From 5647bc293ab15f66a7b1cda850c5e9d162a6c7c2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 19 Oct 2012 10:46:20 +0100 Subject: mm: compaction: Move migration fail/success stats to migrate.c The compact_pages_moved and compact_pagemigrate_failed events are convenient for determining if compaction is active and to what degree migration is succeeding but it's at the wrong level. Other users of migration may also want to know if migration is working properly and this will be particularly true for any automated NUMA migration. This patch moves the counters down to migration with the new events called pgmigrate_success and pgmigrate_fail. The compact_blocks_moved counter is removed because while it was useful for debugging initially, it's worthless now as no meaningful conclusions can be drawn from its value. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel --- mm/migrate.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 77ed2d77370..04687f69cc1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -962,6 +962,7 @@ int migrate_pages(struct list_head *from, { int retry = 1; int nr_failed = 0; + int nr_succeeded = 0; int pass = 0; struct page *page; struct page *page2; @@ -988,6 +989,7 @@ int migrate_pages(struct list_head *from, retry++; break; case 0: + nr_succeeded++; break; default: /* Permanent failure */ @@ -998,6 +1000,10 @@ int migrate_pages(struct list_head *from, } rc = 0; out: + if (nr_succeeded) + count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded); + if (nr_failed) + count_vm_events(PGMIGRATE_FAIL, nr_failed); if (!swapwrite) current->flags &= ~PF_SWAPWRITE; -- cgit v1.2.3-18-g5258 From 7b2a2d4a18fffac3c4872021529b0657896db788 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 19 Oct 2012 14:07:31 +0100 Subject: mm: migrate: Add a tracepoint for migrate_pages The pgmigrate_success and pgmigrate_fail vmstat counters tells the user about migration activity but not the type or the reason. This patch adds a tracepoint to identify the type of page migration and why the page is being migrated. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel --- mm/migrate.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 04687f69cc1..27be9c923dc 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -38,6 +38,9 @@ #include +#define CREATE_TRACE_POINTS +#include + #include "internal.h" /* @@ -958,7 +961,7 @@ out: */ int migrate_pages(struct list_head *from, new_page_t get_new_page, unsigned long private, bool offlining, - enum migrate_mode mode) + enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; @@ -1004,6 +1007,8 @@ out: count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded); if (nr_failed) count_vm_events(PGMIGRATE_FAIL, nr_failed); + trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason); + if (!swapwrite) current->flags &= ~PF_SWAPWRITE; @@ -1145,7 +1150,8 @@ set_status: err = 0; if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm, 0, MIGRATE_SYNC); + (unsigned long)pm, 0, MIGRATE_SYNC, + MR_SYSCALL); if (err) putback_lru_pages(&pagelist); } -- cgit v1.2.3-18-g5258 From 7039e1dbec6eeaa8ecab43a82d6589eeced995c3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Oct 2012 14:16:34 +0200 Subject: mm: migrate: Introduce migrate_misplaced_page() Note: This was originally based on Peter's patch "mm/migrate: Introduce migrate_misplaced_page()" but borrows extremely heavily from Andrea's "autonuma: memory follows CPU algorithm and task/mm_autonuma stats collection". The end result is barely recognisable so signed-offs had to be dropped. If original authors are ok with it, I'll re-add the signed-off-bys. Add migrate_misplaced_page() which deals with migrating pages from faults. Based-on-work-by: Lee Schermerhorn Based-on-work-by: Peter Zijlstra Based-on-work-by: Andrea Arcangeli Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel --- mm/migrate.c | 108 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 106 insertions(+), 2 deletions(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 27be9c923dc..d168aec9842 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -282,7 +282,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, struct buffer_head *head, enum migrate_mode mode) { - int expected_count; + int expected_count = 0; void **pslot; if (!mapping) { @@ -1415,4 +1415,108 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, } return err; } -#endif + +#ifdef CONFIG_NUMA_BALANCING +/* + * Returns true if this is a safe migration target node for misplaced NUMA + * pages. Currently it only checks the watermarks which crude + */ +static bool migrate_balanced_pgdat(struct