[PATCH 3/4] mm: Centralize & improve oom reporting in show_mem.c

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This patch:
 - Moves lib/show_mem.c to mm/show_mem.c
 - Changes show_mem() to always report on slab usage
 - Instead of reporting on all slabs, we only report on top 10 slabs,
   and in sorted order
 - Also reports on shrinkers, with the new shrinkers_to_text().

More OOM reporting can be moved to show_mem.c and improved, this patch
is only a small start.

Signed-off-by: Kent Overstreet <kent.overstreet@xxxxxxxxx>
---
 lib/Makefile           |  2 +-
 mm/Makefile            |  2 +-
 mm/oom_kill.c          | 23 ------------------
 {lib => mm}/show_mem.c | 14 +++++++++++
 mm/slab.h              |  6 +++--
 mm/slab_common.c       | 53 +++++++++++++++++++++++++++++++++++-------
 6 files changed, 65 insertions(+), 35 deletions(-)
 rename {lib => mm}/show_mem.c (78%)

diff --git a/lib/Makefile b/lib/Makefile
index 31a3904eda..c5041d33d0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -30,7 +30,7 @@ endif
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o extable.o sha1.o irq_regs.o argv_split.o \
-	 flex_proportions.o ratelimit.o show_mem.o \
+	 flex_proportions.o ratelimit.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
 	 nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o \
diff --git a/mm/Makefile b/mm/Makefile
index 70d4309c9c..97c0be12f3 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -54,7 +54,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   mm_init.o percpu.o slab_common.o \
 			   compaction.o vmacache.o \
 			   interval_tree.o list_lru.o workingset.o \
-			   debug.o gup.o mmap_lock.o $(mmu-y)
+			   debug.o gup.o mmap_lock.o show_mem.o $(mmu-y)
 
 # Give 'page_alloc' its own module-parameter namespace
 page-alloc-y := page_alloc.o
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 832fb33037..659c7d6376 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -171,27 +171,6 @@ static bool oom_unkillable_task(struct task_struct *p)
 	return false;
 }
 
-/*
- * Check whether unreclaimable slab amount is greater than
- * all user memory(LRU pages).
- * dump_unreclaimable_slab() could help in the case that
- * oom due to too much unreclaimable slab used by kernel.
-*/
-static bool should_dump_unreclaim_slab(void)
-{
-	unsigned long nr_lru;
-
-	nr_lru = global_node_page_state(NR_ACTIVE_ANON) +
-		 global_node_page_state(NR_INACTIVE_ANON) +
-		 global_node_page_state(NR_ACTIVE_FILE) +
-		 global_node_page_state(NR_INACTIVE_FILE) +
-		 global_node_page_state(NR_ISOLATED_ANON) +
-		 global_node_page_state(NR_ISOLATED_FILE) +
-		 global_node_page_state(NR_UNEVICTABLE);
-
-	return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru);
-}
-
 /**
  * oom_badness - heuristic function to determine which candidate task to kill
  * @p: task struct of which task we should calculate
@@ -465,8 +444,6 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 		mem_cgroup_print_oom_meminfo(oc->memcg);
 	else {
 		show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask);
-		if (should_dump_unreclaim_slab())
-			dump_unreclaimable_slab();
 	}
 	if (sysctl_oom_dump_tasks)
 		dump_tasks(oc);
diff --git a/lib/show_mem.c b/mm/show_mem.c
similarity index 78%
rename from lib/show_mem.c
rename to mm/show_mem.c
index 1c26c14ffb..c9f37f13d6 100644
--- a/lib/show_mem.c
+++ b/mm/show_mem.c
@@ -7,11 +7,15 @@
 
