Merge branch 'topic/slub-defrag' into for-next

2 files changed, 93 insertions, 14 deletions

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index d79eeda7a699..5e7329a1abcc 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -38,6 +38,7 @@ Currently, these files are in /proc/sys/vm:
 - numa_zonelist_order
 - nr_hugepages
 - nr_overcommit_hugepages
+- slab_defrag_limit
 
 ==============================================================
 
@@ -347,3 +348,14 @@ Change the maximum size of the hugepage pool. The maximum is
 nr_hugepages + nr_overcommit_hugepages.
 
 See Documentation/vm/hugetlbpage.txt
+
+==============================================================
+
+slab_defrag_limit
+
+Determines the frequency of calls from reclaim into slab defragmentation.
+Slab defrag reclaims objects from sparsely populates slab pages.
+The default is 1000. Increase if slab defragmentation occurs
+too frequently. Decrease if more slab defragmentation passes
+are needed. The slabinfo tool can report on the frequency of the callbacks.
+
diff --git a/Documentation/vm/slabinfo.c b/Documentation/vm/slabinfo.c
index df3227605d59..75b56e8fc651 100644
--- a/Documentation/vm/slabinfo.c
+++ b/Documentation/vm/slabinfo.c
@@ -31,6 +31,8 @@ struct slabinfo {
 	int hwcache_align, object_size, objs_per_slab;
 	int sanity_checks, slab_size, store_user, trace;
 	int order, poison, reclaim_account, red_zone;
+	int defrag, ctor;
+	int defrag_ratio, remote_node_defrag_ratio;
 	unsigned long partial, objects, slabs, objects_partial, objects_total;
 	unsigned long alloc_fastpath, alloc_slowpath;
 	unsigned long free_fastpath, free_slowpath;
@@ -39,6 +41,9 @@ struct slabinfo {
 	unsigned long cpuslab_flush, deactivate_full, deactivate_empty;
 	unsigned long deactivate_to_head, deactivate_to_tail;
 	unsigned long deactivate_remote_frees, order_fallback;
+	unsigned long shrink_calls, shrink_attempt_defrag, shrink_empty_slab;
+	unsigned long shrink_slab_skipped, shrink_slab_reclaimed;
+	unsigned long shrink_object_reclaim_failed;
 	int numa[MAX_NODES];
 	int numa_partial[MAX_NODES];
 } slabinfo[MAX_SLABS];
@@ -64,6 +69,8 @@ int show_slab = 0;
 int skip_zero = 1;
 int show_numa = 0;
 int show_track = 0;
+int show_defrag = 0;
+int show_ctor = 0;
 int show_first_alias = 0;
 int validate = 0;
 int shrink = 0;
@@ -75,6 +82,7 @@ int sort_active = 0;
 int set_debug = 0;
 int show_ops = 0;
 int show_activity = 0;
+int show_defragcount = 0;
 
 /* Debug options */
 int sanity = 0;
@@ -100,20 +108,23 @@ void fatal(const char *x, ...)
 void usage(void)
 {
 	printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n"
-		"slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n"
+		"slabinfo [-aCdDefFhnpvtsz] [-d debugopts] [slab-regexp]\n"
 		"-a|--aliases           Show aliases\n"
 		"-A|--activity          Most active slabs first\n"
 		"-d<options>|--debug=<options> Set/Clear Debug options\n"
+		"-C|--ctor              Show slabs with ctors\n"
 		"-D|--display-active    Switch line format to activity\n"
 		"-e|--empty             Show empty slabs\n"
 		"-f|--first-alias       Show first alias\n"
+		"-F|--defrag            Show defragmentable caches\n"
+		"-G|--display-defrag    Display defrag counters\n"
 		"-h|--help              Show usage information\n"
 		"-i|--inverted          Inverted list\n"
 		"-l|--slabs             Show slabs\n"
 		"-n|--numa              Show NUMA information\n"
-		"-o|--ops		Show kmem_cache_ops\n"
+		"-o|--ops               Show kmem_cache_ops\n"
 		"-s|--shrink            Shrink slabs\n"
-		"-r|--report		Detailed report on single slabs\n"
+		"-r|--report            Detailed report on single slabs\n"
 		"-S|--Size              Sort by size\n"
 		"-t|--tracking          Show alloc/free information\n"
 		"-T|--Totals            Show summary information\n"
@@ -294,9 +305,11 @@ void first_line(void)
 {
 	if (show_activity)
 		printf("Name                   Objects      Alloc       Free   %%Fast Fallb O\n");
+	else if (show_defragcount)
+		printf("Name                   Objects DefragRQ  Slabs Success   Empty Skipped  Failed\n");
 	else
 		printf("Name                   Objects Objsize    Space "
-			"Slabs/Part/Cpu  O/S O %%Fr %%Ef Flg\n");
+			"Slabs/Part/Cpu  O/S O %%Ra %%Ef Flg\n");
 }
 
