All of lore.kernel.org
 help / color / mirror / Atom feed
diff for duplicates of <20140613024005.GA8704@gmail.com>

diff --git a/a/1.txt b/N1/1.txt
index 9da47d0..2beec12 100644
--- a/a/1.txt
+++ b/N1/1.txt
@@ -93,3 +93,276 @@ It's good to me.
 
 Another topic: I couldn't find any cond_resched. Anyway, it could be
 another patch.
+
+>From a4b7c288d8de670adbc45c85991ed3bef31e4e16 Mon Sep 17 00:00:00 2001
+From: Minchan Kim <minchan@kernel.org>
+Date: Fri, 13 Jun 2014 10:59:26 +0900
+Subject: [PATCH] mm: call cond_resched right before failing compaction
+
+David reported in many case of direct compaction for THP page fault
+is failed since the async compaction was abort by need_resched.
+It's okay because THP could be fallback to 4K page but the problem
+is if need_resched is true, we should give a chance to next process
+to schedul in for the latency so that we are not greedy any more.
+
+Signed-off-by: Minchan Kim <minchan@kernel.org>
+---
+ mm/page_alloc.c | 10 +++++++++-
+ 1 file changed, 9 insertions(+), 1 deletion(-)
+
+diff --git a/mm/page_alloc.c b/mm/page_alloc.c
+index 4f59fa2..1ac5133 100644
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -2617,8 +2617,16 @@ rebalance:
+ 	 * system then fail the allocation instead of entering direct reclaim.
+ 	 */
+ 	if ((deferred_compaction || contended_compaction) &&
+-						(gfp_mask & __GFP_NO_KSWAPD))
++						(gfp_mask & __GFP_NO_KSWAPD)) {
++		/*
++		 * When THP page fault occurs in large memory system,
++		 * contended_compaction is likely to be true by need_resched
++		 * checking so let's schedule right before returning NULL page.
++		 * That makes I'm not greedy!
++		 */
++		cond_resched();
+ 		goto nopage;
++	}
+ 
+ 	/* Try direct reclaim and then allocating */
+ 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
+-- 
+2.0.0
+
+With your change(ie, direct compaction is only aware of lock contetion,
+not need_resched), when THP page fault occurs and it found rescheduling
+while doing async direct compaction, it goes *direct reclaim path*,
+not "nopage" and async direct compaction again and then finally nopage.
+I think you are changing the behavior heavily to increase latency,
+which is not what direct reclaim path want even though I have no data.
+
+So, what I want is following as.
+It is based on previoius inline patch.
+
+---
+ mm/page_alloc.c | 13 +++++++++++--
+ 1 file changed, 11 insertions(+), 2 deletions(-)
+
+diff --git a/mm/page_alloc.c b/mm/page_alloc.c
+index 1ac5133..8a4480e5 100644
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -2624,8 +2624,17 @@ rebalance:
+ 		 * checking so let's schedule right before returning NULL page.
+ 		 * That makes I'm not greedy!
+ 		 */
+-		cond_resched();
+-		goto nopage;
++		int ret = cond_resched();
++
++		/* When THP page fault, we want to bail out for the latency */
++		if (!(current->flags & PF_KTHREAD) || !ret)
++			goto nopage;
++
++		/*
++		 * I'm khugepaged and took a rest so want to try compaction
++		 * with synchronous rather than giving up easily.
++		 */
++		WARN_ON(migration_mode == MIGRATE_ASYNC);
+ 	}
+ 
+ 	/* Try direct reclaim and then allocating */
+-- 
+2.0.0
+
+I'm off from now on. :)
+
+> 
+> >I don't mean we should abort but the process could sleep and retry.
+> >The point is that we should give latency pain to the process request
+> >high-order alocation, not another random process.
+> 
+> So basically you are saying that there should be cond_resched() also
+> for async compaction when need_resched() is true? Now need_resched()
+> is a trigger to back off rather quickly all the way back to
+> __alloc_pages_direct_compact() which does contain a cond_resched().
+> So there should be a yield before retry. Or are you worried that the
+> back off is not quick enough and it shoudl cond_resched()
+> immediately?
