From: Vlastimil Babka <vbabka@suse.cz> To: Xishi Qiu <qiuxishi@huawei.com>, David Rientjes <rientjes@google.com>, Andrew Morton <akpm@linux-foundation.org>, Joonsoo Kim <iamjoonsoo.kim@lge.com>, Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Linux MM <linux-mm@kvack.org>, LKML <linux-kernel@vger.kernel.org>, Minchan Kim <minchan@kernel.org> Subject: Re: [PATCH 2/2] mem-hotplug: use different mempolicy in alloc_migrate_target() Date: Mon, 18 Jul 2016 10:00:52 +0200 [thread overview] Message-ID: <882dd251-9043-8fa0-4fe9-57b95fc6de3a@suse.cz> (raw) In-Reply-To: <57884FAA.9040500@huawei.com> On 07/15/2016 04:51 AM, Xishi Qiu wrote: > When we offline a node, the new page should alloced from other > nodes instead of the current node, because re-migrate is a waste of > time. Ugh, I'm surprised that it's not the case already. Maybe the allocation from same node is already prevented indirectly somehow? > So use prefer mempolicy for hotplug, use default mempolicy for cma. IMHO CMA should prefer the same node as the migrated page, if anything. Current task's mempolicy shouldn't restrict it (it's likely migrating pages of somebody else) or even guide its preferences. Ideally it would keep the original page's mempolicy, but we can't afford to track that... > Signed-off-by: Xishi Qiu <qiuxishi@huawei.com> > --- > include/linux/page-isolation.h | 2 +- > mm/memory_hotplug.c | 5 ++++- > mm/page_alloc.c | 2 +- > mm/page_isolation.c | 8 +++++--- > 4 files changed, 11 insertions(+), 6 deletions(-) > > diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h > index 047d647..c163de3 100644 > --- a/include/linux/page-isolation.h > +++ b/include/linux/page-isolation.h > @@ -65,7 +65,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, > int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, > bool skip_hwpoisoned_pages); > > -struct page *alloc_migrate_target(struct page *page, unsigned long private, > +struct page *alloc_migrate_target(struct page *page, unsigned long nid, > int **resultp); > > #endif > diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c > index e3cbdca..b5963bf 100644 > --- a/mm/memory_hotplug.c > +++ b/mm/memory_hotplug.c > @@ -1510,12 +1510,15 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) > int move_pages = NR_OFFLINE_AT_ONCE_PAGES; > int not_managed = 0; > int ret = 0; > + int nid = NUMA_NO_NODE; > LIST_HEAD(source); > > for (pfn = start_pfn; pfn < end_pfn && move_pages > 0; pfn++) { > if (!pfn_valid(pfn)) > continue; > page = pfn_to_page(pfn); > + if (nid == NUMA_NO_NODE) > + nid = next_node_in(page_to_nid(page), node_online_map); > > if (PageHuge(page)) { > struct page *head = compound_head(page); > @@ -1568,7 +1571,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) > * alloc_migrate_target should be improooooved!! So, is this patch improooooving it enough that we can delete the comment? If not, could the patch be improooooved? :) > * migrate_pages returns # of failed pages. > */ > - ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, > + ret = migrate_pages(&source, alloc_migrate_target, NULL, nid, > MIGRATE_SYNC, MR_MEMORY_HOTPLUG); > if (ret) > putback_movable_pages(&source); > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index 6903b69..b99f1c2 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -7322,7 +7322,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, > cc->nr_migratepages -= nr_reclaimed; > > ret = migrate_pages(&cc->migratepages, alloc_migrate_target, > - NULL, 0, cc->mode, MR_CMA); > + NULL, NUMA_NO_NODE, cc->mode, MR_CMA); > } > if (ret < 0) { > putback_movable_pages(&cc->migratepages); > diff --git a/mm/page_isolation.c b/mm/page_isolation.c > index 4f32c9f..f471be6 100644 > --- a/mm/page_isolation.c > +++ b/mm/page_isolation.c > @@ -279,18 +279,20 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, > return pfn < end_pfn ? -EBUSY : 0; > } > > -struct page *alloc_migrate_target(struct page *page, unsigned long private, > +struct page *alloc_migrate_target(struct page *page, unsigned long nid, > int **resultp) > { > /* > - * TODO: allocate a destination hugepage from a nearest neighbor node, > + * hugeTLB: allocate a destination page from a nearest neighbor node, for hugeTLB it's still a TODO, by removing the word the rest of comment doesn't make much sense > * accordance with memory policy of the user process if possible. For > * now as a simple work-around, we use the next node for destination. > + * Normal page: use prefer mempolicy for destination if called by > + * hotplug, use default mempolicy for destination if called by cma. > */ > if (PageHuge(page)) > return alloc_huge_page_node(page_hstate(compound_head(page)), > next_node_in(page_to_nid(page), > node_online_map)); > else > - return alloc_page(GFP_HIGHUSER_MOVABLE); > + return alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0); > } >
WARNING: multiple messages have this Message-ID (diff)
From: Vlastimil Babka <vbabka@suse.cz> To: Xishi Qiu <qiuxishi@huawei.com>, David Rientjes <rientjes@google.com>, Andrew Morton <akpm@linux-foundation.org>, Joonsoo Kim <iamjoonsoo.kim@lge.com>, Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Linux MM <linux-mm@kvack.org>, LKML <linux-kernel@vger.kernel.org>, Minchan Kim <minchan@kernel.org> Subject: Re: [PATCH 2/2] mem-hotplug: use different mempolicy in alloc_migrate_target() Date: Mon, 18 Jul 2016 10:00:52 +0200 [thread overview] Message-ID: <882dd251-9043-8fa0-4fe9-57b95fc6de3a@suse.cz> (raw) In-Reply-To: <57884FAA.9040500@huawei.com> On 07/15/2016 04:51 AM, Xishi Qiu wrote: > When we offline a node, the new page should alloced from other > nodes instead of the current node, because re-migrate is a waste of > time. Ugh, I'm surprised that it's not the case already. Maybe the allocation from same node is already prevented indirectly somehow? > So use prefer mempolicy for hotplug, use default mempolicy for cma. IMHO CMA should prefer the same node as the migrated page, if anything. Current task's mempolicy shouldn't restrict it (it's likely migrating pages of somebody else) or even guide its preferences. Ideally it would keep the original page's mempolicy, but we can't afford to track that... > Signed-off-by: Xishi Qiu <qiuxishi@huawei.com> > --- > include/linux/page-isolation.h | 2 +- > mm/memory_hotplug.c | 5 ++++- > mm/page_alloc.c | 2 +- > mm/page_isolation.c | 8 +++++--- > 4 files changed, 11 insertions(+), 6 deletions(-) > > diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h > index 047d647..c163de3 100644 > --- a/include/linux/page-isolation.h > +++ b/include/linux/page-isolation.h > @@ -65,7 +65,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, > int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, > bool skip_hwpoisoned_pages); > > -struct page *alloc_migrate_target(struct page *page, unsigned long private, > +struct page *alloc_migrate_target(struct page *page, unsigned long nid, > int **resultp); > > #endif > diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c > index e3cbdca..b5963bf 100644 > --- a/mm/memory_hotplug.c > +++ b/mm/memory_hotplug.c > @@ -1510,12 +1510,15 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) > int move_pages = NR_OFFLINE_AT_ONCE_PAGES; > int not_managed = 0; > int ret = 0; > + int nid = NUMA_NO_NODE; > LIST_HEAD(source); > > for (pfn = start_pfn; pfn < end_pfn && move_pages > 0; pfn++) { > if (!pfn_valid(pfn)) > continue; > page = pfn_to_page(pfn); > + if (nid == NUMA_NO_NODE) > + nid = next_node_in(page_to_nid(page), node_online_map); > > if (PageHuge(page)) { > struct page *head = compound_head(page); > @@ -1568,7 +1571,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) > * alloc_migrate_target should be improooooved!! So, is this patch improooooving it enough that we can delete the comment? If not, could the patch be improooooved? :) > * migrate_pages returns # of failed pages. > */ > - ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, > + ret = migrate_pages(&source, alloc_migrate_target, NULL, nid, > MIGRATE_SYNC, MR_MEMORY_HOTPLUG); > if (ret) > putback_movable_pages(&source); > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index 6903b69..b99f1c2 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -7322,7 +7322,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, > cc->nr_migratepages -= nr_reclaimed; > > ret = migrate_pages(&cc->migratepages, alloc_migrate_target, > - NULL, 0, cc->mode, MR_CMA); > + NULL, NUMA_NO_NODE, cc->mode, MR_CMA); > } > if (ret < 0) { > putback_movable_pages(&cc->migratepages); > diff --git a/mm/page_isolation.c b/mm/page_isolation.c > index 4f32c9f..f471be6 100644 > --- a/mm/page_isolation.c > +++ b/mm/page_isolation.c > @@ -279,18 +279,20 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, > return pfn < end_pfn ? -EBUSY : 0; > } > > -struct page *alloc_migrate_target(struct page *page, unsigned long private, > +struct page *alloc_migrate_target(struct page *page, unsigned long nid, > int **resultp) > { > /* > - * TODO: allocate a destination hugepage from a nearest neighbor node, > + * hugeTLB: allocate a destination page from a nearest neighbor node, for hugeTLB it's still a TODO, by removing the word the rest of comment doesn't make much sense > * accordance with memory policy of the user process if possible. For > * now as a simple work-around, we use the next node for destination. > + * Normal page: use prefer mempolicy for destination if called by > + * hotplug, use default mempolicy for destination if called by cma. > */ > if (PageHuge(page)) > return alloc_huge_page_node(page_hstate(compound_head(page)), > next_node_in(page_to_nid(page), > node_online_map)); > else > - return alloc_page(GFP_HIGHUSER_MOVABLE); > + return alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0); > } > -- 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:[~2016-07-18 8:00 UTC|newest] Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-07-15 2:47 [PATCH 1/2] mem-hotplug: use GFP_HIGHUSER_MOVABLE in, alloc_migrate_target() Xishi Qiu 2016-07-15 2:47 ` Xishi Qiu 2016-07-15 2:51 ` [PATCH 2/2] mem-hotplug: use different mempolicy in alloc_migrate_target() Xishi Qiu 2016-07-15 2:51 ` Xishi Qiu 2016-07-18 8:00 ` Vlastimil Babka [this message] 2016-07-18 8:00 ` Vlastimil Babka 2016-07-18 5:51 ` [PATCH 1/2] mem-hotplug: use GFP_HIGHUSER_MOVABLE in, alloc_migrate_target() Joonsoo Kim 2016-07-18 5:51 ` Joonsoo Kim 2016-07-18 7:45 ` Vlastimil Babka 2016-07-18 7:45 ` Vlastimil Babka 2016-07-18 8:00 ` Xishi Qiu 2016-07-18 8:00 ` Xishi Qiu 2016-07-18 8:05 ` Vlastimil Babka 2016-07-18 8:05 ` Vlastimil Babka 2016-07-18 8:31 ` Xishi Qiu 2016-07-18 8:31 ` Xishi Qiu 2016-07-19 6:50 ` Joonsoo Kim 2016-07-19 6:50 ` Joonsoo Kim 2016-07-19 7:18 ` Xishi Qiu 2016-07-19 7:18 ` Xishi Qiu 2016-07-19 19:05 ` David Rientjes 2016-07-19 19:05 ` David Rientjes
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=882dd251-9043-8fa0-4fe9-57b95fc6de3a@suse.cz \ --to=vbabka@suse.cz \ --cc=akpm@linux-foundation.org \ --cc=iamjoonsoo.kim@lge.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=minchan@kernel.org \ --cc=n-horiguchi@ah.jp.nec.com \ --cc=qiuxishi@huawei.com \ --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.