Linux-mm Archive on lore.kernel.org
 help / Atom feed
From: Zi Yan <zi.yan@sent.com>
To: Dave Hansen <dave.hansen@linux.intel.com>,
	Yang Shi <yang.shi@linux.alibaba.com>,
	Keith Busch <keith.busch@intel.com>,
	Fengguang Wu <fengguang.wu@intel.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>,
	Michal Hocko <mhocko@kernel.org>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Vlastimil Babka <vbabka@suse.cz>,
	Mel Gorman <mgorman@techsingularity.net>,
	John Hubbard <jhubbard@nvidia.com>,
	Mark Hairgrove <mhairgrove@nvidia.com>,
	Nitin Gupta <nigupta@nvidia.com>,
	Javier Cabezas <jcabezas@nvidia.com>,
	David Nellans <dnellans@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 24/25] memory manage: limit migration batch size.
Date: Wed,  3 Apr 2019 19:00:45 -0700
Message-ID: <20190404020046.32741-25-zi.yan@sent.com> (raw)
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

Make migration batch size adjustable to avoid excessive migration
overheads when a lot of pages are under migration.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 kernel/sysctl.c    |  8 ++++++++
 mm/memory_manage.c | 60 ++++++++++++++++++++++++++++++++++++------------------
 2 files changed, 48 insertions(+), 20 deletions(-)

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b8712eb..b92e2da9 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -105,6 +105,7 @@ extern int accel_page_copy;
 extern unsigned int limit_mt_num;
 extern int use_all_dma_chans;
 extern int limit_dma_chans;
+extern int migration_batch_size;
 
 /* External variables not in a header file. */
 extern int suid_dumpable;
@@ -1470,6 +1471,13 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	 },
 	 {
+		.procname	= "migration_batch_size",
+		.data		= &migration_batch_size,
+		.maxlen		= sizeof(migration_batch_size),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	 },
+	 {
 		.procname	= "hugetlb_shm_group",
 		.data		= &sysctl_hugetlb_shm_group,
 		.maxlen		= sizeof(gid_t),
diff --git a/mm/memory_manage.c b/mm/memory_manage.c
index d63ad25..8b76fcf 100644
--- a/mm/memory_manage.c
+++ b/mm/memory_manage.c
@@ -16,6 +16,8 @@
 
 #include "internal.h"
 
+int migration_batch_size = 16;
+
 enum isolate_action {
 	ISOLATE_COLD_PAGES = 1,
 	ISOLATE_HOT_PAGES,
@@ -137,35 +139,49 @@ static unsigned long isolate_pages_from_lru_list(pg_data_t *pgdat,
 }
 
 static int migrate_to_node(struct list_head *page_list, int nid,
-		enum migrate_mode mode)
+		enum migrate_mode mode, int batch_size)
 {
 	bool migrate_concur = mode & MIGRATE_CONCUR;
+	bool unlimited_batch_size = (batch_size <=0 || !migrate_concur);
 	int num = 0;
-	int from_nid;
+	int from_nid = -1;
 	int err;
 
 	if (list_empty(page_list))
 		return num;
 
-	from_nid = page_to_nid(list_first_entry(page_list, struct page, lru));
+	while (!list_empty(page_list)) {
+		LIST_HEAD(batch_page_list);
+		int i;
 
-	if (migrate_concur)
-		err = migrate_pages_concur(page_list, alloc_new_node_page,
-			NULL, nid, mode, MR_SYSCALL);
-	else
-		err = migrate_pages(page_list, alloc_new_node_page,
-			NULL, nid, mode, MR_SYSCALL);
+		/* it should move all pages to batch_page_list if !migrate_concur */
+		for (i = 0; i < batch_size || unlimited_batch_size; i++) {
+			struct page *item = list_first_entry_or_null(page_list, struct page, lru);
+			if (!item)
+				break;
+			list_move(&item->lru, &batch_page_list);
+		}
 
-	if (err) {
-		struct page *page;
+		from_nid = page_to_nid(list_first_entry(&batch_page_list, struct page, lru));
 
-		list_for_each_entry(page, page_list, lru)
-			num += hpage_nr_pages(page);
-		pr_debug("%d pages failed to migrate from %d to %d\n",
-			num, from_nid, nid);
+		if (migrate_concur)
+			err = migrate_pages_concur(&batch_page_list, alloc_new_node_page,
+				NULL, nid, mode, MR_SYSCALL);
+		else
+			err = migrate_pages(&batch_page_list, alloc_new_node_page,
+				NULL, nid, mode, MR_SYSCALL);
 
-		putback_movable_pages(page_list);
+		if (err) {
+			struct page *page;
+
+			list_for_each_entry(page, &batch_page_list, lru)
+				num += hpage_nr_pages(page);
+
+			putback_movable_pages(&batch_page_list);
+		}
 	}
+	pr_debug("%d pages failed to migrate from %d to %d\n",
+		num, from_nid, nid);
 	return num;
 }
 
