mm/page-writeback: highmem_is_dirtyable option

Add vm.highmem_is_dirtyable toggle

A 32 bit machine with HIGHMEM64 enabled running DCC has an MMAPed file of
approximately 2Gb size which contains a hash format that is written
randomly by the dbclean process.  On 2.6.16 this process took a few
minutes.  With lowmem only accounting of dirty ratios, this takes about 12
hours of 100% disk IO, all random writes.

Include a toggle in /proc/sys/vm/highmem_is_dirtyable which can be set to 1 to
add the highmem back to the total available memory count.

[akpm@linux-foundation.org: Fix the CONFIG_DETECT_SOFTLOCKUP=y build]
Signed-off-by: Bron Gondwana <brong@fastmail.fm>
Cc: Ethan Solomita <solo@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: WU Fengguang <wfg@mail.ustc.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 0b1b0c0086137c6bb07a1f220ccb6df7d31832b6..07231afca72df8add1e5fb1c54613f7341349f60 100644 (file)
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1315,6 +1315,21 @@ for writeout by the pdflush daemons.  It is expressed in 100'ths of a second.
 Data which has been dirty in-memory for longer than this interval will be
 written out next time a pdflush daemon wakes up.
 
+highmem_is_dirtyable
+--------------------
+
+Only present if CONFIG_HIGHMEM is set.
+
+This defaults to 0 (false), meaning that the ratios set above are calculated
+as a percentage of lowmem only.  This protects against excessive scanning
+in page reclaim, swapping and general VM distress.
+
+Setting this to 1 can be useful on 32 bit machines where you want to make
+random changes within an MMAPed file that is larger than your available
+lowmem without causing large quantities of random IO.  Is is safe if the
+behavior of all programs running on the machine is known and memory will
+not be otherwise stressed.
+
 legacy_va_layout
 ----------------
 

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 6f31f0a247d03137b85955bf59d06a666e34b1a0..24eac1bc735d733df28901555eefe36217d5dd2a 100644 (file)
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -22,6 +22,7 @@ Currently, these files are in /proc/sys/vm:
 - dirty_background_ratio
 - dirty_expire_centisecs
 - dirty_writeback_centisecs
+- highmem_is_dirtyable   (only if CONFIG_HIGHMEM set)
 - max_map_count
 - min_free_kbytes
 - laptop_mode
@@ -40,9 +41,9 @@ Currently, these files are in /proc/sys/vm:
 ==============================================================
 
 dirty_ratio, dirty_background_ratio, dirty_expire_centisecs,
-dirty_writeback_centisecs, vfs_cache_pressure, laptop_mode,
-block_dump, swap_token_timeout, drop-caches,
-hugepages_treat_as_movable:
+dirty_writeback_centisecs, highmem_is_dirtyable,
+vfs_cache_pressure, laptop_mode, block_dump, swap_token_timeout,
+drop-caches, hugepages_treat_as_movable:
 
 See Documentation/filesystems/proc.txt
 

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index c6148bbf1250a37ec4d29ba49732ff87a2019506..b2cd826a8c90ecf40a9eb5e2ba29c49785f311e7 100644 (file)
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -100,6 +100,7 @@ extern int dirty_background_ratio;
 extern int vm_dirty_ratio;
 extern int dirty_writeback_interval;
 extern int dirty_expire_interval;
+extern int vm_highmem_is_dirtyable;
 extern int block_dump;
 extern int laptop_mode;
 

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7cb1ac3e6fff9583c0d880788190d14da6e2ced1..d0b47b85906731a5cda80d5630ea3dbb11a86810 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -84,8 +84,11 @@ extern int sysctl_stat_interval;
 extern int latencytop_enabled;
 
 /* Constants used for minimum and  maximum */
-#ifdef CONFIG_DETECT_SOFTLOCKUP
+#if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
 static int one = 1;
+#endif
+
+#ifdef CONFIG_DETECT_SOFTLOCKUP
 static int sixty = 60;
 #endif
 
@@ -1150,6 +1153,19 @@ static struct ctl_table vm_table[] = {
                .extra1         = &zero,
        },
 #endif
+#ifdef CONFIG_HIGHMEM
+       {
+               .ctl_name       = CTL_UNNUMBERED,
+               .procname       = "highmem_is_dirtyable",
+               .data           = &vm_highmem_is_dirtyable,
+               .maxlen         = sizeof(vm_highmem_is_dirtyable),
+               .mode           = 0644,
+               .proc_handler   = &proc_dointvec_minmax,
+               .strategy       = &sysctl_intvec,
+               .extra1         = &zero,
+               .extra2         = &one,
+       },
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 8137482abd6e862249fa9b4e8a66fcff6cf22821..c689b60af000105de4cf3bb90e73e74d41a91339 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -68,6 +68,12 @@ static inline long sync_writeback_pages(void)
  */
 int dirty_background_ratio = 5;
 
+/*
+ * free highmem will not be subtracted from the total free memory
+ * for calculating free ratios if vm_highmem_is_dirtyable is true
+ */
+int vm_highmem_is_dirtyable;
+
 /*
  * The generator of dirty data starts writeback at this percentage
  */
@@ -287,7 +293,10 @@ static unsigned long determine_dirtyable_memory(void)
        x = global_page_state(NR_FREE_PAGES)
                + global_page_state(NR_INACTIVE)
                + global_page_state(NR_ACTIVE);
-       x -= highmem_dirtyable_memory(x);
+
+       if (!vm_highmem_is_dirtyable)
+               x -= highmem_dirtyable_memory(x);
+
        return x + 1;   /* Ensure that we never return 0 */
 }