 #include <linux/mm.h>
 #include <linux/cma.h>
+#include <linux/printbuf.h>
+
+#include "slab.h"
 
 void show_mem(unsigned int filter, nodemask_t *nodemask)
 {
 	pg_data_t *pgdat;
 	unsigned long total = 0, reserved = 0, highmem = 0;
+	struct printbuf buf = PRINTBUF;
 
 	printk("Mem-Info:\n");
 	show_free_areas(filter, nodemask);
@@ -41,4 +45,14 @@ void show_mem(unsigned int filter, nodemask_t *nodemask)
 #ifdef CONFIG_MEMORY_FAILURE
 	printk("%lu pages hwpoisoned\n", atomic_long_read(&num_poisoned_pages));
 #endif
+
+	pr_info("Unreclaimable slab info:\n");
+	dump_unreclaimable_slab(&buf);
+	printk("%s", buf.buf);
+	printbuf_reset(&buf);
+
+	printk("Shrinkers:\n");
+	shrinkers_to_text(&buf);
+	printk("%s", buf.buf);
+	printbuf_exit(&buf);
 }
diff --git a/mm/slab.h b/mm/slab.h
index c7f2abc2b1..abefbf7674 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -788,10 +788,12 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 
 #endif
 
+struct printbuf;
+
 #if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
-void dump_unreclaimable_slab(void);
+void dump_unreclaimable_slab(struct printbuf *);
 #else
-static inline void dump_unreclaimable_slab(void)
+static inline void dump_unreclaimable_slab(struct printbuf *out)
 {
 }
 #endif
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 23f2ab0713..cb1c548c73 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -24,6 +24,7 @@
 #include <asm/tlbflush.h>
 #include <asm/page.h>
 #include <linux/memcontrol.h>
+#include <linux/printbuf.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/kmem.h>
@@ -1084,10 +1085,15 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-void dump_unreclaimable_slab(void)
+void dump_unreclaimable_slab(struct printbuf *out)
 {
 	struct kmem_cache *s;
 	struct slabinfo sinfo;
+	struct slab_by_mem {
+		struct kmem_cache *s;
+		size_t total, active;
+	} slabs_by_mem[10], n;
+	int i, nr = 0;
 
 	/*
 	 * Here acquiring slab_mutex is risky since we don't prefer to get
@@ -1097,12 +1103,11 @@ void dump_unreclaimable_slab(void)
 	 * without acquiring the mutex.
 	 */
 	if (!mutex_trylock(&slab_mutex)) {
-		pr_warn("excessive unreclaimable slab but cannot dump stats\n");
+		pr_buf(out, "excessive unreclaimable slab but cannot dump stats\n");
 		return;
 	}
 
-	pr_info("Unreclaimable slab info:\n");
-	pr_info("Name                      Used          Total\n");
+	buf->atomic++;
 
 	list_for_each_entry(s, &slab_caches, list) {
 		if (s->flags & SLAB_RECLAIM_ACCOUNT)
@@ -1110,11 +1115,43 @@ void dump_unreclaimable_slab(void)
 
 		get_slabinfo(s, &sinfo);
 
-		if (sinfo.num_objs > 0)
-			pr_info("%-17s %10luKB %10luKB\n", s->name,
-				(sinfo.active_objs * s->size) / 1024,
-				(sinfo.num_objs * s->size) / 1024);
+		if (!sinfo.num_objs)
+			continue;
+
+		n.s = s;
+		n.total = sinfo.num_objs * s->size;
+		n.active = sinfo.active_objs * s->size;
+
+		for (i = 0; i < nr; i++)
+			if (n.total < slabs_by_mem[i].total)
+				break;
+
+		if (nr < ARRAY_SIZE(slabs_by_mem)) {
+			memmove(&slabs_by_mem[i + 1],
+				&slabs_by_mem[i],
+				sizeof(slabs_by_mem[0]) * (nr - i));
+			nr++;
+		} else if (i) {
+			i--;
+			memmove(&slabs_by_mem[0],
+				&slabs_by_mem[1],
+				sizeof(slabs_by_mem[0]) * i);
+		} else {
+			continue;
+		}
+
+		slabs_by_mem[i] = n;
+	}
+
+	for (i = nr - 1; i >= 0; --i) {
+		pr_buf(out, "%-17s total: ", slabs_by_mem[i].s->name);
+		pr_human_readable_u64(out, slabs_by_mem[i].total);
+		pr_buf(out, " active: ");
+		pr_human_readable_u64(out, slabs_by_mem[i].active);
+		pr_newline(out);
 	}
+
+	--buf->atomic;
 	mutex_unlock(&slab_mutex);
 }
 
-- 
2.35.2




[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [NTFS 3]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [NTFS 3]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux