From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS, URIBL_BLOCKED,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 58602C433E1 for ; Thu, 14 May 2020 07:05:11 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 1E1A8206B6 for ; Thu, 14 May 2020 07:05:11 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 1E1A8206B6 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id AB5F78004D; Thu, 14 May 2020 03:05:10 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id A411C900028; Thu, 14 May 2020 03:05:10 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 955B88004D; Thu, 14 May 2020 03:05:10 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0248.hostedemail.com [216.40.44.248]) by kanga.kvack.org (Postfix) with ESMTP id 7B324900028 for ; Thu, 14 May 2020 03:05:10 -0400 (EDT) Received: from smtpin08.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id 3780A181AEF0B for ; Thu, 14 May 2020 07:05:10 +0000 (UTC) X-FDA: 76814437980.08.beef72_844a0620fad1a X-HE-Tag: beef72_844a0620fad1a X-Filterd-Recvd-Size: 7712 Received: from mga18.intel.com (mga18.intel.com [134.134.136.126]) by imf24.hostedemail.com (Postfix) with ESMTP for ; Thu, 14 May 2020 07:05:08 +0000 (UTC) IronPort-SDR: IaMCJGT+pscyV737xE0joyOO5OwH2bGq0uqfesmxMyo17Qr9R4yvCASYPPUlxniY/3+xsd+kvk A1HxRnsshuyQ== X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga004.jf.intel.com ([10.7.209.38]) by orsmga106.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 14 May 2020 00:05:07 -0700 IronPort-SDR: 6FVzJxd1jEXGZrJHw+CDmJpWFALfuA+k3nIje0Xr3qyJy3EMB35Gc/KTRKZNG/QA0kFqTnPoAs +RMw1oudHNAw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.73,390,1583222400"; d="scan'208";a="409968776" Received: from unknown (HELO yhuang-mobile.sh.intel.com) ([10.238.6.207]) by orsmga004.jf.intel.com with ESMTP; 14 May 2020 00:05:02 -0700 From: Huang Ying To: Andrew Morton Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Huang Ying , Michal Hocko , Minchan Kim , Tim Chen , Hugh Dickins Subject: [PATCH] swap: Add percpu cluster_next to reduce lock contention on swap cache Date: Thu, 14 May 2020 15:04:24 +0800 Message-Id: <20200514070424.16017-1-ying.huang@intel.com> X-Mailer: git-send-email 2.26.2 MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: In some swap scalability test, it is found that there are heavy lock contention on swap cache even if we have split one swap cache radix tree per swap device to one swap cache radix tree every 64 MB trunk in commit 4b3ef9daa4fc ("mm/swap: split swap cache into 64MB trunks"). The reason is as follow. After the swap device becomes fragmented so that there's no free swap cluster, the swap device will be scanned linearly to find the free swap slots. swap_info_struct->cluster_next is the next scanning base that is shared by all CPUs. So nearby free swap slots will be allocated for different CPUs. The probability for multiple CPUs to operate on the same 64 MB trunk is high. This causes the lock contention on the swap cache. To solve the issue, in this patch, for SSD swap device, a percpu version next scanning base (cluster_next_cpu) is added. Every CPU will use its own next scanning base. So the probability for multiple CPUs to operate on the same 64 MB trunk is reduced greatly. Thus the lock contention is reduced too. For HDD, because sequential access is more important for IO performance, the original shared next scanning base is used. To test the patch, we have run 16-process pmbench memory benchmark on a 2-socket server machine with 48 cores. One ram disk is configured as the swap device per socket. The pmbench working-set size is much larger than the available memory so that swapping is triggered. The memory read/write ratio is 80/20 and the accessing pattern is random. In the original implementation, the lock contention on the swap cache is heavy. The perf profiling data of the lock contention code path is as following, _raw_spin_lock_irq.add_to_swap_cache.add_to_swap.shrink_page_list: 7= .93 _raw_spin_lock_irqsave.