Skip to contentSkip to conversation

oom-kill: direct hardware access processes should get bonus

PATCH Superseded Figo.zhang 6 participants 45 messages Nov 2, 2010 – Jan 6, 2011 1 message not in the archive

Subsystems (2)
lore
Share & tools
lore

Figo.zhang

author
#0 lore raw

PATCH 1/1 oom-kill: direct hardware access processes should get bonus

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get 3% bonus for protection.

---
mm/oom_kill.c | 8 +++++---

 1 files changed, 5 insertions(+), 3 deletions(-)
mm/oom_kill.c +5 -3
index 4029583..df6a9da 100644
@@ -195,10 +195,12 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	task_unlock(p);
 
 	/*
-	 * Root processes get 3% bonus, just like the __vm_enough_memory()
-	 * implementation used by LSMs.
+	 * Root and direct hardware access processes get 3% bonus, just like the
+	 * __vm_enough_memory() implementation used by LSMs.
 	 */
-	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
 		points -= 30;
 
 	/*
#1 lore raw
Quoted 5 lines · Figo.zhang

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get 3% bonus for protection.

Which applications are you referring to that cannot gracefully exit if killed?

Quoted 10 lines

---
mm/oom_kill.c | 8 +++++---

 1 files changed, 5 insertions(+), 3 deletions(-)
mm/oom_kill.c +0 -0
index 4029583..df6a9da 100644

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 199

Quoted 7 lines
mm/oom_kill.c +2 -2
@@ -195,10 +195,12 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	task_unlock(p);
 
 	/*
-	 * Root processes get 3% bonus, just like the __vm_enough_memory()
-	 * implementation used by LSMs.
+	 * Root and direct hardware access processes get 3% bonus, just like the
+	 * __vm_enough_memory() implementation used by LSMs.

LSM's have this bonus for CAP_SYS_ADMIN, but not for CAP_SYS_RAWIO, so this comment is incorrect.

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 206

Quoted 8 lines
mm/oom_kill.c +3 -1
 	 */
-	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
 		points -= 30;
 
 	/*

CAP_SYS_RAWIO had a much more dramatic impact in the previous heuristic to such a point that it would often allow memory hogging tasks to elude the oom killer at the expense of innocent tasks. I'm not sure this is the best way to go.

author
#2 lore raw
Quoted 4 lines

Which applications are you referring to that cannot gracefully exit if killed?

like Xorg server, if xorg server be killed, the gnome desktop will be crashed.

Quoted 5 lines

CAP_SYS_RAWIO had a much more dramatic impact in the previous heuristic to such a point that it would often allow memory hogging tasks to elude the oom killer at the expense of innocent tasks. I'm not sure this is the best way to go.

is it some experiments for demonstration the CAP_SYS_RAWIO will elude the oom killer?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#3 lore raw
Quoted 6 lines · Figo.zhang
Quoted 2 lines

Which applications are you referring to that cannot gracefully exit if killed?

like Xorg server, if xorg server be killed, the gnome desktop will be crashed.

Right, but you didn't explicitly prohibit such applications from being killed, so that suggests that doing so may be inconvenient but doesn't incur something like corruption or data loss, which is what I would consider "unstable" or "inconsistent" state.

We're trying to avoid any additional heuristics from being introduced for specific usecases, even for Xorg. That ensures that the heuristic remains as predictable as possible and frees a large amount of memory. If Xorg is being killed first instead of a true memory hogger, then it seems like a forkbomb scenario instead; could you please post your kernel log so that we can diagnose that issue seperately?

Quoted 8 lines
Quoted 4 lines

CAP_SYS_RAWIO had a much more dramatic impact in the previous heuristic to such a point that it would often allow memory hogging tasks to elude the oom killer at the expense of innocent tasks. I'm not sure this is the best way to go.

is it some experiments for demonstration the CAP_SYS_RAWIO will elude the oom killer?

The old heuristic would allow it to elude the oom killer because it would divide the score by four if a task had the capability, which is a much more drastic "bonus" than you suggest here. That would reduce the score for the memory hogging task significantly enough that we killed tons of innocent tasks instead before eventually killing the task that was leaking memory but failed to be identified because it had CAP_SYS_RAWIO. I'm trying to avoid any such repeats.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

author
#4 lore raw

PATCH v2 1/1 oom-kill: CAP_SYS_RESOURCE should get bonus

In reply to Figo.zhang

CAP_SYS_RESOURCE also had better get 3% bonus for protection.

---
mm/oom_kill.c | 3 ++-

 1 files changed, 2 insertions(+), 1 deletions(-)
mm/oom_kill.c +2 -1
index 4029583..30b24b9 100644
@@ -198,7 +198,8 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	 * Root processes get 3% bonus, just like the __vm_enough_memory()
 	 * implementation used by LSMs.
 	 */
-	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE))
 		points -= 30;
 
 	/*

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#5 lore raw

Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 2 lines · Figo.zhang

CAP_SYS_RESOURCE also had better get 3% bonus for protection.

Would you like to elaborate as to why?

Quoted 10 lines

---
mm/oom_kill.c | 3 ++-

 1 files changed, 2 insertions(+), 1 deletions(-)
mm/oom_kill.c +0 -0
index 4029583..30b24b9 100644

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 205

Quoted 9 lines
mm/oom_kill.c +2 -1
@@ -198,7 +198,8 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	 * Root processes get 3% bonus, just like the __vm_enough_memory()
 	 * implementation used by LSMs.
 	 */
-	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE))
 		points -= 30;
 
 	/*

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

A message that is not in the archive (sent off-list or not yet received): [email protected]

#7 lore raw

Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 13 lines · Figo.zhang
Quoted 3 lines

CAP_SYS_RESOURCE also had better get 3% bonus for protection.

Would you like to elaborate as to why?

process with CAP_SYS_RESOURCE capibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process with CAP_SYS_ADMIN.

Best,

Figo.zhang

reviewer NAK
#8 lore raw

Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 4 lines · Figo.zhang
Quoted 4 lines
Quoted 2 lines

CAP_SYS_RESOURCE also had better get 3% bonus for protection.

Quoted 8 lines
Quoted 3 lines

Would you like to elaborate as to why?

process with CAP_SYS_RESOURCE capibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process with CAP_SYS_ADMIN.

NACK, there's no justification that these tasks should be given a 3% memory bonus in the oom killer heuristic; in fact, since they can allocate without limits it is more important to target these tasks if they are using an egregious amount of memory. CAP_SYS_RESOURCE threads have the ability to lower their own oom_score_adj values, thus, they should protect themselves if necessary like everything else.

#9 lore raw

Re: Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 15 lines · David Rientjes
Quoted 4 lines · Figo.zhang
Quoted 4 lines
Quoted 2 lines

CAP_SYS_RESOURCE also had better get 3% bonus for protection.

Quoted 8 lines
Quoted 3 lines

Would you like to elaborate as to why?

process with CAP_SYS_RESOURCE capibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process with CAP_SYS_ADMIN.

Quoted 6 lines

NACK, there's no justification that these tasks should be given a 3% memory bonus in the oom killer heuristic; in fact, since they can allocate without limits it is more important to target these tasks if they are using an egregious amount of memory. CAP_SYS_RESOURCE threads have the ability to lower their own oom_score_adj values, thus, they should protect themselves if necessary like everything else.

In your new heuristic, you also get CAP_SYS_RESOURCE to protection. see fs/proc/base.c, line 1167:

	if (oom_score_adj < task->signal->oom_score_adj &&
			!capable(CAP_SYS_RESOURCE)) {
		err = -EACCES;
		goto err_sighand;
	}

so i want to protect some process like normal process not CAP_SYS_RESOUCE, i set a small oom_score_adj , if new oom_score_adj is small than now and it is not limited resource, it will not adjust, that seems not right?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#10 lore raw

Re: Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 7 lines · Figo.zhang

In your new heuristic, you also get CAP_SYS_RESOURCE to protection. see fs/proc/base.c, line 1167:

	if (oom_score_adj < task->signal->oom_score_adj &&
			!capable(CAP_SYS_RESOURCE)) {
		err = -EACCES;
		goto err_sighand;
	}

That's unchanged from the old behavior with oom_adj.

Quoted 5 lines

so i want to protect some process like normal process not CAP_SYS_RESOUCE, i set a small oom_score_adj , if new oom_score_adj is small than now and it is not limited resource, it will not adjust, that seems not right?

Tasks without CAP_SYS_RESOURCE cannot lower their own oom_score_adj, otherwise it can trivially kill other tasks. They can, however, increase their own oom_score_adj so the oom killer prefers to kill it first.

I think you may be confused: CAP_SYS_RESOURCE override resource limits.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#11 lore raw

Re: Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 12 lines · David Rientjes
Quoted 7 lines · Figo.zhang

In your new heuristic, you also get CAP_SYS_RESOURCE to protection. see fs/proc/base.c, line 1167:

	if (oom_score_adj < task->signal->oom_score_adj &&
			!capable(CAP_SYS_RESOURCE)) {
		err = -EACCES;
		goto err_sighand;
	}

That's unchanged from the old behavior with oom_adj.

Quoted 7 lines
Quoted 5 lines

so i want to protect some process like normal process not CAP_SYS_RESOUCE, i set a small oom_score_adj , if new oom_score_adj is small than now and it is not limited resource, it will not adjust, that seems not right?

Tasks without CAP_SYS_RESOURCE cannot lower their own oom_score_adj,

CAP_SYS_RESOURCE == 1 means without resource limits just like a superuser,
CAP_SYS_RESOURCE == 0 means hold resource limits, like normal user, right?

a new lower oom_score_adj will protect the process, right?

Tasks without CAP_SYS_RESOURCE, means that it is not a superuser, why user canot protect it by oom_score_adj?

like i want to protect my program such as gnome-terminal which is without CAP_SYS_RESOURCE (have resource limits),

[figo@myhost ~]$ ps -ax | grep gnome-ter
Warning: bad ps syntax, perhaps a bogus '-'? See
http://procps.sf.net/faq.html

 2280 ?        Sl     0:01 gnome-terminal
 8839 pts/0    S+     0:00 grep gnome-ter

[figo@myhost ~]$ cat /proc/2280/oom_adj
3
[figo@myhost ~]$ echo -17 > /proc/2280/oom_adj
bash: echo: write error: Permission denied
[figo@myhost ~]$

so, i canot protect my program.

Quoted 4 lines

otherwise it can trivially kill other tasks. They can, however, increase their own oom_score_adj so the oom killer prefers to kill it first.

I think you may be confused: CAP_SYS_RESOURCE override resource limits.

#12 lore raw

Re: Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 5 lines · Figo.zhang

CAP_SYS_RESOURCE == 1 means without resource limits just like a superuser,
CAP_SYS_RESOURCE == 0 means hold resource limits, like normal user, right?

Yes.

Quoted 2 lines

a new lower oom_score_adj will protect the process, right?

Yes.

Quoted 3 lines

Tasks without CAP_SYS_RESOURCE, means that it is not a superuser, why user canot protect it by oom_score_adj?

Because, as I said, it would be trivial for a user program to deplete all memory (either intentionally or unintentioally) and cause every other task on the system to be oom killed as a result. That's an undesired result of a blatently obvious DoS.

Quoted 8 lines

like i want to protect my program such as gnome-terminal which is without CAP_SYS_RESOURCE (have resource limits),

[figo@myhost ~]$ ps -ax | grep gnome-ter
Warning: bad ps syntax, perhaps a bogus '-'? See
http://procps.sf.net/faq.html

 2280 ?        Sl     0:01 gnome-terminal
 8839 pts/0    S+     0:00 grep gnome-ter
Quoted 8 lines

[figo@myhost ~]$ cat /proc/2280/oom_adj
3
[figo@myhost ~]$ echo -17 > /proc/2280/oom_adj
bash: echo: write error: Permission denied
[figo@myhost ~]$

so, i canot protect my program.

If this is your system, you can either give yourself CAP_SYS_RESOURCE or do it through the superuser. This isn't exactly new, it's been the case for the past four years.

I'm still struggling to find out the problem that you're trying to address with your various patches, perhaps because you haven't said what it is.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#13 lore raw

Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

In reply to David Rientjes
Quoted 15 lines · Figo.zhang
Quoted 5 lines
Quoted 5 lines
Quoted 3 lines

CAP_SYS_RESOURCE also had better get 3% bonus for protection.

Quoted 8 lines
Quoted 3 lines

Would you like to elaborate as to why?

process with CAP_SYS_RESOURCE capibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process with CAP_SYS_ADMIN.

Quoted 6 lines

NACK, there's no justification that these tasks should be given a 3% memory bonus in the oom killer heuristic; in fact, since they can allocate without limits it is more important to target these tasks if they are using an egregious amount of memory. CAP_SYS_RESOURCE threads have the ability to lower their own oom_score_adj values, thus, they should protect themselves if necessary like everything else.

David, Stupid are YOU. you removed CAP_SYS_RESOURCE condition with ZERO explanation and Figo reported a regression. That's enough the reason to undo. YOU have a guilty to explain why do you want to change and why do you think it has justification.

Don't blame bug reporter. That's completely wrong.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#14 lore raw

Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 10 lines
Quoted 9 lines
Quoted 4 lines

process with CAP_SYS_RESOURCE capibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process with CAP_SYS_ADMIN.

NACK, there's no justification that these tasks should be given a 3% memory bonus in the oom killer heuristic; in fact, since they can allocate without limits it is more important to target these tasks if they are using an egregious amount of memory.

Quoted 6 lines

David, Stupid are YOU. you removed CAP_SYS_RESOURCE condition with ZERO explanation and Figo reported a regression. That's enough the reason to undo. YOU have a guilty to explain why do you want to change and why do you think it has justification.

Don't blame bug reporter. That's completely wrong.

Can people stop throwing things at each other and worry about the facts

- If it's a regression it should get reverted or fixed. But is it actually a regression ? Has the underlying behaviour changed in a problematic way?

"CAP_SYS_RESOURCE threads have the ability to lower their own oom_score_adj
values, thus, they should protect themselves if necessary like everything else."

The reverse can be argued equally - that they can unprotect themselves if necessary. In fact it seems to be a "point of view" sort of question which way you deal with CAP_SYS_RESOURCE, and that to me argues that changing from old expected behaviour to a new behaviour is a regression.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#15 lore raw

Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 5 lines · Alan Cox

The reverse can be argued equally - that they can unprotect themselves if necessary. In fact it seems to be a "point of view" sort of question which way you deal with CAP_SYS_RESOURCE, and that to me argues that changing from old expected behaviour to a new behaviour is a regression.

I didn't check earlier, but CAP_SYS_RESOURCE hasn't had a place in the oom killer's heuristic in over five years, so what regression are we referring to in this thread? These tasks already have full control over oom_score_adj to modify its oom killing priority in either direction.

And, as I said, giving these threads a bonus to be less preferred doesn't seem appropriate since (1) it's not a defined or expected behavior of CAP_SYS_RESOURCE like it is for sysadmin tasks, and (2) these threads are not bound by resource limits and thus have a higher liklihood of consuming larger amounts of memory.

That's why I nack'd the patch in the first place and still do, there's no regression here and it's not in the best interest of freeing a large amount of memory which is the sole purpose of the oom killer.

Futhermore, the heuristic was entirely rewritten, but I wouldn't consider all the old factors such as cputime and nice level being removed as "regressions" since the aim was to make it more predictable and more likely to kill a large consumer of memory such that we don't have to kill more tasks in the near future.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#16 lore raw

Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 5 lines · David Rientjes

I didn't check earlier, but CAP_SYS_RESOURCE hasn't had a place in the oom killer's heuristic in over five years, so what regression are we referring to in this thread? These tasks already have full control over oom_score_adj to modify its oom killing priority in either direction.

Yes, CAP_SYS_RESOURCE was a part of the heuristic in 2.6.25 along with CAP_SYS_ADMIN and was removed with the rewrite; when I said it "hasn't had a place in the oom killer's heuristic," I meant it's an unnecessary extention to CAP_SYS_ADMIN and allows for killing innocent tasks when a CAP_SYS_RESOURCE task is using too much memory.

The fundamental issue here is whether or not we should give a bonus to CAP_SYS_RESOURCE tasks because they are, by definition, allowed to access extra resources and we're willing to sacrifice other tasks for that. This is antagonist to the oom killer's sole goal, however, which is to kill the task consuming the largest amount of memory unless protected by userspace (which CAP_SYS_RESOURCE has completely control in doing).

Since these threads have complete ability to give themselves this bonus (echo -30 > /proc/self/oom_score_adj), I don't think this needs to be a part of the core heuristic nor with such an arbitrary value of 3% (the old heuristic divided its badness score by 4, another arbitrary value).

author
#17 lore raw

Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

In reply to David Rientjes
Quoted 8 lines · David Rientjes
Quoted 5 lines · Alan Cox

The reverse can be argued equally - that they can unprotect themselves if necessary. In fact it seems to be a "point of view" sort of question which way you deal with CAP_SYS_RESOURCE, and that to me argues that changing from old expected behaviour to a new behaviour is a regression.

Quoted 4 lines

I didn't check earlier, but CAP_SYS_RESOURCE hasn't had a place in the oom killer's heuristic in over five years, so what regression are we referring to in this thread? These tasks already have full control over oom_score_adj to modify its oom killing priority in either direction.

yes, it can control by user, but is it all system administrators will adjust all of the processes by each one and one in real word? suppose if it has thousands of processes in database system.

Quoted 5 lines

Futhermore, the heuristic was entirely rewritten, but I wouldn't consider all the old factors such as cputime and nice level being removed as "regressions" since the aim was to make it more predictable and more likely to kill a large consumer of memory such that we don't have to kill more tasks in the near future.

the goal of oom_killer is to find out the best process to kill, the one should be:
1. it is a most memory comsuming process in all processes
2. and it was a proper process to kill, which will not be let system into unpredictable state as possible.

if a user process and a process such email cleint "evolution" with ditecly hareware access such as "Xorg", they have eat the equal memory, so which process are you want to kill?

#18 lore raw

Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus

Quoted 9 lines · Figo.zhang
Quoted 4 lines

I didn't check earlier, but CAP_SYS_RESOURCE hasn't had a place in the oom killer's heuristic in over five years, so what regression are we referring to in this thread? These tasks already have full control over oom_score_adj to modify its oom killing priority in either direction.

yes, it can control by user, but is it all system administrators will adjust all of the processes by each one and one in real word? suppose if it has thousands of processes in database system.

Yes, the kernel can't possibly know the oom killing priorities of your task so if you have such requirements then you must use the userspace tunable.

Quoted 6 lines
Quoted 5 lines

Futhermore, the heuristic was entirely rewritten, but I wouldn't consider all the old factors such as cputime and nice level being removed as "regressions" since the aim was to make it more predictable and more likely to kill a large consumer of memory such that we don't have to kill more tasks in the near future.

Quoted 6 lines

the goal of oom_killer is to find out the best process to kill, the one should be:
1. it is a most memory comsuming process in all processes
2. and it was a proper process to kill, which will not be let system into unpredictable state as possible.

There are four types of tasks that are improper to kill and this is relatively unchanged in the past five years of the oom killer:

- init,

- kthreads,

- tasks that are bound to a disjoint set of cpuset mems or mempolicy nodes that are not oom, and

- those disabled from oom killing by userspace.

That does not include CAP_SYS_RESOURCE, nor CAP_SYS_ADMIN. Your argument about killing some tasks that have CAP_SYS_RESOURCE leaving hardware in an unpredictable state isn't even addressed by your own patch, you only give them a 3% memory bonus so they are still eligible.

As mentioned previously, for this patch to make sense, you would need to show that CAP_SYS_RESOURCE equates to 3% of the available memory's capacity for a task. I don't believe that evidence has been presented. This has nothing to do with preventing these threads from being killed (at the risk of possibly panicking the machine) since your patch doesn't do that.

Quoted 4 lines

if a user process and a process such email cleint "evolution" with ditecly hareware access such as "Xorg", they have eat the equal memory, so which process are you want to kill?

Both have equal oom killing priority according to the heuristic if they are not run by root. If you would like to protect Xorg, then you need to use the userspace tunable to protect it just like everything else does. This is completely unchanged from the oom killer rewrite.

If you actually have a problem that you're reporting, however, it would probably be better to show the oom killer log from that event and let us address it instead of introducing arbitrary heuristics into something which aims to be as predictable as possible.

Reviewed-by on v1 1/1
#19 lore raw
In reply to Figo.zhang
Quoted 7 lines

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get 3% bonus for protection.

I was surprised this issue is still there. This was pointed out half year ago already :-/

Quoted 9 lines

---
mm/oom_kill.c | 8 +++++---

 1 files changed, 5 insertions(+), 3 deletions(-)
mm/oom_kill.c +0 -0
index 4029583..df6a9da 100644

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 200

Quoted 8 lines
mm/oom_kill.c +2 -2
@@ -195,10 +195,12 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	task_unlock(p);
 
 	/*
-	 * Root processes get 3% bonus, just like the __vm_enough_memory()
-	 * implementation used by LSMs.
+	 * Root and direct hardware access processes get 3% bonus, just like the
+	 * __vm_enough_memory() implementation used by LSMs.
 	 */

This comment is incorrect. LSM is care only CAP_SYS_ADMIN.

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 204

Quoted 5 lines
mm/oom_kill.c +3 -1
-	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
 		points -= 30;

But yes. OOM need to care both CAP_SYS_RESOURCE and CAP_SYS_RAWIO.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

author
#20 lore raw

PATCH v2 1/1 mm/oom-kill: direct hardware access processes should get bonus

In reply to Figo.zhang

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get 3% bonus for protection.

in v2, fix the incorrect comment.

---
mm/oom_kill.c | 7 +++++--

 1 files changed, 5 insertions(+), 2 deletions(-)
mm/oom_kill.c +5 -2
index 4029583..9b06f56 100644
@@ -196,9 +196,12 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 
 	/*
 	 * Root processes get 3% bonus, just like the __vm_enough_memory()
-	 * implementation used by LSMs.
+	 * implementation used by LSMs. And direct hardware access processes
+	 * also get 3% bonus.
 	 */
-	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
 		points -= 30;
 
 	/*

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#21 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 6 lines · Figo.zhang

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get 3% bonus for protection.

The logic here is wrong: if killing these tasks can leave hardware in an unpredictable state (and that state is presumably harmful), then they should be completely immune from oom killing since you're still leaving them exposed here to be killed.

So the question that needs to be answered is: why do these threads deserve to use 3% more memory (not >4%) than others without getting killed? If there was some evidence that these threads have a certain quantity of memory they require as a fundamental attribute of CAP_SYS_RAWIO, then I have no objection, but that's going to be expressed in a memory quantity not a percentage as you have here.

The CAP_SYS_ADMIN heuristic has a background: it is used in the oom killer because we have used the same 3% in __vm_enough_memory() for a long time and we want consistency amongst the heuristics. Adding additional bonuses with arbitrary values like 3% of memory for things like CAP_SYS_RAWIO makes the heuristic less predictable and moves us back toward the old heuristic which was almost entirely arbitrary.

Now before KOSAKI-san comes out and says the old heuristic considered CAP_SYS_RAWIO and the new one does not so it _must_ be a regression: the old heuristic also divided the badness score by 4 for that capability as a completely arbitrary value (just like 3% is here). Other traits like runtime and nice levels were also removed from the heuristic. What needs to be shown is that CAP_SYS_RAWIO requires additional memory just to run or we should neglect to free 3% of memory, which could be gigabytes, because it has this trait.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

author
#22 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 9 lines · David Rientjes
Quoted 6 lines · Figo.zhang

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get 3% bonus for protection.

Quoted 4 lines

The logic here is wrong: if killing these tasks can leave hardware in an unpredictable state (and that state is presumably harmful), then they should be completely immune from oom killing since you're still leaving them exposed here to be killed.

we let the processes with hardware access get bonus for protection. the goal is not select them to be killed as possible.

Quoted 8 lines

So the question that needs to be answered is: why do these threads deserve to use 3% more memory (not >4%) than others without getting killed? If there was some evidence that these threads have a certain quantity of memory they require as a fundamental attribute of CAP_SYS_RAWIO, then I have no objection, but that's going to be expressed in a memory quantity not a percentage as you have here.

Quoted 6 lines

The CAP_SYS_ADMIN heuristic has a background: it is used in the oom killer because we have used the same 3% in __vm_enough_memory() for a long time and we want consistency amongst the heuristics. Adding additional bonuses with arbitrary values like 3% of memory for things like CAP_SYS_RAWIO makes the heuristic less predictable and moves us back toward the old heuristic which was almost entirely arbitrary.

yes, i think it is be better those processes which be protection maybe divided the badness score by 4, like old heuristic.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#23 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

In reply to David Rientjes
Quoted 11 lines
Quoted 5 lines

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get 3% bonus for protection.

The logic here is wrong: if killing these tasks can leave hardware in an unpredictable state (and that state is presumably harmful), then they should be completely immune from oom killing since you're still leaving them exposed here to be killed.

Quoted 6 lines

So the question that needs to be answered is: why do these threads deserve to use 3% more memory (not >4%) than others without getting killed? If there was some evidence that these threads have a certain quantity of memory they require as a fundamental attribute of CAP_SYS_RAWIO, then I have no objection, but that's going to be expressed in a memory quantity not a percentage as you have here.

3% is choosed by you :-/

Quoted 6 lines

The CAP_SYS_ADMIN heuristic has a background: it is used in the oom killer because we have used the same 3% in __vm_enough_memory() for a long time and we want consistency amongst the heuristics. Adding additional bonuses with arbitrary values like 3% of memory for things like CAP_SYS_RAWIO makes the heuristic less predictable and moves us back toward the old heuristic which was almost entirely arbitrary.

That's bogus. __vm_enough_memory() does track virtual adress space. oom-killer doesn't. It's unrelated.

Quoted 8 lines

Now before KOSAKI-san comes out and says the old heuristic considered CAP_SYS_RAWIO and the new one does not so it _must_ be a regression: the old heuristic also divided the badness score by 4 for that capability as a completely arbitrary value (just like 3% is here). Other traits like runtime and nice levels were also removed from the heuristic. What needs to be shown is that CAP_SYS_RAWIO requires additional memory just to run or we should neglect to free 3% of memory, which could be gigabytes, because it has this trait.

Old background is very simple and cleaner.

CAP_SYS_RESOURCE mean the process has a privilege of using more resource. then, oom-killer gave it additonal bonus.

CAP_SYS_RAWIO mean the process has a direct hardware access privilege (eg X.org, RDB). and then, killing it might makes system crash.

In another story, somebody doubt 4x bonus is good or not. but 3% has the same problem.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#24 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 9 lines · KOSAKI Motohiro
Quoted 6 lines

So the question that needs to be answered is: why do these threads deserve to use 3% more memory (not >4%) than others without getting killed? If there was some evidence that these threads have a certain quantity of memory they require as a fundamental attribute of CAP_SYS_RAWIO, then I have no objection, but that's going to be expressed in a memory quantity not a percentage as you have here.

3% is choosed by you :-/

No, 3% was chosen in __vm_enough_memory() for LSMs as the comment in the oom killer shows:

/*
* Root processes get 3% bonus, just like the __vm_enough_memory()
* implementation used by LSMs.
*/

and is described in Documentation/filesystems/proc.txt.

I think in cases of heuristics like this where we obviously want to give some bonus to CAP_SYS_ADMIN that there is consistency with other bonuses given elsewhere in the kernel.

Quoted 2 lines

Old background is very simple and cleaner.

The old heuristic divided the arbitrary badness score by 4 with CAP_SYS_RESOURCE. The new heuristic doesn't consider it.

How is that more clean?

Quoted 3 lines

CAP_SYS_RESOURCE mean the process has a privilege of using more resource. then, oom-killer gave it additonal bonus.

As a side-effect of being given more resources to allocate, those applications are relatively unbounded in terms of memory consumption to other tasks. Thus, it's possible that these applications are using a massive amount of memory (say, 75%) and now with the proposed change a task using 25% of memory would be killed instead. This increases the liklihood that the CAP_SYS_RESOURCE thread will have to be killed eventually, anyway, and the goal is to kill as few tasks as possible to free sufficient amount of memory.

Since threads having CAP_SYS_RESOURCE have full control over their oom_score_adj, they can take the additional precautions to protect themselves if necessary. It doesn't need to be a part of the heuristic to bias these tasks which will lead to the undesired result described above by default rather than intentionally from userspace.

Quoted 3 lines

CAP_SYS_RAWIO mean the process has a direct hardware access privilege (eg X.org, RDB). and then, killing it might makes system crash.

Then you would want to explicitly filter these tasks from oom kill just as OOM_SCORE_ADJ_MIN works rather than giving them a memory quantity bonus.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#25 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 20 lines · KOSAKI Motohiro
Quoted 10 lines
Quoted 7 lines

So the question that needs to be answered is: why do these threads deserve to use 3% more memory (not >4%) than others without getting killed? If there was some evidence that these threads have a certain quantity of memory they require as a fundamental attribute of CAP_SYS_RAWIO, then I have no objection, but that's going to be expressed in a memory quantity not a percentage as you have here.

3% is choosed by you :-/

No, 3% was chosen in __vm_enough_memory() for LSMs as the comment in the oom killer shows:

/*
* Root processes get 3% bonus, just like the __vm_enough_memory()
* implementation used by LSMs.
*/

Quoted 5 lines

and is described in Documentation/filesystems/proc.txt.

I think in cases of heuristics like this where we obviously want to give some bonus to CAP_SYS_ADMIN that there is consistency with other bonuses given elsewhere in the kernel.

Keep comparision apple to apple. vm_enough_memory() account _virtual_ memory. oom-killer try to free _physical_ memory. It's unrelated.

Quoted 13 lines
Quoted 3 lines

Old background is very simple and cleaner.

The old heuristic divided the arbitrary badness score by 4 with CAP_SYS_RESOURCE. The new heuristic doesn't consider it.

How is that more clean?

Quoted 3 lines

CAP_SYS_RESOURCE mean the process has a privilege of using more resource. then, oom-killer gave it additonal bonus.

Quoted 8 lines

As a side-effect of being given more resources to allocate, those applications are relatively unbounded in terms of memory consumption to other tasks. Thus, it's possible that these applications are using a massive amount of memory (say, 75%) and now with the proposed change a task using 25% of memory would be killed instead. This increases the liklihood that the CAP_SYS_RESOURCE thread will have to be killed eventually, anyway, and the goal is to kill as few tasks as possible to free sufficient amount of memory.

You are talking two difference at once. 3% vs 4x and CAP_SYS_RESOURCE and CAP_SYS_ADMIN.

Please keep comparing apple to apple.

Quoted 7 lines

Since threads having CAP_SYS_RESOURCE have full control over their oom_score_adj, they can take the additional precautions to protect themselves if necessary. It doesn't need to be a part of the heuristic to bias these tasks which will lead to the undesired result described above by default rather than intentionally from userspace.

Quoted 6 lines
Quoted 3 lines

CAP_SYS_RAWIO mean the process has a direct hardware access privilege (eg X.org, RDB). and then, killing it might makes system crash.

Then you would want to explicitly filter these tasks from oom kill just as OOM_SCORE_ADJ_MIN works rather than giving them a memory quantity bonus.

No. Why does userland recover your mistake?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#26 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 7 lines · KOSAKI Motohiro
Quoted 3 lines

I think in cases of heuristics like this where we obviously want to give some bonus to CAP_SYS_ADMIN that there is consistency with other bonuses given elsewhere in the kernel.

Keep comparision apple to apple. vm_enough_memory() account _virtual_ memory. oom-killer try to free _physical_ memory. It's unrelated.

It's not unrelated, the LSM function gives an arbitrary 3% bonus to CAP_SYS_ADMIN. Such threads should also be preferred in the oom killer over other threads since they tend to be more important but not an overly drastic bias such that they don't get killed when using an egregious amount of memory. So in selecting a small percentage of memory that tends to be a significant bias but not overwhelming, I went with the 3% found elsewhere in the kernel. __vm_enough_memory() doesn't have that preference for any scientifically calculated reason, it's a heuristic just like oom_badness().

Quoted 9 lines
Quoted 6 lines
Quoted 3 lines

CAP_SYS_RAWIO mean the process has a direct hardware access privilege (eg X.org, RDB). and then, killing it might makes system crash.

Then you would want to explicitly filter these tasks from oom kill just as OOM_SCORE_ADJ_MIN works rather than giving them a memory quantity bonus.

No. Why does userland recover your mistake?

You just said killing any CAP_SYS_RAWIO task may make the system crash, so presuming that you don't want the system to crash, you are suggesting we should make these threads completely immune? That's never been the case (and isn't for oom_kill_allocating_task, either), so there's no history you can draw from to support your argument.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#27 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 6 lines · KOSAKI Motohiro
Quoted 5 lines
Quoted 4 lines

I think in cases of heuristics like this where we obviously want to give some bonus to CAP_SYS_ADMIN that there is consistency with other bonuses given elsewhere in the kernel.

Quoted 6 lines
Quoted 3 lines

Keep comparision apple to apple. vm_enough_memory() account _virtual_ memory. oom-killer try to free _physical_ memory. It's unrelated.

It's not unrelated, the LSM function gives an arbitrary 3% bonus to CAP_SYS_ADMIN.

Unrelated. LSM _is_ security module. and It only account virtual memory.

Quoted 8 lines

Such threads should also be preferred in the oom killer
over other threads since they tend to be more important but not an overly drastic bias such that they don't get killed when using an egregious amount of memory. So in selecting a small percentage of memory that tends to be a significant bias but not overwhelming, I went with the 3% found elsewhere in the kernel. __vm_enough_memory() doesn't have that preference for any scientifically calculated reason, it's a heuristic just like oom_badness().

