summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2014-01-21 15:49:05 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-01-21 16:19:43 -0800
commit34e431b0ae398fc54ea69ff85ec700722c9da773 (patch)
treea2a0de67b4cc754b5aa7627df3b0d1778d4cf10f
parent5eaf1a9e233d61438377f57facb167f8208ba9fd (diff)
downloadlinux-34e431b0ae398fc54ea69ff85ec700722c9da773.tar.bz2
/proc/meminfo: provide estimated available memory
Many load balancing and workload placing programs check /proc/meminfo to estimate how much free memory is available. They generally do this by adding up "free" and "cached", which was fine ten years ago, but is pretty much guaranteed to be wrong today. It is wrong because Cached includes memory that is not freeable as page cache, for example shared memory segments, tmpfs, and ramfs, and it does not include reclaimable slab memory, which can take up a large fraction of system memory on mostly idle systems with lots of files. Currently, the amount of memory that is available for a new workload, without pushing the system into swap, can be estimated from MemFree, Active(file), Inactive(file), and SReclaimable, as well as the "low" watermarks from /proc/zoneinfo. However, this may change in the future, and user space really should not be expected to know kernel internals to come up with an estimate for the amount of free memory. It is more convenient to provide such an estimate in /proc/meminfo. If things change in the future, we only have to change it in one place. Signed-off-by: Rik van Riel <riel@redhat.com> Reported-by: Erik Mouw <erik.mouw_2@nxp.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--Documentation/filesystems/proc.txt9
-rw-r--r--fs/proc/meminfo.c37
2 files changed, 46 insertions, 0 deletions
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 22d89aa37218..8533f5f9bb2d 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -767,6 +767,7 @@ The "Locked" indicates whether the mapping is locked in memory or not.
MemTotal: 16344972 kB
MemFree: 13634064 kB
+MemAvailable: 14836172 kB
Buffers: 3656 kB
Cached: 1195708 kB
SwapCached: 0 kB
@@ -799,6 +800,14 @@ AnonHugePages: 49152 kB
MemTotal: Total usable ram (i.e. physical ram minus a few reserved
bits and the kernel binary code)
MemFree: The sum of LowFree+HighFree
+MemAvailable: An estimate of how much memory is available for starting new
+ applications, without swapping. Calculated from MemFree,
+ SReclaimable, the size of the file LRU lists, and the low
+ watermarks in each zone.
+ The estimate takes into account that the system needs some
+ page cache to function well, and that not all reclaimable
+ slab will be reclaimable, due to items being in use. The
+ impact of those factors will vary from system to system.
Buffers: Relatively temporary storage for raw disk blocks
shouldn't get tremendously large (20MB or so)
Cached: in-memory cache for files read from the disk (the
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index a77d2b299199..24270eceddbf 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -26,7 +26,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
unsigned long committed;
struct vmalloc_info vmi;
long cached;
+ long available;
+ unsigned long pagecache;
+ unsigned long wmark_low = 0;
unsigned long pages[NR_LRU_LISTS];
+ struct zone *zone;
int lru;
/*
@@ -47,12 +51,44 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
pages[lru] = global_page_state(NR_LRU_BASE + lru);
+ for_each_zone(zone)
+ wmark_low += zone->watermark[WMARK_LOW];
+
+ /*
+ * Estimate the amount of memory available for userspace allocations,
+ * without causing swapping.
+ *
+ * Free memory cannot be taken below the low watermark, before the
+ * system starts swapping.
+ */
+ available = i.freeram - wmark_low;
+
+ /*
+ * Not all the page cache can be freed, otherwise the system will
+ * start swapping. Assume at least half of the page cache, or the
+ * low watermark worth of cache, needs to stay.
+ */
+ pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
+ pagecache -= min(pagecache / 2, wmark_low);
+ available += pagecache;
+
+ /*
+ * Part of the reclaimable swap consists of items that are in use,
+ * and cannot be freed. Cap this estimate at the low watermark.
+ */
+ available += global_page_state(NR_SLAB_RECLAIMABLE) -
+ min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+
+ if (available < 0)
+ available = 0;
+
/*
* Tagged format, for easy grepping and expansion.
*/
seq_printf(m,
"MemTotal: %8lu kB\n"
"MemFree: %8lu kB\n"
+ "MemAvailable: %8lu kB\n"
"Buffers: %8lu kB\n"
"Cached: %8lu kB\n"
"SwapCached: %8lu kB\n"
@@ -105,6 +141,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
,
K(i.totalram),
K(i.freeram),
+ K(available),
K(i.bufferram),
K(cached),
K(total_swapcache_pages()),