pglist_data *pgdat, + int nr_migrate_pages) +{ + int z; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + if (zone->all_unreclaimable) + continue; + + /* Avoid waking kswapd by allocating pages_to_migrate pages. */ + if (!zone_watermark_ok(zone, 0, + high_wmark_pages(zone) + + nr_migrate_pages, + 0, 0)) + continue; + return true; + } + return false; +} + +static struct page *alloc_misplaced_dst_page(struct page *page, + unsigned long data, + int **result) +{ + int nid = (int) data; + struct page *newpage; + + newpage = alloc_pages_exact_node(nid, + (GFP_HIGHUSER_MOVABLE | GFP_THISNODE | + __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN) & + ~GFP_IOFS, 0); + return newpage; +} + +/* + * Attempt to migrate a misplaced page to the specified destination + * node. Caller is expected to have an elevated reference count on + * the page that will be dropped by this function before returning. + */ +int migrate_misplaced_page(struct page *page, int node) +{ + int isolated = 0; + LIST_HEAD(migratepages); + + /* + * Don't migrate pages that are mapped in multiple processes. + * TODO: Handle false sharing detection instead of this hammer + */ + if (page_mapcount(page) != 1) { + put_page(page); + goto out; + } + + /* Avoid migrating to a node that is nearly full */ + if (migrate_balanced_pgdat(NODE_DATA(node), 1)) { + int page_lru; + + if (isolate_lru_page(page)) { + put_page(page); + goto out; + } + isolated = 1; + + /* + * Page is isolated which takes a reference count so now the + * callers reference can be safely dropped without the page + * disappearing underneath us during migration + */ + put_page(page); + + page_lru = page_is_file_cache(page); + inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru); + list_add(&page->lru, &migratepages); + } + + if (isolated) { + int nr_remaining; + + nr_remaining = migrate_pages(&migratepages, + alloc_misplaced_dst_page, + node, false, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); + if (nr_remaining) { + putback_lru_pages(&migratepages); + isolated = 0; + } + } + BUG_ON(!list_empty(&migratepages)); +out: + return isolated; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#endif /* CONFIG_NUMA */ -- cgit v1.2.3-18-g5258 From 149c33e1c98f83050870514f380902dc6d617bd5 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 27 Nov 2012 14:03:05 +0000 Subject: mm: migrate: Drop the misplaced pages reference count if the target node is full If we have to avoid migrating to a node that is nearly full, put page and return zero. Signed-off-by: Hillf Danton Signed-off-by: Mel Gorman --- mm/migrate.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index d168aec9842..c7d550011a6 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1489,18 +1489,21 @@ int migrate_misplaced_page(struct page *page, int node) } isolated = 1; - /* - * Page is isolated which takes a reference count so now the - * callers reference can be safely dropped without the page - * disappearing underneath us during migration - */ - put_page(page); - page_lru = page_is_file_cache(page); inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru); list_add(&page->lru, &migratepages); } + /* + * Page is either isolated or there is not enough space on the target + * node. If isolated, then it has taken a reference count and the + * callers reference can be safely dropped without the page + * disappearing underneath us during migration. Otherwise the page is + * not to be migrated but the callers reference should still be + * dropped so it does not leak. + */ + put_page(page); + if (isolated) { int nr_remaining; -- cgit v1.2.3-18-g5258 From 03c5a6e16322c997bf8f264851bfa3f532ad515f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 2 Nov 2012 14:52:48 +0000 Subject: mm: numa: Add pte updates, hinting and migration stats It is tricky to quantify the basic cost of automatic NUMA placement in a meaningful manner. This patch adds some vmstats that can be used as part of a basic costing model. u = basic unit = sizeof(void *) Ca = cost of struct page access = sizeof(struct page) / u Cpte = Cost PTE access = Ca Cupdate = Cost PTE update = (2 * Cpte) + (2 * Wlock) where Cpte is incurred twice for a read and a write and Wlock is a constant representing the cost of taking or releasing a lock Cnumahint = Cost of a minor page fault = some high constant e.g. 1000 Cpagerw = Cost to read or write a full page = Ca + PAGE_SIZE/u Ci = Cost of page isolation = Ca + Wi where Wi is a constant that should reflect the approximate cost of the locking operation Cpagecopy = Cpagerw + (Cpagerw * Wnuma) + Ci + (Ci * Wnuma) where Wnuma is the approximate NUMA factor. 