__vm_enough_memory() only gurard to memory overcommiting. And it doesn't have any recover way. We expect admin should recover their HAND. In the other hand, oom-killer _is_ automatic recover way. It's no need admin's hand. That's the reason why CAP_ADMIN is important or not.

Quoted 7 lines
Quoted 7 lines
Quoted 6 lines
Quoted 3 lines

CAP_SYS_RAWIO mean the process has a direct hardware access privilege (eg X.org, RDB). and then, killing it might makes system crash.

Then you would want to explicitly filter these tasks from oom kill just as OOM_SCORE_ADJ_MIN works rather than giving them a memory quantity bonus.

Quoted 8 lines
Quoted 2 lines

No. Why does userland recover your mistake?

You just said killing any CAP_SYS_RAWIO task may make the system crash, so presuming that you don't want the system to crash, you are suggesting we should make these threads completely immune? That's never been the case (and isn't for oom_kill_allocating_task, either), so there's no history you can draw from to support your argument.

No. I only require YOU have to investigate userland usecase BEFORE making change.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#28 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 4 lines · KOSAKI Motohiro
Quoted 4 lines
Quoted 4 lines
Quoted 3 lines

I think in cases of heuristics like this where we obviously want to give some bonus to CAP_SYS_ADMIN that there is consistency with other bonuses given elsewhere in the kernel.

Quoted 9 lines
Quoted 6 lines
Quoted 3 lines

Keep comparision apple to apple. vm_enough_memory() account _virtual_ memory. oom-killer try to free _physical_ memory. It's unrelated.

It's not unrelated, the LSM function gives an arbitrary 3% bonus to CAP_SYS_ADMIN.

Unrelated. LSM _is_ security module. and It only account virtual memory.

I needed a small bias for CAP_SYS_ADMIN tasks so I chose 3% since it's the same proportion used elsewhere in the kernel and works nicely since the badness score is now a proportion. If you'd like to propose a different percentage or suggest removing the bias for root tasks altogether, feel free to propose a patch. Thanks!

#29 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 13 lines · KOSAKI Motohiro
Quoted 12 lines
Quoted 11 lines
Quoted 8 lines
Quoted 4 lines

I think in cases of heuristics like this where we obviously want to give some bonus to CAP_SYS_ADMIN that there is consistency with other bonuses given elsewhere in the kernel.

Keep comparision apple to apple. vm_enough_memory() account _virtual_ memory. oom-killer try to free _physical_ memory. It's unrelated.

It's not unrelated, the LSM function gives an arbitrary 3% bonus to CAP_SYS_ADMIN.

Quoted 6 lines
Quoted 2 lines

Unrelated. LSM _is_ security module. and It only account virtual memory.

I needed a small bias for CAP_SYS_ADMIN tasks so I chose 3% since it's the same proportion used elsewhere in the kernel and works nicely since the badness score is now a proportion.

Why? Is this important than X?

Quoted 3 lines

If you'd like to propose a different
percentage or suggest removing the bias for root tasks altogether, feel free to propose a patch. Thanks!

I only need to revert bad change.

Thanks.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#30 lore raw

Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus

Quoted 6 lines · KOSAKI Motohiro
Quoted 3 lines

I needed a small bias for CAP_SYS_ADMIN tasks so I chose 3% since it's the same proportion used elsewhere in the kernel and works nicely since the badness score is now a proportion.

Why? Is this important than X?

We have always preferred to break ties between applications by not preferring the root task over the user task in the oom killer. If you'd like to remove this bonus for CAP_SYS_ADMIN, please propose a patch. Thanks!

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

author
#31 lore raw

PATCH v3 1/1 mm/oom-kill: direct hardware access processes should get bonus

In reply to Figo.zhang

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get bonus for protection.

in v2, fix the incorrect comment.
in v3, change the divided the badness score by 4, like old heuristic for protection. we just want the oom_killer don't select Root/RESOURCE/RAWIO process as possible.

suppose that if a user process A such as email cleint "evolution" and a process B with ditecly hareware access such as "Xorg", they have eat the equal memory (the badness score is the same),so which process are you want to kill? so in new heuristic, it will kill the process B. but in reality, we want to kill process A.

mm/oom_kill.c | 9 +++++++++

 1 files changed, 9 insertions(+), 0 deletions(-)
mm/oom_kill.c +9 -0
index 4029583..f43d759 100644
@@ -202,6 +202,15 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 		points -= 30;
 
 	/*
+	 * Root and direct hareware access processor are usually more 
+	 * important, so them should get bonus for protection. 
+	 */
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
+		points /= 4;
+
+	/*
 	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
 	 * either completely disable oom killing or always prefer a certain
 	 * task.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

author
#32 lore raw

PATCH v3 1/1 mm/oom-kill: direct hardware access processes should get bonus

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get bonus for protection.

in v2, fix the incorrect comment.
in v3, change the divided the badness score by 4, like old heuristic for protection. we just want the oom_killer don't select Root/RESOURCE/RAWIO process as possible.

suppose that if a user process A such as email cleint "evolution" and a process B with ditecly hareware access such as "Xorg", they have eat the equal memory (the badness score is the same),so which process are you want to kill? so in new heuristic, it will kill the process B. but in reality, we want to kill process A.

---
mm/oom_kill.c | 9 +++++++++

 1 files changed, 9 insertions(+), 0 deletions(-)
mm/oom_kill.c +9 -0
index 4029583..f43d759 100644
@@ -202,6 +202,15 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 		points -= 30;
 
 	/*
+	 * Root and direct hareware access processes are usually more 
+	 * important, so they should get bonus for protection. 
+	 */
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
+		points /= 4;
+
+	/*
 	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
 	 * either completely disable oom killing or always prefer a certain
 	 * task.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#33 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

Quoted 5 lines · Figo.zhang

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get bonus for protection.

Again, this argument doesn't work: if killing the task leaves hardware in an unpredictable state (and that's presumably harmful), then they shouldn't be killed at all.

Please show why CAP_SYS_RESOURCE equates to 3% additional memory for such tasks.

CAP_SYS_RESOURCE allows those threads to override resource limits, so these have potentially unbounded amounts of memory usage. Thus, they may have the highest memory usage on the machine and now your patch has caused other innocent tasks to be killed before this is actually targeted. That's a bad result. Why do we need this type of hack in the oom killer when these threads have the privilege to modify oom killing priorities for all tasks on the system? Laziness, at the cost of a less predictable heuristic?

Why aren't you doing the same change for __vm_enough_memory() for LSMs?

Quoted 9 lines

in v2, fix the incorrect comment.
in v3, change the divided the badness score by 4, like old heuristic for protection. we just want the oom_killer don't select Root/RESOURCE/RAWIO process as possible.

suppose that if a user process A such as email cleint "evolution" and a process B with ditecly hareware access such as "Xorg", they have eat the equal memory (the badness score is the same),so which process are you want to kill? so in new heuristic, it will kill the process B. but in reality, we want to kill process A.

Then you need to protect process B accordingly and since it has CAP_SYS_RESOURCE it can easily do that on its own or the admin can protect Xorg.

Quoted 2 lines

Unless you did this in private, I didn't see KOSAKI-san's reviewed-by line for this change and it is drastically different from what you've proposed before.

Quoted 10 lines

---
mm/oom_kill.c | 9 +++++++++

 1 files changed, 9 insertions(+), 0 deletions(-)
mm/oom_kill.c +0 -0
index 4029583..f43d759 100644
@@ -202,6 +202,15 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 		points -= 30;

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 212

Quoted 10 lines
mm/oom_kill.c +8 -0
 
 	/*
+	 * Root and direct hareware access processes are usually more 
+	 * important, so they should get bonus for protection. 
+	 */
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
+		points /= 4;
+

What on earth? So now CAP_SYS_ADMIN gets a 3% bonus in the if-clause above this, then we divide a percentage of memory use by 4? What does that mean AT ALL?

And now you've thrown CAP_SYS_RAWIO in there without any mention in the changelog?

Are you just trying to introduce all the old arbitrary heuristics from before the rewrite back into the oom killer like this?

Do you actually have a log from an event where the oom killer targeted the incorrect task?

#34 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

In reply to Figo.zhang
Quoted 9 lines

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get bonus for protection.

in v2, fix the incorrect comment.
in v3, change the divided the badness score by 4, like old heuristic for protection. we just want the oom_killer don't select Root/RESOURCE/RAWIO process as possible.

Quoted 7 lines

suppose that if a user process A such as email cleint "evolution" and a process B with ditecly hareware access such as "Xorg", they have eat the equal memory (the badness score is the same),so which process are you want to kill? so in new heuristic, it will kill the process B. but in reality, we want to kill process A.

Sorry for the delay. I've sent completely revert patch to linus. It will disappear your headache, I believe. I'm sorry that our development caused your harm. We really don't want it.

Thanks.

Quoted 16 lines

---
mm/oom_kill.c | 9 +++++++++

 1 files changed, 9 insertions(+), 0 deletions(-)
mm/oom_kill.c +2 -0
index 4029583..f43d759 100644
@@ -202,6 +202,15 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 		points -= 30;
 
 	/*
+	 * Root and direct hareware access processes are usually more 
+	 * important, so they should get bonus for protection. 

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 216

Quoted 10 lines
mm/oom_kill.c +7 -0
+	 */
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
+		points /= 4;
+
+	/*
 	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
 	 * either completely disable oom killing or always prefer a certain
 	 * task.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#35 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

Quoted 14 lines · KOSAKI Motohiro
Quoted 14 lines

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get bonus for protection.

in v2, fix the incorrect comment.
in v3, change the divided the badness score by 4, like old heuristic for protection. we just want the oom_killer don't select Root/RESOURCE/RAWIO process as possible.

suppose that if a user process A such as email cleint "evolution" and a process B with ditecly hareware access such as "Xorg", they have eat the equal memory (the badness score is the same),so which process are you want to kill? so in new heuristic, it will kill the process B. but in reality, we want to kill process A.

Quoted 7 lines
Quoted 2 lines

Sorry for the delay. I've sent completely revert patch to linus. It will disappear your headache, I believe. I'm sorry that our development caused your harm. We really don't want it.

Oh please, your dramatics are getting better and better.

Figo.zhang never described a problem that was being addressed but rather proposed several different variants of a patch (some with CAP_SYS_ADMIN, some with CAP_SYS_RESOURCE, some with CAP_SYS_RAWIO, some with a combination, some with a 3% bonus, some with a order-of-2 bonus, etc) to return the same heuristic used in the old oom killer. I asked several times to show the oom killer log from the problematic behavior and none were presented.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#36 lore raw

Re: [PATCH] Revert oom rewrite series

Quoted 5 lines

Nothing to say, really. Seems each time we're told about a bug or a regression, David either fixes the bug or points out why it wasn't a bug or why it wasn't a regression or how it was a deliberate behaviour change for the better.

Quoted 7 lines

I just haven't seen any solid reason to be concerned about the state of the current oom-killer, sorry.

I'm concerned that you're concerned! A lot. When someone such as yourself is unhappy with part of MM then I sit up and pay attention. But after all this time I simply don't understand the technical issues which you're seeing here.

we just talk about oom-killer technical issues.

i am doubt that a new rewrite but the athor canot provide some evidence and experiment result, why did you do that? what is the prominent change for your new algorithm?

as KOSAKI Motohiro said, "you removed CAP_SYS_RESOURCE condition with ZERO explanation".

David just said that pls use userspace tunable for protection by oom_score_adj. but may i ask question:

1. what is your innovation for your new algorithm, the old one have the same way for user tunable oom_adj.

2. if server like db-server/financial-server have huge import processes (such as root/hardware access processes)want to be protection, you let the administrator to find out which processes should be protection. you will let the financial-server administrator huge crazy!! and lose so many money!! ^~^

3. i see your email in LKML, you just said
"I have repeatedly said that the oom killer no longer kills KDE when run on my desktop in the presence of a memory hogging task that was written specifically to oom the machine."
http://thread.gmane.org/gmane.linux.kernel.mm/48998

so you just test your new oom_killer algorithm on your desktop with KDE, so have you provide the detail how you do the test? is it do the experiment again for anyone and got the same result as your comment ?

as KOSAKI Motohiro said, in reality word, it we makes 5-6 brain simulation, embedded, desktop, web server,db server, hpc, finance. Different workloads certenally makes big impact. have you do those experiments?

i think that technology should base on experiment not on imagine.

Best,
Figo.zhang

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#37 lore raw

Re: [PATCH] Revert oom rewrite series

Quoted 4 lines · Figo.zhang

i am doubt that a new rewrite but the athor canot provide some evidence and experiment result, why did you do that? what is the prominent change for your new algorithm?

Quoted 9 lines

as KOSAKI Motohiro said, "you removed CAP_SYS_RESOURCE condition with ZERO explanation".

David just said that pls use userspace tunable for protection by oom_score_adj. but may i ask question:

1. what is your innovation for your new algorithm, the old one have the same way for user tunable oom_adj.

The goal was to make the oom killer heuristic as predictable as possible and to kill the most memory-hogging task to avoid having to recall it and needlessly kill several tasks.

The goal behind oom_score_adj vs. oom_adj was for several reasons, as pointed out before:

- give it a unit (proportion of available memory), oom_adj had no unit,

- allow it to work on a linear scale for more control over prioritization, oom_adj had an exponential scale,

- give it a much higher resolution so it can be fine-tuned, it works with a granularity of 0.1% of memory (~128M on a 128G machine), and

- allow it to describe the oom killing priority of a task regardless of its cpuset attachment, mempolicy, or memcg, or when their respective limits change.

Quoted 6 lines

2. if server like db-server/financial-server have huge import processes (such as root/hardware access processes)want to be protection, you let the administrator to find out which processes should be protection. you will let the financial-server administrator huge crazy!! and lose so many money!! ^~^

You have full control over disabling a task from being considered with oom_score_adj just like you did with oom_adj. Since oom_adj is deprecated for two years, you can even use the old interface until then.

Quoted 10 lines

3. i see your email in LKML, you just said
"I have repeatedly said that the oom killer no longer kills KDE when run on my desktop in the presence of a memory hogging task that was written specifically to oom the machine."
http://thread.gmane.org/gmane.linux.kernel.mm/48998

so you just test your new oom_killer algorithm on your desktop with KDE, so have you provide the detail how you do the test? is it do the experiment again for anyone and got the same result as your comment ?

Xorg tends to be killed less because of the change to the heuristic's baseline, which is now based on rss and swap instead of total_vm. This is seperate from the issues you list above, but is a benefit to the oom killer that desktop users especially will notice. I, personally, am interested more in the server market and that's why I looked for a more robust userspace tunable that would still be applicable when things like cpusets have a node added or removed.

#38 lore raw

Re: [PATCH] Revert oom rewrite series

Quoted 3 lines

The goal was to make the oom killer heuristic as predictable as possible and to kill the most memory-hogging task to avoid having to recall it and needlessly kill several tasks.

Meta question - why is that a good thing. In a desktop environment it's frequently wrong, in a server environment it is often wrong. We had this before where people spend months fiddling with the vm and make it work slightly differently and it suits their workload, then other workloads go downhill. Then the cycle repeats.

Quoted 3 lines

You have full control over disabling a task from being considered with oom_score_adj just like you did with oom_adj. Since oom_adj is deprecated for two years, you can even use the old interface until then.

Which changeset added it to the Documentation directory as deprecated ?

Alan

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#39 lore raw

Re: [PATCH] Revert oom rewrite series

Quoted 10 lines · Alan Cox
Quoted 3 lines

The goal was to make the oom killer heuristic as predictable as possible and to kill the most memory-hogging task to avoid having to recall it and needlessly kill several tasks.

Meta question - why is that a good thing. In a desktop environment it's frequently wrong, in a server environment it is often wrong. We had this before where people spend months fiddling with the vm and make it work slightly differently and it suits their workload, then other workloads go downhill. Then the cycle repeats.

Most of the arbitrary heuristics were removed from oom_badness(), things like nice level, runtime, CAP_SYS_RESOURCE, etc., so that we only consider the rss and swap usage of each application in comparison to each other when deciding which task to kill. We give root tasks a 3% bonus since they tend to be more important to the productivity or uptime of the machine, which did exist -- albeit with a more dramatic impact -- in the old heursitic.

You'll find that the new heuristic always kills the task consuming the most amount of rss unless influenced by userspace via the tunables (or within 3% of root tasks).

We always want to kill the most memory-hogging task because it avoids needlessly killing additional tasks when we must immediately recall the oom killer because we continue to allocate memory. If that task happens to be of vital importance to userspace, then the user has full control over tuning the oom killer priorities in such circumstances.

Quoted 6 lines
Quoted 3 lines

You have full control over disabling a task from being considered with oom_score_adj just like you did with oom_adj. Since oom_adj is deprecated for two years, you can even use the old interface until then.

