mm: vmscan: remove lumpy reclaim

This series removes lumpy reclaim and some stalling logic that was
unintentionally being used by memory compaction.  The end result is that
stalling on dirty pages during page reclaim now depends on
wait_iff_congested().

Four kernels were compared

  3.3.0     vanilla
  3.4.0-rc2 vanilla
  3.4.0-rc2 lumpyremove-v2 is patch one from this series
  3.4.0-rc2 nosync-v2r3 is the full series

Removing lumpy reclaim saves almost 900 bytes of text whereas the full
series removes 1200 bytes.

     text     data      bss       dec     hex  filename
  6740375  1927944  2260992  10929311  a6c49f  vmlinux-3.4.0-rc2-vanilla
  6739479  1927944  2260992  10928415  a6c11f  vmlinux-3.4.0-rc2-lumpyremove-v2
  6739159  1927944  2260992  10928095  a6bfdf  vmlinux-3.4.0-rc2-nosync-v2

There are behaviour changes in the series and so tests were run with
monitoring of ftrace events.  This disrupts results so the performance
results are distorted but the new behaviour should be clearer.

fs-mark running in a threaded configuration showed little of interest as
it did not push reclaim aggressively

  FS-Mark Multi Threaded
                          3.3.0-vanilla       rc2-vanilla       lumpyremove-v2r3       nosync-v2r3
  Files/s  min           3.20 ( 0.00%)        3.20 ( 0.00%)        3.20 ( 0.00%)        3.20 ( 0.00%)
  Files/s  mean          3.20 ( 0.00%)        3.20 ( 0.00%)        3.20 ( 0.00%)        3.20 ( 0.00%)
  Files/s  stddev        0.00 ( 0.00%)        0.00 ( 0.00%)        0.00 ( 0.00%)        0.00 ( 0.00%)
  Files/s  max           3.20 ( 0.00%)        3.20 ( 0.00%)        3.20 ( 0.00%)        3.20 ( 0.00%)
  Overhead min      508667.00 ( 0.00%)   521350.00 (-2.49%)   544292.00 (-7.00%)   547168.00 (-7.57%)
  Overhead mean     551185.00 ( 0.00%)   652690.73 (-18.42%)   991208.40 (-79.83%)   570130.53 (-3.44%)
  Overhead stddev    18200.69 ( 0.00%)   331958.29 (-1723.88%)  1579579.43 (-8578.68%)     9576.81 (47.38%)
  Overhead max      576775.00 ( 0.00%)  1846634.00 (-220.17%)  6901055.00 (-1096.49%)   585675.00 (-1.54%)
  MMTests Statistics: duration
  Sys Time Running Test (seconds)             309.90    300.95    307.33    298.95
  User+Sys Time Running Test (seconds)        319.32    309.67    315.69    307.51
  Total Elapsed Time (seconds)               1187.85   1193.09   1191.98   1193.73

  MMTests Statistics: vmstat
  Page Ins                                       80532       82212       81420       79480
  Page Outs                                  111434984   111456240   111437376   111582628
  Swap Ins                                           0           0           0           0
  Swap Outs                                          0           0           0           0
  Direct pages scanned                           44881       27889       27453       34843
  Kswapd pages scanned                        25841428    25860774    25861233    25843212
  Kswapd pages reclaimed                      25841393    25860741    25861199    25843179
  Direct pages reclaimed                         44881       27889       27453       34843
  Kswapd efficiency                                99%         99%         99%         99%
  Kswapd velocity                            21754.791   21675.460   21696.029   21649.127
  Direct efficiency                               100%        100%        100%        100%
  Direct velocity                               37.783      23.375      23.031      29.188
  Percentage direct scans                           0%          0%          0%          0%

ftrace showed that there was no stalling on writeback or pages submitted
for IO from reclaim context.

postmark was similar and while it was more interesting, it also did not
push reclaim heavily.