@@ -325,10 +341,12 @@ static int do_mm_manage(struct task_struct *p, struct mm_struct *mm,
 		/* Migrate pages to slow node */
 		/* No multi-threaded migration for base pages */
 		nr_isolated_fast_base_pages -=
-			migrate_to_node(&fast_base_page_list, slow_nid, mode & ~MIGRATE_MT);
+			migrate_to_node(&fast_base_page_list, slow_nid,
+				mode & ~MIGRATE_MT, migration_batch_size);
 
 		nr_isolated_fast_huge_pages -=
-			migrate_to_node(&fast_huge_page_list, slow_nid, mode);
+			migrate_to_node(&fast_huge_page_list, slow_nid, mode,
+				migration_batch_size);
 	}
 
 	if (nr_isolated_fast_base_pages != ULONG_MAX &&
@@ -342,10 +360,12 @@ static int do_mm_manage(struct task_struct *p, struct mm_struct *mm,
 	/* Migrate pages to fast node */
 	/* No multi-threaded migration for base pages */
 	nr_isolated_slow_base_pages -=
-		migrate_to_node(&slow_base_page_list, fast_nid, mode & ~MIGRATE_MT);
+		migrate_to_node(&slow_base_page_list, fast_nid, mode & ~MIGRATE_MT,
+				migration_batch_size);
 
 	nr_isolated_slow_huge_pages -=
-		migrate_to_node(&slow_huge_page_list, fast_nid, mode);
+		migrate_to_node(&slow_huge_page_list, fast_nid, mode,
+				migration_batch_size);
 
 	return err;
 }
-- 
2.7.4


  parent reply index

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-04  2:00 [RFC PATCH 00/25] Accelerate page migration and use memcg for PMEM management Zi Yan
2019-04-04  2:00 ` [RFC PATCH 01/25] mm: migrate: Change migrate_mode to support combination migration modes Zi Yan
2019-04-04  2:00 ` [RFC PATCH 02/25] mm: migrate: Add mode parameter to support future page copy routines Zi Yan
2019-04-04  2:00 ` [RFC PATCH 03/25] mm: migrate: Add a multi-threaded page migration function Zi Yan
2019-04-04  2:00 ` [RFC PATCH 04/25] mm: migrate: Add copy_page_multithread into migrate_pages Zi Yan
2019-04-04  2:00 ` [RFC PATCH 05/25] mm: migrate: Add vm.accel_page_copy in sysfs to control page copy acceleration Zi Yan
2019-04-04  2:00 ` [RFC PATCH 06/25] mm: migrate: Make the number of copy threads adjustable via sysctl Zi Yan
2019-04-04  2:00 ` [RFC PATCH 07/25] mm: migrate: Add copy_page_dma to use DMA Engine to copy pages Zi Yan
2019-04-04  2:00 ` [RFC PATCH 08/25] mm: migrate: Add copy_page_dma into migrate_page_copy Zi Yan
2019-04-04  2:00 ` [RFC PATCH 09/25] mm: migrate: Add copy_page_lists_dma_always to support copy a list of pages Zi Yan
2019-04-04  2:00 ` [RFC PATCH 10/25] mm: migrate: copy_page_lists_mt() to copy a page list using multi-threads Zi Yan
2019-04-04  2:00 ` [RFC PATCH 11/25] mm: migrate: Add concurrent page migration into move_pages syscall Zi Yan
2019-04-04  2:00 ` [RFC PATCH 12/25] exchange pages: new page migration mechanism: exchange_pages() Zi Yan
2019-04-04  2:00 ` [RFC PATCH 13/25] exchange pages: add multi-threaded exchange pages Zi Yan
2019-04-04  2:00 ` [RFC PATCH 14/25] exchange pages: concurrent " Zi Yan
2019-04-04  2:00 ` [RFC PATCH 15/25] exchange pages: exchange anonymous page and file-backed page Zi Yan
2019-04-04  2:00 ` [RFC PATCH 16/25] exchange page: Add THP exchange support Zi Yan
2019-04-04  2:00 ` [RFC PATCH 17/25] exchange page: Add exchange_page() syscall Zi Yan
2019-04-04  2:00 ` [RFC PATCH 18/25] memcg: Add per node memory usage&max stats in memcg Zi Yan
2019-04-04  2:00 ` [RFC PATCH 19/25] mempolicy: add MPOL_F_MEMCG flag, enforcing memcg memory limit Zi Yan
2019-04-04  2:00 ` [RFC PATCH 20/25] memory manage: Add memory manage syscall Zi Yan
2019-04-04  2:00 ` [RFC PATCH 21/25] mm: move update_lru_sizes() to mm_inline.h for broader use Zi Yan
2019-04-04  2:00 ` [RFC PATCH 22/25] memory manage: active/inactive page list manipulation in memcg Zi Yan
2019-04-04  2:00 ` [RFC PATCH 23/25] memory manage: page migration based page manipulation between NUMA nodes Zi Yan
2019-04-04  2:00 ` Zi Yan [this message]
2019-04-04  2:00 ` [RFC PATCH 25/25] memory manage: use exchange pages to memory manage to improve throughput Zi Yan
2019-04-04  7:13 ` [RFC PATCH 00/25] Accelerate page migration and use memcg for PMEM management Michal Hocko
2019-04-05  0:32 ` Yang Shi
2019-04-05 17:20   ` Zi Yan

Reply instructions:

You may reply publically 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=20190404020046.32741-25-zi.yan@sent.com \
    --to=zi.yan@sent.com \
    --cc=akpm@linux-foundation.org \
    --cc=daniel.m.jordan@oracle.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dnellans@nvidia.com \
    --cc=fengguang.wu@intel.com \
    --cc=jcabezas@nvidia.com \
    --cc=jhubbard@nvidia.com \
    --cc=keith.busch@intel.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhairgrove@nvidia.com \
    --cc=mhocko@kernel.org \
    --cc=nigupta@nvidia.com \
    --cc=vbabka@suse.cz \
    --cc=yang.shi@linux.alibaba.com \
    --cc=ziy@nvidia.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: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org linux-mm@archiver.kernel.org
	public-inbox-index linux-mm


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/ public-inbox