+> 
+> >IMHO, if we want to increase high-order alloc ratio in page fault,
+> >kswapd should be more aggressive than now via feedback loop from
+> >fail rate from direct compaction.
+> 
+> Recently I think we have been rather decreasing high-order alloc
+> ratio in page fault :) But (at least for the THP) page fault
+> allocation attempts contain __GFP_NO_KSWAPD, so there's no feedback
+> loop. I guess changing that would be rather disruptive.
+> 
+> >>
+> >>>We have taken care of it in direct reclaim path so why direct compaction is
+> >>>so special?
+> >>
+> >>I admit I'm not that familiar with reclaim but I didn't quickly find
+> >>any need_resched() there? There's plenty of cond_resched() but that
+> >>doesn't mean it will abort? Could you explain for me?
+> >
+> >I meant cond_resched.
+> >
+> >>
+> >>>Why does khugepaged give up easily if lock contention/need_resched happens?
+> >>>khugepaged is important for success ratio as I read your description so IMO,
+> >>>khugepaged should do synchronously without considering early bail out by
+> >>>lock/rescheduling.
+> >>
+> >>Well a stupid answer is that's how __alloc_pages_slowpath() works :)
+> >>I don't think it's bad to try using first a more lightweight
+> >>approach before trying the heavyweight one. As long as the
+> >>heavyweight one is not skipped for khugepaged.
+> >
+> >I'm not saying current two-stage trying is bad. My stand is that we should
+> >take care of need_resched and shouldn't become a greedy but khugepaged would
+> >be okay.
+> >
+> >>
+> >>>If it causes problems, user should increase scan_sleep_millisecs/alloc_sleep_millisecs,
+> >>>which is exactly the knob for that cases.
+> >>>
+> >>>So, my point is how about making khugepaged doing always dumb synchronous
+> >>>compaction thorough PG_KHUGEPAGED or GFP_SYNC_TRANSHUGE?
+> >>>
+> >>>>
+> >>>>Reported-by: David Rientjes <rientjes@google.com>
+> >>>>Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
+> >>>>Cc: Minchan Kim <minchan@kernel.org>
+> >>>>Cc: Mel Gorman <mgorman@suse.de>
+> >>>>Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
+> >>>>Cc: Michal Nazarewicz <mina86@mina86.com>
+> >>>>Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+> >>>>Cc: Christoph Lameter <cl@linux.com>
+> >>>>Cc: Rik van Riel <riel@redhat.com>
+> >>>>---
+> >>>>  mm/compaction.c | 20 ++++++++++++++------
+> >>>>  mm/internal.h   | 15 +++++++++++----
+> >>>>  2 files changed, 25 insertions(+), 10 deletions(-)
+> >>>>
+> >>>>diff --git a/mm/compaction.c b/mm/compaction.c
+> >>>>index b73b182..d37f4a8 100644
+> >>>>--- a/mm/compaction.c
+> >>>>+++ b/mm/compaction.c
+> >>>>@@ -185,9 +185,14 @@ static void update_pageblock_skip(struct compact_control *cc,
+> >>>>  }
+> >>>>  #endif /* CONFIG_COMPACTION */
+> >>>>
+> >>>>-static inline bool should_release_lock(spinlock_t *lock)
+> >>>>+enum compact_contended should_release_lock(spinlock_t *lock)
+> >>>>  {
+> >>>>-	return need_resched() || spin_is_contended(lock);
+> >>>>+	if (need_resched())
+> >>>>+		return COMPACT_CONTENDED_SCHED;
+> >>>>+	else if (spin_is_contended(lock))
+> >>>>+		return COMPACT_CONTENDED_LOCK;
+> >>>>+	else
+> >>>>+		return COMPACT_CONTENDED_NONE;
+> >>>>  }
+> >>>>
+> >>>>  /*
+> >>>>@@ -202,7 +207,9 @@ static inline bool should_release_lock(spinlock_t *lock)