  POSTMARK
                                       3.3.0-vanilla       rc2-vanilla  lumpyremove-v2r3       nosync-v2r3
  Transactions per second:               16.00 ( 0.00%)    20.00 (25.00%)    18.00 (12.50%)    17.00 ( 6.25%)
  Data megabytes read per second:        18.80 ( 0.00%)    24.27 (29.10%)    22.26 (18.40%)    20.54 ( 9.26%)
  Data megabytes written per second:     35.83 ( 0.00%)    46.25 (29.08%)    42.42 (18.39%)    39.14 ( 9.24%)
  Files created alone per second:        28.00 ( 0.00%)    38.00 (35.71%)    34.00 (21.43%)    30.00 ( 7.14%)
  Files create/transact per second:       8.00 ( 0.00%)    10.00 (25.00%)     9.00 (12.50%)     8.00 ( 0.00%)
  Files deleted alone per second:       556.00 ( 0.00%)  1224.00 (120.14%)  3062.00 (450.72%)  6124.00 (1001.44%)
  Files delete/transact per second:       8.00 ( 0.00%)    10.00 (25.00%)     9.00 (12.50%)     8.00 ( 0.00%)

  MMTests Statistics: duration
  Sys Time Running Test (seconds)             113.34    107.99    109.73    108.72
  User+Sys Time Running Test (seconds)        145.51    139.81    143.32    143.55
  Total Elapsed Time (seconds)               1159.16    899.23    980.17   1062.27

  MMTests Statistics: vmstat
  Page Ins                                    13710192    13729032    13727944    13760136
  Page Outs                                   43071140    42987228    42733684    42931624
  Swap Ins                                           0           0           0           0
  Swap Outs                                          0           0           0           0
  Direct pages scanned                               0           0           0           0
  Kswapd pages scanned                         9941613     9937443     9939085     9929154
  Kswapd pages reclaimed                       9940926     9936751     9938397     9928465
  Direct pages reclaimed                             0           0           0           0
  Kswapd efficiency                                99%         99%         99%         99%
  Kswapd velocity                             8576.567   11051.058   10140.164    9347.109
  Direct efficiency                               100%        100%        100%        100%
  Direct velocity                                0.000       0.000       0.000       0.000

It looks like here that the full series regresses performance but as
ftrace showed no usage of wait_iff_congested() or sync reclaim I am
assuming it's a disruption due to monitoring.  Other data such as memory
usage, page IO, swap IO all looked similar.

Running a benchmark with a plain DD showed nothing very interesting.
The full series stalled in wait_iff_congested() slightly less but stall
times on vanilla kernels were marginal.

Running a benchmark that hammered on file-backed mappings showed stalls
due to congestion but not in sync writebacks

  MICRO
                                       3.3.0-vanilla       rc2-vanilla  lumpyremove-v2r3       nosync-v2r3
  MMTests Statistics: duration
  Sys Time Running Test (seconds)             308.13    294.50    298.75    299.53
  User+Sys Time Running Test (seconds)        330.45    316.28    318.93    320.79
  Total Elapsed Time (seconds)               1814.90   1833.88   1821.14   1832.91

  MMTests Statistics: vmstat
  Page Ins                                      108712      120708       97224      110344
  Page Outs                                  155514576   156017404   155813676   156193256
  Swap Ins                                           0           0           0           0
  Swap Outs                                          0           0           0           0
  Direct pages scanned                         2599253     1550480     2512822     2414760
  Kswapd pages scanned                        69742364    71150694    68839041    69692533
  Kswapd pages reclaimed                      34824488    34773341    34796602    34799396
  Direct pages reclaimed                         53693       94750       61792       75205
  Kswapd efficiency                                49%         48%         50%         49%
  Kswapd velocity                            38427.662   38797.901   37799.972   38022.889
  Direct efficiency                                 2%          6%          2%          3%
  Direct velocity                             1432.174     845.464    1379.807    1317.446
  Percentage direct scans                           3%          2%          3%          3%
  Page writes by reclaim                             0           0           0           0
  Page writes file                                   0           0           0           0
  Page writes anon                                   0           0           0           0
  Page reclaim immediate                             0           0           0        1218
  Page rescued immediate                             0           0           0           0
  Slabs scanned                                  15360       16384       13312       16384
  Direct inode steals                                0           0           0           0
  Kswapd inode steals                             4340        4327        1630        4323