1 is local. 1.2 would imply that remote accesses are 20% more expensive Balancing cost = Cpte * numa_pte_updates + Cnumahint * numa_hint_faults + Ci * numa_pages_migrated + Cpagecopy * numa_pages_migrated Note that numa_pages_migrated is used as a measure of how many pages were isolated even though it would miss pages that failed to migrate. A vmstat counter could have been added for it but the isolation cost is pretty marginal in comparison to the overall cost so it seemed overkill. The ideal way to measure automatic placement benefit would be to count the number of remote accesses versus local accesses and do something like benefit = (remote_accesses_before - remove_access_after) * Wnuma but the information is not readily available. As a workload converges, the expection would be that the number of remote numa hints would reduce to 0. convergence = numa_hint_faults_local / numa_hint_faults where this is measured for the last N number of numa hints recorded. When the workload is fully converged the value is 1. This can measure if the placement policy is converging and how fast it is doing it. Signed-off-by: Mel Gorman Acked-by: Rik van Riel --- mm/migrate.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index c7d550011a6..23bba5d6edf 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1514,7 +1514,8 @@ int migrate_misplaced_page(struct page *page, int node) if (nr_remaining) { putback_lru_pages(&migratepages); isolated = 0; - } + } else + count_vm_numa_event(NUMA_PAGE_MIGRATE); } BUG_ON(!list_empty(&migratepages)); out: -- cgit v1.2.3-18-g5258 From a8f6077213d285ca08dbf6d4a67470787388138b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 14 Nov 2012 21:41:46 +0000 Subject: mm: numa: Rate limit the amount of memory that is migrated between nodes NOTE: This is very heavily based on similar logic in autonuma. It should be signed off by Andrea but because there was no standalone patch and it's sufficiently different from what he did that the signed-off is omitted. Will be added back if requested. If a large number of pages are misplaced then the memory bus can be saturated just migrating pages between nodes. This patch rate-limits the amount of memory that can be migrating between nodes. Signed-off-by: Mel Gorman --- mm/migrate.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 23bba5d6edf..4b8267f1842 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1460,6 +1460,14 @@ static struct page *alloc_misplaced_dst_page(struct page *page, return newpage; } +/* + * page migration rate limiting control. + * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs + * window of time. Default here says do not migrate more than 1280M per second. + */ +static unsigned int migrate_interval_millisecs __read_mostly = 100; +static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); + /* * Attempt to migrate a misplaced page to the specified destination * node. Caller is expected to have an elevated reference count on @@ -1467,6 +1475,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, */ int migrate_misplaced_page(struct page *page, int node) { + pg_data_t *pgdat = NODE_DATA(node); int isolated = 0; LIST_HEAD(migratepages); @@ -1479,8 +1488,27 @@ int migrate_misplaced_page(struct page *page, int node) goto out; } + /* + * Rate-limit the amount of data that is being migrated to a node. + * Optimal placement is no good if the memory bus is saturated and + * all the time is being spent migrating! + */ + spin_lock(&pgdat->numabalancing_migrate_lock); + if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) { + pgdat->numabalancing_migrate_nr_pages = 0; + pgdat->numabalancing_migrate_next_window = jiffies + + msecs_to_jiffies(migrate_interval_millisecs); + } + if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { + spin_unlock(&pgdat->numabalancing_migrate_lock); + put_page(page); + goto out; + } + pgdat->numabalancing_migrate_nr_pages++; + spin_unlock(&pgdat->numabalancing_migrate_lock); + /* Avoid migrating to a node that is nearly full */ - if (migrate_balanced_pgdat(NODE_DATA(node), 1)) { + if (migrate_balanced_pgdat(pgdat, 1)) { int page_lru; if (isolate_lru_page(page)) { -- cgit v1.2.3-18-g5258 From e14808b49f55e0e1135da5e4a154a540dd9f3662 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 19 Nov 2012 10:59:15 +0000 Subject: mm: numa: Rate limit setting of pte_numa if node is saturated If there are a large number of NUMA hinting faults and all of them are resulting in migrations it may indicate that memory is just bouncing uselessly around. NUMA balancing cost is likely exceeding any benefit from locality. Rate limit the PTE updates if the node is migration rate-limited. As noted in the comments, this distorts the NUMA faulting statistics. Signed-off-by: Mel Gorman --- mm/migrate.