+> >>>>  static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
+> >>>>  				      bool locked, struct compact_control *cc)
+> >>>>  {
+> >>>>-	if (should_release_lock(lock)) {
+> >>>>+	enum compact_contended contended = should_release_lock(lock);
+> >>>>+
+> >>>>+	if (contended) {
+> >>>>  		if (locked) {
+> >>>>  			spin_unlock_irqrestore(lock, *flags);
+> >>>>  			locked = false;
+> >>>>@@ -210,7 +217,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
+> >>>>
+> >>>>  		/* async aborts if taking too long or contended */
+> >>>>  		if (cc->mode == MIGRATE_ASYNC) {
+> >>>>-			cc->contended = true;
+> >>>>+			cc->contended = contended;
+> >>>>  			return false;
+> >>>>  		}
+> >>>>
+> >>>>@@ -236,7 +243,7 @@ static inline bool compact_should_abort(struct compact_control *cc)
+> >>>>  	/* async compaction aborts if contended */
+> >>>>  	if (need_resched()) {
+> >>>>  		if (cc->mode == MIGRATE_ASYNC) {
+> >>>>-			cc->contended = true;
+> >>>>+			cc->contended = COMPACT_CONTENDED_SCHED;
+> >>>>  			return true;
+> >>>>  		}
+> >>>>
+> >>>>@@ -1095,7 +1102,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
+> >>>>  	VM_BUG_ON(!list_empty(&cc.freepages));
+> >>>>  	VM_BUG_ON(!list_empty(&cc.migratepages));
+> >>>>
+> >>>>-	*contended = cc.contended;
+> >>>>+	/* We only signal lock contention back to the allocator */
+> >>>>+	*contended = cc.contended == COMPACT_CONTENDED_LOCK;
+> >>>>  	return ret;
+> >>>>  }
+> >>>>
+> >>>>diff --git a/mm/internal.h b/mm/internal.h
+> >>>>index 7f22a11f..4659e8e 100644
+> >>>>--- a/mm/internal.h
+> >>>>+++ b/mm/internal.h
+> >>>>@@ -117,6 +117,13 @@ extern int user_min_free_kbytes;
+> >>>>
+> >>>>  #if defined CONFIG_COMPACTION || defined CONFIG_CMA
+> >>>>
+> >>>>+/* Used to signal whether compaction detected need_sched() or lock contention */
+> >>>>+enum compact_contended {
+> >>>>+	COMPACT_CONTENDED_NONE = 0, /* no contention detected */
+> >>>>+	COMPACT_CONTENDED_SCHED,    /* need_sched() was true */
+> >>>>+	COMPACT_CONTENDED_LOCK,     /* zone lock or lru_lock was contended */
+> >>>>+};
+> >>>>+
+> >>>>  /*
+> >>>>   * in mm/compaction.c
+> >>>>   */
+> >>>>@@ -144,10 +151,10 @@ struct compact_control {
+> >>>>  	int order;			/* order a direct compactor needs */
+> >>>>  	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
+> >>>>  	struct zone *zone;
+> >>>>-	bool contended;			/* True if a lock was contended, or
+> >>>>-					 * need_resched() true during async
+> >>>>-					 * compaction
+> >>>>-					 */
+> >>>>+	enum compact_contended contended; /* Signal need_sched() or lock
+> >>>>+					   * contention detected during
+> >>>>+					   * compaction
+> >>>>+					   */
+> >>>>  };
+> >>>>
+> >>>>  unsigned long
+> >>>>--
+> >>>>1.8.4.5
+> >>>>
+> >>>>--
+> >>>>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>
+> >>>
+> >>
+> >>--
+> >>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>
+> >
+> 
+> --
+> 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>
+
+-- 
+Kind regards,
+Minchan Kim
diff --git a/a/content_digest b/N1/content_digest
index a853ba5..a8928e1 100644
--- a/a/content_digest
+++ b/N1/content_digest
@@ -115,6 +115,279 @@
  "It's good to me.\n"
  "\n"
  "Another topic: I couldn't find any cond_resched. Anyway, it could be\n"
- another patch.