  FTrace Reclaim Statistics: congestion_wait
  Direct number congest     waited                 0          0          0          0
  Direct time   congest     waited               0ms        0ms        0ms        0ms
  Direct full   congest     waited                 0          0          0          0
  Direct number conditional waited               900        870        754        789
  Direct time   conditional waited               0ms        0ms        0ms       20ms
  Direct full   conditional waited                 0          0          0          0
  KSwapd number congest     waited              2106       2308       2116       1915
  KSwapd time   congest     waited          139924ms   157832ms   125652ms   132516ms
  KSwapd full   congest     waited              1346       1530       1202       1278
  KSwapd number conditional waited             12922      16320      10943      14670
  KSwapd time   conditional waited               0ms        0ms        0ms        0ms
  KSwapd full   conditional waited                 0          0          0          0

Reclaim statistics are not radically changed.  The stall times in kswapd
are massive but it is clear that it is due to calls to congestion_wait()
and that is almost certainly the call in balance_pgdat().  Otherwise
stalls due to dirty pages are non-existant.

I ran a benchmark that stressed high-order allocation.  This is very
artifical load but was used in the past to evaluate lumpy reclaim and
compaction.  Generally I look at allocation success rates and latency
figures.

  STRESS-HIGHALLOC
                   3.3.0-vanilla       rc2-vanilla  lumpyremove-v2r3       nosync-v2r3
  Pass 1          81.00 ( 0.00%)    28.00 (-53.00%)    24.00 (-57.00%)    28.00 (-53.00%)
  Pass 2          82.00 ( 0.00%)    39.00 (-43.00%)    38.00 (-44.00%)    43.00 (-39.00%)
  while Rested    88.00 ( 0.00%)    87.00 (-1.00%)    88.00 ( 0.00%)    88.00 ( 0.00%)

  MMTests Statistics: duration
  Sys Time Running Test (seconds)             740.93    681.42    685.14    684.87
  User+Sys Time Running Test (seconds)       2922.65   3269.52   3281.35   3279.44
  Total Elapsed Time (seconds)               1161.73   1152.49   1159.55   1161.44

  MMTests Statistics: vmstat
  Page Ins                                     4486020     2807256     2855944     2876244
  Page Outs                                    7261600     7973688     7975320     7986120
  Swap Ins                                       31694           0           0           0
  Swap Outs                                      98179           0           0           0
  Direct pages scanned                           53494       57731       34406      113015
  Kswapd pages scanned                         6271173     1287481     1278174     1219095
  Kswapd pages reclaimed                       2029240     1281025     1260708     1201583
  Direct pages reclaimed                          1468       14564       16649       92456
  Kswapd efficiency                                32%         99%         98%         98%
  Kswapd velocity                             5398.133    1117.130    1102.302    1049.641
  Direct efficiency                                 2%         25%         48%         81%
  Direct velocity                               46.047      50.092      29.672      97.306
  Percentage direct scans                           0%          4%          2%          8%
  Page writes by reclaim                       1616049           0           0           0
  Page writes file                             1517870           0           0           0
  Page writes anon                               98179           0           0           0
  Page reclaim immediate                        103778       27339        9796       17831
  Page rescued immediate                             0           0           0           0
  Slabs scanned                                1096704      986112      980992      998400
  Direct inode steals                              223      215040      216736      247881
  Kswapd inode steals                           175331       61548       68444       63066
  Kswapd skipped wait                            21991           0           1           0
  THP fault alloc                                    1         135         125         134
  THP collapse alloc                               393         311         228         236
  THP splits                                        25          13           7           8
  THP fault fallback                                 0           0           0           0
  THP collapse fail                                  3           5           7           7
  Compaction stalls                                865        1270        1422        1518
  Compaction success                               370         401         353         383
  Compaction failures                              495         869        1069        1135
  Compaction pages moved                        870155     3828868     4036106     4423626
  Compaction move failure                        26429       23865       29742       27514