Which changeset added it to the Documentation directory as deprecated ?

51b1bd2a was the actual change that deprecated it, which was a direct follow-up to a63d83f4 which actually obsoleted it.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#40 lore raw

Re: [PATCH] Revert oom rewrite series

In reply to Alan Cox

sorry for the delay.

Quoted 10 lines
Quoted 3 lines

The goal was to make the oom killer heuristic as predictable as possible and to kill the most memory-hogging task to avoid having to recall it and needlessly kill several tasks.

Meta question - why is that a good thing. In a desktop environment it's frequently wrong, in a server environment it is often wrong. We had this before where people spend months fiddling with the vm and make it work slightly differently and it suits their workload, then other workloads go downhill. Then the cycle repeats.

Quoted 5 lines
Quoted 3 lines

You have full control over disabling a task from being considered with oom_score_adj just like you did with oom_adj. Since oom_adj is deprecated for two years, you can even use the old interface until then.

Which changeset added it to the Documentation directory as deprecated ?

It's insufficient.
a63d83f427fbce97a6cea0db2e64b0eb8435cd10 (oom: badness heuristic rewrite) introduced a lot of incompatibility to oom_adj and oom_score. Theresore I would sugestted full revert and resubmit some patches which cherry pick no pain piece.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#41 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

In reply to Figo.zhang

i had send the patch to protect the hardware access processes for oom-killer before, but rientjes have not agree with me.

but today i catch log from my desktop. oom-killer have kill my "minicom" and "Xorg". so i think it should add protection about it.

my desktop run on linux-2.6.36.

[figo@figo-desktop android]$ uname -a
Linux figo-desktop 2.6.36-ARCH #1 SMP PREEMPT Fri Dec 10 20:01:53 UTC 2010 i686 Intel(R) Core(TM)2 Duo CPU E8400 @ 3.00GHz GenuineIntel GNU/Linux [figo@figo-desktop android]$

pls see the log:

