Skip to contentSkip to conversation

x86: mce: Fix thermal throttling message storm

tip:x86/urgent tip-bot for Ingo Molnar 1 participant 1 message Sep 22, 2009 x86

lore
Share & tools
lore
#0 lore raw
Commit-ID:  b417c9fd8690637f0c91479435ab3e2bf450c038
Gitweb:     http://git.kernel.org/tip/b417c9fd8690637f0c91479435ab3e2bf450c038
Author:     Ingo Molnar <[email protected]>
AuthorDate: Tue, 22 Sep 2009 15:50:24 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Tue, 22 Sep 2009 17:30:45 +0200

x86: mce: Fix thermal throttling message storm

If a system switches back and forth between hot and cold mode, the MCE code will print a stream of critical kernel messages.

Extend the throttling code to properly notice this, by only printing the first hot + cold transition and omitting the rest up to CHECK_INTERVAL (5 minutes).

This way we'll only get a single incident of:

 [  102.356584] CPU0: Temperature above threshold, cpu clock throttled (total events = 1)
 [  102.357000] Disabling lock debugging due to kernel taint
 [  102.369223] CPU0: Temperature/speed normal

Every 5 minutes. The 'total events' count tells the number of cold/hot transitions detected, should overheating occur after 5 minutes again:

[  402.357580] CPU0: Temperature above threshold, cpu clock throttled (total events = 24891)
[  402.358001] CPU0: Temperature/speed normal
[  450.704142] Machine check events logged

Cc: Hidetoshi Seto <[email protected]>
Cc: Huang Ying <[email protected]>
Cc: Andi Kleen <[email protected]>
LKML-Reference: <new-submission>

---
 arch/x86/kernel/cpu/mcheck/therm_throt.c |    6 ++++--
 1 files changed, 4 insertions(+), 2 deletions(-)
arch/x86/kernel/cpu/mcheck/therm_throt.c +4 -2
index db80b57..b3a1dba 100644
@@ -42,6 +42,7 @@ struct thermal_state {
 
 	u64			next_check;
 	unsigned long		throttle_count;
+	unsigned long		last_throttle_count;
 };
 
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
@@ -120,11 +121,12 @@ static int therm_throt_process(bool is_throttled)
 	if (is_throttled)
 		state->throttle_count++;
 
-	if (!(was_throttled ^ is_throttled) &&
-			time_before64(now, state->next_check))
+	if (time_before64(now, state->next_check) &&
+			state->throttle_count != state->last_throttle_count)
 		return 0;
 
 	state->next_check = now + CHECK_INTERVAL;
+	state->last_throttle_count = state->throttle_count;
 
 	/* if we just entered the thermal event */
 	if (is_throttled) {