Success rates are completely hosed for 3.4-rc2 which is almost certainly
due to commit fe2c2a106663 ("vmscan: reclaim at order 0 when compaction
is enabled").  I expected this would happen for kswapd and impair
allocation success rates (https://lkml.org/lkml/2012/1/25/166) but I did
not anticipate this much a difference: 80% less scanning, 37% less
reclaim by kswapd

In comparison, reclaim/compaction is not aggressive and gives up easily
which is the intended behaviour.  hugetlbfs uses __GFP_REPEAT and would
be much more aggressive about reclaim/compaction than THP allocations
are.  The stress test above is allocating like neither THP or hugetlbfs
but is much closer to THP.

Mainline is now impaired in terms of high order allocation under heavy
load although I do not know to what degree as I did not test with
__GFP_REPEAT.  Keep this in mind for bugs related to hugepage pool
resizing, THP allocation and high order atomic allocation failures from
network devices.

In terms of congestion throttling, I see the following for this test

  FTrace Reclaim Statistics: congestion_wait
  Direct number congest     waited                 3          0          0          0
  Direct time   congest     waited               0ms        0ms        0ms        0ms
  Direct full   congest     waited                 0          0          0          0
  Direct number conditional waited               957        512       1081       1075
  Direct time   conditional waited               0ms        0ms        0ms        0ms
  Direct full   conditional waited                 0          0          0          0
  KSwapd number congest     waited                36          4          3          5
  KSwapd time   congest     waited            3148ms      400ms      300ms      500ms
  KSwapd full   congest     waited                30          4          3          5
  KSwapd number conditional waited             88514        197        332        542
  KSwapd time   conditional waited            4980ms        0ms        0ms        0ms
  KSwapd full   conditional waited                49          0          0          0

The "conditional waited" times are the most interesting as this is
directly impacted by the number of dirty pages encountered during scan.
As lumpy reclaim is no longer scanning contiguous ranges, it is finding
fewer dirty pages.  This brings wait times from about 5 seconds to 0.
kswapd itself is still calling congestion_wait() so it'll still stall but
it's a lot less.

In terms of the type of IO we were doing, I see this

  FTrace Reclaim Statistics: mm_vmscan_writepage
  Direct writes anon  sync                         0          0          0          0
  Direct writes anon  async                        0          0          0          0
  Direct writes file  sync                         0          0          0          0
  Direct writes file  async                        0          0          0          0
  Direct writes mixed sync                         0          0          0          0
  Direct writes mixed async                        0          0          0          0
  KSwapd writes anon  sync                         0          0          0          0
  KSwapd writes anon  async                    91682          0          0          0
  KSwapd writes file  sync                         0          0          0          0
  KSwapd writes file  async                   822629          0          0          0
  KSwapd writes mixed sync                         0          0          0          0
  KSwapd writes mixed async                        0          0          0          0

In 3.2, kswapd was doing a bunch of async writes of pages but
reclaim/compaction was never reaching a point where it was doing sync
IO.  This does not guarantee that reclaim/compaction was not calling
wait_on_page_writeback() but I would consider it unlikely.  It indicates
that merging patches 2 and 3 to stop reclaim/compaction calling
wait_on_page_writeback() should be safe.

This patch:

Lumpy reclaim had a purpose but in the mind of some, it was to kick the
system so hard it trashed.  For others the purpose was to complicate
vmscan.c.  Over time it was giving softer shoes and a nicer attitude but
memory compaction needs to step up and replace it so this patch sends
lumpy reclaim to the farm.

