[RFC v3] oom: capture unreclaimable slab info in oom message when kernel panic

[RFC v3] oom: capture unreclaimable slab info in oom message when kernel panic

[Yang Shi]

Recently we ran into a oom issue, kernel panic due to no killable process.
The dmesg shows huge unreclaimable slabs used almost 100% memory, but kdump doesn't capture vmcore due to some reason.

So, it may sound better to capture unreclaimable slab info in oom message when kernel panic to aid trouble shooting and cover the corner case.
Since kernel already panic, so capturing more information sounds worthy and doesn't bother normal oom killer.

With the patchset, tools/vm/slabinfo has a new option, "-U", to show unreclaimable slab only.

And, oom will print all non zero (num_objs * size != 0) unreclaimable slabs in oom killer message.

For details, please see the commit log for each commit.

Changelog v2 a??> v3:
* Show used size and total size of each kmem cache per Davida??s comment

Changelog v1 a??> v2:
* Removed the original patch 1 (a??mm: slab: output reclaimable flag in /proc/slabinfoa??) since Christoph suggested it might break the compatibility and /proc/slabinfo is legacy
* Added Christopha??s Acked-by
* Removed acquiring slab_mutex per Tetsuoa??s comment


Yang Shi (2):
      tools: slabinfo: add "-U" option to show unreclaimable slabs only
      mm: oom: show unreclaimable slab info when kernel panic

 mm/oom_kill.c       | 13 +++++++++++--
 mm/slab.c           |  1 +
 mm/slab.h           |  7 +++++++
 mm/slab_common.c    | 31 +++++++++++++++++++++++++++++++
 mm/slub.c           |  1 +
 tools/vm/slabinfo.c | 11 ++++++++++-
 6 files changed, 61 insertions(+), 3 deletions(-)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 1/2] tools: slabinfo: add "-U" option to show unreclaimable slabs only

[Yang Shi]

Add "-U" option to show unreclaimable slabs only.

"-U" and "-S" together can tell us what unreclaimable slabs use the most
memory to help debug huge unreclaimable slabs issue.

Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
Acked-by: Christoph Lameter <cl@linux.com>
---
 tools/vm/slabinfo.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index b9d34b3..9673190 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -83,6 +83,7 @@ struct aliasinfo {
 int sort_loss;
 int extended_totals;
 int show_bytes;
+int unreclaim_only;
 
 /* Debug options */
 int sanity;
@@ -132,6 +133,7 @@ static void usage(void)
 		"-L|--Loss              Sort by loss\n"
 		"-X|--Xtotals           Show extended summary information\n"
 		"-B|--Bytes             Show size in bytes\n"
+		"-U|--unreclaim		Show unreclaimable slabs only\n"
 		"\nValid debug options (FZPUT may be combined)\n"
 		"a / A          Switch on all debug options (=FZUP)\n"
 		"-              Switch off all debug options\n"
@@ -568,6 +570,9 @@ static void slabcache(struct slabinfo *s)
 	if (strcmp(s->name, "*") == 0)
 		return;
 
+	if (unreclaim_only && s->reclaim_account)
+		return;
+		
 	if (actual_slabs == 1) {
 		report(s);
 		return;
@@ -1346,6 +1351,7 @@ struct option opts[] = {
 	{ "Loss", no_argument, NULL, 'L'},
 	{ "Xtotals", no_argument, NULL, 'X'},
 	{ "Bytes", no_argument, NULL, 'B'},
+	{ "unreclaim", no_argument, NULL, 'U'},
 	{ NULL, 0, NULL, 0 }
 };
 
@@ -1357,7 +1363,7 @@ int main(int argc, char *argv[])
 
 	page_size = getpagesize();
 
-	while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXB",
+	while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXBU",
 						opts, NULL)) != -1)
 		switch (c) {
 		case '1':
@@ -1438,6 +1444,9 @@ int main(int argc, char *argv[])
 		case 'B':
 			show_bytes = 1;
 			break;
+		case 'U':
+			unreclaim_only = 1;
+			break;
 		default:
 			fatal("%s: Invalid option '%c'\n", argv[0], optopt);
 
-- 
1.8.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

Kernel may panic when oom happens without killable process sometimes it
is caused by huge unreclaimable slabs used by kernel.

Altough kdump could help debug such problem, however, kdump is not
available on all architectures and it might be malfunction sometime.
And, since kernel already panic it is worthy capturing such information
in dmesg to aid touble shooting.

Add a field in struct slibinfo to show if this slab is reclaimable or
not, and a helper function to achieve the value from
SLAB_RECLAIM_ACCOUNT flag.

Print out unreclaimable slab info (used size and total size) which actual
memory usage is not zero (num_objs * size != 0) when panic_on_oom is set or
no killable process. Since such information is just showed when kernel panic,
so it will not lead too verbose message for normal oom.

The output looks like:

Unreclaimable slab info:
Name                      Used          Total
rpc_buffers               31KB         31KB
rpc_tasks                  7KB          7KB
ebitmap_node            1964KB       1964KB
avtab_node              5024KB       5024KB
xfs_buf                 1402KB       1402KB
xfs_ili                  134KB        134KB
xfs_efi_item             115KB        115KB
xfs_efd_item             115KB        115KB
xfs_buf_item             134KB        134KB
xfs_log_item_desc        342KB        342KB
xfs_trans               1412KB       1412KB
xfs_ifork                212KB        212KB

Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
---
 mm/oom_kill.c    | 13 +++++++++++--
 mm/slab.c        |  1 +
 mm/slab.h        |  7 +++++++
 mm/slab_common.c | 31 +++++++++++++++++++++++++++++++
 mm/slub.c        |  1 +
 5 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e0..173c423 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -43,6 +43,7 @@
 
 #include <asm/tlb.h>
 #include "internal.h"
+#include "slab.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -427,6 +428,14 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 		dump_tasks(oc->memcg, oc->nodemask);
 }
 
+static void dump_header_with_slabinfo(struct oom_control *oc, struct task_struct *p)
+{
+	dump_header(oc, p);
+
+	if (IS_ENABLED(CONFIG_SLABINFO))
+		show_unreclaimable_slab();
+}
+
 /*
  * Number of OOM victims in flight
  */
@@ -959,7 +968,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 	/* Do not panic for oom kills triggered by sysrq */
 	if (is_sysrq_oom(oc))
 		return;
-	dump_header(oc, NULL);
+	dump_header_with_slabinfo(oc, NULL);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
@@ -1043,7 +1052,7 @@ bool out_of_memory(struct oom_control *oc)
 	select_bad_process(oc);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
-		dump_header(oc, NULL);
+		dump_header_with_slabinfo(oc, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL) {
diff --git a/mm/slab.c b/mm/slab.c
index 04dec48..4f4971c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4132,6 +4132,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 	sinfo->shared = cachep->shared;
 	sinfo->objects_per_slab = cachep->num;
 	sinfo->cache_order = cachep->gfporder;
+	sinfo->reclaim = is_reclaimable(cachep);
 }
 
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
diff --git a/mm/slab.h b/mm/slab.h
index 0733628..2f1ebce 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -186,6 +186,7 @@ struct slabinfo {
 	unsigned int shared;
 	unsigned int objects_per_slab;
 	unsigned int cache_order;
+	unsigned int reclaim;
 };
 
 void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
@@ -352,6 +353,11 @@ static inline void memcg_link_cache(struct kmem_cache *s)
 
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
+static inline bool is_reclaimable(struct kmem_cache *s)
+{
+	return (s->flags & SLAB_RECLAIM_ACCOUNT) ? true : false;
+}
+
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {
 	struct kmem_cache *cachep;
@@ -504,6 +510,7 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
 void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
+void show_unreclaimable_slab(void);
 
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83b..f2c6200 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -35,6 +35,8 @@
 static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
 		    slab_caches_to_rcu_destroy_workfn);
 