Quoted 858 lines
Jan  4 15:22:17 figo-desktop kernel: Mem-Info:
Jan  4 15:22:17 figo-desktop kernel: DMA per-cpu:
Jan  4 15:22:17 figo-desktop kernel: CPU    0: hi:    0, btch:   1 usd:   0
Jan  4 15:22:17 figo-desktop kernel: CPU    1: hi:    0, btch:   1 usd:   0
Jan  4 15:22:17 figo-desktop kernel: Normal per-cpu:
Jan  4 15:22:17 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  61
Jan  4 15:22:17 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:  31
Jan  4 15:22:17 figo-desktop kernel: HighMem per-cpu:
Jan  4 15:22:17 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  51
Jan  4 15:22:17 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:  50
Jan  4 15:22:17 figo-desktop kernel: active_anon:123081 inactive_anon:170583 isolated_anon:0
Jan  4 15:22:17 figo-desktop kernel: active_file:53958 inactive_file:122582 isolated_file:0
Jan  4 15:22:17 figo-desktop kernel: unevictable:17 dirty:6 writeback:31 unstable:0
Jan  4 15:22:17 figo-desktop kernel: free:11919 slab_reclaimable:5454 slab_unreclaimable:6124
Jan  4 15:22:17 figo-desktop kernel: mapped:49964 shmem:29206 pagetables:2585 bounce:0
Jan  4 15:22:17 figo-desktop kernel: DMA free:7976kB min:64kB low:80kB high:96kB active_anon:1272kB inactive_anon:4672kB active_file:516kB inactive_file:760kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15788kB mlocked:0kB dirty:0kB writeback:0kB mapped:752kB shmem:488kB slab_reclaimable:480kB slab_unreclaimable:112kB kernel_stack:8kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:2513 all_unreclaimable? no
Jan  4 15:22:17 figo-desktop kernel: lowmem_reserve[]: 0 865 1980 1980
Jan  4 15:22:17 figo-desktop kernel: Normal free:39220kB min:3728kB low:4660kB high:5592kB active_anon:137716kB inactive_anon:312976kB active_file:85368kB inactive_file:207988kB unevictable:68kB isolated(anon):0kB isolated(file):0kB present:885944kB mlocked:68kB dirty:0kB writeback:0kB mapped:57464kB shmem:45012kB slab_reclaimable:21336kB slab_unreclaimable:24384kB kernel_stack:3272kB pagetables:10340kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:441679 all_unreclaimable? yes
Jan  4 15:22:17 figo-desktop kernel: lowmem_reserve[]: 0 0 8921 8921
Jan  4 15:22:17 figo-desktop kernel: HighMem free:480kB min:512kB low:1712kB high:2912kB active_anon:353336kB inactive_anon:364684kB active_file:129948kB inactive_file:281580kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:1141984kB mlocked:0kB dirty:24kB writeback:124kB mapped:141640kB shmem:71324kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:650648 all_unreclaimable? yes
Jan  4 15:22:17 figo-desktop kernel: lowmem_reserve[]: 0 0 0 0
Jan  4 15:22:17 figo-desktop kernel: DMA: 1482*4kB 256*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 7976kB
Jan  4 15:22:17 figo-desktop kernel: Normal: 1409*4kB 3862*8kB 44*16kB 8*32kB 3*64kB 2*128kB 3*256kB 1*512kB 0*1024kB 0*2048kB 0*4096kB = 39220kB
Jan  4 15:22:17 figo-desktop kernel: HighMem: 20*4kB 10*8kB 18*16kB 1*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 480kB
Jan  4 15:22:17 figo-desktop kernel: 212446 total pagecache pages
Jan  4 15:22:17 figo-desktop kernel: 6668 pages in swap cache
Jan  4 15:22:17 figo-desktop kernel: Swap cache stats: add 789540, delete 782872, find 277051/391346
Jan  4 15:22:17 figo-desktop kernel: Free swap  = -28688kB
Jan  4 15:22:17 figo-desktop kernel: Total swap = 0kB
Jan  4 15:22:17 figo-desktop kernel: 515070 pages RAM
Jan  4 15:22:17 figo-desktop kernel: 287745 pages HighMem
Jan  4 15:22:17 figo-desktop kernel: 8297 pages reserved
Jan  4 15:22:17 figo-desktop kernel: 306524 pages shared
Jan  4 15:22:17 figo-desktop kernel: 304318 pages non-shared
Jan  4 15:22:17 figo-desktop kernel: [ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name
Jan  4 15:22:17 figo-desktop kernel: [  583]     0   583      581      221   0     -17         -1000 udevd
Jan  4 15:22:17 figo-desktop kernel: [ 1303]     0  1303      868       37   0       0             0 syslog-ng
Jan  4 15:22:17 figo-desktop kernel: [ 1304]     0  1304     1604      358   0       0             0 syslog-ng
Jan  4 15:22:17 figo-desktop kernel: [ 1306]    81  1306      808      351   0       0             0 dbus-daemon
Jan  4 15:22:17 figo-desktop kernel: [ 1309]    82  1309     3777      366   1       0             0 hald
Jan  4 15:22:17 figo-desktop kernel: [ 1310]     0  1310      903      128   1       0             0 hald-runner
Jan  4 15:22:17 figo-desktop kernel: [ 1339]     0  1339      919       92   0       0             0 hald-addon-inpu
Jan  4 15:22:17 figo-desktop kernel: [ 1357]     0  1357      919      184   0       0             0 hald-addon-stor
Jan  4 15:22:17 figo-desktop kernel: [ 1359]    82  1359      824      107   1       0             0 hald-addon-acpi
Jan  4 15:22:17 figo-desktop kernel: [ 1448]     0  1448      616      294   1       0             0 crond
Jan  4 15:22:17 figo-desktop kernel: [ 1477]     0  1477      720      107   0       0             0 mysqld_safe
Jan  4 15:22:17 figo-desktop kernel: [ 1484]     0  1484     3580      269   0       0             0 gdm-binary
Jan  4 15:22:17 figo-desktop kernel: [ 1497]     0  1497      440       67   1       0             0 agetty
Jan  4 15:22:17 figo-desktop kernel: [ 1498]     0  1498      440       67   0       0             0 agetty
Jan  4 15:22:17 figo-desktop kernel: [ 1499]     0  1499      440       67   0       0             0 agetty
Jan  4 15:22:17 figo-desktop kernel: [ 1500]     0  1500      440       67   1       0             0 agetty
Jan  4 15:22:17 figo-desktop kernel: [ 1501]     0  1501      440       67   0       0             0 agetty
Jan  4 15:22:17 figo-desktop kernel: [ 1502]     0  1502      440       68   0       0             0 agetty
Jan  4 15:22:17 figo-desktop kernel: [ 1553]     0  1553     6607      615   0       0             0 NetworkManager
Jan  4 15:22:17 figo-desktop kernel: [ 1592]     0  1592     2256      329   0       0             0 cupsd
Jan  4 15:22:17 figo-desktop kernel: [ 1597]    89  1597    29903     2811   1       0             0 mysqld
Jan  4 15:22:17 figo-desktop kernel: [ 1598]     0  1598     1652      147   1     -17         -1000 sshd
Jan  4 15:22:17 figo-desktop kernel: [ 1612]     0  1612     6263      506   1       0             0 polkitd
Jan  4 15:22:17 figo-desktop kernel: [ 1613]     0  1613     2015      122   0       0             0 vmware-usbarbit
Jan  4 15:22:17 figo-desktop kernel: [ 1617]     0  1617     2887     1483   1       0             0 cntlm
Jan  4 15:22:17 figo-desktop kernel: [ 1620]     0  1620     4398      365   0       0             0 gdm-simple-slav
Jan  4 15:22:17 figo-desktop kernel: [ 1636]     0  1636    37300    12287   0       0             0 Xorg
Jan  4 15:22:17 figo-desktop kernel: [ 1638]     0  1638     1248       88   0       0             0 wpa_supplicant
Jan  4 15:22:17 figo-desktop kernel: [ 1720]     0  1720     4789     1551   1       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [ 1722]     0  1722      488       93   0       0             0 dhcpcd
Jan  4 15:22:17 figo-desktop kernel: [ 1732]     0  1732      519       62   1       0             0 vmnet-bridge
Jan  4 15:22:17 figo-desktop kernel: [ 1750]     0  1750     4922      302   1       0             0 smbd
Jan  4 15:22:17 figo-desktop kernel: [ 1764]     0  1764      655       39   1       0             0 vmnet-dhcpd
Jan  4 15:22:17 figo-desktop kernel: [ 1772]     0  1772      513       15   0       0             0 vmnet-netifup
Jan  4 15:22:17 figo-desktop kernel: [ 1774]     0  1774      655       39   0       0             0 vmnet-dhcpd
Jan  4 15:22:17 figo-desktop kernel: [ 1776]     0  1776     4922      224   0       0             0 smbd
Jan  4 15:22:17 figo-desktop kernel: [ 1778]     0  1778      634       44   0       0             0 vmnet-natd
Jan  4 15:22:17 figo-desktop kernel: [ 1780]     0  1780      513       14   1       0             0 vmnet-netifup
Jan  4 15:22:17 figo-desktop kernel: [ 1796]     0  1796     6677      326   0       0             0 console-kit-dae
Jan  4 15:22:17 figo-desktop kernel: [ 1899]   120  1899     6587      598   0       0             0 polkit-gnome-au
Jan  4 15:22:17 figo-desktop kernel: [ 1903]     0  1903     3905      245   0       0             0 gdm-session-wor
Jan  4 15:22:17 figo-desktop kernel: [ 1906]     0  1906     3677      314   1       0             0 upowerd
Jan  4 15:22:17 figo-desktop kernel: [ 1974]  1000  1974    10963     1246   0       0             0 gnome-keyring-d
Jan  4 15:22:17 figo-desktop kernel: [ 1993]  1000  1993     9253      768   0       0             0 gnome-session
Jan  4 15:22:17 figo-desktop kernel: [ 2012]  1000  2012      796      102   0       0             0 dbus-launch
Jan  4 15:22:17 figo-desktop kernel: [ 2013]  1000  2013     5854     3940   0       0             0 dbus-daemon
Jan  4 15:22:17 figo-desktop kernel: [ 2015]  1000  2015      887       54   0       0             0 ssh-agent
Jan  4 15:22:17 figo-desktop kernel: [ 2022]  1000  2022    10904     4577   0       0             0 fcitx
Jan  4 15:22:17 figo-desktop kernel: [ 2032]  1000  2032    41764     1992   0       0             0 gnome-settings-
Jan  4 15:22:17 figo-desktop kernel: [ 2036]  1000  2036     2367      413   0       0             0 gvfsd
Jan  4 15:22:17 figo-desktop kernel: [ 2039]  1000  2039    85188    29574   1       0             0 metacity
Jan  4 15:22:17 figo-desktop kernel: [ 2049]  1000  2049    14162      277   1       0             0 gvfs-fuse-daemo
Jan  4 15:22:17 figo-desktop kernel: [ 2053]  1000  2053    76657     3521   1       0             0 gnome-panel
Jan  4 15:22:17 figo-desktop kernel: [ 2056]  1000  2056    10978      456   1       0             0 gvfs-gdu-volume
Jan  4 15:22:17 figo-desktop kernel: [ 2058]     0  2058     5767      451   1       0             0 udisks-daemon
Jan  4 15:22:17 figo-desktop kernel: [ 2059]     0  2059     1291       72   1       0             0 udisks-daemon
Jan  4 15:22:17 figo-desktop kernel: [ 2069]  1000  2069   168292    49344   1       0             0 nautilus
Jan  4 15:22:17 figo-desktop kernel: [ 2071]  1000  2071    12907      223   0       0             0 bonobo-activati
Jan  4 15:22:17 figo-desktop kernel: [ 2081]  1000  2081     1633      136   0       0             0 sh
Jan  4 15:22:17 figo-desktop kernel: [ 2082]  1000  2082     1666      136   1       0             0 thunderbird
Jan  4 15:22:17 figo-desktop kernel: [ 2084]  1000  2084    46718     3505   1       0             0 wnck-applet
Jan  4 15:22:17 figo-desktop kernel: [ 2086]  1000  2086    42862     1463   0       0             0 polkit-gnome-au
Jan  4 15:22:17 figo-desktop kernel: [ 2087]  1000  2087   285933     1579   0       0             0 nm-applet
Jan  4 15:22:17 figo-desktop kernel: [ 2104]  1000  2104     5056      693   1       0             0 gdu-notificatio
Jan  4 15:22:17 figo-desktop kernel: [ 2107]  1000  2107     1666      142   1       0             0 run-mozilla.sh
Jan  4 15:22:17 figo-desktop kernel: [ 2108]  1000  2108    39395      919   0       0             0 gnome-power-man
Jan  4 15:22:17 figo-desktop kernel: [ 2109]  1000  2109     7886      701   0       0             0 vino-server
Jan  4 15:22:17 figo-desktop kernel: [ 2110]  1000  2110    10764      791   1       0             0 evolution-alarm
Jan  4 15:22:17 figo-desktop kernel: [ 2114]  1000  2114   167865    28925   1       0             0 thunderbird-bin
Jan  4 15:22:17 figo-desktop kernel: [ 2121]  1000  2121    42098     1969   1       0             0 notify-osd
Jan  4 15:22:17 figo-desktop kernel: [ 2125]  1000  2125    42488     1203   0       0             0 cpufreq-applet
Jan  4 15:22:17 figo-desktop kernel: [ 2126]  1000  2126    41394     1145   1       0             0 multiload-apple
Jan  4 15:22:17 figo-desktop kernel: [ 2129]  1000  2129    64405     1826   0       0             0 mixer_applet2
Jan  4 15:22:17 figo-desktop kernel: [ 2131]  1000  2131    75346     2473   0       0             0 clock-applet
Jan  4 15:22:17 figo-desktop kernel: [ 2132]  1000  2132    41163      931   0       0             0 notification-ar
Jan  4 15:22:17 figo-desktop kernel: [ 2149]  1000  2149    15325      695   1       0             0 e-calendar-fact
Jan  4 15:22:17 figo-desktop kernel: [ 2153]  1000  2153     7497     1010   0       0             0 gnome-screensav
Jan  4 15:22:17 figo-desktop kernel: [ 2155]  1000  2155     3848      202   1       0             0 pxgconf
Jan  4 15:22:17 figo-desktop kernel: [ 2163]  1000  2163     1781      341   0       0             0 mission-control
Jan  4 15:22:17 figo-desktop kernel: [ 2173]  1000  2173     4486      424   0       0             0 gvfsd-trash
Jan  4 15:22:17 figo-desktop kernel: [ 2186]     0  2186     3543      190   1       0             0 system-tools-ba
Jan  4 15:22:17 figo-desktop kernel: [ 2210]  1000  2210     2202      238   0       0             0 gvfsd-burn
Jan  4 15:22:17 figo-desktop kernel: [ 2245]  1000  2245     3895     1586   0       0             0 gvfsd-metadata
Jan  4 15:22:17 figo-desktop kernel: [ 2274]  1000  2274    22823      424   1       0             0 conky
Jan  4 15:22:17 figo-desktop kernel: [ 2281]     0  2281     3295     2278   0       0             0 SystemToolsBack
Jan  4 15:22:17 figo-desktop kernel: [ 2663]  1000  2663    68807     3072   0       0             0 gnome-terminal
Jan  4 15:22:17 figo-desktop kernel: [ 2683]  1000  2683      451       76   0       0             0 gnome-pty-helpe
Jan  4 15:22:17 figo-desktop kernel: [ 2685]  1000  2685     2072      566   0       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [ 2885]     0  2885     1489      119   0       0             0 sudo
Jan  4 15:22:17 figo-desktop kernel: [ 2886]     0  2886     6273      352   1       0             0 vim
Jan  4 15:22:17 figo-desktop kernel: [ 2887]  1000  2887      472       84   0       0             0 ping
Jan  4 15:22:17 figo-desktop kernel: [ 2892]  1000  2892      472       83   1       0             0 ping
Jan  4 15:22:17 figo-desktop kernel: [ 2894]  1000  2894    76113     5872   1       0             0 vmware
Jan  4 15:22:17 figo-desktop kernel: [ 2919]  1000  2919    51497     3314   1       0             0 vmware-tray
Jan  4 15:22:17 figo-desktop kernel: [ 2954]  1000  2954    48676     1589   1       0             0 vmware-unity-he
Jan  4 15:22:17 figo-desktop kernel: [ 2988]  1000  2988   190471    42233   1       0             0 vmware-vmx
Jan  4 15:22:17 figo-desktop kernel: [ 3207]  1000  3207     4377      360   1       0             0 gvfsd-computer
Jan  4 15:22:17 figo-desktop kernel: [ 3211]  1000  3211     9920      506   0       0             0 gvfsd-smb-brows
Jan  4 15:22:17 figo-desktop kernel: [ 3217]  1000  3217     9876      564   0       0             0 gvfsd-smb
Jan  4 15:22:17 figo-desktop kernel: [15186]  1000 15186     2069      558   1       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [17451]  1000 17451     5679      496   0       0             0 dconf-service
Jan  4 15:22:17 figo-desktop kernel: [19085]  1000 19085     1576      149   0       0             0 ssh
Jan  4 15:22:17 figo-desktop kernel: [19261]  1000 19261     1682      962   0       0             0 wineserver
Jan  4 15:22:17 figo-desktop kernel: [19266]  1000 19266   399085      212   0       0             0 services.exe
Jan  4 15:22:17 figo-desktop kernel: [19269]  1000 19269   399117      158   1       0             0 winedevice.exe
Jan  4 15:22:17 figo-desktop kernel: [19342]  1000 19342   404518      639   0       0             0 explorer.exe
Jan  4 15:22:17 figo-desktop kernel: [19344]  1000 19344   550020    10958   0       0             0 insight3.exe
Jan  4 15:22:17 figo-desktop kernel: [  360]  1000   360     2069      540   1       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [ 9821]  1000  9821   166228     2900   0       0             0 stardict
Jan  4 15:22:17 figo-desktop kernel: [14614]  1000 14614     2040      521   1       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [17002]  1000 17002     2069      541   0       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [18612]     0 18612     1536      125   1       0             0 sudo
Jan  4 15:22:17 figo-desktop kernel: [18613]     0 18613     1988      608   1       0             0 minicom
Jan  4 15:22:17 figo-desktop kernel: [21183]  1000 21183     2041      517   1       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [21194]  1000 21194     1611      125   0       0             0 ssh
Jan  4 15:22:17 figo-desktop kernel: [22451]  1000 22451     2069      571   1       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [23428]  1000 23428     6475      552   1       0             0 vim
Jan  4 15:22:17 figo-desktop kernel: [23484]  1000 23484     6501      593   1       0             0 vim
Jan  4 15:22:17 figo-desktop kernel: [23549]  1000 23549     6501      591   0       0             0 vim
Jan  4 15:22:17 figo-desktop kernel: [23642]  1000 23642     9865      578   0       0             0 gvfsd-smb
Jan  4 15:22:17 figo-desktop kernel: [26358]  1000 26358   407339     5016   1       0             0 insight3.exe
Jan  4 15:22:17 figo-desktop kernel: [29711]  1000 29711     9943      606   0       0             0 gvfsd-smb
Jan  4 15:22:17 figo-desktop kernel: [26156]  1000 26156    61269     9117   0       0             0 skype
Jan  4 15:22:17 figo-desktop kernel: [32490]  1000 32490     2647      684   0       0             0 gconfd-2
Jan  4 15:22:17 figo-desktop kernel: [10622]  1000 10622     2072      734   0       0             0 bash
Jan  4 15:22:17 figo-desktop kernel: [10634]  1000 10634     1576      156   0       0             0 ssh
Jan  4 15:22:17 figo-desktop kernel: [15410]  1000 15410    76559    12123   0       0             0 evince
Jan  4 15:22:17 figo-desktop kernel: [15415]  1000 15415     5490      216   1       0             0 evinced
Jan  4 15:22:17 figo-desktop kernel: [16754]  1000 16754     9899      482   0       0             0 gvfsd-smb
Jan  4 15:22:17 figo-desktop kernel: [16772]  1000 16772     9900      485   0       0             0 gvfsd-smb
Jan  4 15:22:17 figo-desktop kernel: [25390]  1000 25390   407306     2149   0       0             0 insight3.exe
Jan  4 15:22:17 figo-desktop kernel: [ 2127]  1000  2127     1609      122   0       0             0 ssh
Jan  4 15:22:17 figo-desktop kernel: [10661]    33 10661     4775     1503   1       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [10662]    33 10662     4823     1565   0       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [10663]    33 10663     4823     1566   0       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [10664]    33 10664     4823     1565   0       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [10665]    33 10665     4823     1565   0       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [10666]    33 10666     4823     1565   1       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [32159]  1000 32159   166096    38997   0       0             0 firefox