+ "another patch.\n"
+ "\n"
+ ">From a4b7c288d8de670adbc45c85991ed3bef31e4e16 Mon Sep 17 00:00:00 2001\n"
+ "From: Minchan Kim <minchan@kernel.org>\n"
+ "Date: Fri, 13 Jun 2014 10:59:26 +0900\n"
+ "Subject: [PATCH] mm: call cond_resched right before failing compaction\n"
+ "\n"
+ "David reported in many case of direct compaction for THP page fault\n"
+ "is failed since the async compaction was abort by need_resched.\n"
+ "It's okay because THP could be fallback to 4K page but the problem\n"
+ "is if need_resched is true, we should give a chance to next process\n"
+ "to schedul in for the latency so that we are not greedy any more.\n"
+ "\n"
+ "Signed-off-by: Minchan Kim <minchan@kernel.org>\n"
+ "---\n"
+ " mm/page_alloc.c | 10 +++++++++-\n"
+ " 1 file changed, 9 insertions(+), 1 deletion(-)\n"
+ "\n"
+ "diff --git a/mm/page_alloc.c b/mm/page_alloc.c\n"
+ "index 4f59fa2..1ac5133 100644\n"
+ "--- a/mm/page_alloc.c\n"
+ "+++ b/mm/page_alloc.c\n"
+ "@@ -2617,8 +2617,16 @@ rebalance:\n"
+ " \t * system then fail the allocation instead of entering direct reclaim.\n"
+ " \t */\n"
+ " \tif ((deferred_compaction || contended_compaction) &&\n"
+ "-\t\t\t\t\t\t(gfp_mask & __GFP_NO_KSWAPD))\n"
+ "+\t\t\t\t\t\t(gfp_mask & __GFP_NO_KSWAPD)) {\n"
+ "+\t\t/*\n"
+ "+\t\t * When THP page fault occurs in large memory system,\n"
+ "+\t\t * contended_compaction is likely to be true by need_resched\n"
+ "+\t\t * checking so let's schedule right before returning NULL page.\n"
+ "+\t\t * That makes I'm not greedy!\n"
+ "+\t\t */\n"
+ "+\t\tcond_resched();\n"
+ " \t\tgoto nopage;\n"
+ "+\t}\n"
+ " \n"
+ " \t/* Try direct reclaim and then allocating */\n"
+ " \tpage = __alloc_pages_direct_reclaim(gfp_mask, order,\n"
+ "-- \n"
+ "2.0.0\n"
+ "\n"
+ "With your change(ie, direct compaction is only aware of lock contetion,\n"
+ "not need_resched), when THP page fault occurs and it found rescheduling\n"
+ "while doing async direct compaction, it goes *direct reclaim path*,\n"
+ "not \"nopage\" and async direct compaction again and then finally nopage.\n"
+ "I think you are changing the behavior heavily to increase latency,\n"
+ "which is not what direct reclaim path want even though I have no data.\n"
+ "\n"
+ "So, what I want is following as.\n"
+ "It is based on previoius inline patch.\n"
+ "\n"
+ "---\n"
+ " mm/page_alloc.c | 13 +++++++++++--\n"
+ " 1 file changed, 11 insertions(+), 2 deletions(-)\n"
+ "\n"
+ "diff --git a/mm/page_alloc.c b/mm/page_alloc.c\n"
+ "index 1ac5133..8a4480e5 100644\n"
+ "--- a/mm/page_alloc.c\n"
+ "+++ b/mm/page_alloc.c\n"
+ "@@ -2624,8 +2624,17 @@ rebalance:\n"
+ " \t\t * checking so let's schedule right before returning NULL page.\n"
+ " \t\t * That makes I'm not greedy!\n"
+ " \t\t */\n"
+ "-\t\tcond_resched();\n"
+ "-\t\tgoto nopage;\n"
+ "+\t\tint ret = cond_resched();\n"
+ "+\n"
+ "+\t\t/* When THP page fault, we want to bail out for the latency */\n"
+ "+\t\tif (!(current->flags & PF_KTHREAD) || !ret)\n"
+ "+\t\t\tgoto nopage;\n"
+ "+\n"
+ "+\t\t/*\n"
