mm: allow compaction of unevictable pages

Currently, pages which are marked as unevictable are protected from
compaction, but not from other types of migration.  The POSIX real time
extension explicitly states that mlock() will prevent a major page
fault, but the spirit of this is that mlock() should give a process the
ability to control sources of latency, including minor page faults.
However, the mlock manpage only explicitly says that a locked page will
not be written to swap and this can cause some confusion.  The
compaction code today does not give a developer who wants to avoid swap
but wants to have large contiguous areas available any method to achieve
this state.  This patch introduces a sysctl for controlling compaction
behavior with respect to the unevictable lru.  Users who demand no page
faults after a page is present can set compact_unevictable_allowed to 0
and users who need the large contiguous areas can enable compaction on
locked memory by leaving the default value of 1.

To illustrate this problem I wrote a quick test program that mmaps a
large number of 1MB files filled with random data.  These maps are
created locked and read only.  Then every other mmap is unmapped and I
attempt to allocate huge pages to the static huge page pool.  When the
compact_unevictable_allowed sysctl is 0, I cannot allocate hugepages
after fragmenting memory.  When the value is set to 1, allocations
succeed.

Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Lameter <cl@linux.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 902b4574acfbbae33be058eeae51551600d2fd21..9832ec52f859a2f4e3c99b0767ef957a59a97bf1 100644 (file)
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -21,6 +21,7 @@ Currently, these files are in /proc/sys/vm:
 - admin_reserve_kbytes
 - block_dump
 - compact_memory
+- compact_unevictable_allowed
 - dirty_background_bytes
 - dirty_background_ratio
 - dirty_bytes
@@ -106,6 +107,16 @@ huge pages although processes will also directly compact memory as required.
 
 ==============================================================
 
+compact_unevictable_allowed
+
+Available only when CONFIG_COMPACTION is set. When set to 1, compaction is
+allowed to examine the unevictable lru (mlocked pages) for pages to compact.
+This should be used on systems where stalls for minor page faults are an
+acceptable trade for large contiguous free memory.  Set to 0 to prevent
+compaction from moving pages that are unevictable.  Default value is 1.
+
+==============================================================
+
 dirty_background_bytes
 
 Contains the amount of dirty memory at which the background kernel

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index a014559e4a49d7a3bb95d49e72e68221ef8f4548..aa8f61cf3a19fa3a28214f2a504e031e9e7d3e68 100644 (file)
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -34,6 +34,7 @@ extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 extern int sysctl_extfrag_threshold;
 extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
                        void __user *buffer, size_t *length, loff_t *ppos);
+extern int sysctl_compact_unevictable_allowed;
 
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order,

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8c0eabd418862bcaaebc7b01dcc3ea7ce4951a2b..42b7fc2860c15a2748e4d8209d29a28179d059e0 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1335,6 +1335,15 @@ static struct ctl_table vm_table[] = {
                .extra1         = &min_extfrag_threshold,
                .extra2         = &max_extfrag_threshold,
        },
+       {
+               .procname       = "compact_unevictable_allowed",
+               .data           = &sysctl_compact_unevictable_allowed,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec,
+               .extra1         = &zero,
+               .extra2         = &one,
+       },
 
 #endif /* CONFIG_COMPACTION */
        {

diff --git a/mm/compaction.c b/mm/compaction.c
index a18201a8124e5d0443e8231f8600cb3e2976d55c..570426edcadf8e08f0adc3ade02841c4fbea9e3e 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1046,6 +1046,12 @@ typedef enum {
        ISOLATE_SUCCESS,        /* Pages isolated, migrate */
 } isolate_migrate_t;
 
+/*
+ * Allow userspace to control policy on scanning the unevictable LRU for
+ * compactable pages.
+ */
+int sysctl_compact_unevictable_allowed __read_mostly = 1;
+
 /*
  * Isolate all pages that can be migrated from the first suitable block,
  * starting at the block pointed to by the migrate scanner pfn within
@@ -1057,6 +1063,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
        unsigned long low_pfn, end_pfn;
        struct page *page;
        const isolate_mode_t isolate_mode =
+               (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
                (cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0);
 
        /*