Jan  4 15:22:17 figo-desktop kernel: [32228]    33 32228     4823     1508   0       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [32233]    33 32233     4857     1591   1       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [32234]    33 32234     4857     1593   1       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [32241]    33 32241     4789     1532   1       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [32246]    33 32246     4789     1532   0       0             0 httpd
Jan  4 15:22:17 figo-desktop kernel: [32268]  1000 32268    27543     4106   1       0             0 plugin-containe
Jan  4 15:22:17 figo-desktop kernel: [32320]  1000 32320    16230     1439   1       0             0 GoogleTalkPlugi
Jan  4 15:22:17 figo-desktop kernel: [  970]  1000   970   407197     2574   1       0             0 insight3.exe
Jan  4 15:22:17 figo-desktop kernel: [ 1240]  1000  1240      601      101   1       0             0 top
Jan  4 15:22:17 figo-desktop kernel: [ 2038]  1000  2038   407785     2659   1       0             0 insight3.exe
Jan  4 15:22:17 figo-desktop kernel: [12415]     0 12415      580      192   1     -17         -1000 udevd
Jan  4 15:22:17 figo-desktop kernel: [12416]     0 12416      580      192   1     -17         -1000 udevd
Jan  4 15:22:17 figo-desktop kernel: [13760]     0 13760      719      217   1       0             0 sh
Jan  4 15:22:17 figo-desktop kernel: [13762]     0 13762      719      213   0       0             0 sh
Jan  4 15:22:17 figo-desktop kernel: [13765]     0 13765     1187      161   1       0             0 git
Jan  4 15:22:17 figo-desktop kernel: [13766]     0 13766      719      236   1       0             0 git-pull
Jan  4 15:22:17 figo-desktop kernel: [13782]     0 13782     1189      172   0       0             0 git
Jan  4 15:22:17 figo-desktop kernel: [13784]     0 13784     1575      353   1       0             0 ssh
Jan  4 15:22:17 figo-desktop kernel: [13824]     0 13824     1535      244   1       0             0 sudo
Jan  4 15:22:17 figo-desktop kernel: [13825]     0 13825     1386      124   1       0             0 swapoff
Jan  4 15:22:51 figo-desktop kernel: minicom invoked oom-killer: gfp_mask=0x201da, order=0, oom_adj=0, oom_score_adj=0
Jan  4 15:22:51 figo-desktop kernel: minicom cpuset=/ mems_allowed=0
Jan  4 15:22:51 figo-desktop kernel: Pid: 18613, comm: minicom Not tainted 2.6.36-ARCH #1
Jan  4 15:22:51 figo-desktop kernel: Call Trace:
Jan  4 15:22:51 figo-desktop kernel: [<c10c11d0>] dump_header.clone.5+0x80/0x1e0
Jan  4 15:22:51 figo-desktop kernel: [<c10c153c>] oom_kill_process+0x5c/0x1c0
Jan  4 15:22:51 figo-desktop kernel: [<c10c171d>] ? select_bad_process.clone.7+0x7d/0xd0
Jan  4 15:22:51 figo-desktop kernel: [<c10c1a0f>] out_of_memory+0xbf/0x1d0
Jan  4 15:22:51 figo-desktop kernel: [<c10c18d8>] ? try_set_zonelist_oom+0xc8/0xe0
Jan  4 15:22:51 figo-desktop kernel: [<c10c5288>] __alloc_pages_nodemask+0x5e8/0x600
Jan  4 15:22:51 figo-desktop kernel: [<c10c6c35>] __do_page_cache_readahead+0x105/0x230
Jan  4 15:22:51 figo-desktop kernel: [<c10c6fc1>] ra_submit+0x21/0x30
Jan  4 15:22:51 figo-desktop kernel: [<c10bf31b>] filemap_fault+0x36b/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c10d637b>] __do_fault+0x3b/0x4f0
Jan  4 15:22:51 figo-desktop kernel: [<c122e619>] ? check_modem_status+0x19/0x1d0
Jan  4 15:22:51 figo-desktop kernel: [<c10befb0>] ? filemap_fault+0x0/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c10d95c1>] handle_mm_fault+0x111/0x970
Jan  4 15:22:51 figo-desktop kernel: [<c1172121>] ? tomoyo_init_request_info+0x41/0x50
Jan  4 15:22:51 figo-desktop kernel: [<c1028d60>] ? do_page_fault+0x0/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c1028eb0>] do_page_fault+0x150/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c1170eb2>] ? tomoyo_file_ioctl+0x12/0x20
Jan  4 15:22:51 figo-desktop kernel: [<c110c43f>] ? sys_ioctl+0x5f/0x80
Jan  4 15:22:51 figo-desktop kernel: [<c1028d60>] ? do_page_fault+0x0/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c130753b>] error_code+0x67/0x6c
Jan  4 15:22:51 figo-desktop kernel: Mem-Info:
Jan  4 15:22:51 figo-desktop kernel: DMA per-cpu:
Jan  4 15:22:51 figo-desktop kernel: CPU    0: hi:    0, btch:   1 usd:   0
Jan  4 15:22:51 figo-desktop kernel: CPU    1: hi:    0, btch:   1 usd:   0
Jan  4 15:22:51 figo-desktop kernel: Normal per-cpu:
Jan  4 15:22:51 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  61
Jan  4 15:22:54 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:   1
Jan  4 15:22:54 figo-desktop kernel: HighMem per-cpu:
Jan  4 15:22:54 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  30
Jan  4 15:22:54 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:  30
Jan  4 15:22:54 figo-desktop kernel: active_anon:191656 inactive_anon:101947 isolated_anon:0
Jan  4 15:22:54 figo-desktop kernel: active_file:54186 inactive_file:122506 isolated_file:0
Jan  4 15:22:54 figo-desktop kernel: unevictable:17 dirty:0 writeback:0 unstable:0
Jan  4 15:22:54 figo-desktop kernel: free:11958 slab_reclaimable:5450 slab_unreclaimable:6123
Jan  4 15:22:54 figo-desktop kernel: mapped:49649 shmem:29219 pagetables:2559 bounce:0
Jan  4 15:22:54 figo-desktop kernel: DMA free:7960kB min:64kB low:80kB high:96kB active_anon:4772kB inactive_anon:1180kB active_file:524kB inactive_file:768kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15788kB mlocked:0kB dirty:0kB writeback:0kB mapped:592kB shmem:348kB slab_reclaimable:480kB slab_unreclaimable:112kB kernel_stack:8kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:2689 all_unreclaimable? yes
Jan  4 15:22:55 figo-desktop kernel: lowmem_reserve[]: 0 865 1980 1980
Jan  4 15:22:55 figo-desktop kernel: Normal free:39364kB min:3728kB low:4660kB high:5592kB active_anon:224324kB inactive_anon:226020kB active_file:86076kB inactive_file:207880kB unevictable:68kB isolated(anon):0kB isolated(file):0kB present:885944kB mlocked:68kB dirty:0kB writeback:0kB mapped:57272kB shmem:42072kB slab_reclaimable:21320kB slab_unreclaimable:24380kB kernel_stack:3224kB pagetables:10236kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:445029 all_unreclaimable? yes
Jan  4 15:22:55 figo-desktop kernel: lowmem_reserve[]: 0 0 8921 8921
Jan  4 15:22:55 figo-desktop kernel: HighMem free:508kB min:512kB low:1712kB high:2912kB active_anon:537528kB inactive_anon:180588kB active_file:130144kB inactive_file:281376kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:1141984kB mlocked:0kB dirty:0kB writeback:0kB mapped:140732kB shmem:74456kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:644938 all_unreclaimable? yes
Jan  4 15:22:55 figo-desktop kernel: lowmem_reserve[]: 0 0 0 0
Jan  4 15:22:55 figo-desktop kernel: DMA: 1500*4kB 245*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 7960kB
Jan  4 15:22:55 figo-desktop kernel: Normal: 1399*4kB 3723*8kB 91*16kB 21*32kB 5*64kB 2*128kB 3*256kB 1*512kB 0*1024kB 0*2048kB 0*4096kB = 39364kB
Jan  4 15:22:55 figo-desktop kernel: HighMem: 27*4kB 10*8kB 18*16kB 1*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 508kB
Jan  4 15:22:55 figo-desktop kernel: 206073 total pagecache pages
Jan  4 15:22:55 figo-desktop kernel: 151 pages in swap cache
Jan  4 15:22:55 figo-desktop kernel: Swap cache stats: add 889409, delete 889258, find 277087/391428
Jan  4 15:22:55 figo-desktop kernel: Free swap  = -1636kB
Jan  4 15:22:55 figo-desktop kernel: Total swap = 0kB
Jan  4 15:22:55 figo-desktop kernel: 515070 pages RAM
Jan  4 15:22:55 figo-desktop kernel: 287745 pages HighMem
Jan  4 15:22:55 figo-desktop kernel: 8297 pages reserved
Jan  4 15:22:55 figo-desktop kernel: 304095 pages shared
Jan  4 15:22:55 figo-desktop kernel: 306148 pages non-shared
Jan  4 15:22:55 figo-desktop kernel: [ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name
Jan  4 15:22:55 figo-desktop kernel: [  583]     0   583      581      207   1     -17         -1000 udevd
Jan  4 15:22:55 figo-desktop kernel: [ 1303]     0  1303      868       37   0       0             0 syslog-ng
Jan  4 15:22:55 figo-desktop kernel: [ 1304]     0  1304     1604      350   0       0             0 syslog-ng
Jan  4 15:22:55 figo-desktop kernel: [ 1306]    81  1306      808      396   1       0             0 dbus-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 1309]    82  1309     3777      406   0       0             0 hald
Jan  4 15:22:55 figo-desktop kernel: [ 1310]     0  1310      903      130   1       0             0 hald-runner
Jan  4 15:22:55 figo-desktop kernel: [ 1339]     0  1339      919       90   1       0             0 hald-addon-inpu
Jan  4 15:22:55 figo-desktop kernel: [ 1357]     0  1357      919      184   1       0             0 hald-addon-stor
Jan  4 15:22:55 figo-desktop kernel: [ 1359]    82  1359      824      107   1       0             0 hald-addon-acpi
Jan  4 15:22:55 figo-desktop kernel: [ 1448]     0  1448      616      294   0       0             0 crond
Jan  4 15:22:55 figo-desktop kernel: [ 1477]     0  1477      720      108   0       0             0 mysqld_safe
Jan  4 15:22:55 figo-desktop kernel: [ 1484]     0  1484     3580      269   0       0             0 gdm-binary
Jan  4 15:22:55 figo-desktop kernel: [ 1497]     0  1497      440       67   1       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1498]     0  1498      440       67   0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1499]     0  1499      440       67   0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1500]     0  1500      440       67   1       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1501]     0  1501      440       67   0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1502]     0  1502      440       68   0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1553]     0  1553     6607      619   0       0             0 NetworkManager
Jan  4 15:22:55 figo-desktop kernel: [ 1592]     0  1592     2256      330   0       0             0 cupsd
Jan  4 15:22:55 figo-desktop kernel: [ 1597]    89  1597    29903     2812   1       0             0 mysqld
Jan  4 15:22:55 figo-desktop kernel: [ 1598]     0  1598     1652      147   1     -17         -1000 sshd
Jan  4 15:22:55 figo-desktop kernel: [ 1612]     0  1612     6263      508   1       0             0 polkitd
Jan  4 15:22:55 figo-desktop kernel: [ 1613]     0  1613     2015      123   1       0             0 vmware-usbarbit
Jan  4 15:22:55 figo-desktop kernel: [ 1617]     0  1617     2887     1603   0       0             0 cntlm
Jan  4 15:22:55 figo-desktop kernel: [ 1620]     0  1620     4398      366   0       0             0 gdm-simple-slav
Jan  4 15:22:55 figo-desktop kernel: [ 1636]     0  1636    37298    12186   0       0             0 Xorg
Jan  4 15:22:55 figo-desktop kernel: [ 1638]     0  1638     1248       88   0       0             0 wpa_supplicant
Jan  4 15:22:55 figo-desktop kernel: [ 1720]     0  1720     4789     1555   1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [ 1722]     0  1722      488       93   0       0             0 dhcpcd
Jan  4 15:22:55 figo-desktop kernel: [ 1732]     0  1732      519       62   1       0             0 vmnet-bridge
Jan  4 15:22:55 figo-desktop kernel: [ 1750]     0  1750     4922      304   1       0             0 smbd
Jan  4 15:22:55 figo-desktop kernel: [ 1764]     0  1764      655       39   1       0             0 vmnet-dhcpd
Jan  4 15:22:55 figo-desktop kernel: [ 1772]     0  1772      513       15   0       0             0 vmnet-netifup
Jan  4 15:22:55 figo-desktop kernel: [ 1774]     0  1774      655       39   0       0             0 vmnet-dhcpd
Jan  4 15:22:55 figo-desktop kernel: [ 1776]     0  1776     4922      225   0       0             0 smbd
Jan  4 15:22:55 figo-desktop kernel: [ 1778]     0  1778      634       44   0       0             0 vmnet-natd
Jan  4 15:22:55 figo-desktop kernel: [ 1780]     0  1780      513       14   1       0             0 vmnet-netifup
Jan  4 15:22:55 figo-desktop kernel: [ 1796]     0  1796     6677      329   0       0             0 console-kit-dae
Jan  4 15:22:55 figo-desktop kernel: [ 1899]   120  1899     6587      598   0       0             0 polkit-gnome-au
Jan  4 15:22:55 figo-desktop kernel: [ 1903]     0  1903     3905      245   0       0             0 gdm-session-wor
Jan  4 15:22:55 figo-desktop kernel: [ 1906]     0  1906     3677      314   1       0             0 upowerd
Jan  4 15:22:55 figo-desktop kernel: [ 1974]  1000  1974    10963     1248   0       0             0 gnome-keyring-d
Jan  4 15:22:55 figo-desktop kernel: [ 1993]  1000  1993     9253      776   0       0             0 gnome-session
Jan  4 15:22:55 figo-desktop kernel: [ 2012]  1000  2012      796      103   0       0             0 dbus-launch
Jan  4 15:22:55 figo-desktop kernel: [ 2013]  1000  2013     5854     4985   0       0             0 dbus-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 2015]  1000  2015      887       54   0       0             0 ssh-agent
Jan  4 15:22:55 figo-desktop kernel: [ 2022]  1000  2022    10904     4789   0       0             0 fcitx
Jan  4 15:22:55 figo-desktop kernel: [ 2032]  1000  2032    41764     2007   0       0             0 gnome-settings-
Jan  4 15:22:55 figo-desktop kernel: [ 2036]  1000  2036     2367      416   0       0             0 gvfsd
Jan  4 15:22:55 figo-desktop kernel: [ 2039]  1000  2039    85188    29636   1       0             0 metacity
Jan  4 15:22:55 figo-desktop kernel: [ 2049]  1000  2049    14162      280   1       0             0 gvfs-fuse-daemo
Jan  4 15:22:55 figo-desktop kernel: [ 2053]  1000  2053    76657     3620   0       0             0 gnome-panel
Jan  4 15:22:55 figo-desktop kernel: [ 2056]  1000  2056    10978      563   1       0             0 gvfs-gdu-volume
Jan  4 15:22:55 figo-desktop kernel: [ 2058]     0  2058     5767      503   0       0             0 udisks-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 2059]     0  2059     1291       72   0       0             0 udisks-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 2069]  1000  2069   168292    50943   0       0             0 nautilus
Jan  4 15:22:55 figo-desktop kernel: [ 2071]  1000  2071    12907      223   0       0             0 bonobo-activati
Jan  4 15:22:55 figo-desktop kernel: [ 2081]  1000  2081     1633      136   0       0             0 sh
Jan  4 15:22:55 figo-desktop kernel: [ 2082]  1000  2082     1666      136   1       0             0 thunderbird
Jan  4 15:22:55 figo-desktop kernel: [ 2084]  1000  2084    46718     3501   1       0             0 wnck-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2086]  1000  2086    42862     1487   0       0             0 polkit-gnome-au
Jan  4 15:22:55 figo-desktop kernel: [ 2087]  1000  2087   285933     1584   0       0             0 nm-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2104]  1000  2104     5056      715   0       0             0 gdu-notificatio
Jan  4 15:22:55 figo-desktop kernel: [ 2107]  1000  2107     1666      142   1       0             0 run-mozilla.sh
Jan  4 15:22:55 figo-desktop kernel: [ 2108]  1000  2108    39395      973   0       0             0 gnome-power-man
Jan  4 15:22:55 figo-desktop kernel: [ 2109]  1000  2109     7886      709   0       0             0 vino-server
Jan  4 15:22:55 figo-desktop kernel: [ 2110]  1000  2110    10764      791   1       0             0 evolution-alarm
Jan  4 15:22:55 figo-desktop kernel: [ 2114]  1000  2114   167865    29673   1       0             0 thunderbird-bin
Jan  4 15:22:55 figo-desktop kernel: [ 2121]  1000  2121    42098     1965   0       0             0 notify-osd
Jan  4 15:22:55 figo-desktop kernel: [ 2125]  1000  2125    42488     1203   1       0             0 cpufreq-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2126]  1000  2126    41394     1148   1       0             0 multiload-apple
Jan  4 15:22:55 figo-desktop kernel: [ 2129]  1000  2129    64405     1827   0       0             0 mixer_applet2
Jan  4 15:22:55 figo-desktop kernel: [ 2131]  1000  2131    75346     2489   0       0             0 clock-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2132]  1000  2132    41163      930   1       0             0 notification-ar
Jan  4 15:22:55 figo-desktop kernel: [ 2149]  1000  2149    15325      697   1       0             0 e-calendar-fact
Jan  4 15:22:55 figo-desktop kernel: [ 2153]  1000  2153     7497     1008   0       0             0 gnome-screensav
Jan  4 15:22:55 figo-desktop kernel: [ 2155]  1000  2155     3848      202   1       0             0 pxgconf
Jan  4 15:22:55 figo-desktop kernel: [ 2163]  1000  2163     1781      342   0       0             0 mission-control
Jan  4 15:22:55 figo-desktop kernel: [ 2173]  1000  2173     4486      428   0       0             0 gvfsd-trash
Jan  4 15:22:55 figo-desktop kernel: [ 2186]     0  2186     3543      192   1       0             0 system-tools-ba
Jan  4 15:22:55 figo-desktop kernel: [ 2210]  1000  2210     2202      238   0       0             0 gvfsd-burn
Jan  4 15:22:55 figo-desktop kernel: [ 2245]  1000  2245     3895     1730   0       0             0 gvfsd-metadata
Jan  4 15:22:55 figo-desktop kernel: [ 2274]  1000  2274    22823      424   0       0             0 conky
Jan  4 15:22:55 figo-desktop kernel: [ 2281]     0  2281     3295     2278   0       0             0 SystemToolsBack
Jan  4 15:22:55 figo-desktop kernel: [ 2663]  1000  2663    68807     3042   1       0             0 gnome-terminal
Jan  4 15:22:55 figo-desktop kernel: [ 2683]  1000  2683      451       76   0       0             0 gnome-pty-helpe
Jan  4 15:22:55 figo-desktop kernel: [ 2685]  1000  2685     2072      570   0       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [ 2885]     0  2885     1489      119   0       0             0 sudo
Jan  4 15:22:55 figo-desktop kernel: [ 2886]     0  2886     6273      355   1       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [ 2887]  1000  2887      472       84   0       0             0 ping
Jan  4 15:22:55 figo-desktop kernel: [ 2892]  1000  2892      472       83   1       0             0 ping
Jan  4 15:22:55 figo-desktop kernel: [ 2894]  1000  2894    76113     5890   0       0             0 vmware
Jan  4 15:22:55 figo-desktop kernel: [ 2919]  1000  2919    51497     3315   1       0             0 vmware-tray
Jan  4 15:22:55 figo-desktop kernel: [ 2954]  1000  2954    48676     1589   0       0             0 vmware-unity-he
Jan  4 15:22:55 figo-desktop kernel: [ 2988]  1000  2988   190471    42400   0       0             0 vmware-vmx
Jan  4 15:22:55 figo-desktop kernel: [ 3207]  1000  3207     4377      362   1       0             0 gvfsd-computer
Jan  4 15:22:55 figo-desktop kernel: [ 3211]  1000  3211     9920      509   0       0             0 gvfsd-smb-brows