+#define K(x) ((x)/1024)
+
 /*
  * Set of flags that will prevent slab merging
  */
@@ -1272,6 +1274,35 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+void show_unreclaimable_slab()
+{
+	struct kmem_cache *s = NULL;
+	struct slabinfo sinfo;
+
+	memset(&sinfo, 0, sizeof(sinfo));
+
+	printk("Unreclaimable slab info:\n");
+	printk("Name                      Used          Total\n");
+
+	/*
+	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
+	 * get sleep in oom path right before kernel panic, and avoid race condition.
+	 * Since it is already oom, so there should be not any big allocation
+	 * which could change the statistics significantly.
+	 */
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		get_slabinfo(s, &sinfo);
+
+		if (!is_reclaimable(s) && sinfo.num_objs > 0)
+			printk("%-17s %10luKB %10luKB\n", cache_name(s), K(sinfo.active_objs * s->size), K(sinfo.num_objs * s->size));
+	}
+}
+EXPORT_SYMBOL(show_unreclaimable_slab);
+#undef K
+
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 void *memcg_slab_start(struct seq_file *m, loff_t *pos)
 {
diff --git a/mm/slub.c b/mm/slub.c
index 163352c..5c17c0a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5872,6 +5872,7 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 	sinfo->num_slabs = nr_slabs;
 	sinfo->objects_per_slab = oo_objects(s->oo);
 	sinfo->cache_order = oo_order(s->oo);
+	sinfo->reclaim = is_reclaimable(s);
 }
 
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)
-- 
1.8.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 1/2] tools: slabinfo: add "-U" option to show unreclaimable slabs only

[David Rientjes]

On Thu, 21 Sep 2017, Yang Shi wrote:

> diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
> index b9d34b3..9673190 100644
> --- a/tools/vm/slabinfo.c
> +++ b/tools/vm/slabinfo.c
> @@ -83,6 +83,7 @@ struct aliasinfo {
>  int sort_loss;
>  int extended_totals;
>  int show_bytes;
> +int unreclaim_only;
>  
>  /* Debug options */
>  int sanity;
> @@ -132,6 +133,7 @@ static void usage(void)
>  		"-L|--Loss              Sort by loss\n"
>  		"-X|--Xtotals           Show extended summary information\n"
>  		"-B|--Bytes             Show size in bytes\n"
> +		"-U|--unreclaim		Show unreclaimable slabs only\n"
>  		"\nValid debug options (FZPUT may be combined)\n"
>  		"a / A          Switch on all debug options (=FZUP)\n"
>  		"-              Switch off all debug options\n"

I suppose this should be s/unreclaim/Unreclaim/

> @@ -568,6 +570,9 @@ static void slabcache(struct slabinfo *s)
>  	if (strcmp(s->name, "*") == 0)
>  		return;
>  
> +	if (unreclaim_only && s->reclaim_account)
> +		return;
> +		
>  	if (actual_slabs == 1) {
>  		report(s);
>  		return;
> @@ -1346,6 +1351,7 @@ struct option opts[] = {
>  	{ "Loss", no_argument, NULL, 'L'},
>  	{ "Xtotals", no_argument, NULL, 'X'},
>  	{ "Bytes", no_argument, NULL, 'B'},
> +	{ "unreclaim", no_argument, NULL, 'U'},
>  	{ NULL, 0, NULL, 0 }
>  };
>  

Same.

After that:

Acked-by: David Rientjes <rientjes@google.com>

Also, you may find it better to remove the "RFC" tag from the patchset's 
header email since it's agreed that we want this.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[David Rientjes]

On Thu, 21 Sep 2017, Yang Shi wrote:

> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 99736e0..173c423 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -43,6 +43,7 @@
>  
>  #include <asm/tlb.h>
>  #include "internal.h"
> +#include "slab.h"
>  
>  #define CREATE_TRACE_POINTS
>  #include <trace/events/oom.h>
> @@ -427,6 +428,14 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
>  		dump_tasks(oc->memcg, oc->nodemask);
>  }
>  
> +static void dump_header_with_slabinfo(struct oom_control *oc, struct task_struct *p)
> +{
> +	dump_header(oc, p);
> +
> +	if (IS_ENABLED(CONFIG_SLABINFO))
> +		show_unreclaimable_slab();
> +}
> +
>  /*
>   * Number of OOM victims in flight
>   */

I don't think we need a new function for this.  Where you want to dump 
unreclaimable slab before panic, just call a new dump_unreclaimable_slab() 
function that gets declared in slab.h that is a no-op when CONFIG_SLABINFO 
is disabled.  We just want to do

	dump_header(...);
	dump_unreclaimable_slab(...);
	panic(...);

> diff --git a/mm/slab.c b/mm/slab.c
> index 04dec48..4f4971c 100644
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -4132,6 +4132,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
>  	sinfo->shared = cachep->shared;
>  	sinfo->objects_per_slab = cachep->num;
>  	sinfo->cache_order = cachep->gfporder;
> +	sinfo->reclaim = is_reclaimable(cachep);

We don't need a new field, we already have cachep->flags accessible.

>  }
>  
>  void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
> diff --git a/mm/slab.h b/mm/slab.h
> index 0733628..2f1ebce 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -186,6 +186,7 @@ struct slabinfo {
>  	unsigned int shared;
>  	unsigned int objects_per_slab;
>  	unsigned int cache_order;
> +	unsigned int reclaim;

Not needed.

>  };
>  
>  void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
> @@ -352,6 +353,11 @@ static inline void memcg_link_cache(struct kmem_cache *s)
>  
>  #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
>  
> +static inline bool is_reclaimable(struct kmem_cache *s)
> +{
> +	return (s->flags & SLAB_RECLAIM_ACCOUNT) ? true : false;
> +}
> +

I don't think we need this.

>  static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
>  {
>  	struct kmem_cache *cachep;
> @@ -504,6 +510,7 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
>  void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
>  void memcg_slab_stop(struct seq_file *m, void *p);
>  int memcg_slab_show(struct seq_file *m, void *p);
> +void show_unreclaimable_slab(void);
>  
>  void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
>  
> diff --git a/mm/slab_common.c b/mm/slab_common.c
> index 904a83b..f2c6200 100644
> --- a/mm/slab_common.c
> +++ b/mm/slab_common.c
> @@ -35,6 +35,8 @@
>  static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
>  		    slab_caches_to_rcu_destroy_workfn);
>  
> +#define K(x) ((x)/1024)
> +

I don't think we need this.

>  /*
>   * Set of flags that will prevent slab merging
>   */
> @@ -1272,6 +1274,35 @@ static int slab_show(struct seq_file *m, void *p)
>  	return 0;
>  }
>  
> +void show_unreclaimable_slab()

void show_unreclaimable_slab(void)

> +{
> +	struct kmem_cache *s = NULL;

No initialization needed.

> +	struct slabinfo sinfo;
> +
> +	memset(&sinfo, 0, sizeof(sinfo));
> +
> +	printk("Unreclaimable slab info:\n");
> +	printk("Name                      Used          Total\n");
> +
> +	/*
> +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
> +	 * get sleep in oom path right before kernel panic, and avoid race condition.
> +	 * Since it is already oom, so there should be not any big allocation
> +	 * which could change the statistics significantly.
> +	 */
> +	list_for_each_entry(s, &slab_caches, list) {
> +		if (!is_root_cache(s))
> +			continue;
> +

We need to do the memset() here.

> +		get_slabinfo(s, &sinfo);
> +
> +		if (!is_reclaimable(s) && sinfo.num_objs > 0)
> +			printk("%-17s %10luKB %10luKB\n", cache_name(s), K(sinfo.active_objs * s->size), K(sinfo.num_objs * s->size));

I think you can just check for SLAB_RECLAIM_ACCOUNT here.

Everything in this function should be pr_info().

> +	}
> +}
> +EXPORT_SYMBOL(show_unreclaimable_slab);
> +#undef K
> +
>  #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
>  void *memcg_slab_start(struct seq_file *m, loff_t *pos)
>  {
> diff --git a/mm/slub.c b/mm/slub.c
> index 163352c..5c17c0a 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -5872,6 +5872,7 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
>  	sinfo->num_slabs = nr_slabs;
>  	sinfo->objects_per_slab = oo_objects(s->oo);
>  	sinfo->cache_order = oo_order(s->oo);
> +	sinfo->reclaim = is_reclaimable(s);

Not needed.