+ "+\t\t * I'm khugepaged and took a rest so want to try compaction\n"
+ "+\t\t * with synchronous rather than giving up easily.\n"
+ "+\t\t */\n"
+ "+\t\tWARN_ON(migration_mode == MIGRATE_ASYNC);\n"
+ " \t}\n"
+ " \n"
+ " \t/* Try direct reclaim and then allocating */\n"
+ "-- \n"
+ "2.0.0\n"
+ "\n"
+ "I'm off from now on. :)\n"
+ "\n"
+ "> \n"
+ "> >I don't mean we should abort but the process could sleep and retry.\n"
+ "> >The point is that we should give latency pain to the process request\n"
+ "> >high-order alocation, not another random process.\n"
+ "> \n"
+ "> So basically you are saying that there should be cond_resched() also\n"
+ "> for async compaction when need_resched() is true? Now need_resched()\n"
+ "> is a trigger to back off rather quickly all the way back to\n"
+ "> __alloc_pages_direct_compact() which does contain a cond_resched().\n"
+ "> So there should be a yield before retry. Or are you worried that the\n"
+ "> back off is not quick enough and it shoudl cond_resched()\n"
+ "> immediately?\n"
+ "> \n"
+ "> >IMHO, if we want to increase high-order alloc ratio in page fault,\n"
+ "> >kswapd should be more aggressive than now via feedback loop from\n"
+ "> >fail rate from direct compaction.\n"
+ "> \n"
+ "> Recently I think we have been rather decreasing high-order alloc\n"
+ "> ratio in page fault :) But (at least for the THP) page fault\n"
+ "> allocation attempts contain __GFP_NO_KSWAPD, so there's no feedback\n"
+ "> loop. I guess changing that would be rather disruptive.\n"
+ "> \n"
+ "> >>\n"
+ "> >>>We have taken care of it in direct reclaim path so why direct compaction is\n"
+ "> >>>so special?\n"
+ "> >>\n"
+ "> >>I admit I'm not that familiar with reclaim but I didn't quickly find\n"
+ "> >>any need_resched() there? There's plenty of cond_resched() but that\n"
+ "> >>doesn't mean it will abort? Could you explain for me?\n"
+ "> >\n"
+ "> >I meant cond_resched.\n"
+ "> >\n"
+ "> >>\n"
+ "> >>>Why does khugepaged give up easily if lock contention/need_resched happens?\n"
+ "> >>>khugepaged is important for success ratio as I read your description so IMO,\n"
+ "> >>>khugepaged should do synchronously without considering early bail out by\n"
+ "> >>>lock/rescheduling.\n"
+ "> >>\n"
+ "> >>Well a stupid answer is that's how __alloc_pages_slowpath() works :)\n"
+ "> >>I don't think it's bad to try using first a more lightweight\n"
+ "> >>approach before trying the heavyweight one. As long as the\n"
+ "> >>heavyweight one is not skipped for khugepaged.\n"
+ "> >\n"
+ "> >I'm not saying current two-stage trying is bad. My stand is that we should\n"
+ "> >take care of need_resched and shouldn't become a greedy but khugepaged would\n"
+ "> >be okay.\n"
+ "> >\n"
+ "> >>\n"
+ "> >>>If it causes problems, user should increase scan_sleep_millisecs/alloc_sleep_millisecs,\n"
+ "> >>>which is exactly the knob for that cases.\n"
+ "> >>>\n"
+ "> >>>So, my point is how about making khugepaged doing always dumb synchronous\n"