The tracepoint format changes for isolating LRU pages with this patch
applied.  Furthermore reclaim/compaction can no longer queue dirty pages
in pageout() if the underlying BDI is congested.  Lumpy reclaim used
this logic and reclaim/compaction was using it in error.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ying Han <yinghan@google.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 19 insertions, 151 deletions

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 572195459d58..bdaf32f8a874 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -263,22 +263,16 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
-		unsigned long nr_lumpy_taken,
-		unsigned long nr_lumpy_dirty,
-		unsigned long nr_lumpy_failed,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file),
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
 
 	TP_STRUCT__entry(
 		__field(int, order)
 		__field(unsigned long, nr_requested)
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_taken)
-		__field(unsigned long, nr_lumpy_taken)
-		__field(unsigned long, nr_lumpy_dirty)
-		__field(unsigned long, nr_lumpy_failed)
 		__field(isolate_mode_t, isolate_mode)
 		__field(int, file)
 	),
@@ -288,22 +282,16 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		__entry->nr_requested = nr_requested;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_taken = nr_taken;
-		__entry->nr_lumpy_taken = nr_lumpy_taken;
-		__entry->nr_lumpy_dirty = nr_lumpy_dirty;
-		__entry->nr_lumpy_failed = nr_lumpy_failed;
 		__entry->isolate_mode = isolate_mode;
 		__entry->file = file;
 	),
 
-	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu contig_taken=%lu contig_dirty=%lu contig_failed=%lu file=%d",
+	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
 		__entry->isolate_mode,
 		__entry->order,
 		__entry->nr_requested,
 		__entry->nr_scanned,
 		__entry->nr_taken,
-		__entry->nr_lumpy_taken,
-		__entry->nr_lumpy_dirty,
-		__entry->nr_lumpy_failed,
 		__entry->file)
 );
 
@@ -313,13 +301,10 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
-		unsigned long nr_lumpy_taken,
-		unsigned long nr_lumpy_dirty,
-		unsigned long nr_lumpy_failed,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file)
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
@@ -329,13 +314,10 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
-		unsigned long nr_lumpy_taken,
-		unsigned long nr_lumpy_dirty,
-		unsigned long nr_lumpy_failed,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file)
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ca46080bb074..546d02ce90ee 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -58,9 +58,6 @@
  * RECLAIM_MODE_SINGLE: Reclaim only order-0 pages
  * RECLAIM_MODE_ASYNC:  Do not block
  * RECLAIM_MODE_SYNC:   Allow blocking e.g. call wait_on_page_writeback
- * RECLAIM_MODE_LUMPYRECLAIM: For high-order allocations, take a reference
- *			page from the LRU and reclaim all pages within a
- *			naturally aligned range
  * RECLAIM_MODE_COMPACTION: For high-order allocations, reclaim a number of
  *			order-0 pages and then compact the zone
  */
@@ -68,7 +65,6 @@ typedef unsigned __bitwise__ reclaim_mode_t;
 #define RECLAIM_MODE_SINGLE		((__force reclaim_mode_t)0x01u)
 #define RECLAIM_MODE_ASYNC		((__force reclaim_mode_t)0x02u)
 #define RECLAIM_MODE_SYNC		((__force reclaim_mode_t)0x04u)
-#define RECLAIM_MODE_LUMPYRECLAIM	((__force reclaim_mode_t)0x08u)
 #define RECLAIM_MODE_COMPACTION		((__force reclaim_mode_t)0x10u)
 
 struct scan_control {
@@ -367,27 +363,17 @@ out:
 static void set_reclaim_mode(int priority, struct scan_control *sc,
 				   bool sync)
 {
+	/* Sync reclaim used only for compaction */
 	reclaim_mode_t syncmode = sync ? RECLAIM_MODE_SYNC : RECLAIM_MODE_ASYNC;
 