>  }
>  
>  void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 1/2] tools: slabinfo: add "-U" option to show unreclaimable slabs only

[Yang Shi]

On 9/20/17 1:45 PM, David Rientjes wrote:
> On Thu, 21 Sep 2017, Yang Shi wrote:
> 
>> diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
>> index b9d34b3..9673190 100644
>> --- a/tools/vm/slabinfo.c
>> +++ b/tools/vm/slabinfo.c
>> @@ -83,6 +83,7 @@ struct aliasinfo {
>>   int sort_loss;
>>   int extended_totals;
>>   int show_bytes;
>> +int unreclaim_only;
>>   
>>   /* Debug options */
>>   int sanity;
>> @@ -132,6 +133,7 @@ static void usage(void)
>>   		"-L|--Loss              Sort by loss\n"
>>   		"-X|--Xtotals           Show extended summary information\n"
>>   		"-B|--Bytes             Show size in bytes\n"
>> +		"-U|--unreclaim		Show unreclaimable slabs only\n"
>>   		"\nValid debug options (FZPUT may be combined)\n"
>>   		"a / A          Switch on all debug options (=FZUP)\n"
>>   		"-              Switch off all debug options\n"
> 
> I suppose this should be s/unreclaim/Unreclaim/
> 
>> @@ -568,6 +570,9 @@ static void slabcache(struct slabinfo *s)
>>   	if (strcmp(s->name, "*") == 0)
>>   		return;
>>   
>> +	if (unreclaim_only && s->reclaim_account)
>> +		return;
>> +		
>>   	if (actual_slabs == 1) {
>>   		report(s);
>>   		return;
>> @@ -1346,6 +1351,7 @@ struct option opts[] = {
>>   	{ "Loss", no_argument, NULL, 'L'},
>>   	{ "Xtotals", no_argument, NULL, 'X'},
>>   	{ "Bytes", no_argument, NULL, 'B'},
>> +	{ "unreclaim", no_argument, NULL, 'U'},
>>   	{ NULL, 0, NULL, 0 }
>>   };
>>   
> 
> Same.
> 
> After that:
> 
> Acked-by: David Rientjes <rientjes@google.com>
> 
> Also, you may find it better to remove the "RFC" tag from the patchset's
> header email since it's agreed that we want this.

Thanks, will get fixed in v4.

Yang

> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

On 9/20/17 2:00 PM, David Rientjes wrote:
> On Thu, 21 Sep 2017, Yang Shi wrote:
> 
>> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
>> index 99736e0..173c423 100644
>> --- a/mm/oom_kill.c
>> +++ b/mm/oom_kill.c
>> @@ -43,6 +43,7 @@
>>   
>>   #include <asm/tlb.h>
>>   #include "internal.h"
>> +#include "slab.h"
>>   
>>   #define CREATE_TRACE_POINTS
>>   #include <trace/events/oom.h>
>> @@ -427,6 +428,14 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
>>   		dump_tasks(oc->memcg, oc->nodemask);
>>   }
>>   
>> +static void dump_header_with_slabinfo(struct oom_control *oc, struct task_struct *p)
>> +{
>> +	dump_header(oc, p);
>> +
>> +	if (IS_ENABLED(CONFIG_SLABINFO))
>> +		show_unreclaimable_slab();
>> +}
>> +
>>   /*
>>    * Number of OOM victims in flight
>>    */
> 
> I don't think we need a new function for this.  Where you want to dump
> unreclaimable slab before panic, just call a new dump_unreclaimable_slab()
> function that gets declared in slab.h that is a no-op when CONFIG_SLABINFO
> is disabled.  We just want to do
> 
> 	dump_header(...);
> 	dump_unreclaimable_slab(...);
> 	panic(...);

Thanks for the comment, they will be solved in v4.

Yang

> 
>> diff --git a/mm/slab.c b/mm/slab.c
>> index 04dec48..4f4971c 100644
>> --- a/mm/slab.c
>> +++ b/mm/slab.c
>> @@ -4132,6 +4132,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
>>   	sinfo->shared = cachep->shared;
>>   	sinfo->objects_per_slab = cachep->num;
>>   	sinfo->cache_order = cachep->gfporder;
>> +	sinfo->reclaim = is_reclaimable(cachep);
> 
> We don't need a new field, we already have cachep->flags accessible.
> 
>>   }
>>   
>>   void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
>> diff --git a/mm/slab.h b/mm/slab.h
>> index 0733628..2f1ebce 100644
>> --- a/mm/slab.h
>> +++ b/mm/slab.h
>> @@ -186,6 +186,7 @@ struct slabinfo {
>>   	unsigned int shared;
>>   	unsigned int objects_per_slab;
>>   	unsigned int cache_order;
>> +	unsigned int reclaim;
> 
> Not needed.
> 
>>   };
>>   
>>   void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
>> @@ -352,6 +353,11 @@ static inline void memcg_link_cache(struct kmem_cache *s)
>>   
>>   #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
>>   
>> +static inline bool is_reclaimable(struct kmem_cache *s)
>> +{
>> +	return (s->flags & SLAB_RECLAIM_ACCOUNT) ? true : false;
>> +}
>> +
> 
> I don't think we need this.
> 
>>   static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
>>   {
>>   	struct kmem_cache *cachep;
>> @@ -504,6 +510,7 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
>>   void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
>>   void memcg_slab_stop(struct seq_file *m, void *p);
>>   int memcg_slab_show(struct seq_file *m, void *p);
>> +void show_unreclaimable_slab(void);
>>   
>>   void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
>>   
>> diff --git a/mm/slab_common.c b/mm/slab_common.c
>> index 904a83b..f2c6200 100644
>> --- a/mm/slab_common.c
>> +++ b/mm/slab_common.c
>> @@ -35,6 +35,8 @@
>>   static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
>>   		    slab_caches_to_rcu_destroy_workfn);
>>   
>> +#define K(x) ((x)/1024)
>> +
> 
> I don't think we need this.
> 
>>   /*
>>    * Set of flags that will prevent slab merging
>>    */
>> @@ -1272,6 +1274,35 @@ static int slab_show(struct seq_file *m, void *p)
>>   	return 0;
>>   }
>>   
>> +void show_unreclaimable_slab()
> 
> void show_unreclaimable_slab(void)
> 
>> +{
>> +	struct kmem_cache *s = NULL;
> 
> No initialization needed.
> 
>> +	struct slabinfo sinfo;
>> +
>> +	memset(&sinfo, 0, sizeof(sinfo));
>> +
>> +	printk("Unreclaimable slab info:\n");
>> +	printk("Name                      Used          Total\n");
>> +
>> +	/*
>> +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
>> +	 * get sleep in oom path right before kernel panic, and avoid race condition.
>> +	 * Since it is already oom, so there should be not any big allocation
>> +	 * which could change the statistics significantly.
>> +	 */
>> +	list_for_each_entry(s, &slab_caches, list) {
>> +		if (!is_root_cache(s))
>> +			continue;
>> +
> 
> We need to do the memset() here.
> 
>> +		get_slabinfo(s, &sinfo);
>> +
>> +		if (!is_reclaimable(s) && sinfo.num_objs > 0)
>> +			printk("%-17s %10luKB %10luKB\n", cache_name(s), K(sinfo.active_objs * s->size), K(sinfo.num_objs * s->size));
> 
> I think you can just check for SLAB_RECLAIM_ACCOUNT here.
> 
> Everything in this function should be pr_info().
> 
>> +	}
>> +}
>> +EXPORT_SYMBOL(show_unreclaimable_slab);
>> +#undef K
>> +
>>   #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
>>   void *memcg_slab_start(struct seq_file *m, loff_t *pos)
>>   {
>> diff --git a/mm/slub.c b/mm/slub.c
>> index 163352c..5c17c0a 100644
>> --- a/mm/slub.c
>> +++ b/mm/slub.c
>> @@ -5872,6 +5872,7 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
>>   	sinfo->num_slabs = nr_slabs;
>>   	sinfo->objects_per_slab = oo_objects(s->oo);
>>   	sinfo->cache_order = oo_order(s->oo);
>> +	sinfo->reclaim = is_reclaimable(s);
> 
> Not needed.
> 
>>   }
>>   
>>   void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Qixuan Wu]

On Sat, Sep 23, 2017, Yang Shi <yang.s@alibaba-inc.com> wrote：
>
> Kernel may panic when oom happens without killable process sometimes it
> is caused by huge unreclaimable slabs used by kernel.
>
> Although kdump could help debug such problem, however, kdump is not
> available on all architectures and it might be malfunction sometime.
> And, since kernel already panic it is worthy capturing such information
> in dmesg to aid touble shooting.
......