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 4b8267f1842..32a1afca600 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1464,10 +1464,30 @@ static struct page *alloc_misplaced_dst_page(struct page *page, * page migration rate limiting control. * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs * window of time. Default here says do not migrate more than 1280M per second. + * If a node is rate-limited then PTE NUMA updates are also rate-limited. However + * as it is faults that reset the window, pte updates will happen unconditionally + * if there has not been a fault since @pteupdate_interval_millisecs after the + * throttle window closed. */ static unsigned int migrate_interval_millisecs __read_mostly = 100; +static unsigned int pteupdate_interval_millisecs __read_mostly = 1000; static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); +/* Returns true if NUMA migration is currently rate limited */ +bool migrate_ratelimited(int node) +{ + pg_data_t *pgdat = NODE_DATA(node); + + if (time_after(jiffies, pgdat->numabalancing_migrate_next_window + + msecs_to_jiffies(pteupdate_interval_millisecs))) + return false; + + if (pgdat->numabalancing_migrate_nr_pages < ratelimit_pages) + return false; + + return true; +} + /* * Attempt to migrate a misplaced page to the specified destination * node. Caller is expected to have an elevated reference count on -- cgit v1.2.3-18-g5258 From bac0382c6ad764156025978845147e5a6eccca09 Mon Sep 17 00:00:00 2001 From: Hillf Danton Date: Tue, 27 Nov 2012 14:46:24 +0000 Subject: mm: numa: migrate: Set last_nid on newly allocated page Pass last_nid from misplaced page to newly allocated migration target page. Signed-off-by: Hillf Danton Signed-off-by: Mel Gorman --- mm/migrate.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 32a1afca600..2a5ce135eef 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1457,6 +1457,9 @@ static struct page *alloc_misplaced_dst_page(struct page *page, __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & ~GFP_IOFS, 0); + if (newpage) + page_xchg_last_nid(newpage, page_last_nid(page)); + return newpage; } -- cgit v1.2.3-18-g5258 From b32967ff101a7508f70be8de59b278d4df92fa00 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 19 Nov 2012 12:35:47 +0000 Subject: mm: numa: Add THP migration for the NUMA working set scanning fault case. Note: This is very heavily based on a patch from Peter Zijlstra with fixes from Ingo Molnar, Hugh Dickins and Johannes Weiner. That patch put a lot of migration logic into mm/huge_memory.c where it does not belong. This version puts tries to share some of the migration logic with migrate_misplaced_page. However, it should be noted that now migrate.c is doing more with the pagetable manipulation than is preferred. The end result is barely recognisable so as before, the signed-offs had to be removed but will be re-added if the original authors are ok with it. Add THP migration for the NUMA working set scanning fault case. It uses the page lock to serialize. No migration pte dance is necessary because the pte is already unmapped when we decide to migrate. [dhillf@gmail.com: Fix memory leak on isolation failure] [dhillf@gmail.com: Fix transfer of last_nid information] Signed-off-by: Mel Gorman --- mm/migrate.c | 231 ++++++++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 190 insertions(+), 41 deletions(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 2a5ce135eef..c9400960fd5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -410,7 +410,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, */ void migrate_page_copy(struct page *newpage, struct page *page) { - if (PageHuge(page)) + if (PageHuge(page) || PageTransHuge(page)) copy_huge_page(newpage, page); else copy_highpage(newpage, page); @@ -1491,25 +1491,10 @@ bool migrate_ratelimited(int node) return true; } -/* - * Attempt to migrate a misplaced page to the specified destination - * node. Caller is expected to have an elevated reference count on - * the page that will be dropped by this function before returning. - */ -int migrate_misplaced_page(struct page *page, int node) +/* Returns true if the node is migrate rate-limited after the update */ +bool numamigrate_update_ratelimit(pg_data_t *pgdat) { - pg_data_t *pgdat = NODE_DATA(node); - int isolated = 0; - LIST_HEAD(migratepages); - - /* - * Don't migrate