Add two sysctl entries (vm.oom_dump_ratelimit and
vm.oom_dump_ratelimit_burst) to control the rate limiting interval and
burst, respectively, of the OOM killer output (oom_kill_process()).
These entries are disabled by default and can be enabled during kernel
configuration with CONFIG_DUMP_RATELIMIT. They take
DEFAULT_RATELIMIT_INTERVAL and DEFAULT_RATELIMIT_BURST as their default
values.
In some setups, the amount of output that the OOM killer generates when
it kills a process and dumps the list of tasks can be too
large. Unfortunately, the rate-limiting used for it uses the default
values for the rate limit interval and burst. This patch allows the user
to configure these values.
Signed-off-by: Ricardo Cañuelo <ricardo.canuelo@xxxxxxxxxxxxx>
---
I'm sending this v2 because I found a mistake in the first version: the
oom_dump_ratelimit sysctl parameter must use proc_dointvec_jiffies
instead of proc_dointvec so that the user can use it to specify the
number of seconds easily.
I also added the rationale to the commit log as Michal suggested and
moved the config option to mm/Kconfig.debug as suggested by Sergey:
I personally like this patch. There are no universal ratelimit
values, so having some sort of user configuration makes sense.
One thing - I think that config option should be in mm/Kconfig.debug
but I'd like to keep the discussion open as there seem to be many
different opinions about this topic.
Cheers,
Ricardo
include/linux/oom.h | 2 ++
kernel/sysctl.c | 16 ++++++++++++++++
mm/Kconfig.debug | 9 +++++++++
mm/oom_kill.c | 5 +++++
4 files changed, 32 insertions(+)
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 2db9a1432511..76c560a1a4c7 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -127,4 +127,6 @@ extern struct task_struct *find_lock_task_mm(struct task_struct *p);
extern int sysctl_oom_dump_tasks;
extern int sysctl_oom_kill_allocating_task;
extern int sysctl_panic_on_oom;
+extern int sysctl_oom_dump_ratelimit;
+extern int sysctl_oom_dump_ratelimit_burst;
#endif /* _INCLUDE_LINUX_OOM_H */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ce75c67572b9..dd51a7e26a54 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2708,6 +2708,22 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+#ifdef CONFIG_OOM_DUMP_RATELIMIT
+ {
+ .procname = "oom_dump_ratelimit",
+ .data = &sysctl_oom_dump_ratelimit,
+ .maxlen = sizeof(sysctl_oom_dump_ratelimit),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
+ .procname = "oom_dump_ratelimit_burst",
+ .data = &sysctl_oom_dump_ratelimit_burst,
+ .maxlen = sizeof(sysctl_oom_dump_ratelimit_burst),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif
{
.procname = "overcommit_ratio",
.data = &sysctl_overcommit_ratio,
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 864f129f1937..93207f26d57a 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -170,3 +170,12 @@ config PTDUMP_DEBUGFS
kernel.
If in doubt, say N.
+
+config OOM_DUMP_RATELIMIT
+ bool "Enable rate limiting for OOM dumps"
+ default n
+ help
+ Say Y here to enable the configuration of the rate limiting of
+ OOM task dumps to the console through sysctl entries
+ vm.oom_dump_ratelimit (rate limit interval) and
+ vm.oom_dump_ratelimit_burst (rate limit burst).
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 8b84661a6410..2b3fa826a172 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -54,6 +54,8 @@
int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks = 1;
+int sysctl_oom_dump_ratelimit = DEFAULT_RATELIMIT_INTERVAL;
+int sysctl_oom_dump_ratelimit_burst = DEFAULT_RATELIMIT_BURST;
/*
* Serializes oom killer invocations (out_of_memory()) from all contexts to
@@ -959,6 +961,9 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
+ oom_rs.interval = sysctl_oom_dump_ratelimit;
+ oom_rs.burst = sysctl_oom_dump_ratelimit_burst;
+
/*
* If the task is already exiting, don't alarm the sysadmin or kill
* its children or threads, just give it access to memory reserves
--
2.18.0