> +void dump_unreclaimable_slab(void)
> +{
> +       struct kmem_cache *s, *s2;
> +       struct slabinfo sinfo;
> +
> +       pr_info("Unreclaimable slab info:\n");
> +       pr_info("Name                      Used          Total\n");
> +
> +       /*
> +        * Here acquiring slab_mutex is unnecessary since we don't prefer to
> +        * get sleep in oom path right before kernel panic, and avoid race
> +        * condition.
> +        * Since it is already oom, so there should be not any big allocation
> +        * which could change the statistics significantly.
> +        */
> +       list_for_each_entry_safe(s, s2, &slab_caches, list) {
> +               if (!is_root_cache(s) || (s->flags & SLAB_RECLAIM_ACCOUNT))
> +                       continue;
> +
> +               memset(&sinfo, 0, sizeof(sinfo));
> +               get_slabinfo(s, &sinfo);
> +
> +               if (sinfo.num_objs > 0)
> +                       pr_info("%-17s %10luKB %10luKB\n", cache_name(s),
> +                               (sinfo.active_objs * s->size) / 1024,
> +                               (sinfo.num_objs * s->size) / 1024);
> +       }
> +}
> +

Seems it's a good feature and patch is fine, maybe modify like below is better.

Change
 if (sinfo.num_objs > 0)
to
 if (sinfo.num_objs > 0 && sinfo.actives_objs > 0)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

Kernel may panic when oom happens without killable process sometimes it
is caused by huge unreclaimable slabs used by kernel.

Although kdump could help debug such problem, however, kdump is not
available on all architectures and it might be malfunction sometime.
And, since kernel already panic it is worthy capturing such information
in dmesg to aid touble shooting.

Print out unreclaimable slab info (used size and total size) which
actual memory usage is not zero (num_objs * size != 0) when panic_on_oom
is set or no killable process. Since such information is just showed when
kernel panic, so it will not lead too verbose message for normal oom.

The output looks like:

Unreclaimable slab info:
Name                      Used          Total
rpc_buffers               31KB         31KB
rpc_tasks                  7KB          7KB
ebitmap_node            1964KB       1964KB
avtab_node              5024KB       5024KB
xfs_buf                 1402KB       1402KB
xfs_ili                  134KB        134KB
xfs_efi_item             115KB        115KB
xfs_efd_item             115KB        115KB
xfs_buf_item             134KB        134KB
xfs_log_item_desc        342KB        342KB
xfs_trans               1412KB       1412KB
xfs_ifork                212KB        212KB

Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
---
 mm/oom_kill.c    |  3 +++
 mm/slab.h        |  8 ++++++++
 mm/slab_common.c | 29 +++++++++++++++++++++++++++++
 3 files changed, 40 insertions(+)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e0..bd48d34 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -43,6 +43,7 @@
 
 #include <asm/tlb.h>
 #include "internal.h"
+#include "slab.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -960,6 +961,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 	if (is_sysrq_oom(oc))
 		return;
 	dump_header(oc, NULL);
+	dump_unreclaimable_slab();
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
@@ -1044,6 +1046,7 @@ bool out_of_memory(struct oom_control *oc)
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
 		dump_header(oc, NULL);
+		dump_unreclaimable_slab();
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL) {
diff --git a/mm/slab.h b/mm/slab.h
index 0733628..b0496d1 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -505,6 +505,14 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
 
+#ifdef CONFIG_SLABINFO
+void dump_unreclaimable_slab(void);
+#else
+static inline void dump_unreclaimable_slab(void)
+{
+}
+#endif
+
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
 
 #ifdef CONFIG_SLAB_FREELIST_RANDOM
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83b..d08213d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1272,6 +1272,35 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+void dump_unreclaimable_slab(void)
+{
+	struct kmem_cache *s, *s2;
+	struct slabinfo sinfo;
+
+	pr_info("Unreclaimable slab info:\n");
+	pr_info("Name                      Used          Total\n");
+
+	/*
+	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
+	 * get sleep in oom path right before kernel panic, and avoid race
+	 * condition.
+	 * Since it is already oom, so there should be not any big allocation
+	 * which could change the statistics significantly.
+	 */
+	list_for_each_entry_safe(s, s2, &slab_caches, list) {
+		if (!is_root_cache(s) || (s->flags & SLAB_RECLAIM_ACCOUNT))
+			continue;
+
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(s, &sinfo);
+
+		if (sinfo.num_objs > 0)
+			pr_info("%-17s %10luKB %10luKB\n", cache_name(s),
+				(sinfo.active_objs * s->size) / 1024,
+				(sinfo.num_objs * s->size) / 1024);
+	}
+}
+
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 void *memcg_slab_start(struct seq_file *m, loff_t *pos)
 {
-- 
1.8.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

Kernel may panic when oom happens without killable process sometimes it
is caused by huge unreclaimable slabs used by kernel.

Although kdump could help debug such problem, however, kdump is not
available on all architectures and it might be malfunction sometime.
And, since kernel already panic it is worthy capturing such information
in dmesg to aid touble shooting.

Print out unreclaimable slab info (used size and total size) which
actual memory usage is not zero (num_objs * size != 0) when panic_on_oom
is set or no killable process. Since such information is just showed when
kernel panic, so it will not lead too verbose message for normal oom.

The output looks like:

Unreclaimable slab info:
Name                      Used          Total
rpc_buffers               31KB         31KB
rpc_tasks                  7KB          7KB
ebitmap_node            1964KB       1964KB
avtab_node              5024KB       5024KB
xfs_buf                 1402KB       1402KB
xfs_ili                  134KB        134KB
xfs_efi_item             115KB        115KB
xfs_efd_item             115KB        115KB
xfs_buf_item             134KB        134KB
xfs_log_item_desc        342KB        342KB
xfs_trans               1412KB       1412KB
xfs_ifork                212KB        212KB

Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
---
 mm/oom_kill.c    |  3 +++
 mm/slab.h        |  8 ++++++++
 mm/slab_common.c | 29 +++++++++++++++++++++++++++++
 3 files changed, 40 insertions(+)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e0..bd48d34 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -43,6 +43,7 @@
 
 #include <asm/tlb.h>
 #include "internal.h"
+#include "slab.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -960,6 +961,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 	if (is_sysrq_oom(oc))
 		return;
 	dump_header(oc, NULL);
+	dump_unreclaimable_slab();
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
@@ -1044,6 +1046,7 @@ bool out_of_memory(struct oom_control *oc)
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
 		dump_header(oc, NULL);
+		dump_unreclaimable_slab();
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL) {
diff --git a/mm/slab.h b/mm/slab.h
index 0733628..b0496d1 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -505,6 +505,14 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
 
+#ifdef CONFIG_SLABINFO
+void dump_unreclaimable_slab(void);
+#else
+static inline void dump_unreclaimable_slab(void)
+{
+}
+#endif
+
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
 
 #ifdef CONFIG_SLAB_FREELIST_RANDOM
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83b..72331ae 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1272,6 +1272,35 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+void dump_unreclaimable_slab(void)
+{
+	struct kmem_cache *s, *s2;
+	struct slabinfo sinfo;
+
+	pr_info("Unreclaimable slab info:\n");
+	pr_info("Name                      Used          Total\n");
+
+	/*
+	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
+	 * get sleep in oom path right before kernel panic, and avoid race
+	 * condition.
+	 * Since it is already oom, so there should be not any big allocation
+	 * which could change the statistics significantly.
+	 */
+	list_for_each_entry_safe(s, s2, &slab_caches, list) {
+		if (!is_root_cache(s) || (s->flags & SLAB_RECLAIM_ACCOUNT))
+			continue;
+
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(s, &sinfo);
+
+		if (sinfo.num_objs > 0)
+			pr_info("%-17s %10luKB %10luKB\n", cache_name(s), \
+				(sinfo.active_objs * s->size) / 1024, \
+				(sinfo.num_objs * s->size) / 1024);
+	}
+}
+
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 void *memcg_slab_start(struct seq_file *m, loff_t *pos)
 {
-- 
1.8.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