pages that are mapped in multiple processes. - * TODO: Handle false sharing detection instead of this hammer - */ - if (page_mapcount(page) != 1) { - put_page(page); - goto out; - } + bool rate_limited = false; /* * Rate-limit the amount of data that is being migrated to a node. @@ -1522,13 +1507,18 @@ int migrate_misplaced_page(struct page *page, int node) pgdat->numabalancing_migrate_next_window = jiffies + msecs_to_jiffies(migrate_interval_millisecs); } - if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { - spin_unlock(&pgdat->numabalancing_migrate_lock); - put_page(page); - goto out; - } - pgdat->numabalancing_migrate_nr_pages++; + if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) + rate_limited = true; + else + pgdat->numabalancing_migrate_nr_pages++; spin_unlock(&pgdat->numabalancing_migrate_lock); + + return rate_limited; +} + +int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) +{ + int ret = 0; /* Avoid migrating to a node that is nearly full */ if (migrate_balanced_pgdat(pgdat, 1)) { @@ -1536,13 +1526,18 @@ int migrate_misplaced_page(struct page *page, int node) if (isolate_lru_page(page)) { put_page(page); - goto out; + return 0; } - isolated = 1; + /* Page is isolated */ + ret = 1; page_lru = page_is_file_cache(page); - inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru); - list_add(&page->lru, &migratepages); + if (!PageTransHuge(page)) + inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru); + else + mod_zone_page_state(page_zone(page), + NR_ISOLATED_ANON + page_lru, + HPAGE_PMD_NR); } /* @@ -1555,23 +1550,177 @@ int migrate_misplaced_page(struct page *page, int node) */ put_page(page); - if (isolated) { - int nr_remaining; - - nr_remaining = migrate_pages(&migratepages, - alloc_misplaced_dst_page, - node, false, MIGRATE_ASYNC, - MR_NUMA_MISPLACED); - if (nr_remaining) { - putback_lru_pages(&migratepages); - isolated = 0; - } else - count_vm_numa_event(NUMA_PAGE_MIGRATE); + return ret; +} + +/* + * Attempt to migrate a misplaced page to the specified destination + * node. Caller is expected to have an elevated reference count on + * the page that will be dropped by this function before returning. + */ +int migrate_misplaced_page(struct page *page, int node) +{ + pg_data_t *pgdat = NODE_DATA(node); + int isolated = 0; + int nr_remaining; + LIST_HEAD(migratepages); + + /* + * Don't migrate pages that are mapped in multiple processes. + * TODO: Handle false sharing detection instead of this hammer + */ + if (page_mapcount(page) != 1) { + put_page(page); + goto out; } + + /* + * Rate-limit the amount of data that is being migrated to a node. + * Optimal placement is no good if the memory bus is saturated and + * all the time is being spent migrating! + */ + if (numamigrate_update_ratelimit(pgdat)) { + put_page(page); + goto out; + } + + isolated = numamigrate_isolate_page(pgdat, page); + if (!isolated) + goto out; + + list_add(&page->lru, &migratepages); + nr_remaining = migrate_pages(&migratepages, + alloc_misplaced_dst_page, + node, false, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); + if (nr_remaining) { + putback_lru_pages(&migratepages); + isolated = 0; + } else + count_vm_numa_event(NUMA_PAGE_MIGRATE); BUG_ON(!list_empty(&migratepages)); out: return isolated; } + +int migrate_misplaced_transhuge_page(struct mm_struct *mm, + struct vm_area_struct *vma, + pmd_t *pmd, pmd_t entry, + unsigned long address, + struct page *page, int node) +{ + unsigned long haddr = address & HPAGE_PMD_MASK; + pg_data_t *pgdat = NODE_DATA(node); + int isolated = 0; + struct page *new_page = NULL; + struct mem_cgroup *memcg = NULL; + int page_lru = page_is_file_cache(page); + + /* + * Don't migrate pages that are mapped in multiple processes. + * TODO: Handle false sharing detection instead of this hammer + */ + if (page_mapcount(page) != 1) + goto out_dropref; + + /* + * Rate-limit the amount of data that is being migrated to a node. + * Optimal placement is no good if the memory bus is saturated and + * all the time is being spent migrating! + */ + if (numamigrate_update_ratelimit(pgdat)) + goto out_dropref; + + new_page = alloc_pages_node(node, + (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER); + if (!new_page) + goto out_dropref; + page_xchg_last_nid(new_page, page_last_nid(page)); + + isolated = numamigrate_isolate_page(pgdat, page); + if (!isolated) { + put_page(new_page); + goto out_keep_locked; + } + + /* Prepare a page as a migration target */ + __set_page_locked(new_page); + SetPageSwapBacked(new_page); + + /* anon mapping, we can simply copy page->mapping