 	/*
-	 * Initially assume we are entering either lumpy reclaim or
-	 * reclaim/compaction.Depending on the order, we will either set the
-	 * sync mode or just reclaim order-0 pages later.
-	 */
-	if (COMPACTION_BUILD)
-		sc->reclaim_mode = RECLAIM_MODE_COMPACTION;
-	else
-		sc->reclaim_mode = RECLAIM_MODE_LUMPYRECLAIM;
-
-	/*
-	 * Avoid using lumpy reclaim or reclaim/compaction if possible by
-	 * restricting when its set to either costly allocations or when
+	 * Restrict reclaim/compaction to costly allocations or when
 	 * under memory pressure
 	 */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		sc->reclaim_mode |= syncmode;
-	else if (sc->order && priority < DEF_PRIORITY - 2)
-		sc->reclaim_mode |= syncmode;
+	if (COMPACTION_BUILD && sc->order &&
+			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
+			 priority < DEF_PRIORITY - 2))
+		sc->reclaim_mode = RECLAIM_MODE_COMPACTION | syncmode;
 	else
 		sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
 }
@@ -416,10 +402,6 @@ static int may_write_to_queue(struct backing_dev_info *bdi,
 		return 1;
 	if (bdi == current->backing_dev_info)
 		return 1;
-
-	/* lumpy reclaim for hugepage often need a lot of write */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		return 1;
 	return 0;
 }
 
@@ -710,10 +692,6 @@ static enum page_references page_check_references(struct page *page,
 	referenced_ptes = page_referenced(page, 1, mz->mem_cgroup, &vm_flags);
 	referenced_page = TestClearPageReferenced(page);
 
-	/* Lumpy reclaim - ignore references */
-	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		return PAGEREF_RECLAIM;
-
 	/*
 	 * Mlock lost the isolation race with us.  Let try_to_unmap()
 	 * move the page to the unevictable list.
@@ -824,7 +802,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				wait_on_page_writeback(page);
 			else {
 				unlock_page(page);
-				goto keep_lumpy;
+				goto keep_reclaim_mode;
 			}
 		}
 
@@ -908,7 +886,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto activate_locked;
 			case PAGE_SUCCESS:
 				if (PageWriteback(page))
-					goto keep_lumpy;
+					goto keep_reclaim_mode;
 				if (PageDirty(page))
 					goto keep;
 
@@ -1008,7 +986,7 @@ keep_locked:
 		unlock_page(page);
 keep:
 		reset_reclaim_mode(sc);
-keep_lumpy:
+keep_reclaim_mode:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
@@ -1064,11 +1042,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
 	if (!all_lru_mode && !!page_is_file_cache(page) != file)
 		return ret;
 
-	/*
-	 * When this function is being called for lumpy reclaim, we
-	 * initially look into all LRU pages, active, inactive and
-	 * unevictable; only give shrink_page_list evictable pages.
-	 */
+	/* Do not give back unevictable pages for compaction */
 	if (PageUnevictable(page))
 		return ret;
 
@@ -1153,9 +1127,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	struct lruvec *lruvec;
 	struct list_head *src;
 	unsigned long nr_taken = 0;
-	unsigned long nr_lumpy_taken = 0;
-	unsigned long nr_lumpy_dirty = 0;
-	unsigned long nr_lumpy_failed = 0;
 	unsigned long scan;
 	int lru = LRU_BASE;
 
@@ -1168,10 +1139,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
 		struct page *page;
-		unsigned long pfn;
-		unsigned long end_pfn;
-		unsigned long page_pfn;
-		int zone_id;
 