 /*
@@ -345,7 +358,7 @@ void slab_numa(struct slabinfo *s, int mode)
 		return;
 
 	if (!line) {
-		printf("\n%-21s:", mode ? "NUMA nodes" : "Slab");
+		printf("\n%-21s: Rto ", mode ? "NUMA nodes" : "Slab");
 		for(node = 0; node <= highest_node; node++)
 			printf(" %4d", node);
 		printf("\n----------------------");
@@ -354,6 +367,7 @@ void slab_numa(struct slabinfo *s, int mode)
 		printf("\n");
 	}
 	printf("%-21s ", mode ? "All slabs" : s->name);
+	printf("%3d ", s->remote_node_defrag_ratio);
 	for(node = 0; node <= highest_node; node++) {
 		char b[20];
 
@@ -459,22 +473,28 @@ void slab_stats(struct slabinfo *s)
 
 	printf("Total                %8lu %8lu\n\n", total_alloc, total_free);
 
-	if (s->cpuslab_flush)
-		printf("Flushes %8lu\n", s->cpuslab_flush);
-
-	if (s->alloc_refill)
-		printf("Refill %8lu\n", s->alloc_refill);
+	if (s->cpuslab_flush || s->alloc_refill)
+		printf("CPU Slab  : Flushes=%lu Refills=%lu\n",
+			s->cpuslab_flush, s->alloc_refill);
 
 	total = s->deactivate_full + s->deactivate_empty +
 			s->deactivate_to_head + s->deactivate_to_tail;
 
 	if (total)
-		printf("Deactivate Full=%lu(%lu%%) Empty=%lu(%lu%%) "
+		printf("Deactivate: Full=%lu(%lu%%) Empty=%lu(%lu%%) "
 			"ToHead=%lu(%lu%%) ToTail=%lu(%lu%%)\n",
 			s->deactivate_full, (s->deactivate_full * 100) / total,
 			s->deactivate_empty, (s->deactivate_empty * 100) / total,
 			s->deactivate_to_head, (s->deactivate_to_head * 100) / total,
 			s->deactivate_to_tail, (s->deactivate_to_tail * 100) / total);
+
+	if (s->shrink_calls)
+		printf("Shrink    : Calls=%lu Attempts=%lu Empty=%lu Successful=%lu\n",
+			s->shrink_calls, s->shrink_attempt_defrag,
+			s->shrink_empty_slab, s->shrink_slab_reclaimed);
+	if (s->shrink_slab_skipped || s->shrink_object_reclaim_failed)
+		printf("Defrag    : Slabs skipped=%lu Object reclaim failed=%lu\n",
+		s->shrink_slab_skipped, s->shrink_object_reclaim_failed);
 }
 
 void report(struct slabinfo *s)
@@ -492,6 +512,8 @@ void report(struct slabinfo *s)
 		printf("** Slabs are destroyed via RCU\n");
 	if (s->reclaim_account)
 		printf("** Reclaim accounting active\n");
+	if (s->defrag)
+		printf("** Defragmentation at %d%%\n", s->defrag_ratio);
 
 	printf("\nSizes (bytes)     Slabs              Debug                Memory\n");
 	printf("------------------------------------------------------------------------\n");
@@ -539,6 +561,12 @@ void slabcache(struct slabinfo *s)
 	if (show_empty && s->slabs)
 		return;
 