+ "> >>>compaction thorough PG_KHUGEPAGED or GFP_SYNC_TRANSHUGE?\n"
+ "> >>>\n"
+ "> >>>>\n"
+ "> >>>>Reported-by: David Rientjes <rientjes@google.com>\n"
+ "> >>>>Signed-off-by: Vlastimil Babka <vbabka@suse.cz>\n"
+ "> >>>>Cc: Minchan Kim <minchan@kernel.org>\n"
+ "> >>>>Cc: Mel Gorman <mgorman@suse.de>\n"
+ "> >>>>Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>\n"
+ "> >>>>Cc: Michal Nazarewicz <mina86@mina86.com>\n"
+ "> >>>>Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>\n"
+ "> >>>>Cc: Christoph Lameter <cl@linux.com>\n"
+ "> >>>>Cc: Rik van Riel <riel@redhat.com>\n"
+ "> >>>>---\n"
+ "> >>>>  mm/compaction.c | 20 ++++++++++++++------\n"
+ "> >>>>  mm/internal.h   | 15 +++++++++++----\n"
+ "> >>>>  2 files changed, 25 insertions(+), 10 deletions(-)\n"
+ "> >>>>\n"
+ "> >>>>diff --git a/mm/compaction.c b/mm/compaction.c\n"
+ "> >>>>index b73b182..d37f4a8 100644\n"
+ "> >>>>--- a/mm/compaction.c\n"
+ "> >>>>+++ b/mm/compaction.c\n"
+ "> >>>>@@ -185,9 +185,14 @@ static void update_pageblock_skip(struct compact_control *cc,\n"
+ "> >>>>  }\n"
+ "> >>>>  #endif /* CONFIG_COMPACTION */\n"
+ "> >>>>\n"
+ "> >>>>-static inline bool should_release_lock(spinlock_t *lock)\n"
+ "> >>>>+enum compact_contended should_release_lock(spinlock_t *lock)\n"
+ "> >>>>  {\n"
+ "> >>>>-\treturn need_resched() || spin_is_contended(lock);\n"
+ "> >>>>+\tif (need_resched())\n"
+ "> >>>>+\t\treturn COMPACT_CONTENDED_SCHED;\n"
+ "> >>>>+\telse if (spin_is_contended(lock))\n"
+ "> >>>>+\t\treturn COMPACT_CONTENDED_LOCK;\n"
+ "> >>>>+\telse\n"
+ "> >>>>+\t\treturn COMPACT_CONTENDED_NONE;\n"
+ "> >>>>  }\n"
+ "> >>>>\n"
+ "> >>>>  /*\n"
+ "> >>>>@@ -202,7 +207,9 @@ static inline bool should_release_lock(spinlock_t *lock)\n"
+ "> >>>>  static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,\n"
+ "> >>>>  \t\t\t\t      bool locked, struct compact_control *cc)\n"
+ "> >>>>  {\n"
+ "> >>>>-\tif (should_release_lock(lock)) {\n"
+ "> >>>>+\tenum compact_contended contended = should_release_lock(lock);\n"
+ "> >>>>+\n"
+ "> >>>>+\tif (contended) {\n"
+ "> >>>>  \t\tif (locked) {\n"
+ "> >>>>  \t\t\tspin_unlock_irqrestore(lock, *flags);\n"
+ "> >>>>  \t\t\tlocked = false;\n"
+ "> >>>>@@ -210,7 +217,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,\n"
+ "> >>>>\n"
+ "> >>>>  \t\t/* async aborts if taking too long or contended */\n"
+ "> >>>>  \t\tif (cc->mode == MIGRATE_ASYNC) {\n"
+ "> >>>>-\t\t\tcc->contended = true;\n"
+ "> >>>>+\t\t\tcc->contended = contended;\n"
+ "> >>>>  \t\t\treturn false;\n"
+ "> >>>>  \t\t}\n"
+ "> >>>>\n"
+ "> >>>>@@ -236,7 +243,7 @@ static inline bool compact_should_abort(struct compact_control *cc)\n"
+ "> >>>>  \t/* async compaction aborts if contended */\n"
+ "> >>>>  \tif (need_resched()) {\n"
+ "> >>>>  \t\tif (cc->mode == MIGRATE_ASYNC) {\n"
+ "> >>>>-\t\t\tcc->contended = true;\n"
+ "> >>>>+\t\t\tcc->contended = COMPACT_CONTENDED_SCHED;\n"
+ "> >>>>  \t\t\treturn true;\n"
+ "> >>>>  \t\t}\n"
+ "> >>>>\n"
