The patch titled
mm: export fragmentation index via debugfs
has been added to the -mm tree. Its filename is
mm-export-fragmentation-index-via-debugfs.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mm: export fragmentation index via debugfs
From: Mel Gorman <mel@xxxxxxxxx>
The fragmentation fragmentation index, is only meaningful if an allocation
would fail and indicates what the failure is due to. A value of -1 such
as in many of the examples above states that the allocation would succeed.
If it would fail, the value is between 0 and 1. A value tending towards
0 implies the allocation failed due to a lack of memory. A value tending
towards 1 implies it failed due to external fragmentation.
For the most part, the huge page size will be the size of interest but not
necessarily so it is exported on a per-order and per-zo basis via
/sys/kernel/debug/extfrag/extfrag_index
> cat /sys/kernel/debug/extfrag/extfrag_index
Node 0, zone DMA -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.00
Node 0, zone Normal -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.954
Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
Reviewed-by: Minchan Kim <minchan.kim@xxxxxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
Reviewed-by: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmstat.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 84 insertions(+)
diff -puN mm/vmstat.c~mm-export-fragmentation-index-via-debugfs mm/vmstat.c
--- a/mm/vmstat.c~mm-export-fragmentation-index-via-debugfs
+++ a/mm/vmstat.c
@@ -16,6 +16,7 @@
#include <linux/cpu.h>
#include <linux/vmstat.h>
#include <linux/sched.h>
+#include <linux/math64.h>
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -420,6 +421,33 @@ static void fill_contig_page_info(struct
(order - suitable_order);
}
}
+
+/*
+ * A fragmentation index only makes sense if an allocation of a requested
+ * size would fail. If that is true, the fragmentation index indicates
+ * whether external fragmentation or a lack of memory was the problem.
+ * The value can be used to determine if page reclaim or compaction
+ * should be used
+ */
+int fragmentation_index(unsigned int order, struct contig_page_info *info)
+{
+ unsigned long requested = 1UL << order;
+
+ if (!info->free_blocks_total)
+ return 0;
+
+ /* Fragmentation index only makes sense when a request would fail */
+ if (info->free_blocks_suitable)
+ return -1000;
+
+ /*
+ * Index is between 0 and 1 so return within 3 decimal places
+ *
+ * 0 => allocation would fail due to lack of memory
+ * 1 => allocation would fail due to fragmentation
+ */
+ return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
+}
#endif
#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION)
@@ -1087,6 +1115,58 @@ static const struct file_operations unus
.release = seq_release,
};
+static void extfrag_show_print(struct seq_file *m,
+ pg_data_t *pgdat, struct zone *zone)
+{
+ unsigned int order;
+ int index;
+
+ /* Alloc on stack as interrupts are disabled for zone walk */
+ struct contig_page_info info;
+
+ seq_printf(m, "Node %d, zone %8s ",
+ pgdat->node_id,
+ zone->name);
+ for (order = 0; order < MAX_ORDER; ++order) {
+ fill_contig_page_info(zone, order, &info);
+ index = fragmentation_index(order, &info);
+ seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
+ }
+
+ seq_putc(m, '\n');
+}
+
+/*
+ * Display fragmentation index for orders that allocations would fail for
+ */
+static int extfrag_show(struct seq_file *m, void *arg)
+{
+ pg_data_t *pgdat = (pg_data_t *)arg;
+
+ walk_zones_in_node(m, pgdat, extfrag_show_print);
+
+ return 0;
+}
+
+static const struct seq_operations extfrag_op = {
+ .start = frag_start,
+ .next = frag_next,
+ .stop = frag_stop,
+ .show = extfrag_show,
+};
+
+static int extfrag_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &extfrag_op);
+}
+
+static const struct file_operations extfrag_file_ops = {
+ .open = extfrag_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
static int __init extfrag_debug_init(void)
{
extfrag_debug_root = debugfs_create_dir("extfrag", NULL);
@@ -1097,6 +1177,10 @@ static int __init extfrag_debug_init(voi
extfrag_debug_root, NULL, &unusable_file_ops))
return -ENOMEM;
+ if (!debugfs_create_file("extfrag_index", 0444,
+ extfrag_debug_root, NULL, &extfrag_file_ops))
+ return -ENOMEM;
+
return 0;
}
_
Patches currently in -mm which might be from mel@xxxxxxxxx are
linux-next.patch
hugetlb-fix-infinite-loop-in-get_futex_key-when-backed-by-huge-pages.patch
hugetlb-fix-infinite-loop-in-get_futex_key-when-backed-by-huge-pages-fix.patch
hugetlbfs-kill-applications-that-use-map_noreserve-with-sigbus-instead-of-oom-killer.patch
page-allocator-reduce-fragmentation-in-buddy-allocator-by-adding-buddies-that-are-merging-to-the-tail-of-the-free-lists.patch
mempolicy-remove-redundant-code.patch
mm-default-to-node-zonelist-ordering-when-nodes-have-only-lowmem.patch
mmmigration-take-a-reference-to-the-anon_vma-before-migrating.patch
mmmigration-share-the-anon_vma-ref-counts-between-ksm-and-page-migration.patch
mmmigration-do-not-try-to-migrate-unmapped-anonymous-pages.patch
mmmigration-allow-the-migration-of-pageswapcache-pages.patch
mm-allow-config_migration-to-be-set-without-config_numa-or-memory-hot-remove.patch
mm-export-unusable-free-space-index-via-debugfs.patch
mm-export-fragmentation-index-via-debugfs.patch
mm-move-definition-for-lru-isolation-modes-to-a-header.patch
mmcompaction-memory-compaction-core.patch
mmcompaction-add-proc-trigger-for-memory-compaction.patch
mmcompaction-add-sys-trigger-for-per-node-memory-compaction.patch
mmcompaction-direct-compact-when-a-high-order-allocation-fails.patch
mmcompaction-add-a-tunable-that-decides-when-memory-should-be-compacted-and-when-it-should-be-reclaimed.patch
mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails.patch
mm-introduce-free_pages_prepare.patch
mm-introduce-free_pages_prepare-fix.patch
delay-accounting-re-implement-c-for-getdelaysc-to-report-information-on-a-target-command.patch
delay-accounting-re-implement-c-for-getdelaysc-to-report-information-on-a-target-command-checkpatch-fixes.patch
numa-add-generic-percpu-var-numa_node_id-implementation.patch
numa-x86_64-use-generic-percpu-var-numa_node_id-implementation.patch
numa-ia64-use-generic-percpu-var-numa_node_id-implementation.patch
numa-introduce-numa_mem_id-effective-local-memory-node-id.patch
numa-ia64-support-numa_mem_id-for-memoryless-nodes.patch
numa-slab-use-numa_mem_id-for-slab-local-memory-node.patch
numa-in-kernel-profiling-use-cpu_to_mem-for-per-cpu-allocations.patch
numa-update-documentation-vm-numa-add-memoryless-node-info.patch
add-debugging-aid-for-memory-initialisation-problems.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