On 9/21/17 1:23 AM, David Rientjes wrote:
> On Thu, 21 Sep 2017, Yang Shi wrote:
> 
>> Kernel may panic when oom happens without killable process sometimes it
>> is caused by huge unreclaimable slabs used by kernel.
>>
>> Although kdump could help debug such problem, however, kdump is not
>> available on all architectures and it might be malfunction sometime.
>> And, since kernel already panic it is worthy capturing such information
>> in dmesg to aid touble shooting.
>>
>> Print out unreclaimable slab info (used size and total size) which
>> actual memory usage is not zero (num_objs * size != 0) when panic_on_oom is set
>> or no killable process. Since such information is just showed when kernel
>> panic, so it will not lead too verbose message for normal oom.
>>
>> The output looks like:
>>
>> Unreclaimable slab info:
>> Name                      Used          Total
>> rpc_buffers               31KB         31KB
>> rpc_tasks                  7KB          7KB
>> ebitmap_node            1964KB       1964KB
>> avtab_node              5024KB       5024KB
>> xfs_buf                 1402KB       1402KB
>> xfs_ili                  134KB        134KB
>> xfs_efi_item             115KB        115KB
>> xfs_efd_item             115KB        115KB
>> xfs_buf_item             134KB        134KB
>> xfs_log_item_desc        342KB        342KB
>> xfs_trans               1412KB       1412KB
>> xfs_ifork                212KB        212KB
>>
>> Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
>> ---
>>   mm/oom_kill.c    |  3 +++
>>   mm/slab.h        |  8 ++++++++
>>   mm/slab_common.c | 26 ++++++++++++++++++++++++++
>>   3 files changed, 37 insertions(+)
>>
>> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
>> index 99736e0..bd48d34 100644
>> --- a/mm/oom_kill.c
>> +++ b/mm/oom_kill.c
>> @@ -43,6 +43,7 @@
>>   
>>   #include <asm/tlb.h>
>>   #include "internal.h"
>> +#include "slab.h"
>>   
>>   #define CREATE_TRACE_POINTS
>>   #include <trace/events/oom.h>
>> @@ -960,6 +961,7 @@ static void check_panic_on_oom(struct oom_control *oc,
>>   	if (is_sysrq_oom(oc))
>>   		return;
>>   	dump_header(oc, NULL);
>> +	dump_unreclaimable_slab();
>>   	panic("Out of memory: %s panic_on_oom is enabled\n",
>>   		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
>>   }
>> @@ -1044,6 +1046,7 @@ bool out_of_memory(struct oom_control *oc)
>>   	/* Found nothing?!?! Either we hang forever, or we panic. */
>>   	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
>>   		dump_header(oc, NULL);
>> +		dump_unreclaimable_slab();
>>   		panic("Out of memory and no killable processes...\n");
>>   	}
>>   	if (oc->chosen && oc->chosen != (void *)-1UL) {
>> diff --git a/mm/slab.h b/mm/slab.h
>> index 0733628..734a92d 100644
>> --- a/mm/slab.h
>> +++ b/mm/slab.h
>> @@ -505,6 +505,14 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
>>   void memcg_slab_stop(struct seq_file *m, void *p);
>>   int memcg_slab_show(struct seq_file *m, void *p);
>>   
>> +#ifdef CONFIG_SLABINFO
>> +void dump_unreclaimable_slab(void);
>> +#else
>> +void dump_unreclaimable_slab(void);
> 
> This won't compile when CONFIG_SLABINFO is disabled.
> 
> static inline void dump_unreclaimable_slab(void)
> {
> }
> 
> when CONFIG_SLABINFO=n.

Thanks for pointing this. Just tested CONFIG_SLANINFO = n case. It can't 
be disabled in menuconfig, just manually modified init/Kconfig to test it.

> 
>> +{
>> +}
>> +#endif
>> +
>>   void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
>>   
>>   #ifdef CONFIG_SLAB_FREELIST_RANDOM
>> diff --git a/mm/slab_common.c b/mm/slab_common.c
>> index 904a83b..90d9de3 100644
>> --- a/mm/slab_common.c
>> +++ b/mm/slab_common.c
>> @@ -1272,6 +1272,32 @@ static int slab_show(struct seq_file *m, void *p)
>>   	return 0;
>>   }
>>   
>> +void dump_unreclaimable_slab(void)
>> +{
>> +	struct kmem_cache *s;
>> +	struct slabinfo sinfo;
>> +
>> +	pr_info("Unreclaimable slab info:\n");
>> +	pr_info("Name                      Used          Total\n");
>> +
>> +	/*
>> +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
>> +	 * get sleep in oom path right before kernel panic, and avoid race condition.
>> +	 * Since it is already oom, so there should be not any big allocation
>> +	 * which could change the statistics significantly.
> 
> The statistics themselves aren't protected by slab_mutex, it protects the
> iteration of the list.  I would suggest still taking the mutex here unless
> there's a reason to avoid it.

I don't think we prefer to sleep in oom path. Instead of acquiring the 
mutex, I think we can use list_for_each_entry_safe() to avoid the 
removal of kmem cache when printing the statistics.

> 
>> +	 */
>> +	list_for_each_entry(s, &slab_caches, list) {
>> +		if (!is_root_cache(s))
>> +			continue;
> 
> if (!(s->flags & SLAB_RECLAIM_ACCOUNT))
> 	continue;
> 
> No need to do the memset or get_slabinfo() if it's reclaimable, so just
> short-circuit it early in that case.
> 
>> +
>> +		memset(&sinfo, 0, sizeof(sinfo));
>> +		get_slabinfo(s, &sinfo);
>> +
>> +		if (!(s->flags & SLAB_RECLAIM_ACCOUNT) && sinfo.num_objs > 0)
>> +			pr_info("%-17s %10luKB %10luKB\n", cache_name(s), (sinfo.active_objs * s->size) / 1024, (sinfo.num_objs * s->size) / 1024);
>> +	}
>> +}
>> +
>>   #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
>>   void *memcg_slab_start(struct seq_file *m, loff_t *pos)
>>   {
> 
> Please run scripts/checkpatch.pl on your patch since there's some
> stylistic problems.  Otherwise, I think we need one more revision and
> we'll be good to go!

Thanks, will prepare v5 soon.

Yang

> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[David Rientjes]

On Thu, 21 Sep 2017, Yang Shi wrote:

> Kernel may panic when oom happens without killable process sometimes it
> is caused by huge unreclaimable slabs used by kernel.
> 
> Although kdump could help debug such problem, however, kdump is not
> available on all architectures and it might be malfunction sometime.
> And, since kernel already panic it is worthy capturing such information
> in dmesg to aid touble shooting.
> 
> Print out unreclaimable slab info (used size and total size) which
> actual memory usage is not zero (num_objs * size != 0) when panic_on_oom is set
> or no killable process. Since such information is just showed when kernel
> panic, so it will not lead too verbose message for normal oom.
> 
> The output looks like:
> 
> Unreclaimable slab info:
> Name                      Used          Total
> rpc_buffers               31KB         31KB
> rpc_tasks                  7KB          7KB
> ebitmap_node            1964KB       1964KB
> avtab_node              5024KB       5024KB
> xfs_buf                 1402KB       1402KB
> xfs_ili                  134KB        134KB
> xfs_efi_item             115KB        115KB
> xfs_efd_item             115KB        115KB
> xfs_buf_item             134KB        134KB
> xfs_log_item_desc        342KB        342KB
> xfs_trans               1412KB       1412KB
> xfs_ifork                212KB        212KB
> 
> Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
> ---
>  mm/oom_kill.c    |  3 +++
>  mm/slab.h        |  8 ++++++++
>  mm/slab_common.c | 26 ++++++++++++++++++++++++++
>  3 files changed, 37 insertions(+)
> 
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 99736e0..bd48d34 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -43,6 +43,7 @@
>  
>  #include <asm/tlb.h>
>  #include "internal.h"
> +#include "slab.h"
>  
>  #define CREATE_TRACE_POINTS
>  #include <trace/events/oom.h>
> @@ -960,6 +961,7 @@ static void check_panic_on_oom(struct oom_control *oc,
>  	if (is_sysrq_oom(oc))
>  		return;
>  	dump_header(oc, NULL);
> +	dump_unreclaimable_slab();
>  	panic("Out of memory: %s panic_on_oom is enabled\n",
>  		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
>  }
> @@ -1044,6 +1046,7 @@ bool out_of_memory(struct oom_control *oc)
>  	/* Found nothing?!?! Either we hang forever, or we panic. */
>  	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
>  		dump_header(oc, NULL);
> +		dump_unreclaimable_slab();
>  		panic("Out of memory and no killable processes...\n");
>  	}
>  	if (oc->chosen && oc->chosen != (void *)-1UL) {
> diff --git a/mm/slab.h b/mm/slab.h
> index 0733628..734a92d 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -505,6 +505,14 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
>  void memcg_slab_stop(struct seq_file *m, void *p);
>  int memcg_slab_show(struct seq_file *m, void *p);
>  
> +#ifdef CONFIG_SLABINFO
> +void dump_unreclaimable_slab(void);
> +#else
> +void dump_unreclaimable_slab(void);

This won't compile when CONFIG_SLABINFO is disabled.

static inline void dump_unreclaimable_slab(void)
{
}

when CONFIG_SLABINFO=n.