__remove_mapping.shrink_page_list: 7.03 _raw_spin_lock_irq.mem_cgroup_commit_charge.do_swap_page: 3.7 _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 2= .9 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 1.32 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.01 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 0.87 After applying this patch, it becomes, _raw_spin_lock_irq.mem_cgroup_commit_charge.do_swap_page: 3.99 _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 3= .0 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 1= .47 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 1.31 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 0.88 _raw_spin_lock.scan_swap_map_slots.get_swap_pages.get_swap_page: 0.76 _raw_spin_lock_irq.add_to_swap_cache.add_to_swap.shrink_page_list: 0= .53 The lock contention on the swap cache is almost eliminated. And the pmbench score increases 15.9%. The swapin throughput increases 16.2% from 2.84 GB/s to 3.3 GB/s. While the swapout throughput increases 16.1% from 2.87 GB/s to 3.33 GB/s. Signed-off-by: "Huang, Ying" Cc: Michal Hocko Cc: Minchan Kim Cc: Tim Chen Cc: Hugh Dickins --- include/linux/swap.h | 1 + mm/swapfile.c | 27 +++++++++++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index b42fb47d8cbe..e96820fb7472 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -252,6 +252,7 @@ struct swap_info_struct { unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ + unsigned int __percpu *cluster_next_cpu; /*percpu index for next alloca= tion */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap locat= ion */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 35be7a7271f4..9f1343b066c1 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -746,7 +746,16 @@ static int scan_swap_map_slots(struct swap_info_stru= ct *si, */ =20 si->flags +=3D SWP_SCANNING; - scan_base =3D offset =3D si->cluster_next; + /* + * Use percpu scan base for SSD to reduce lock contention on + * cluster and swap cache. For HDD, sequential access is more + * important. + */ + if (si->flags & SWP_SOLIDSTATE) + scan_base =3D this_cpu_read(*si->cluster_next_cpu); + else + scan_base =3D si->cluster_next; + offset =3D scan_base; =20 /* SSD algorithm */ if (si->cluster_info) { @@ -835,7 +844,10 @@ static int scan_swap_map_slots(struct swap_info_stru= ct *si, unlock_cluster(ci); =20 swap_range_alloc(si, offset, 1); - si->cluster_next =3D offset + 1; + if (si->flags & SWP_SOLIDSTATE) + this_cpu_write(*si->cluster_next_cpu, offset + 1); + else + si->cluster_next =3D offset + 1; slots[n_ret++] =3D swp_entry(si->type, offset); =20 /* got enough slots or reach max slots? */ @@ -2828,6 +2840,11 @@ static struct swap_info_struct *alloc_swap_info(vo= id) p =3D kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); + p->cluster_next_cpu =3D alloc_percpu(unsigned int); + if (!p->cluster_next_cpu) { + kvfree(p); + return ERR_PTR(-ENOMEM); + } =20 spin_lock(&swap_lock); for (type =3D 0; type < nr_swapfiles; type++) { @@ -2962,6 +2979,8 @@ static unsigned long read_swap_header(struct swap_i= nfo_struct *p, =20 p->lowest_bit =3D 1; p->cluster_next =3D 1; + for_each_possible_cpu(i) + per_cpu(*p->cluster_next_cpu, i) =3D 1; p->cluster_nr =3D 0; =20 maxpages =3D max_swapfile_size(); @@ -3204,6 +3223,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, speci= alfile, int, swap_flags) * SSD */ p->cluster_next =3D 1 + prandom_u32_max(p->highest_bit); + for_each_possible_cpu(cpu) { + per_cpu(*p->cluster_next_cpu, cpu) =3D + 1 + prandom_u32_max(p->highest_bit); + } nr_cluster =3D DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); =20 cluster_info =3D kvcalloc(nr_cluster, sizeof(*cluster_info), --=20 2.26.2