Jan  4 15:22:55 figo-desktop kernel: [ 3217]  1000  3217     9876      569   0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [15186]  1000 15186     2069      558   1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [17451]  1000 17451     5679      503   0       0             0 dconf-service
Jan  4 15:22:55 figo-desktop kernel: [19085]  1000 19085     1576      149   0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [19261]  1000 19261     1682      967   0       0             0 wineserver
Jan  4 15:22:55 figo-desktop kernel: [19266]  1000 19266   399085      212   0       0             0 services.exe
Jan  4 15:22:55 figo-desktop kernel: [19269]  1000 19269   399117      158   1       0             0 winedevice.exe
Jan  4 15:22:55 figo-desktop kernel: [19342]  1000 19342   404518      643   0       0             0 explorer.exe
Jan  4 15:22:55 figo-desktop kernel: [19344]  1000 19344   550020    11028   1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [  360]  1000   360     2069      541   1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [ 9821]  1000  9821   166228     2915   0       0             0 stardict
Jan  4 15:22:55 figo-desktop kernel: [14614]  1000 14614     2040      523   1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [17002]  1000 17002     2069      541   0       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [18612]     0 18612     1536      125   1       0             0 sudo
Jan  4 15:22:55 figo-desktop kernel: [18613]     0 18613     1988      608   1       0             0 minicom
Jan  4 15:22:55 figo-desktop kernel: [21183]  1000 21183     2041      517   1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [21194]  1000 21194     1611      125   0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [22451]  1000 22451     2069      578   1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [23428]  1000 23428     6475      554   1       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [23484]  1000 23484     6501      594   1       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [23549]  1000 23549     6501      594   0       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [23642]  1000 23642     9865      594   0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [26358]  1000 26358   407339     5019   1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [29711]  1000 29711     9943      617   0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [26156]  1000 26156    61269     9179   0       0             0 skype
Jan  4 15:22:55 figo-desktop kernel: [32490]  1000 32490     2647      684   0       0             0 gconfd-2
Jan  4 15:22:55 figo-desktop kernel: [10622]  1000 10622     2072      725   1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [10634]  1000 10634     1576      156   0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [15410]  1000 15410    76559    12161   0       0             0 evince
Jan  4 15:22:55 figo-desktop kernel: [15415]  1000 15415     5490      217   1       0             0 evinced
Jan  4 15:22:55 figo-desktop kernel: [16754]  1000 16754     9899      485   0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [16772]  1000 16772     9900      500   0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [25390]  1000 25390   407306     2164   1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [ 2127]  1000  2127     1609      125   0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [10661]    33 10661     4775     1510   1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10662]    33 10662     4823     1569   0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10663]    33 10663     4823     1570   0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10664]    33 10664     4823     1569   0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10665]    33 10665     4823     1569   0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10666]    33 10666     4823     1569   1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32159]  1000 32159   166096    39479   0       0             0 firefox
Jan  4 15:22:55 figo-desktop kernel: [32228]    33 32228     4823     1512   0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32233]    33 32233     4857     1596   1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32234]    33 32234     4857     1597   1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32241]    33 32241     4789     1536   1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32246]    33 32246     4789     1536   0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32268]  1000 32268    27543     4279   1       0             0 plugin-containe
Jan  4 15:22:55 figo-desktop kernel: [32320]  1000 32320    16230     1445   1       0             0 GoogleTalkPlugi
Jan  4 15:22:55 figo-desktop kernel: [  970]  1000   970   407197     2636   1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [ 1240]  1000  1240      601      116   1       0             0 top
Jan  4 15:22:55 figo-desktop kernel: [ 2038]  1000  2038   407786     2842   0       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [12415]     0 12415      543      232   1     -17         -1000 udevd
Jan  4 15:22:55 figo-desktop kernel: [12416]     0 12416      580      195   1     -17         -1000 udevd
Jan  4 15:22:55 figo-desktop kernel: [13904]     0 13904     1488      219   1       0             0 sudo
Jan  4 15:22:55 figo-desktop kernel: [13906]     0 13906     1386      131   0       0             0 swapoff
Jan  4 15:23:30 figo-desktop kernel: hald-addon-stor invoked oom-killer: gfp_mask=0x280da, order=0, oom_adj=0, oom_score_adj=0
Jan  4 15:23:30 figo-desktop kernel: hald-addon-stor cpuset=/ mems_allowed=0
Jan  4 15:23:30 figo-desktop kernel: Pid: 1357, comm: hald-addon-stor Not tainted 2.6.36-ARCH #1
Jan  4 15:23:30 figo-desktop kernel: Call Trace:
Jan  4 15:23:30 figo-desktop kernel: [<c10c11d0>] dump_header.clone.5+0x80/0x1e0
Jan  4 15:23:30 figo-desktop kernel: [<c10c153c>] oom_kill_process+0x5c/0x1c0
Jan  4 15:23:30 figo-desktop kernel: [<c10c171d>] ? select_bad_process.clone.7+0x7d/0xd0
Jan  4 15:23:30 figo-desktop kernel: [<c10c1a0f>] out_of_memory+0xbf/0x1d0
Jan  4 15:23:30 figo-desktop kernel: [<c10c18d8>] ? try_set_zonelist_oom+0xc8/0xe0
Jan  4 15:23:30 figo-desktop kernel: [<c10c5288>] __alloc_pages_nodemask+0x5e8/0x600
Jan  4 15:23:35 figo-desktop kernel: [<c10d9b42>] handle_mm_fault+0x692/0x970
Jan  4 15:23:35 figo-desktop kernel: [<c110f2c9>] ? prepend_path+0x59/0x140
Jan  4 15:23:35 figo-desktop kernel: [<c10f1b85>] ? __kmalloc+0xb5/0x1b0
Jan  4 15:23:35 figo-desktop kernel: [<c1028d60>] ? do_page_fault+0x0/0x3e0
Jan  4 15:23:35 figo-desktop kernel: [<c1028eb0>] do_page_fault+0x150/0x3e0
Jan  4 15:23:35 figo-desktop kernel: [<c1171e27>] ? tomoyo_fill_path_info+0x17/0xf0
Jan  4 15:23:35 figo-desktop kernel: [<c113e74a>] ? dquot_file_open+0x1a/0x50
Jan  4 15:23:35 figo-desktop kernel: [<f81e2225>] ? ext4_file_open+0x45/0xe0 [ext4]
Jan  4 15:23:35 figo-desktop kernel: [<c1028d60>] ? do_page_fault+0x0/0x3e0
Jan  4 15:23:35 figo-desktop kernel: [<c130753b>] error_code+0x67/0x6c
Jan  4 15:23:35 figo-desktop kernel: [<c10be3eb>] ? file_read_actor+0x2b/0xd0
Jan  4 15:23:35 figo-desktop kernel: [<c10be719>] ? find_get_page+0x29/0xb0
Jan  4 15:23:35 figo-desktop kernel: [<c10c0381>] generic_file_aio_read+0x331/0x760
Jan  4 15:23:35 figo-desktop kernel: [<c10fd2dc>] do_sync_read+0x9c/0xd0
Jan  4 15:23:35 figo-desktop kernel: [<c10fd5ed>] ? rw_verify_area+0x5d/0xd0
Jan  4 15:23:35 figo-desktop kernel: [<c10fda87>] vfs_read+0x97/0x160
Jan  4 15:23:35 figo-desktop kernel: [<c10fd240>] ? do_sync_read+0x0/0xd0
Jan  4 15:23:35 figo-desktop kernel: [<c10fdb8d>] sys_read+0x3d/0x70
Jan  4 15:23:35 figo-desktop kernel: [<c100379f>] sysenter_do_call+0x12/0x28
Jan  4 15:23:35 figo-desktop kernel: Mem-Info:
Jan  4 15:23:35 figo-desktop kernel: DMA per-cpu:
Jan  4 15:23:35 figo-desktop kernel: CPU    0: hi:    0, btch:   1 usd:   0
Jan  4 15:23:35 figo-desktop kernel: CPU    1: hi:    0, btch:   1 usd:   0
Jan  4 15:23:35 figo-desktop kernel: Normal per-cpu:
Jan  4 15:23:35 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  31
Jan  4 15:23:35 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:   0
Jan  4 15:23:35 figo-desktop kernel: HighMem per-cpu:
Jan  4 15:23:35 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  30
Jan  4 15:23:35 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:   0
Jan  4 15:23:35 figo-desktop kernel: active_anon:184575 inactive_anon:108966 isolated_anon:0
Jan  4 15:23:35 figo-desktop kernel: active_file:54381 inactive_file:122394 isolated_file:0
Jan  4 15:23:35 figo-desktop kernel: unevictable:17 dirty:1 writeback:0 unstable:0
Jan  4 15:23:35 figo-desktop kernel: free:11938 slab_reclaimable:5448 slab_unreclaimable:6124
Jan  4 15:23:35 figo-desktop kernel: mapped:48017 shmem:28204 pagetables:2587 bounce:0
Jan  4 15:23:35 figo-desktop kernel: DMA free:7964kB min:64kB low:80kB high:96kB active_anon:4624kB inactive_anon:1316kB active_file:532kB inactive_file:760kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15788kB mlocked:0kB dirty:0kB writeback:0kB mapped:548kB shmem:72kB slab_reclaimable:480kB slab_unreclaimable:112kB kernel_stack:8kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:1963 all_unreclaimable? yes
Jan  4 15:23:35 figo-desktop kernel: lowmem_reserve[]: 0 865 1980 1980
Jan  4 15:23:35 figo-desktop kernel: Normal free:39344kB min:3728kB low:4660kB high:5592kB active_anon:234180kB inactive_anon:216232kB active_file:86148kB inactive_file:207704kB unevictable:68kB isolated(anon):0kB isolated(file):0kB present:885944kB mlocked:68kB dirty:4kB writeback:0kB mapped:55852kB shmem:36852kB slab_reclaimable:21312kB slab_unreclaimable:24384kB kernel_stack:3272kB pagetables:10348kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:441365 all_unreclaimable? yes
Jan  4 15:23:35 figo-desktop kernel: lowmem_reserve[]: 0 0 8921 8921
Jan  4 15:23:35 figo-desktop kernel: HighMem free:444kB min:512kB low:1712kB high:2912kB active_anon:499496kB inactive_anon:218316kB active_file:130844kB inactive_file:281112kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:1141984kB mlocked:0kB dirty:0kB writeback:0kB mapped:135668kB shmem:75892kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:686994 all_unreclaimable? yes
Jan  4 15:23:35 figo-desktop kernel: lowmem_reserve[]: 0 0 0 0
Jan  4 15:23:35 figo-desktop kernel: DMA: 1549*4kB 221*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 7964kB
Jan  4 15:23:35 figo-desktop kernel: Normal: 1472*4kB 3840*8kB 47*16kB 8*32kB 3*64kB 2*128kB 3*256kB 1*512kB 0*1024kB 0*2048kB 0*4096kB = 39344kB
Jan  4 15:23:35 figo-desktop kernel: HighMem: 13*4kB 9*8kB 18*16kB 1*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 444kB
Jan  4 15:23:35 figo-desktop kernel: 224327 total pagecache pages
Jan  4 15:23:35 figo-desktop kernel: 19316 pages in swap cache
Jan  4 15:23:35 figo-desktop kernel: Swap cache stats: add 999341, delete 980025, find 277475/391898
Jan  4 15:23:35 figo-desktop kernel: Free swap  = -79552kB
Jan  4 15:23:35 figo-desktop kernel: Total swap = 0kB
Jan  4 15:23:35 figo-desktop kernel: 515070 pages RAM
Jan  4 15:23:35 figo-desktop kernel: 287745 pages HighMem
Jan  4 15:23:35 figo-desktop kernel: 8297 pages reserved
Jan  4 15:23:35 figo-desktop kernel: 300103 pages shared
Jan  4 15:23:35 figo-desktop kernel: 310097 pages non-shared
Jan  4 15:23:35 figo-desktop kernel: [ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name
Jan  4 15:23:35 figo-desktop kernel: [  583]     0   583      581      195   0     -17         -1000 udevd
Jan  4 15:23:35 figo-desktop kernel: [ 1303]     0  1303      868       35   0       0             0 syslog-ng
Jan  4 15:23:35 figo-desktop kernel: [ 1304]     0  1304     1604      387   0       0             0 syslog-ng
Jan  4 15:23:35 figo-desktop kernel: [ 1306]    81  1306      808      375   0       0             0 dbus-daemon
Jan  4 15:23:35 figo-desktop kernel: [ 1309]    82  1309     3777      391   0       0             0 hald
Jan  4 15:23:35 figo-desktop kernel: [ 1310]     0  1310      903      128   1       0             0 hald-runner
Jan  4 15:23:35 figo-desktop kernel: [ 1339]     0  1339      919       87   1       0             0 hald-addon-inpu
Jan  4 15:23:35 figo-desktop kernel: [ 1357]     0  1357      920      184   1       0             0 hald-addon-stor
Jan  4 15:23:35 figo-desktop kernel: [ 1359]    82  1359      824      106   1       0             0 hald-addon-acpi
Jan  4 15:23:35 figo-desktop kernel: [ 1448]     0  1448      616      294   1       0             0 crond
Jan  4 15:23:35 figo-desktop kernel: [ 1477]     0  1477      720      108   0       0             0 mysqld_safe
Jan  4 15:23:35 figo-desktop kernel: [ 1484]     0  1484     3580      268   0       0             0 gdm-binary
Jan  4 15:23:35 figo-desktop kernel: [ 1497]     0  1497      440       66   1       0             0 agetty
Jan  4 15:23:35 figo-desktop kernel: [ 1498]     0  1498      440       66   0       0             0 agetty
Jan  4 15:23:35 figo-desktop kernel: [ 1499]     0  1499      440       66   0       0             0 agetty
Jan  4 15:23:35 figo-desktop kernel: [ 1500]     0  1500      440       67   1       0             0 agetty
Jan  4 15:23:35 figo-desktop kernel: [ 1501]     0  1501      440       66   0       0             0 agetty
Jan  4 15:23:35 figo-desktop kernel: [ 1502]     0  1502      440       67   0       0             0 agetty
Jan  4 15:23:35 figo-desktop kernel: [ 1553]     0  1553     6607      650   1       0             0 NetworkManager
Jan  4 15:23:35 figo-desktop kernel: [ 1592]     0  1592     2256      329   0       0             0 cupsd
Jan  4 15:23:35 figo-desktop kernel: [ 1597]    89  1597    29903     2812   1       0             0 mysqld
Jan  4 15:23:35 figo-desktop kernel: [ 1598]     0  1598     1652      147   1     -17         -1000 sshd
Jan  4 15:23:35 figo-desktop kernel: [ 1612]     0  1612     6263      506   1       0             0 polkitd
Jan  4 15:23:35 figo-desktop kernel: [ 1613]     0  1613     2015      121   1       0             0 vmware-usbarbit
Jan  4 15:23:35 figo-desktop kernel: [ 1617]     0  1617     2887     1481   0       0             0 cntlm
Jan  4 15:23:35 figo-desktop kernel: [ 1620]     0  1620     4398      365   0       0             0 gdm-simple-slav
Jan  4 15:23:35 figo-desktop kernel: [ 1636]     0  1636    37287    10088   1       0             0 Xorg
Jan  4 15:23:35 figo-desktop kernel: [ 1638]     0  1638     1248       88   0       0             0 wpa_supplicant
Jan  4 15:23:35 figo-desktop kernel: [ 1720]     0  1720     4789     1527   1       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [ 1722]     0  1722      488       92   0       0             0 dhcpcd
Jan  4 15:23:35 figo-desktop kernel: [ 1732]     0  1732      519       61   1       0             0 vmnet-bridge
Jan  4 15:23:35 figo-desktop kernel: [ 1750]     0  1750     4922      302   1       0             0 smbd
Jan  4 15:23:35 figo-desktop kernel: [ 1764]     0  1764      655       37   1       0             0 vmnet-dhcpd
Jan  4 15:23:35 figo-desktop kernel: [ 1772]     0  1772      513       15   0       0             0 vmnet-netifup
Jan  4 15:23:35 figo-desktop kernel: [ 1774]     0  1774      655       38   0       0             0 vmnet-dhcpd
Jan  4 15:23:35 figo-desktop kernel: [ 1776]     0  1776     4922      223   0       0             0 smbd
Jan  4 15:23:35 figo-desktop kernel: [ 1778]     0  1778      634       43   0       0             0 vmnet-natd
Jan  4 15:23:35 figo-desktop kernel: [ 1780]     0  1780      513       13   1       0             0 vmnet-netifup
Jan  4 15:23:35 figo-desktop kernel: [ 1796]     0  1796     6677      327   0       0             0 console-kit-dae
Jan  4 15:23:35 figo-desktop kernel: [ 1899]   120  1899     6587      597   0       0             0 polkit-gnome-au
Jan  4 15:23:35 figo-desktop kernel: [ 1903]     0  1903     3905      244   0       0             0 gdm-session-wor
Jan  4 15:23:35 figo-desktop kernel: [ 1906]     0  1906     3677      313   1       0             0 upowerd
Jan  4 15:23:35 figo-desktop kernel: [ 1974]  1000  1974    10963      917   0       0             0 gnome-keyring-d
Jan  4 15:23:35 figo-desktop kernel: [ 1993]  1000  1993     9253      771   0       0             0 gnome-session
Jan  4 15:23:35 figo-desktop kernel: [ 2012]  1000  2012      796      103   0       0             0 dbus-launch
Jan  4 15:23:35 figo-desktop kernel: [ 2013]  1000  2013     5854     4749   0       0             0 dbus-daemon
Jan  4 15:23:35 figo-desktop kernel: [ 2015]  1000  2015      887       54   1       0             0 ssh-agent
Jan  4 15:23:35 figo-desktop kernel: [ 2022]  1000  2022    10904     2634   1       0             0 fcitx
Jan  4 15:23:35 figo-desktop kernel: [ 2032]  1000  2032    41764     1971   1       0             0 gnome-settings-
Jan  4 15:23:35 figo-desktop kernel: [ 2036]  1000  2036     2367      408   0       0             0 gvfsd
Jan  4 15:23:35 figo-desktop kernel: [ 2039]  1000  2039    85188    22437   0       0             0 metacity
Jan  4 15:23:35 figo-desktop kernel: [ 2049]  1000  2049    14162      267   1       0             0 gvfs-fuse-daemo
Jan  4 15:23:35 figo-desktop kernel: [ 2053]  1000  2053    76657     3448   0       0             0 gnome-panel
Jan  4 15:23:35 figo-desktop kernel: [ 2056]  1000  2056    10978      563   0       0             0 gvfs-gdu-volume
Jan  4 15:23:35 figo-desktop kernel: [ 2058]     0  2058     5767      451   1       0             0 udisks-daemon
Jan  4 15:23:35 figo-desktop kernel: [ 2059]     0  2059     1291       72   0       0             0 udisks-daemon
Jan  4 15:23:35 figo-desktop kernel: [ 2069]  1000  2069   168292    48504   0       0             0 nautilus
Jan  4 15:23:35 figo-desktop kernel: [ 2071]  1000  2071    12907      223   0       0             0 bonobo-activati
Jan  4 15:23:35 figo-desktop kernel: [ 2081]  1000  2081     1633      136   0       0             0 sh
Jan  4 15:23:35 figo-desktop kernel: [ 2082]  1000  2082     1666      136   1       0             0 thunderbird
Jan  4 15:23:35 figo-desktop kernel: [ 2084]  1000  2084    46718     3138   0       0             0 wnck-applet
Jan  4 15:23:35 figo-desktop kernel: [ 2086]  1000  2086    42862     1439   0       0             0 polkit-gnome-au
Jan  4 15:23:35 figo-desktop kernel: [ 2087]  1000  2087   285933     1524   0       0             0 nm-applet
Jan  4 15:23:35 figo-desktop kernel: [ 2104]  1000  2104     5056      732   0       0             0 gdu-notificatio
Jan  4 15:23:35 figo-desktop kernel: [ 2107]  1000  2107     1666      142   1       0             0 run-mozilla.sh
Jan  4 15:23:35 figo-desktop kernel: [ 2108]  1000  2108    39395      953   1       0             0 gnome-power-man