> +{
> +}
> +#endif
> +
>  void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
>  
>  #ifdef CONFIG_SLAB_FREELIST_RANDOM
> diff --git a/mm/slab_common.c b/mm/slab_common.c
> index 904a83b..90d9de3 100644
> --- a/mm/slab_common.c
> +++ b/mm/slab_common.c
> @@ -1272,6 +1272,32 @@ static int slab_show(struct seq_file *m, void *p)
>  	return 0;
>  }
>  
> +void dump_unreclaimable_slab(void)
> +{
> +	struct kmem_cache *s;
> +	struct slabinfo sinfo;
> +
> +	pr_info("Unreclaimable slab info:\n");
> +	pr_info("Name                      Used          Total\n");
> +
> +	/*
> +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
> +	 * get sleep in oom path right before kernel panic, and avoid race condition.
> +	 * Since it is already oom, so there should be not any big allocation
> +	 * which could change the statistics significantly.

The statistics themselves aren't protected by slab_mutex, it protects the 
iteration of the list.  I would suggest still taking the mutex here unless 
there's a reason to avoid it.

> +	 */
> +	list_for_each_entry(s, &slab_caches, list) {
> +		if (!is_root_cache(s))
> +			continue;

if (!(s->flags & SLAB_RECLAIM_ACCOUNT))
	continue;

No need to do the memset or get_slabinfo() if it's reclaimable, so just 
short-circuit it early in that case.

> +
> +		memset(&sinfo, 0, sizeof(sinfo));
> +		get_slabinfo(s, &sinfo);
> +
> +		if (!(s->flags & SLAB_RECLAIM_ACCOUNT) && sinfo.num_objs > 0)
> +			pr_info("%-17s %10luKB %10luKB\n", cache_name(s), (sinfo.active_objs * s->size) / 1024, (sinfo.num_objs * s->size) / 1024);
> +	}
> +}
> +
>  #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
>  void *memcg_slab_start(struct seq_file *m, loff_t *pos)
>  {

Please run scripts/checkpatch.pl on your patch since there's some 
stylistic problems.  Otherwise, I think we need one more revision and 
we'll be good to go!

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

Kernel may panic when oom happens without killable process sometimes it
is caused by huge unreclaimable slabs used by kernel.

Although kdump could help debug such problem, however, kdump is not
available on all architectures and it might be malfunction sometime.
And, since kernel already panic it is worthy capturing such information
in dmesg to aid touble shooting.

Print out unreclaimable slab info (used size and total size) which
actual memory usage is not zero (num_objs * size != 0) when panic_on_oom is set
or no killable process. Since such information is just showed when kernel
panic, so it will not lead too verbose message for normal oom.

The output looks like:

Unreclaimable slab info:
Name                      Used          Total
rpc_buffers               31KB         31KB
rpc_tasks                  7KB          7KB
ebitmap_node            1964KB       1964KB
avtab_node              5024KB       5024KB
xfs_buf                 1402KB       1402KB
xfs_ili                  134KB        134KB
xfs_efi_item             115KB        115KB
xfs_efd_item             115KB        115KB
xfs_buf_item             134KB        134KB
xfs_log_item_desc        342KB        342KB
xfs_trans               1412KB       1412KB
xfs_ifork                212KB        212KB

Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
---
 mm/oom_kill.c    |  3 +++
 mm/slab.h        |  8 ++++++++
 mm/slab_common.c | 26 ++++++++++++++++++++++++++
 3 files changed, 37 insertions(+)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e0..bd48d34 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -43,6 +43,7 @@
 
 #include <asm/tlb.h>
 #include "internal.h"
+#include "slab.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -960,6 +961,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 	if (is_sysrq_oom(oc))
 		return;
 	dump_header(oc, NULL);
+	dump_unreclaimable_slab();
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
@@ -1044,6 +1046,7 @@ bool out_of_memory(struct oom_control *oc)
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
 		dump_header(oc, NULL);
+		dump_unreclaimable_slab();
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL) {
diff --git a/mm/slab.h b/mm/slab.h
index 0733628..734a92d 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -505,6 +505,14 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
 
+#ifdef CONFIG_SLABINFO
+void dump_unreclaimable_slab(void);
+#else
+void dump_unreclaimable_slab(void);
+{
+}
+#endif
+
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
 
 #ifdef CONFIG_SLAB_FREELIST_RANDOM
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83b..90d9de3 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1272,6 +1272,32 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+void dump_unreclaimable_slab(void)
+{
+	struct kmem_cache *s;
+	struct slabinfo sinfo;
+
+	pr_info("Unreclaimable slab info:\n");
+	pr_info("Name                      Used          Total\n");
+
+	/*
+	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
+	 * get sleep in oom path right before kernel panic, and avoid race condition.
+	 * Since it is already oom, so there should be not any big allocation
+	 * which could change the statistics significantly.
+	 */
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(s, &sinfo);
+
+		if (!(s->flags & SLAB_RECLAIM_ACCOUNT) && sinfo.num_objs > 0)
+			pr_info("%-17s %10luKB %10luKB\n", cache_name(s), (sinfo.active_objs * s->size) / 1024, (sinfo.num_objs * s->size) / 1024);
+	}
+}
+
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 void *memcg_slab_start(struct seq_file *m, loff_t *pos)
 {
-- 
1.8.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

On 9/19/17 3:41 PM, David Rientjes wrote:
> On Wed, 20 Sep 2017, Yang Shi wrote:
> 
>>>> --- a/mm/slab_common.c
>>>> +++ b/mm/slab_common.c
>>>> @@ -35,6 +35,8 @@
>>>>    static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
>>>>    		    slab_caches_to_rcu_destroy_workfn);
>>>>    +#define K(x) ((x)/1024)
>>>> +
>>>>    /*
>>>>     * Set of flags that will prevent slab merging
>>>>     */
>>>> @@ -1272,6 +1274,34 @@ static int slab_show(struct seq_file *m, void *p)
>>>>    	return 0;
>>>>    }
>>>>    +void show_unreclaimable_slab()
>>>> +{
>>>> +	struct kmem_cache *s = NULL;
>>>> +	struct slabinfo sinfo;
>>>> +
>>>> +	memset(&sinfo, 0, sizeof(sinfo));
>>>> +
>>>> +	printk("Unreclaimable slabs:\n");
>>>> +
>>>> +	/*
>>>> +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
>>>> +	 * get sleep in oom path right before kernel panic, and avoid race
>>>> condition.
>>>> +	 * Since it is already oom, so there should be not any big allocation
>>>> +	 * which could change the statistics significantly.
>>>> +	 */
>>>> +	list_for_each_entry(s, &slab_caches, list) {
>>>> +		if (!is_root_cache(s))
>>>> +			continue;
>>>> +
>>>> +		get_slabinfo(s, &sinfo);
>>>> +
>>>> +		if (!is_reclaimable(s) && sinfo.num_objs > 0)
>>>> +			printk("%-17s %luKB\n", cache_name(s),
>>>> K(sinfo.num_objs * s->size));
>>>> +	}
>>>
>>> I like this, but could we be even more helpful by giving the user more
>>> information from sinfo beyond just the total size of objects allocated?
>>
>> Sure, we definitely can. But, the question is what info is helpful to users to
>> diagnose oom other than the size.
>>
>> I think of the below:
>> 	- the number of active objs, the number of total objs, the percentage
>> of active objs per cache
>> 	- the number of active slabs, the number of total slabs, the
>> percentage of active slabs per cache
>>
>> Anything else?
>>
> 
> Right now it's a useful tool to find out what unreclaimable slab is
> sitting around that is causing the system to run out of memory.  If we
> knew how much of this slab is actually in use vs free, it can determine if
> its stranding or if there's a bug in the slab allocator itself.