+ "> >>>>@@ -1095,7 +1102,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,\n"
+ "> >>>>  \tVM_BUG_ON(!list_empty(&cc.freepages));\n"
+ "> >>>>  \tVM_BUG_ON(!list_empty(&cc.migratepages));\n"
+ "> >>>>\n"
+ "> >>>>-\t*contended = cc.contended;\n"
+ "> >>>>+\t/* We only signal lock contention back to the allocator */\n"
+ "> >>>>+\t*contended = cc.contended == COMPACT_CONTENDED_LOCK;\n"
+ "> >>>>  \treturn ret;\n"
+ "> >>>>  }\n"
+ "> >>>>\n"
+ "> >>>>diff --git a/mm/internal.h b/mm/internal.h\n"
+ "> >>>>index 7f22a11f..4659e8e 100644\n"
+ "> >>>>--- a/mm/internal.h\n"
+ "> >>>>+++ b/mm/internal.h\n"
+ "> >>>>@@ -117,6 +117,13 @@ extern int user_min_free_kbytes;\n"
+ "> >>>>\n"
+ "> >>>>  #if defined CONFIG_COMPACTION || defined CONFIG_CMA\n"
+ "> >>>>\n"
+ "> >>>>+/* Used to signal whether compaction detected need_sched() or lock contention */\n"
+ "> >>>>+enum compact_contended {\n"
+ "> >>>>+\tCOMPACT_CONTENDED_NONE = 0, /* no contention detected */\n"
+ "> >>>>+\tCOMPACT_CONTENDED_SCHED,    /* need_sched() was true */\n"
+ "> >>>>+\tCOMPACT_CONTENDED_LOCK,     /* zone lock or lru_lock was contended */\n"
+ "> >>>>+};\n"
+ "> >>>>+\n"
+ "> >>>>  /*\n"
+ "> >>>>   * in mm/compaction.c\n"
+ "> >>>>   */\n"
+ "> >>>>@@ -144,10 +151,10 @@ struct compact_control {\n"
+ "> >>>>  \tint order;\t\t\t/* order a direct compactor needs */\n"
+ "> >>>>  \tint migratetype;\t\t/* MOVABLE, RECLAIMABLE etc */\n"
+ "> >>>>  \tstruct zone *zone;\n"
+ "> >>>>-\tbool contended;\t\t\t/* True if a lock was contended, or\n"
+ "> >>>>-\t\t\t\t\t * need_resched() true during async\n"
+ "> >>>>-\t\t\t\t\t * compaction\n"
+ "> >>>>-\t\t\t\t\t */\n"
+ "> >>>>+\tenum compact_contended contended; /* Signal need_sched() or lock\n"
+ "> >>>>+\t\t\t\t\t   * contention detected during\n"
+ "> >>>>+\t\t\t\t\t   * compaction\n"
+ "> >>>>+\t\t\t\t\t   */\n"
+ "> >>>>  };\n"
+ "> >>>>\n"
+ "> >>>>  unsigned long\n"
+ "> >>>>--\n"
+ "> >>>>1.8.4.5\n"
+ "> >>>>\n"
+ "> >>>>--\n"
+ "> >>>>To unsubscribe, send a message with 'unsubscribe linux-mm' in\n"
+ "> >>>>the body to majordomo@kvack.org.  For more info on Linux MM,\n"
+ "> >>>>see: http://www.linux-mm.org/ .\n"
+ "> >>>>Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>\n"
+ "> >>>\n"
+ "> >>\n"
+ "> >>--\n"
+ "> >>To unsubscribe, send a message with 'unsubscribe linux-mm' in\n"
+ "> >>the body to majordomo@kvack.org.  For more info on Linux MM,\n"
+ "> >>see: http://www.linux-mm.org/ .\n"
+ "> >>Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>\n"
+ "> >\n"
+ "> \n"
+ "> --\n"
+ "> To unsubscribe, send a message with 'unsubscribe linux-mm' in\n"
+ "> the body to majordomo@kvack.org.  For more info on Linux MM,\n"
+ "> see: http://www.linux-mm.org/ .\n"
+ "> Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>\n"
+ "\n"
+ "-- \n"
+ "Kind regards,\n"
+ Minchan Kim
 
-8af0c10a5486db19c101dd2a3f1c30ea2019cf5ade184ae89ff7bd8b625b3bbf
+13274e66ccf6356aef89dbb622c34e03470b88cfe04f1cda15ddbe8145b9d4b6

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.