On 2020/04/23 20:07, Michal Hocko wrote:
> The existing loglevels we use are not really carved in stone and we can
> prioritize some more than others. dump_tasks is KERN_INFO already and
> this is quite a low priority so you shouldn't really miss much when
> omitting it. But I wouldn't mind making it KERN_DEBUG.
Do you mean
- pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
+ pr_debug("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
in order to suppress printing to consoles? Wow! That will also suppress
saving to log files because syslog daemon is likely configured not to save
KERN_DEBUG level messages.
>> - tune the dump_tasks specifically （vm.oom_dump_tasks）
>> All the consumers are effected.
>> The logfile is fast enough, so we expect that these dump_tasks could
>> be printed into the logfile.
>> The console is so slow that we don't want to print into it.
>> A possilbe way to fix it is improve vm.oom_dump_tasks.
>> vm.oom_dump_tasks : 1 - dump into all consumers
>> 2 - don't dump into console
>> 0 - don't dump into any of
>
> How would that be implemented. I do not know of a way to tell printk
> which consoles to use for the output. Anyway, isn't this something
> that can be configured on the printk level. In other words send only
> important information to slow consoles?
Last year I proposed
https://lkml.kernel.org/r/1550896930-12324-1-git-send-email-penguin-kernel@xxxxxxxxxxxxxxxxxxx
and Sergey Senozhatsky commented
"This is a bit of a strange issue, to be honest. If OOM prints too
many messages then we might want to do some work on the OOM side."
. I was thinking that printing to consoles is a requirement for oom_dump_tasks .
If we can agree with not printing dump_tasks() output to consoles, a trivial
patch shown below will solve the problem. Those who cannot run syslog daemon
in userspace might disagree, but this will be the simplest answer.
include/linux/kern_levels.h | 3 +++
include/linux/printk.h | 1 +
kernel/printk/printk.c | 7 ++++++-
mm/oom_kill.c | 7 ++++---
4 files changed, 14 insertions(+), 4 deletions(-)
diff --git a/include/linux/kern_levels.h b/include/linux/kern_levels.h
index bf2389c26ae3..cd69a9cb3c2a 100644
--- a/include/linux/kern_levels.h
+++ b/include/linux/kern_levels.h
@@ -23,6 +23,9 @@
*/
#define KERN_CONT KERN_SOH "c"
+/* Annotation for "don't print to consoles". */
+#define KERN_NO_CONSOLES KERN_SOH "S"
+
/* integer equivalents of KERN_<LEVEL> */
#define LOGLEVEL_SCHED -2 /* Deferred messages from sched code
* are set to this special level */
diff --git a/include/linux/printk.h b/include/linux/printk.h
index e061635e0409..da338b81c2e1 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -19,6 +19,7 @@ static inline int printk_get_level(const char *buffer)
switch (buffer[1]) {
case '0' ... '7':
case 'c': /* KERN_CONT */
+ case 'S': /* KERN_NO_CONSOLES */
return buffer[1];
}
}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 9a9b6156270b..ed51641af087 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -361,6 +361,7 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
*/
enum log_flags {
+ LOG_NO_CONSOLES = 1, /* don't print to consoles */
LOG_NEWLINE = 2, /* text ended with a newline */
LOG_CONT = 8, /* text is a fragment of a continuation line */
};
@@ -1959,6 +1960,9 @@ int vprintk_store(int facility, int level,
break;
case 'c': /* KERN_CONT */
lflags |= LOG_CONT;
+ break;
+ case 'S': /* KERN_NO_CONSOLES */
+ lflags |= LOG_NO_CONSOLES;
}
text_len -= 2;
@@ -2453,7 +2457,8 @@ void console_unlock(void)
break;
msg = log_from_idx(console_idx);
- if (suppress_message_printing(msg->level)) {
+ if ((msg->flags & LOG_NO_CONSOLES) ||
+ suppress_message_printing(msg->level)) {
/*
* Skip record we have buffered and already printed
* directly to the console when we received it, and
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dfc357614e56..0b487c13a2c9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -400,7 +400,7 @@ static int dump_task(struct task_struct *p, void *arg)
return 0;
}
- pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
+ pr_info(KERN_NO_CONSOLES "[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
task->pid, from_kuid(&init_user_ns, task_uid(task)),
task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
mm_pgtables_bytes(task->mm),
@@ -423,8 +423,9 @@ static int dump_task(struct task_struct *p, void *arg)
*/
static void dump_tasks(struct oom_control *oc)
{
- pr_info("Tasks state (memory values in pages):\n");
- pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n");
+ pr_info_once("Tasks state is sent to syslog.\n");
+ pr_info(KERN_NO_CONSOLES "Tasks state (memory values in pages):\n");
+ pr_info(KERN_NO_CONSOLES "[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n");
if (is_memcg_oom(oc))
mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