I see. You prefer to have a report which looks like:

Cache		Used size		Free size
mm_struct	100K			50K

Or show the total size (used + free) instead of free size. And, may plus 
the number of objs and the number of total objs.

Thanks,
Yang

> 
> We wouldn't need percentages, we can calculate that directly from the
> data if necessary.
> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[David Rientjes]

On Wed, 20 Sep 2017, Yang Shi wrote:

> > > --- a/mm/slab_common.c
> > > +++ b/mm/slab_common.c
> > > @@ -35,6 +35,8 @@
> > >   static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
> > >   		    slab_caches_to_rcu_destroy_workfn);
> > >   +#define K(x) ((x)/1024)
> > > +
> > >   /*
> > >    * Set of flags that will prevent slab merging
> > >    */
> > > @@ -1272,6 +1274,34 @@ static int slab_show(struct seq_file *m, void *p)
> > >   	return 0;
> > >   }
> > >   +void show_unreclaimable_slab()
> > > +{
> > > +	struct kmem_cache *s = NULL;
> > > +	struct slabinfo sinfo;
> > > +
> > > +	memset(&sinfo, 0, sizeof(sinfo));
> > > +
> > > +	printk("Unreclaimable slabs:\n");
> > > +
> > > +	/*
> > > +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
> > > +	 * get sleep in oom path right before kernel panic, and avoid race
> > > condition.
> > > +	 * Since it is already oom, so there should be not any big allocation
> > > +	 * which could change the statistics significantly.
> > > +	 */
> > > +	list_for_each_entry(s, &slab_caches, list) {
> > > +		if (!is_root_cache(s))
> > > +			continue;
> > > +
> > > +		get_slabinfo(s, &sinfo);
> > > +
> > > +		if (!is_reclaimable(s) && sinfo.num_objs > 0)
> > > +			printk("%-17s %luKB\n", cache_name(s),
> > > K(sinfo.num_objs * s->size));
> > > +	}
> > 
> > I like this, but could we be even more helpful by giving the user more
> > information from sinfo beyond just the total size of objects allocated?
> 
> Sure, we definitely can. But, the question is what info is helpful to users to
> diagnose oom other than the size.
> 
> I think of the below:
> 	- the number of active objs, the number of total objs, the percentage
> of active objs per cache
> 	- the number of active slabs, the number of total slabs, the
> percentage of active slabs per cache
> 
> Anything else?
> 

Right now it's a useful tool to find out what unreclaimable slab is 
sitting around that is causing the system to run out of memory.  If we 
knew how much of this slab is actually in use vs free, it can determine if 
its stranding or if there's a bug in the slab allocator itself.

We wouldn't need percentages, we can calculate that directly from the 
data if necessary.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

On 9/19/17 1:57 PM, David Rientjes wrote:
> On Tue, 19 Sep 2017, Yang Shi wrote:
> 
>> --- a/mm/slab_common.c
>> +++ b/mm/slab_common.c
>> @@ -35,6 +35,8 @@
>>   static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
>>   		    slab_caches_to_rcu_destroy_workfn);
>>   
>> +#define K(x) ((x)/1024)
>> +
>>   /*
>>    * Set of flags that will prevent slab merging
>>    */
>> @@ -1272,6 +1274,34 @@ static int slab_show(struct seq_file *m, void *p)
>>   	return 0;
>>   }
>>   
>> +void show_unreclaimable_slab()
>> +{
>> +	struct kmem_cache *s = NULL;
>> +	struct slabinfo sinfo;
>> +
>> +	memset(&sinfo, 0, sizeof(sinfo));
>> +
>> +	printk("Unreclaimable slabs:\n");
>> +
>> +	/*
>> +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
>> +	 * get sleep in oom path right before kernel panic, and avoid race condition.
>> +	 * Since it is already oom, so there should be not any big allocation
>> +	 * which could change the statistics significantly.
>> +	 */
>> +	list_for_each_entry(s, &slab_caches, list) {
>> +		if (!is_root_cache(s))
>> +			continue;
>> +
>> +		get_slabinfo(s, &sinfo);
>> +
>> +		if (!is_reclaimable(s) && sinfo.num_objs > 0)
>> +			printk("%-17s %luKB\n", cache_name(s), K(sinfo.num_objs * s->size));
>> +	}
> 
> I like this, but could we be even more helpful by giving the user more
> information from sinfo beyond just the total size of objects allocated?

Sure, we definitely can. But, the question is what info is helpful to 
users to diagnose oom other than the size.

I think of the below:
	- the number of active objs, the number of total objs, the percentage 
of active objs per cache
	- the number of active slabs, the number of total slabs, the percentage 
of active slabs per cache

Anything else?

Thanks,
Yang

> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[David Rientjes]

On Tue, 19 Sep 2017, Yang Shi wrote:

> --- a/mm/slab_common.c
> +++ b/mm/slab_common.c
> @@ -35,6 +35,8 @@
>  static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
>  		    slab_caches_to_rcu_destroy_workfn);
>  
> +#define K(x) ((x)/1024)
> +
>  /*
>   * Set of flags that will prevent slab merging
>   */
> @@ -1272,6 +1274,34 @@ static int slab_show(struct seq_file *m, void *p)
>  	return 0;
>  }
>  
> +void show_unreclaimable_slab()
> +{
> +	struct kmem_cache *s = NULL;
> +	struct slabinfo sinfo;
> +
> +	memset(&sinfo, 0, sizeof(sinfo));
> +
> +	printk("Unreclaimable slabs:\n");
> +
> +	/*
> +	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
> +	 * get sleep in oom path right before kernel panic, and avoid race condition.
> +	 * Since it is already oom, so there should be not any big allocation
> +	 * which could change the statistics significantly.
> +	 */
> +	list_for_each_entry(s, &slab_caches, list) {
> +		if (!is_root_cache(s))
> +			continue;
> +
> +		get_slabinfo(s, &sinfo);
> +
> +		if (!is_reclaimable(s) && sinfo.num_objs > 0)
> +			printk("%-17s %luKB\n", cache_name(s), K(sinfo.num_objs * s->size));
> +	}

I like this, but could we be even more helpful by giving the user more 
information from sinfo beyond just the total size of objects allocated?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

Kernel may panic when oom happens without killable process sometimes it
is caused by huge unreclaimable slabs used by kernel.

Altough kdump could help debug such problem, however, kdump is not
available on all architectures and it might be malfunction sometime.
And, since kernel already panic it is worthy capturing such information
in dmesg to aid touble shooting.

Add a field in struct slibinfo to show if this slab is reclaimable or
not, and a helper function to achieve the value from
SLAB_RECLAIM_ACCOUNT flag.

Print out unreclaimable slab info which actual memory usage is not zero
(num_objs * size != 0) when panic_on_oom is set or no killable process.
Since such information is just showed when kernel panic, so it will not
lead too verbose message for normal oom.

The output looks like:

rpc_buffers 31KB
rpc_tasks 31KB
avtab_node 46735KB
xfs_buf 624KB
xfs_ili 48KB
xfs_efi_item 31KB
xfs_efd_item 31KB
xfs_buf_item 78KB
xfs_log_item_desc 141KB
xfs_trans 108KB
xfs_ifork 744KB
xfs_trans 108KB
xfs_ifork 744KB
xfs_da_state 126KB

Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
---
 mm/oom_kill.c    | 13 +++++++++++--
 mm/slab.c        |  1 +
 mm/slab.h        |  7 +++++++
 mm/slab_common.c | 30 ++++++++++++++++++++++++++++++
 mm/slub.c        |  1 +
 5 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e0..173c423 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -43,6 +43,7 @@
 
 #include <asm/tlb.h>
 #include "internal.h"
+#include "slab.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -427,6 +428,14 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 		dump_tasks(oc->memcg, oc->nodemask);
 }
 
