aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDavid Howells <dhowells@redhat.com>2009-05-06 19:03:05 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2009-05-06 19:36:10 -0400
commitfc4d5c292b68ef02514d2072dcbf82d090c34875 (patch)
tree6baf6c7a472e57e99e1b6555c277060f7065f482
parent3a6be87fd1e5cdbbc3b6a14d02a3efa9ecba1d3f (diff)
nommu: make the initial mmap allocation excess behaviour Kconfig configurable
NOMMU mmap() has an option controlled by a sysctl variable that determines whether the allocations made by do_mmap_private() should have the excess space trimmed off and returned to the allocator. Make the initial setting of this variable a Kconfig configuration option. The reason there can be excess space is that the allocator only allocates in power-of-2 size chunks, but mmap()'s can be made in sizes that aren't a power of 2. There are two alternatives: (1) Keep the excess as dead space. The dead space then remains unused for the lifetime of the mapping. Mappings of shared objects such as libc, ld.so or busybox's text segment may retain their dead space forever. (2) Return the excess to the allocator. This means that the dead space is limited to less than a page per mapping, but it means that for a transient process, there's more chance of fragmentation as the excess space may be reused fairly quickly. During the boot process, a lot of transient processes are created, and this can cause a lot of fragmentation as the pagecache and various slabs grow greatly during this time. By turning off the trimming of excess space during boot and disabling batching of frees, Coldfire can manage to boot. A better way of doing things might be to have /sbin/init turn this option off. By that point libc, ld.so and init - which are all long-duration processes - have all been loaded and trimmed. Reported-by: Lanttor Guo <lanttor.guo@freescale.com> Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Lanttor Guo <lanttor.guo@freescale.com> Cc: Greg Ungerer <gerg@snapgear.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/Kconfig28
-rw-r--r--mm/nommu.c2
2 files changed, 29 insertions, 1 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 57971d2ab848..c2b57d81e153 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -225,3 +225,31 @@ config HAVE_MLOCKED_PAGE_BIT
225 225
226config MMU_NOTIFIER 226config MMU_NOTIFIER
227 bool 227 bool
228
229config NOMMU_INITIAL_TRIM_EXCESS
230 int "Turn on mmap() excess space trimming before booting"
231 depends on !MMU
232 default 1
233 help
234 The NOMMU mmap() frequently needs to allocate large contiguous chunks
235 of memory on which to store mappings, but it can only ask the system
236 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
237 more than it requires. To deal with this, mmap() is able to trim off
238 the excess and return it to the allocator.
239
240 If trimming is enabled, the excess is trimmed off and returned to the
241 system allocator, which can cause extra fragmentation, particularly
242 if there are a lot of transient processes.
243
244 If trimming is disabled, the excess is kept, but not used, which for
245 long-term mappings means that the space is wasted.
246
247 Trimming can be dynamically controlled through a sysctl option
248 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
249 excess pages there must be before trimming should occur, or zero if
250 no trimming is to occur.
251
252 This option specifies the initial value of this option. The default
253 of 1 says that all excess pages should be trimmed.
254
255 See Documentation/nommu-mmap.txt for more information.
diff --git a/mm/nommu.c b/mm/nommu.c
index 809998aa7b50..67cd1a487ee6 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -66,7 +66,7 @@ struct percpu_counter vm_committed_as;
66int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ 66int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
67int sysctl_overcommit_ratio = 50; /* default is 50% */ 67int sysctl_overcommit_ratio = 50; /* default is 50% */
68int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; 68int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
69int sysctl_nr_trim_pages = 1; /* page trimming behaviour */ 69int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
70int heap_stack_gap = 0; 70int heap_stack_gap = 0;
71 71
72atomic_long_t mmap_pages_allocated; 72atomic_long_t mmap_pages_allocated;