+	if (show_defrag && !s->defrag)
+		return;
+
+	if (show_ctor && !s->ctor)
+		return;
+
 	store_size(size_str, slab_size(s));
 	snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs - s->cpu_slabs,
 						s->partial, s->cpu_slabs);
@@ -550,6 +578,10 @@ void slabcache(struct slabinfo *s)
 		*p++ = '*';
 	if (s->cache_dma)
 		*p++ = 'd';
+	if (s->defrag)
+		*p++ = 'F';
+	if (s->ctor)
+		*p++ = 'C';
 	if (s->hwcache_align)
 		*p++ = 'A';
 	if (s->poison)
@@ -579,12 +611,18 @@ void slabcache(struct slabinfo *s)
 			total_alloc ? (s->alloc_fastpath * 100 / total_alloc) : 0,
 			total_free ? (s->free_fastpath * 100 / total_free) : 0,
 			s->order_fallback, s->order);
-	}
+	} else
+	if (show_defragcount)
+		printf("%-21s %8ld %7lu %7lu %7lu %7lu %7lu %7lu\n",
+			s->name, s->objects, s->shrink_calls, s->shrink_attempt_defrag,
+			s->shrink_slab_reclaimed, s->shrink_empty_slab,
+			s->shrink_slab_skipped, s->shrink_object_reclaim_failed);
 	else
 		printf("%-21s %8ld %7d %8s %14s %4d %1d %3ld %3ld %s\n",
 			s->name, s->objects, s->object_size, size_str, dist_str,
 			s->objs_per_slab, s->order,
-			s->slabs ? (s->partial * 100) / s->slabs : 100,
+			s->slabs ? (s->partial * 100) /
+					(s->slabs * s->objs_per_slab) : 100,
 			s->slabs ? (s->objects * s->object_size * 100) /
 				(s->slabs * (page_size << s->order)) : 100,
 			flags);
@@ -1190,7 +1228,24 @@ void read_slab_dir(void)
 			slab->deactivate_to_tail = get_obj("deactivate_to_tail");
 			slab->deactivate_remote_frees = get_obj("deactivate_remote_frees");
 			slab->order_fallback = get_obj("order_fallback");
+			slab->shrink_calls = get_obj("shrink_calls");
+			slab->shrink_attempt_defrag = get_obj("shrink_attempt_defrag");
+			slab->shrink_empty_slab = get_obj("shrink_empty_slab");
+			slab->shrink_slab_skipped = get_obj("shrink_slab_skipped");
+			slab->shrink_slab_reclaimed = get_obj("shrink_slab_reclaimed");
+			slab->shrink_object_reclaim_failed =
+					get_obj("shrink_object_reclaim_failed");
+			slab->defrag_ratio = get_obj("defrag_ratio");
+			slab->remote_node_defrag_ratio =
+					get_obj("remote_node_defrag_ratio");
 			chdir("..");
+			if (read_slab_obj(slab, "ops")) {
+				if (strstr(buffer, "ctor :"))
+					slab->ctor = 1;
+				if (strstr(buffer, "kick :"))
+					slab->defrag = 1;
+			}
+
 			if (slab->name[0] == ':')
 				alias_targets++;
 			slab++;
@@ -1241,10 +1296,13 @@ void output_slabs(void)
 struct option opts[] = {
 	{ "aliases", 0, NULL, 'a' },
 	{ "activity", 0, NULL, 'A' },
+	{ "ctor", 0, NULL, 'C' },
 	{ "debug", 2, NULL, 'd' },
 	{ "display-activity", 0, NULL, 'D' },
+	{ "display-defrag", 0, NULL, 'G' },
 	{ "empty", 0, NULL, 'e' },
 	{ "first-alias", 0, NULL, 'f' },
+	{ "defrag", 0, NULL, 'F' },
 	{ "help", 0, NULL, 'h' },
 	{ "inverted", 0, NULL, 'i'},
 	{ "numa", 0, NULL, 'n' },
@@ -1267,7 +1325,7 @@ int main(int argc, char *argv[])
 
 	page_size = getpagesize();
 
-	while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTS",
+	while ((c = getopt_long(argc, argv, "aACd::DefFGhil1noprstvzTS",
 						opts, NULL)) != -1)
 		switch (c) {
 		case '1':
@@ -1293,6 +1351,9 @@ int main(int argc, char *argv[])
 		case 'f':
 			show_first_alias = 1;
 			break;
+		case 'G':
+			show_defragcount = 1;
+			break;
 		case 'h':
 			usage();
 			return 0;
@@ -1323,6 +1384,12 @@ int main(int argc, char *argv[])
 		case 'z':
 			skip_zero = 0;
 			break;
+		case 'C':
+			show_ctor = 1;
+			break;
+		case 'F':
+			show_defrag = 1;
+			break;
 		case 'T':
 			show_totals = 1;
 			break;