+static void dump_header_with_slabinfo(struct oom_control *oc, struct task_struct *p)
+{
+	dump_header(oc, p);
+
+	if (IS_ENABLED(CONFIG_SLABINFO))
+		show_unreclaimable_slab();
+}
+
 /*
  * Number of OOM victims in flight
  */
@@ -959,7 +968,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 	/* Do not panic for oom kills triggered by sysrq */
 	if (is_sysrq_oom(oc))
 		return;
-	dump_header(oc, NULL);
+	dump_header_with_slabinfo(oc, NULL);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
@@ -1043,7 +1052,7 @@ bool out_of_memory(struct oom_control *oc)
 	select_bad_process(oc);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
-		dump_header(oc, NULL);
+		dump_header_with_slabinfo(oc, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL) {
diff --git a/mm/slab.c b/mm/slab.c
index 04dec48..4f4971c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4132,6 +4132,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 	sinfo->shared = cachep->shared;
 	sinfo->objects_per_slab = cachep->num;
 	sinfo->cache_order = cachep->gfporder;
+	sinfo->reclaim = is_reclaimable(cachep);
 }
 
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
diff --git a/mm/slab.h b/mm/slab.h
index 0733628..2f1ebce 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -186,6 +186,7 @@ struct slabinfo {
 	unsigned int shared;
 	unsigned int objects_per_slab;
 	unsigned int cache_order;
+	unsigned int reclaim;
 };
 
 void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
@@ -352,6 +353,11 @@ static inline void memcg_link_cache(struct kmem_cache *s)
 
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
+static inline bool is_reclaimable(struct kmem_cache *s)
+{
+	return (s->flags & SLAB_RECLAIM_ACCOUNT) ? true : false;
+}
+
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {
 	struct kmem_cache *cachep;
@@ -504,6 +510,7 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
 void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
+void show_unreclaimable_slab(void);
 
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83b..665baf2 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -35,6 +35,8 @@
 static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
 		    slab_caches_to_rcu_destroy_workfn);
 
+#define K(x) ((x)/1024)
+
 /*
  * Set of flags that will prevent slab merging
  */
@@ -1272,6 +1274,34 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+void show_unreclaimable_slab()
+{
+	struct kmem_cache *s = NULL;
+	struct slabinfo sinfo;
+
+	memset(&sinfo, 0, sizeof(sinfo));
+
+	printk("Unreclaimable slabs:\n");
+
+	/*
+	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
+	 * get sleep in oom path right before kernel panic, and avoid race condition.
+	 * Since it is already oom, so there should be not any big allocation
+	 * which could change the statistics significantly.
+	 */
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		get_slabinfo(s, &sinfo);
+
+		if (!is_reclaimable(s) && sinfo.num_objs > 0)
+			printk("%-17s %luKB\n", cache_name(s), K(sinfo.num_objs * s->size));
+	}
+}
+EXPORT_SYMBOL(show_unreclaimable_slab);
+#undef K
+
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 void *memcg_slab_start(struct seq_file *m, loff_t *pos)
 {
diff --git a/mm/slub.c b/mm/slub.c
index 163352c..5c17c0a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5872,6 +5872,7 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 	sinfo->num_slabs = nr_slabs;
 	sinfo->objects_per_slab = oo_objects(s->oo);
 	sinfo->cache_order = oo_order(s->oo);
+	sinfo->reclaim = is_reclaimable(s);
 }
 
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)
-- 
1.8.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] mm: oom: show unreclaimable slab info when kernel panic

[Yang Shi]

Kernel may panic when oom happens without killable process sometimes it
is caused by huge unreclaimable slabs used by kernel.

Altough kdump could help debug such problem, however, kdump is not
available on all architectures and it might be malfunction sometime.
And, since kernel already panic it is worthy capturing such information
in dmesg to aid touble shooting.

Add a field in struct slibinfo to show if this slab is reclaimable or
not, and a helper function to achieve the value from
SLAB_RECLAIM_ACCOUNT flag.

Print out unreclaimable slab info which actual memory usage is not zero
(num_objs * size != 0) when panic_on_oom is set or no killable process.
Since such information is just showed when kernel panic, so it will not
lead too verbose message for normal oom.

The output looks like:

rpc_buffers 31KB
rpc_tasks 31KB
avtab_node 46735KB
xfs_buf 624KB
xfs_ili 48KB
xfs_efi_item 31KB
xfs_efd_item 31KB
xfs_buf_item 78KB
xfs_log_item_desc 141KB
xfs_trans 108KB
xfs_ifork 744KB
xfs_trans 108KB
xfs_ifork 744KB
xfs_da_state 126KB

Signed-off-by: Yang Shi <yang.s@alibaba-inc.com>
---
 mm/oom_kill.c    | 13 +++++++++++--
 mm/slab.c        |  1 +
 mm/slab.h        |  7 +++++++
 mm/slab_common.c | 30 ++++++++++++++++++++++++++++++
 mm/slub.c        |  1 +
 5 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e0..173c423 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -43,6 +43,7 @@
 
 #include <asm/tlb.h>
 #include "internal.h"
+#include "slab.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -427,6 +428,14 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 		dump_tasks(oc->memcg, oc->nodemask);
 }
 
+static void dump_header_with_slabinfo(struct oom_control *oc, struct task_struct *p)
+{
+	dump_header(oc, p);
+
+	if (IS_ENABLED(CONFIG_SLABINFO))
+		show_unreclaimable_slab();
+}
+
 /*
  * Number of OOM victims in flight
  */
@@ -959,7 +968,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 	/* Do not panic for oom kills triggered by sysrq */
 	if (is_sysrq_oom(oc))
 		return;
-	dump_header(oc, NULL);
+	dump_header_with_slabinfo(oc, NULL);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
@@ -1043,7 +1052,7 @@ bool out_of_memory(struct oom_control *oc)
 	select_bad_process(oc);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
-		dump_header(oc, NULL);
+		dump_header_with_slabinfo(oc, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL) {
diff --git a/mm/slab.c b/mm/slab.c
index 04dec48..4f4971c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4132,6 +4132,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 	sinfo->shared = cachep->shared;
 	sinfo->objects_per_slab = cachep->num;
 	sinfo->cache_order = cachep->gfporder;
+	sinfo->reclaim = is_reclaimable(cachep);
 }
 
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
diff --git a/mm/slab.h b/mm/slab.h
index 0733628..2f1ebce 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -186,6 +186,7 @@ struct slabinfo {
 	unsigned int shared;
 	unsigned int objects_per_slab;
 	unsigned int cache_order;
+	unsigned int reclaim;
 };
 
 void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
@@ -352,6 +353,11 @@ static inline void memcg_link_cache(struct kmem_cache *s)
 
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
+static inline bool is_reclaimable(struct kmem_cache *s)
+{
+	return (s->flags & SLAB_RECLAIM_ACCOUNT) ? true : false;
+}
+
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {
 	struct kmem_cache *cachep;
@@ -504,6 +510,7 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
 void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
+void show_unreclaimable_slab(void);
 
 void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83b..665baf2 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -35,6 +35,8 @@
 static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
 		    slab_caches_to_rcu_destroy_workfn);
 
+#define K(x) ((x)/1024)
+
 /*
  * Set of flags that will prevent slab merging
  */
@@ -1272,6 +1274,34 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+void show_unreclaimable_slab()
+{
+	struct kmem_cache *s = NULL;
+	struct slabinfo sinfo;
+
+	memset(&sinfo, 0, sizeof(sinfo));
+
+	printk("Unreclaimable slabs:\n");
+
+	/*
+	 * Here acquiring slab_mutex is unnecessary since we don't prefer to
+	 * get sleep in oom path right before kernel panic, and avoid race condition.
+	 * Since it is already oom, so there should be not any big allocation
+	 * which could change the statistics significantly.
+	 */
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		get_slabinfo(s, &sinfo);
+
+		if (!is_reclaimable(s) && sinfo.num_objs > 0)
+			printk("%-17s %luKB\n", cache_name(s), K(sinfo.num_objs * s->size));
+	}
+}
+EXPORT_SYMBOL(show_unreclaimable_slab);
+#undef K
+
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 void *memcg_slab_start(struct seq_file *m, loff_t *pos)
 {
diff --git a/mm/slub.c b/mm/slub.c
index 163352c..5c17c0a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5872,6 +5872,7 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 	sinfo->num_slabs = nr_slabs;
 	sinfo->objects_per_slab = oo_objects(s->oo);
 	sinfo->cache_order = oo_order(s->oo);
+	sinfo->reclaim = is_reclaimable(s);
 }
 
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)
-- 
1.8.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>