From 76ab0f530e4a01d4dc20cdc1d5e87753c579dc18 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:28 -0700 Subject: mm: compaction: add /proc trigger for memory compaction Add a proc file /proc/sys/vm/compact_memory. When an arbitrary value is written to the file, all zones are compacted. The expected user of such a trigger is a job scheduler that prepares the system before the target application runs. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Minchan Kim Reviewed-by: KOSAKI Motohiro Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4c93486b45d1..284f330d6a01 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -1121,6 +1122,15 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = drop_caches_sysctl_handler, }, +#ifdef CONFIG_COMPACTION + { + .procname = "compact_memory", + .data = &sysctl_compact_memory, + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = sysctl_compaction_handler, + }, +#endif /* CONFIG_COMPACTION */ { .procname = "min_free_kbytes", .data = &min_free_kbytes, -- cgit v1.2.3-71-gd317 From 5e7719058079a1423ccce56148b0aaa56b2df821 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:31 -0700 Subject: mm: compaction: add a tunable that decides when memory should be compacted and when it should be reclaimed The kernel applies some heuristics when deciding if memory should be compacted or reclaimed to satisfy a high-order allocation. One of these is based on the fragmentation. If the index is below 500, memory will not be compacted. This choice is arbitrary and not based on data. To help optimise the system and set a sensible default for this value, this patch adds a sysctl extfrag_threshold. The kernel will only compact memory if the fragmentation index is above the extfrag_threshold. [randy.dunlap@oracle.com: Fix build errors when proc fs is not configured] Signed-off-by: Mel Gorman Signed-off-by: Randy Dunlap Cc: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 15 +++++++++++++++ include/linux/compaction.h | 3 +++ kernel/sysctl.c | 15 +++++++++++++++ mm/compaction.c | 12 +++++++++++- 4 files changed, 44 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 56dd29b97a91..5fdbb612aeb8 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -27,6 +27,7 @@ Currently, these files are in /proc/sys/vm: - dirty_ratio - dirty_writeback_centisecs - drop_caches +- extfrag_threshold - hugepages_treat_as_movable - hugetlb_shm_group - laptop_mode @@ -149,6 +150,20 @@ user should run `sync' first. ============================================================== +extfrag_threshold + +This parameter affects whether the kernel will compact memory or direct +reclaim to satisfy a high-order allocation. /proc/extfrag_index shows what +the fragmentation index for each order is in each zone in the system. Values +tending towards 0 imply allocations would fail due to lack of memory, +values towards 1000 imply failures are due to fragmentation and -1 implies +that the allocation will succeed as long as watermarks are met. + +The kernel will not compact memory in a zone if the +fragmentation index is <= extfrag_threshold. The default value is 500. + +============================================================== + hugepages_treat_as_movable This parameter is only useful when kernelcore= is specified at boot time to diff --git a/include/linux/compaction.h b/include/linux/compaction.h index eed40ec4280b..3719325c6091 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -15,6 +15,9 @@ extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); +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 fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 284f330d6a01..84ff5e75c084 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -263,6 +263,11 @@ static int min_sched_shares_ratelimit = 100000; /* 100 usec */ static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */ #endif +#ifdef CONFIG_COMPACTION +static int min_extfrag_threshold; +static int max_extfrag_threshold = 1000; +#endif + static struct ctl_table kern_table[] = { { .procname = "sched_child_runs_first", @@ -1130,6 +1135,16 @@ static struct ctl_table vm_table[] = { .mode = 0200, .proc_handler = sysctl_compaction_handler, }, + { + .procname = "extfrag_threshold", + .data = &sysctl_extfrag_threshold, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_extfrag_handler, + .extra1 = &min_extfrag_threshold, + .extra2 = &max_extfrag_threshold, + }, + #endif /* CONFIG_COMPACTION */ { .procname = "min_free_kbytes", diff --git a/mm/compaction.c b/mm/compaction.c index 9583e193dc47..94cce51b0b35 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -433,6 +433,8 @@ static unsigned long compact_zone_order(struct zone *zone, return compact_zone(zone, &cc); } +int sysctl_extfrag_threshold = 500; + /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @zonelist: The zonelist used for the current allocation @@ -491,7 +493,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, * Only compact if a failure would be due to fragmentation. */ fragindex = fragmentation_index(zone, order); - if (fragindex >= 0 && fragindex <= 500) + if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) continue; if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) { @@ -572,6 +574,14 @@ int sysctl_compaction_handler(struct ctl_table *table, int write, return 0; } +int sysctl_extfrag_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + proc_dointvec_minmax(table, write, buffer, length, ppos); + + return 0; +} + #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) ssize_t sysfs_compact_node(struct sys_device *dev, struct sysdev_attribute *attr, -- cgit v1.2.3-71-gd317 From 563b04671017ea00ba563ebeebdc36bce79b1b60 Mon Sep 17 00:00:00 2001 From: "J. R. Okajima" Date: Tue, 25 May 2010 16:10:14 -0700 Subject: proc_dointvec: write a single value The commit 00b7c3395aec3df43de5bd02a3c5a099ca51169f "sysctl: refactor integer handling proc code" modified the behaviour of writing to /proc. Before the commit, write("1\n") to /proc/sys/kernel/printk succeeded. But now it returns EINVAL. This commit supports writing a single value to a multi-valued entry. Signed-off-by: J. R. Okajima Reviewed-and-tested-by: WANG Cong Signed-off-by: David S. Miller --- kernel/sysctl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b12583047757..f948f20f09cb 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2253,6 +2253,8 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, if (write) { left -= proc_skip_spaces(&kbuf); + if (!left) + break; err = proc_get_long(&kbuf, &left, &lval, &neg, proc_wspace_sep, sizeof(proc_wspace_sep), NULL); @@ -2279,7 +2281,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, if (!write && !first && left && !err) err = proc_put_char(&buffer, &left, '\n'); - if (write && !err) + if (write && !err && left) left -= proc_skip_spaces(&kbuf); free: if (write) { -- cgit v1.2.3-71-gd317