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
@@ -1193,84 +1160,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		default:
 			BUG();
 		}
-
-		if (!sc->order || !(sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM))
-			continue;
-
-		/*
-		 * Attempt to take all pages in the order aligned region
-		 * surrounding the tag page.  Only take those pages of
-		 * the same active state as that tag page.  We may safely
-		 * round the target page pfn down to the requested order
-		 * as the mem_map is guaranteed valid out to MAX_ORDER,
-		 * where that page is in a different zone we will detect
-		 * it from its zone id and abort this block scan.
-		 */
-		zone_id = page_zone_id(page);
-		page_pfn = page_to_pfn(page);
-		pfn = page_pfn & ~((1 << sc->order) - 1);
-		end_pfn = pfn + (1 << sc->order);
-		for (; pfn < end_pfn; pfn++) {
-			struct page *cursor_page;
-
-			/* The target page is in the block, ignore it. */
-			if (unlikely(pfn == page_pfn))
-				continue;
-
-			/* Avoid holes within the zone. */
-			if (unlikely(!pfn_valid_within(pfn)))
-				break;
-
-			cursor_page = pfn_to_page(pfn);
-
-			/* Check that we have not crossed a zone boundary. */
-			if (unlikely(page_zone_id(cursor_page) != zone_id))
-				break;
-
-			/*
-			 * If we don't have enough swap space, reclaiming of
-			 * anon page which don't already have a swap slot is
-			 * pointless.
-			 */
-			if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) &&
-			    !PageSwapCache(cursor_page))
-				break;
-
-			if (__isolate_lru_page(cursor_page, mode, file) == 0) {
-				unsigned int isolated_pages;
-
-				mem_cgroup_lru_del(cursor_page);
-				list_move(&cursor_page->lru, dst);
-				isolated_pages = hpage_nr_pages(cursor_page);
-				nr_taken += isolated_pages;
-				nr_lumpy_taken += isolated_pages;
-				if (PageDirty(cursor_page))
-					nr_lumpy_dirty += isolated_pages;
-				scan++;
-				pfn += isolated_pages - 1;
-			} else {
-				/*
-				 * Check if the page is freed already.
-				 *
-				 * We can't use page_count() as that
-				 * requires compound_head and we don't
-				 * have a pin on the page here. If a
-				 * page is tail, we may or may not
-				 * have isolated the head, so assume
-				 * it's not free, it'd be tricky to
-				 * track the head status without a
-				 * page pin.
-				 */
-				if (!PageTail(cursor_page) &&
-				    !atomic_read(&cursor_page->_count))
-					continue;
-				break;
-			}
-		}
-
-		/* If we break out of the loop above, lumpy reclaim failed */
-		if (pfn < end_pfn)
-			nr_lumpy_failed++;
 	}
 
 	*nr_scanned = scan;
@@ -1278,7 +1167,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	trace_mm_vmscan_lru_isolate(sc->order,
 			nr_to_scan, scan,
 			nr_taken,
-			nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
 			mode, file);
 	return nr_taken;
 }
@@ -1466,13 +1354,13 @@ static inline bool should_reclaim_stall(unsigned long nr_taken,
 					int priority,
 					struct scan_control *sc)
 {
-	int lumpy_stall_priority;
+	int stall_priority;
 
 	/* kswapd should not stall on sync IO */
 	if (current_is_kswapd())
 		return false;
 
-	/* Only stall on lumpy reclaim */
+	/* Only stall for memory compaction */
 	if (sc->reclaim_mode & RECLAIM_MODE_SINGLE)
 		return false;
 
@@ -1487,11 +1375,11 @@ static inline bool should_reclaim_stall(unsigned long nr_taken,
 	 * priority to be much higher before stalling.
 	 */
 	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		lumpy_stall_priority = DEF_PRIORITY;
+		stall_priority = DEF_PRIORITY;
 	else
-		lumpy_stall_priority = DEF_PRIORITY / 3;
+		stall_priority = DEF_PRIORITY / 3;
 
-	return priority <= lumpy_stall_priority;
+	return priority <= stall_priority;
 }
 
 /*
@@ -1523,8 +1411,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 	}
 
 	set_reclaim_mode(priority, sc, false);
-	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		isolate_mode |= ISOLATE_ACTIVE;
 
 	lru_add_drain();