drop_caches: add some documentation and info message

There is plenty of anecdotal evidence and a load of blog posts
suggesting that using "drop_caches" periodically keeps your system
running in "tip top shape".  Perhaps adding some kernel documentation
will increase the amount of accurate data on its use.

If we are not shrinking caches effectively, then we have real bugs.
Using drop_caches will simply mask the bugs and make them harder to
find, but certainly does not fix them, nor is it an appropriate
"workaround" to limit the size of the caches.  On the contrary, there
have been bug reports on issues that turned out to be misguided use of
cache dropping.

Dropping caches is a very drastic and disruptive operation that is good
for debugging and running tests, but if it creates bug reports from
production use, kernel developers should be aware of its use.

Add a bit more documentation about it, a syslog message to track down
abusers, and vmstat drop counters to help analyze problem reports.

[akpm@linux-foundation.org: checkpatch fixes]
[hannes@cmpxchg.org: add runtime suppression control]
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
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 d614a9b6a28048ecf879e96b3aada686ecadb6cb..dd9d0e33b44391200c2004584e79d66baf527991 100644 (file)
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -175,18 +175,39 @@ Setting this to zero disables periodic writeback altogether.
 
 drop_caches
 
-Writing to this will cause the kernel to drop clean caches, dentries and
-inodes from memory, causing that memory to become free.
+Writing to this will cause the kernel to drop clean caches, as well as
+reclaimable slab objects like dentries and inodes.  Once dropped, their
+memory becomes free.
 
 To free pagecache:
        echo 1 > /proc/sys/vm/drop_caches
-To free dentries and inodes:
+To free reclaimable slab objects (includes dentries and inodes):
        echo 2 > /proc/sys/vm/drop_caches
-To free pagecache, dentries and inodes:
+To free slab objects and pagecache:
        echo 3 > /proc/sys/vm/drop_caches
 
-As this is a non-destructive operation and dirty objects are not freeable, the
-user should run `sync' first.
+This is a non-destructive operation and will not free any dirty objects.
+To increase the number of objects freed by this operation, the user may run
+`sync' prior to writing to /proc/sys/vm/drop_caches.  This will minimize the
+number of dirty objects on the system and create more candidates to be
+dropped.
+
+This file is not a means to control the growth of the various kernel caches
+(inodes, dentries, pagecache, etc...)  These objects are automatically
+reclaimed by the kernel when memory is needed elsewhere on the system.
+
+Use of this file can cause performance problems.  Since it discards cached
+objects, it may cost a significant amount of I/O and CPU to recreate the
+dropped objects, especially if they were under heavy use.  Because of this,
+use outside of a testing or debugging environment is not recommended.
+
+You may see informational messages in your kernel log when this file is
+used:
+
+       cat (1234): drop_caches: 3
+
+These are informational only.  They do not mean that anything is wrong
+with your system.  To disable them, echo 4 (bit 3) into drop_caches.
 
 ==============================================================
 

diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 9fd702f5bfb2886a715e787b6470615ea07021e0..9280202e488c0557f1478f8bcde6ebfd0893710d 100644 (file)
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -59,10 +59,22 @@ int drop_caches_sysctl_handler(ctl_table *table, int write,
        if (ret)
                return ret;
        if (write) {
-               if (sysctl_drop_caches & 1)
+               static int stfu;
+
+               if (sysctl_drop_caches & 1) {
                        iterate_supers(drop_pagecache_sb, NULL);
-               if (sysctl_drop_caches & 2)
+                       count_vm_event(DROP_PAGECACHE);
+               }
+               if (sysctl_drop_caches & 2) {
                        drop_slab();
+                       count_vm_event(DROP_SLAB);
+               }
+               if (!stfu) {
+                       pr_info("%s (%d): drop_caches: %d\n",
+                               current->comm, task_pid_nr(current),
+                               sysctl_drop_caches);
+               }
+               stfu |= sysctl_drop_caches & 4;
        }
        return 0;
 }

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 3a712e2e7d762f479fc91377f1e37a9186172dc9..486c3972c0be2c698afd06d7ee0dcdb833aa21ff 100644 (file)
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -37,6 +37,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
                PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
                KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
                PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+               DROP_PAGECACHE, DROP_SLAB,
 #ifdef CONFIG_NUMA_BALANCING
                NUMA_PTE_UPDATES,
                NUMA_HUGE_PTE_UPDATES,

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 09d2e2413605bc027066d6c07436f8488371d882..5c14b547882ef1dabfcd9cd80f5903e173ef4ec4 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -123,7 +123,7 @@ static int __maybe_unused neg_one = -1;
 static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
-static int __maybe_unused three = 3;
+static int __maybe_unused four = 4;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 #ifdef CONFIG_PRINTK
@@ -1264,7 +1264,7 @@ static struct ctl_table vm_table[] = {
                .mode           = 0644,
                .proc_handler   = drop_caches_sysctl_handler,
                .extra1         = &one,
-               .extra2         = &three,
+               .extra2         = &four,
        },
 #ifdef CONFIG_COMPACTION
        {

diff --git a/mm/vmstat.c b/mm/vmstat.c
index f3155d51acfd391801d2558741686c8a3fbf5de9..197b4c4a95879832e29e7b933b70c2f4f6e01d17 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -813,6 +813,9 @@ const char * const vmstat_text[] = {
 
        "pgrotated",
 
+       "drop_pagecache",
+       "drop_slab",
+
 #ifdef CONFIG_NUMA_BALANCING
        "numa_pte_updates",
        "numa_huge_pte_updates",