > per-device structure swap_info_struct, so it becomes "per cpu, per > device". That way we should be able to reduce contention further. > > Or maybe we do something else - it all depends upon the significance of > this problem, which is why a full description of your measurements is > useful.
WARNING: multiple messages have this Message-ID (diff)
From: "Huang\, Ying" <ying.huang@intel.com> To: Andrew Morton <akpm@linux-foundation.org> Cc: "Huang, Ying" <ying.huang@intel.com>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Hugh Dickins <hughd@google.com>, Shaohua Li <shli@kernel.org>, Minchan Kim <minchan@kernel.org>, Rik van Riel <riel@redhat.com> Subject: Re: [PATCH -mm -v3] mm, swap: Sort swap entries before free Date: Fri, 14 Apr 2017 09:36:18 +0800 [thread overview] Message-ID: <878tn3db3h.fsf@yhuang-dev.intel.com> (raw) In-Reply-To: <20170407144346.b2e5d3c8364767eb2b4118ed@linux-foundation.org> (Andrew Morton's message of "Fri, 7 Apr 2017 14:43:46 -0700") Andrew Morton <akpm@linux-foundation.org> writes: > On Fri, 7 Apr 2017 14:49:01 +0800 "Huang, Ying" <ying.huang@intel.com> wrote: > >> To reduce the lock contention of swap_info_struct->lock when freeing >> swap entry. The freed swap entries will be collected in a per-CPU >> buffer firstly, and be really freed later in batch. During the batch >> freeing, if the consecutive swap entries in the per-CPU buffer belongs >> to same swap device, the swap_info_struct->lock needs to be >> acquired/released only once, so that the lock contention could be >> reduced greatly. But if there are multiple swap devices, it is >> possible that the lock may be unnecessarily released/acquired because >> the swap entries belong to the same swap device are non-consecutive in >> the per-CPU buffer. >> >> To solve the issue, the per-CPU buffer is sorted according to the swap >> device before freeing the swap entries. Test shows that the time >> spent by swapcache_free_entries() could be reduced after the patch. >> >> Test the patch via measuring the run time of swap_cache_free_entries() >> during the exit phase of the applications use much swap space. The >> results shows that the average run time of swap_cache_free_entries() >> reduced about 20% after applying the patch. > > "20%" is useful info, but it is much better to present the absolute > numbers, please. If it's "20% of one nanosecond" then the patch isn't > very interesting. If it's "20% of 35 seconds" then we know we have > more work to do. I added memory freeing timing capability to vm-scalability test suite. The result shows the memory freeing time reduced from 2.64s to 2.31s (about -12.5%). Best Regards, Huang, Ying > If there is indeed still a significant problem here then perhaps it > would be better to move the percpu swp_entry_t buffer into the > per-device structure swap_info_struct, so it becomes "per cpu, per > device". That way we should be able to reduce contention further. > > Or maybe we do something else - it all depends upon the significance of > this problem, which is why a full description of your measurements is > useful. -- 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:[~2017-04-14 1:36 UTC|newest] Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-04-07 6:49 [PATCH -mm -v3] mm, swap: Sort swap entries before free Huang, Ying 2017-04-07 6:49 ` Huang, Ying 2017-04-07 13:05 ` Rik van Riel 2017-04-07 13:05 ` Rik van Riel 2017-04-07 21:43 ` Andrew Morton 2017-04-07 21:43 ` Andrew Morton 2017-04-11 7:03 ` Huang, Ying 2017-04-11 7:03 ` Huang, Ying 2017-04-14 1:36 ` Huang, Ying [this message] 2017-04-14 1:36 ` Huang, Ying 2017-04-14 1:41 ` Huang, Ying 2017-04-18 4:59 ` Minchan Kim 2017-04-18 4:59 ` Minchan Kim 2017-04-19 8:14 ` Huang, Ying 2017-04-19 8:14 ` Huang, Ying 2017-04-20 6:38 ` Minchan Kim 2017-04-20 6:38 ` Minchan Kim 2017-04-20 7:15 ` Huang, Ying 2017-04-20 7:15 ` Huang, Ying 2017-04-21 12:29 ` Huang, Ying 2017-04-21 12:29 ` Huang, Ying 2017-04-21 23:29 ` Tim Chen 2017-04-21 23:29 ` Tim Chen 2017-04-23 13:16 ` Huang, Ying 2017-04-23 13:16 ` Huang, Ying 2017-04-24 16:03 ` Tim Chen 2017-04-24 16:03 ` Tim Chen 2017-04-24 4:52 ` Minchan Kim 2017-04-24 4:52 ` Minchan Kim 2017-04-24 6:47 ` Huang, Ying 2017-04-24 6:47 ` Huang, Ying 2017-04-26 12:42 ` Huang, Ying 2017-04-26 12:42 ` Huang, Ying 2017-04-26 20:13 ` Tim Chen 2017-04-26 20:13 ` Tim Chen 2017-04-27 1:21 ` Huang, Ying 2017-04-27 1:21 ` Huang, Ying 2017-04-27 16:48 ` Tim Chen 2017-04-27 16:48 ` Tim Chen 2017-04-27 4:35 ` Minchan Kim 2017-04-27 4:35 ` Minchan Kim 2017-04-28 1:09 ` Huang, Ying 2017-04-28 1:09 ` Huang, Ying 2017-04-28 7:42 ` Minchan Kim 2017-04-28 7:42 ` Minchan Kim 2017-04-28 8:05 ` Huang, Ying 2017-04-28 8:05 ` Huang, Ying 2017-04-28 9:00 ` Minchan Kim 2017-04-28 9:00 ` Minchan Kim 2017-04-28 11:48 ` Huang, Ying 2017-04-28 11:48 ` Huang, Ying 2017-04-28 13:35 ` Huang, Ying 2017-04-28 13:35 ` Huang, Ying 2017-05-02 5:02 ` Minchan Kim 2017-05-02 5:02 ` Minchan Kim 2017-05-02 5:35 ` Huang, Ying 2017-05-02 5:35 ` Huang, Ying 2017-05-02 5:48 ` Minchan Kim 2017-05-02 5:48 ` Minchan Kim 2017-05-02 6:08 ` Huang, Ying 2017-05-02 6:08 ` Huang, Ying
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=878tn3db3h.fsf@yhuang-dev.intel.com \ --to=ying.huang@intel.com \ --cc=akpm@linux-foundation.org \ --cc=hughd@google.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=minchan@kernel.org \ --cc=riel@redhat.com \ --cc=shli@kernel.org \ /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.