to the new page: */ + new_page->mapping = page->mapping; + new_page->index = page->index; + migrate_page_copy(new_page, page); + WARN_ON(PageLRU(new_page)); + + /* Recheck the target PMD */ + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_same(*pmd, entry))) { + spin_unlock(&mm->page_table_lock); + + /* Reverse changes made by migrate_page_copy() */ + if (TestClearPageActive(new_page)) + SetPageActive(page); + if (TestClearPageUnevictable(new_page)) + SetPageUnevictable(page); + mlock_migrate_page(page, new_page); + + unlock_page(new_page); + put_page(new_page); /* Free it */ + + unlock_page(page); + putback_lru_page(page); + + count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); + goto out; + } + + /* + * Traditional migration needs to prepare the memcg charge + * transaction early to prevent the old page from being + * uncharged when installing migration entries. Here we can + * save the potential rollback and start the charge transfer + * only when migration is already known to end successfully. + */ + mem_cgroup_prepare_migration(page, new_page, &memcg); + + entry = mk_pmd(new_page, vma->vm_page_prot); + entry = pmd_mknonnuma(entry); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + entry = pmd_mkhuge(entry); + + page_add_new_anon_rmap(new_page, vma, haddr); + + set_pmd_at(mm, haddr, pmd, entry); + update_mmu_cache_pmd(vma, address, entry); + page_remove_rmap(page); + /* + * Finish the charge transaction under the page table lock to + * prevent split_huge_page() from dividing up the charge + * before it's fully transferred to the new page. + */ + mem_cgroup_end_migration(memcg, page, new_page, true); + spin_unlock(&mm->page_table_lock); + + unlock_page(new_page); + unlock_page(page); + put_page(page); /* Drop the rmap reference */ + put_page(page); /* Drop the LRU isolation reference */ + + count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); + count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); + +out: + mod_zone_page_state(page_zone(page), + NR_ISOLATED_ANON + page_lru, + -HPAGE_PMD_NR); + return isolated; + +out_dropref: + put_page(page); +out_keep_locked: + return 0; +} #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_NUMA */ -- cgit v1.2.3-18-g5258 From 220018d388b8ab1fca1c5f0c6474bab47ad2c9c0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 5 Dec 2012 09:32:56 +0000 Subject: mm: numa: Add THP migration for the NUMA working set scanning fault case build fix Commit "Add THP migration for the NUMA working set scanning fault case" breaks the build because HPAGE_PMD_SHIFT and HPAGE_PMD_MASK defined to explode without CONFIG_TRANSPARENT_HUGEPAGE: mm/migrate.c: In function 'migrate_misplaced_transhuge_page_put': mm/migrate.c:1549: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed mm/migrate.c:1564: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed mm/migrate.c:1566: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed mm/migrate.c:1573: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed mm/migrate.c:1606: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed mm/migrate.c:1648: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed CONFIG_NUMA_BALANCING allows compilation without enabling transparent hugepages, so define the dummy function for such a configuration and only define migrate_misplaced_transhuge_page_put() when transparent hugepages are enabled. Signed-off-by: David Rientjes Signed-off-by: Mel Gorman --- mm/migrate.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index c9400960fd5..9341a501d16 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1602,7 +1602,9 @@ int migrate_misplaced_page(struct page *page, int node) out: return isolated; } +#endif /* CONFIG_NUMA_BALANCING */ +#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) int migrate_misplaced_transhuge_page(struct mm_struct *mm, struct vm_area_struct *vma, pmd_t *pmd, pmd_t entry, -- cgit v1.2.3-18-g5258 From 7548341b28956ccd35a63ab12f01d8541041aa70 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 27 Nov 2012 10:31:44 +0000 Subject: mm: numa: Account for failed allocations and isolations as migration failures Subject says it all. Allocation failures and a failure to isolate should be accounted as a migration failure. This is partially another difference between base page and transhuge page migration. A base page migration makes multiple attempts for these conditions before it would be accounted for as a failure. Signed-off-by: Mel Gorman --- mm/migrate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 9341a501d16..26537c4f309 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1635,12 +1635,15 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, new_page = alloc_pages_node(node, (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER); - if (!new_page) + if (!new_page) { + count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); goto out_dropref; + } page_xchg_last_nid(new_page, page_last_nid(page)); isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) { + count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); put_page(new_page); goto out_keep_locked; } -- cgit v1.2.3-18-g5258 From d28d433512f4f387e2563c14db45a7bb8a338b1a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 29 Nov 2012 09:24:36 +0000 Subject: mm: migrate: Account a transhuge page properly when rate limiting If there is excessive migration due to NUMA balancing it gets rate limited. It does this by counting the number of pages it has migrated recently but counts a transhuge page as 1 page. Account for it properly. Signed-off-by: Mel Gorman --- mm/migrate.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index 26537c4f309..f24e9cc49cc 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1492,7 +1492,7 @@ bool migrate_ratelimited(int node) } /* Returns true if the node is migrate rate-limited after the update */ -bool numamigrate_update_ratelimit(pg_data_t *pgdat) +bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages) { bool rate_limited = false; @@ -1510,7 +1510,7 @@ bool numamigrate_update_ratelimit(pg_data_t *pgdat) if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) rate_limited = true; else - pgdat->numabalancing_migrate_nr_pages++; + pgdat->numabalancing_migrate_nr_pages += nr_pages; spin_unlock(&pgdat->numabalancing_migrate_lock); return rate_limited; @@ -1579,7 +1579,7 @@ int migrate_misplaced_page(struct page *page, int node) * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - if (numamigrate_update_ratelimit(pgdat)) { + if (numamigrate_update_ratelimit(pgdat, 1)) { put_page(page); goto out; } @@ -1630,7 +1630,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - if (numamigrate_update_ratelimit(pgdat)) + if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR)) goto out_dropref; new_page = alloc_pages_node(node, -- cgit v1.2.3-18-g5258 From 4fc3f1d66b1ef0d7b8dc11f4ff1cc510f78b37d6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 2 Dec 2012 19:56:50 +0000 Subject: mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable rmap_walk_anon() and try_to_unmap_anon() appears to be too careful about locking the anon vma: while it needs protection against anon vma list modifications, it does not need exclusive access to the list itself. Transforming this exclusive lock to a read-locked rwsem removes a global lock from the hot path of page-migration intense threaded workloads which can cause pathological performance like this: 96.43% process 0 [kernel.kallsyms] [k] perf_trace_sched_switch | --- perf_trace_sched_switch __schedule schedule schedule_preempt_disabled __mutex_lock_common.isra.6 __mutex_lock_slowpath mutex_lock | |--50.61%-- rmap_walk | move_to_new_page | migrate_pages | migrate_misplaced_page | __do_numa_page.isra.69 | handle_pte_fault | handle_mm_fault | __do_page_fault | do_page_fault | page_fault | __memset_sse2 | | | --100.00%-- worker_thread | | | --100.00%-- start_thread | --49.39%-- page_lock_anon_vma try_to_unmap_anon try_to_unmap migrate_pages migrate_misplaced_page __do_numa_page.isra.69 handle_pte_fault handle_mm_fault __do_page_fault do_page_fault page_fault __memset_sse2 | --100.00%-- worker_thread start_thread With this change applied the profile is now nicely flat and there's no anon-vma related scheduling/blocking. Rename anon_vma_[un]lock() => anon_vma_[un]lock_write(), to make it clearer that it's an exclusive write-lock in that case - suggested by Rik van Riel. Suggested-by: Linus Torvalds Cc: Peter Zijlstra Cc: Paul Turner Cc: Lee Schermerhorn Cc: Christoph Lameter Cc: Rik van Riel Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Hugh Dickins Signed-off-by: Ingo Molnar Signed-off-by: Mel Gorman --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/migrate.c') diff --git a/mm/migrate.c b/mm/migrate.c index f24e9cc49cc..6e46485f014 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -754,7 +754,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, */ if (PageAnon(page)) { /* - * Only page_lock_anon_vma() understands the subtleties of + * Only page_lock_anon_vma_read() understands the subtleties of * getting a hold on an anon_vma from outside one of its mms. */ anon_vma = page_get_anon_vma(page); -- cgit v1.2.3-18-g5258