Jan  4 15:23:35 figo-desktop kernel: [ 2109]  1000  2109     7886      709   0       0             0 vino-server
Jan  4 15:23:35 figo-desktop kernel: [ 2110]  1000  2110    10764      790   1       0             0 evolution-alarm
Jan  4 15:23:35 figo-desktop kernel: [ 2114]  1000  2114   167865    29127   0       0             0 thunderbird-bin
Jan  4 15:23:35 figo-desktop kernel: [ 2121]  1000  2121    42098     1885   0       0             0 notify-osd
Jan  4 15:23:35 figo-desktop kernel: [ 2125]  1000  2125    42488     1202   1       0             0 cpufreq-applet
Jan  4 15:23:35 figo-desktop kernel: [ 2126]  1000  2126    41394     1143   0       0             0 multiload-apple
Jan  4 15:23:35 figo-desktop kernel: [ 2129]  1000  2129    64405     1748   0       0             0 mixer_applet2
Jan  4 15:23:35 figo-desktop kernel: [ 2131]  1000  2131    75346     2380   1       0             0 clock-applet
Jan  4 15:23:35 figo-desktop kernel: [ 2132]  1000  2132    41163      924   1       0             0 notification-ar
Jan  4 15:23:35 figo-desktop kernel: [ 2149]  1000  2149    15325      696   1       0             0 e-calendar-fact
Jan  4 15:23:35 figo-desktop kernel: [ 2153]  1000  2153     7497     1006   0       0             0 gnome-screensav
Jan  4 15:23:35 figo-desktop kernel: [ 2155]  1000  2155     3848      202   1       0             0 pxgconf
Jan  4 15:23:35 figo-desktop kernel: [ 2163]  1000  2163     1781      342   0       0             0 mission-control
Jan  4 15:23:35 figo-desktop kernel: [ 2173]  1000  2173     4486      417   0       0             0 gvfsd-trash
Jan  4 15:23:35 figo-desktop kernel: [ 2186]     0  2186     3543      192   1       0             0 system-tools-ba
Jan  4 15:23:35 figo-desktop kernel: [ 2210]  1000  2210     2202      236   0       0             0 gvfsd-burn
Jan  4 15:23:35 figo-desktop kernel: [ 2245]  1000  2245     3895     1713   0       0             0 gvfsd-metadata
Jan  4 15:23:35 figo-desktop kernel: [ 2274]  1000  2274    22825      423   1       0             0 conky
Jan  4 15:23:35 figo-desktop kernel: [ 2281]     0  2281     3295     2278   0       0             0 SystemToolsBack
Jan  4 15:23:35 figo-desktop kernel: [ 2663]  1000  2663    68807     2924   1       0             0 gnome-terminal
Jan  4 15:23:35 figo-desktop kernel: [ 2683]  1000  2683      451       76   0       0             0 gnome-pty-helpe
Jan  4 15:23:35 figo-desktop kernel: [ 2685]  1000  2685     2072      555   0       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [ 2885]     0  2885     1489      118   0       0             0 sudo
Jan  4 15:23:35 figo-desktop kernel: [ 2886]     0  2886     6273      353   1       0             0 vim
Jan  4 15:23:35 figo-desktop kernel: [ 2887]  1000  2887      472       84   0       0             0 ping
Jan  4 15:23:35 figo-desktop kernel: [ 2892]  1000  2892      472       83   1       0             0 ping
Jan  4 15:23:35 figo-desktop kernel: [ 2894]  1000  2894    76113     5382   0       0             0 vmware
Jan  4 15:23:35 figo-desktop kernel: [ 2919]  1000  2919    51497     3224   1       0             0 vmware-tray
Jan  4 15:23:35 figo-desktop kernel: [ 2954]  1000  2954    48676     1588   1       0             0 vmware-unity-he
Jan  4 15:23:35 figo-desktop kernel: [ 2988]  1000  2988   190471    40349   1       0             0 vmware-vmx
Jan  4 15:23:35 figo-desktop kernel: [ 3207]  1000  3207     4377      279   1       0             0 gvfsd-computer
Jan  4 15:23:35 figo-desktop kernel: [ 3211]  1000  3211     9920      416   0       0             0 gvfsd-smb-brows
Jan  4 15:23:35 figo-desktop kernel: [ 3217]  1000  3217     9876      545   0       0             0 gvfsd-smb
Jan  4 15:23:35 figo-desktop kernel: [15186]  1000 15186     2069      551   1       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [17451]  1000 17451     5679      500   0       0             0 dconf-service
Jan  4 15:23:35 figo-desktop kernel: [19085]  1000 19085     1576      147   0       0             0 ssh
Jan  4 15:23:35 figo-desktop kernel: [19261]  1000 19261     1682      957   0       0             0 wineserver
Jan  4 15:23:35 figo-desktop kernel: [19266]  1000 19266   399085      102   0       0             0 services.exe
Jan  4 15:23:35 figo-desktop kernel: [19269]  1000 19269   399117       70   1       0             0 winedevice.exe
Jan  4 15:23:35 figo-desktop kernel: [19342]  1000 19342   404518      611   0       0             0 explorer.exe
Jan  4 15:23:35 figo-desktop kernel: [19344]  1000 19344   550020    10567   0       0             0 insight3.exe
Jan  4 15:23:35 figo-desktop kernel: [  360]  1000   360     2069      508   1       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [ 9821]  1000  9821   166228     2782   0       0             0 stardict
Jan  4 15:23:35 figo-desktop kernel: [14614]  1000 14614     2040      515   1       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [17002]  1000 17002     2069      435   0       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [18612]     0 18612     1536      124   1       0             0 sudo
Jan  4 15:23:35 figo-desktop kernel: [18613]     0 18613     1988      607   1       0             0 minicom
Jan  4 15:23:35 figo-desktop kernel: [21183]  1000 21183     2041      383   1       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [21194]  1000 21194     1611      124   0       0             0 ssh
Jan  4 15:23:35 figo-desktop kernel: [22451]  1000 22451     2069      575   1       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [23428]  1000 23428     6475      549   1       0             0 vim
Jan  4 15:23:35 figo-desktop kernel: [23484]  1000 23484     6501      585   1       0             0 vim
Jan  4 15:23:35 figo-desktop kernel: [23549]  1000 23549     6501      582   0       0             0 vim
Jan  4 15:23:35 figo-desktop kernel: [23642]  1000 23642     9865      569   0       0             0 gvfsd-smb
Jan  4 15:23:35 figo-desktop kernel: [26358]  1000 26358   407339     4454   0       0             0 insight3.exe
Jan  4 15:23:35 figo-desktop kernel: [29711]  1000 29711     9943      549   0       0             0 gvfsd-smb
Jan  4 15:23:35 figo-desktop kernel: [26156]  1000 26156    61269     9022   0       0             0 skype
Jan  4 15:23:35 figo-desktop kernel: [32490]  1000 32490     2647      675   1       0             0 gconfd-2
Jan  4 15:23:35 figo-desktop kernel: [10622]  1000 10622     2072      725   0       0             0 bash
Jan  4 15:23:35 figo-desktop kernel: [10634]  1000 10634     1576      155   0       0             0 ssh
Jan  4 15:23:35 figo-desktop kernel: [15410]  1000 15410    76559    12077   0       0             0 evince
Jan  4 15:23:35 figo-desktop kernel: [15415]  1000 15415     5490      217   1       0             0 evinced
Jan  4 15:23:35 figo-desktop kernel: [16754]  1000 16754     9899      484   0       0             0 gvfsd-smb
Jan  4 15:23:35 figo-desktop kernel: [16772]  1000 16772     9900      498   0       0             0 gvfsd-smb
Jan  4 15:23:35 figo-desktop kernel: [25390]  1000 25390   407306     2127   1       0             0 insight3.exe
Jan  4 15:23:35 figo-desktop kernel: [ 2127]  1000  2127     1609      124   0       0             0 ssh
Jan  4 15:23:35 figo-desktop kernel: [10661]    33 10661     4775     1324   1       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [10662]    33 10662     4823     1557   0       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [10663]    33 10663     4823     1558   0       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [10664]    33 10664     4823     1557   0       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [10665]    33 10665     4823     1557   0       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [10666]    33 10666     4823     1557   1       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [32159]  1000 32159   166096    39370   1       0             0 firefox
Jan  4 15:23:35 figo-desktop kernel: [32228]    33 32228     4823     1500   0       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [32233]    33 32233     4857     1584   1       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [32234]    33 32234     4857     1585   1       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [32241]    33 32241     4789     1524   1       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [32246]    33 32246     4789     1524   0       0             0 httpd
Jan  4 15:23:35 figo-desktop kernel: [32268]  1000 32268    27543     4243   1       0             0 plugin-containe
Jan  4 15:23:35 figo-desktop kernel: [32320]  1000 32320    16230     1445   1       0             0 GoogleTalkPlugi
Jan  4 15:23:35 figo-desktop kernel: [  970]  1000   970   407197     2605   1       0             0 insight3.exe
Jan  4 15:23:35 figo-desktop kernel: [ 1240]  1000  1240      601      116   1       0             0 top
Jan  4 15:23:35 figo-desktop kernel: [ 2038]  1000  2038   407785     2770   1       0             0 insight3.exe
Jan  4 15:23:35 figo-desktop kernel: [12415]     0 12415      543      242   1     -17         -1000 udevd
Jan  4 15:23:35 figo-desktop kernel: [12416]     0 12416      580      195   1     -17         -1000 udevd
Jan  4 15:23:35 figo-desktop kernel: [13911]     0 13911      719      269   0       0             0 sh
Jan  4 15:23:35 figo-desktop kernel: [13914]     0 13914      719      268   0       0             0 sh
Jan  4 15:23:35 figo-desktop kernel: [13916]     0 13916     1187      188   1       0             0 git
Jan  4 15:23:35 figo-desktop kernel: [13918]     0 13918      719      313   0       0             0 git-pull
Jan  4 15:23:35 figo-desktop kernel: [13952]     0 13952     1189      263   1       0             0 git
Jan  4 15:23:35 figo-desktop kernel: [13954]     0 13954     1575      460   1       0             0 ssh
Jan  4 15:23:35 figo-desktop kernel: [13956]     0 13956     1488      219   1       0             0 sudo
Jan  4 15:23:35 figo-desktop kernel: [13957]     0 13957     1386      130   0       0             0 swapoff
Jan  4 15:23:43 figo-desktop kernel: Xorg invoked oom-killer: gfp_mask=0x80d2, order=0, oom_adj=0, oom_score_adj=0
Jan  4 15:23:43 figo-desktop kernel: Xorg cpuset=/ mems_allowed=0
Jan  4 15:23:43 figo-desktop kernel: Pid: 1636, comm: Xorg Not tainted 2.6.36-ARCH #1
Jan  4 15:23:43 figo-desktop kernel: Call Trace:
Jan  4 15:23:43 figo-desktop kernel: [<c10c11d0>] dump_header.clone.5+0x80/0x1e0
Jan  4 15:23:43 figo-desktop kernel: [<c10c153c>] oom_kill_process+0x5c/0x1c0
Jan  4 15:23:43 figo-desktop kernel: [<c10c171d>] ? select_bad_process.clone.7+0x7d/0xd0
Jan  4 15:23:43 figo-desktop kernel: [<c10c1a0f>] out_of_memory+0xbf/0x1d0
Jan  4 15:23:43 figo-desktop kernel: [<c10c18d8>] ? try_set_zonelist_oom+0xc8/0xe0
Jan  4 15:23:43 figo-desktop kernel: [<c10c5288>] __alloc_pages_nodemask+0x5e8/0x600
Jan  4 15:23:44 figo-desktop kernel: [<c10e36f6>] __vmalloc_area_node+0x76/0x100
Jan  4 15:23:44 figo-desktop kernel: [<c102fb30>] ? __wake_up_common+0x40/0x70
Jan  4 15:23:44 figo-desktop kernel: [<f8991f87>] ? i915_gem_do_execbuffer+0xa87/0x1110 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<c10e381a>] __vmalloc_node+0x9a/0xa0
Jan  4 15:23:44 figo-desktop kernel: [<f8991f87>] ? i915_gem_do_execbuffer+0xa87/0x1110 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<f8991f87>] ? i915_gem_do_execbuffer+0xa87/0x1110 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<f8991f87>] ? i915_gem_do_execbuffer+0xa87/0x1110 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<c10e3975>] __vmalloc+0x25/0x30
Jan  4 15:23:44 figo-desktop kernel: [<f8991f87>] ? i915_gem_do_execbuffer+0xa87/0x1110 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<f8991f87>] i915_gem_do_execbuffer+0xa87/0x1110 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<c12e49c8>] ? unix_stream_recvmsg+0x498/0x580
Jan  4 15:23:44 figo-desktop kernel: [<c11a34d2>] ? _copy_from_user+0x32/0x50
Jan  4 15:23:44 figo-desktop kernel: [<f8992687>] i915_gem_execbuffer2+0x77/0x1e0 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<f8323231>] drm_ioctl+0x1e1/0x470 [drm]
Jan  4 15:23:44 figo-desktop kernel: [<f8992610>] ? i915_gem_execbuffer2+0x0/0x1e0 [i915]
Jan  4 15:23:44 figo-desktop kernel: [<c10fd2dc>] ? do_sync_read+0x9c/0xd0
Jan  4 15:23:44 figo-desktop kernel: [<c1064e06>] ? __hrtimer_start_range_ns+0x1a6/0x4d0
Jan  4 15:23:44 figo-desktop kernel: [<f8323050>] ? drm_ioctl+0x0/0x470 [drm]
Jan  4 15:23:44 figo-desktop kernel: [<c110beca>] do_vfs_ioctl+0x7a/0x590
Jan  4 15:23:44 figo-desktop kernel: [<c1172121>] ? tomoyo_init_request_info+0x41/0x50
Jan  4 15:23:44 figo-desktop kernel: [<c116ebb9>] ? tomoyo_path_number_perm+0x29/0xe0
Jan  4 15:23:44 figo-desktop kernel: [<c10fdb39>] ? vfs_read+0x149/0x160
Jan  4 15:23:44 figo-desktop kernel: [<c1170eb2>] ? tomoyo_file_ioctl+0x12/0x20
Jan  4 15:23:44 figo-desktop kernel: [<c110c43f>] sys_ioctl+0x5f/0x80
Jan  4 15:23:44 figo-desktop kernel: [<c100379f>] sysenter_do_call+0x12/0x28
Jan  4 15:23:44 figo-desktop kernel: Mem-Info:
Jan  4 15:23:44 figo-desktop kernel: DMA per-cpu:
Jan  4 15:23:44 figo-desktop kernel: CPU    0: hi:    0, btch:   1 usd:   0
Jan  4 15:23:44 figo-desktop kernel: CPU    1: hi:    0, btch:   1 usd:   0
Jan  4 15:23:44 figo-desktop kernel: Normal per-cpu:
Jan  4 15:23:44 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  37
Jan  4 15:23:44 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:  45
Jan  4 15:23:44 figo-desktop kernel: HighMem per-cpu:
Jan  4 15:23:44 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:   2
Jan  4 15:23:44 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:  36
Jan  4 15:23:44 figo-desktop kernel: active_anon:196238 inactive_anon:97262 isolated_anon:0
Jan  4 15:23:44 figo-desktop kernel: active_file:54385 inactive_file:122363 isolated_file:0
Jan  4 15:23:44 figo-desktop kernel: unevictable:17 dirty:0 writeback:41 unstable:0
Jan  4 15:23:44 figo-desktop kernel: free:11933 slab_reclaimable:5456 slab_unreclaimable:6120
Jan  4 15:23:44 figo-desktop kernel: mapped:47868 shmem:29255 pagetables:2585 bounce:0
Jan  4 15:23:44 figo-desktop kernel: DMA free:7976kB min:64kB low:80kB high:96kB active_anon:2908kB inactive_anon:3020kB active_file:532kB inactive_file:764kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15788kB mlocked:0kB dirty:0kB writeback:0kB mapped:528kB shmem:52kB slab_reclaimable:480kB slab_unreclaimable:112kB kernel_stack:8kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:2053 all_unreclaimable? yes
Jan  4 15:23:44 figo-desktop kernel: lowmem_reserve[]: 0 865 1980 1980
Jan  4 15:23:44 figo-desktop kernel: Normal free:39352kB min:3728kB low:4660kB high:5592kB active_anon:230308kB inactive_anon:219780kB active_file:86232kB inactive_file:207668kB unevictable:68kB isolated(anon):0kB isolated(file):0kB present:885944kB mlocked:68kB dirty:0kB writeback:0kB mapped:55204kB shmem:36960kB slab_reclaimable:21344kB slab_unreclaimable:24368kB kernel_stack:3272kB pagetables:10340kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:448565 all_unreclaimable? yes
Jan  4 15:23:44 figo-desktop kernel: lowmem_reserve[]: 0 0 8921 8921
Jan  4 15:23:44 figo-desktop kernel: HighMem free:404kB min:512kB low:1712kB high:2912kB active_anon:551736kB inactive_anon:166248kB active_file:130776kB inactive_file:281020kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:1141984kB mlocked:0kB dirty:0kB writeback:164kB mapped:135740kB shmem:80008kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:687864 all_unreclaimable? yes
Jan  4 15:23:44 figo-desktop kernel: lowmem_reserve[]: 0 0 0 0
Jan  4 15:23:44 figo-desktop kernel: DMA: 1546*4kB 224*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 7976kB
Jan  4 15:23:44 figo-desktop kernel: Normal: 1678*4kB 3750*8kB 49*16kB 6*32kB 2*64kB 2*128kB 3*256kB 1*512kB 0*1024kB 0*2048kB 0*4096kB = 39352kB
Jan  4 15:23:44 figo-desktop kernel: HighMem: 20*4kB 7*8kB 18*16kB 1*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 456kB
Jan  4 15:23:44 figo-desktop kernel: 209015 total pagecache pages
Jan  4 15:23:44 figo-desktop kernel: 2993 pages in swap cache
Jan  4 15:23:44 figo-desktop kernel: Swap cache stats: add 1046799, delete 1043806, find 277476/391899
Jan  4 15:23:44 figo-desktop kernel: Free swap  = -14768kB
Jan  4 15:23:44 figo-desktop kernel: Total swap = 0kB
Jan  4 15:23:44 figo-desktop kernel: 515070 pages RAM
Jan  4 15:23:44 figo-desktop kernel: 287745 pages HighMem
Jan  4 15:23:44 figo-desktop kernel: 8297 pages reserved
Jan  4 15:23:44 figo-desktop kernel: 302258 pages shared
Jan  4 15:23:44 figo-desktop kernel: 308041 pages non-shared
Jan  4 15:23:44 figo-desktop kernel: [ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name
Jan  4 15:23:44 figo-desktop kernel: [  583]     0   583      581      246   1     -17         -1000 udevd
Jan  4 15:23:44 figo-desktop kernel: [ 1303]     0  1303      868       37   0       0             0 syslog-ng
Jan  4 15:23:44 figo-desktop kernel: [ 1304]     0  1304     1604      383   1       0             0 syslog-ng
Jan  4 15:23:44 figo-desktop kernel: [ 1306]    81  1306      808      362   0       0             0 dbus-daemon
Jan  4 15:23:44 figo-desktop kernel: [ 1309]    82  1309     3777      376   1       0             0 hald
Jan  4 15:23:44 figo-desktop kernel: [ 1310]     0  1310      903      130   1       0             0 hald-runner
Jan  4 15:23:44 figo-desktop kernel: [ 1339]     0  1339      919       87   1       0             0 hald-addon-inpu
Jan  4 15:23:44 figo-desktop kernel: [ 1357]     0  1357      919      184   0       0             0 hald-addon-stor
Jan  4 15:23:44 figo-desktop kernel: [ 1359]    82  1359      824      107   1       0             0 hald-addon-acpi
Jan  4 15:23:44 figo-desktop kernel: [ 1448]     0  1448      616      294   0       0             0 crond
Jan  4 15:23:44 figo-desktop kernel: [ 1477]     0  1477      720      108   0       0             0 mysqld_safe
Jan  4 15:23:44 figo-desktop kernel: [ 1484]     0  1484     3580      269   0       0             0 gdm-binary
Jan  4 15:23:44 figo-desktop kernel: [ 1497]     0  1497      440       67   1       0             0 agetty
Jan  4 15:23:44 figo-desktop kernel: [ 1498]     0  1498      440       67   0       0             0 agetty
Jan  4 15:23:44 figo-desktop kernel: [ 1499]     0  1499      440       67   0       0             0 agetty
Jan  4 15:23:44 figo-desktop kernel: [ 1500]     0  1500      440       67   1       0             0 agetty
Jan  4 15:23:44 figo-desktop kernel: [ 1501]     0  1501      440       67   0       0             0 agetty
Jan  4 15:23:44 figo-desktop kernel: [ 1502]     0  1502      440       68   0       0             0 agetty
Jan  4 15:23:44 figo-desktop kernel: [ 1553]     0  1553     6607      652   0       0             0 NetworkManager
Jan  4 15:23:44 figo-desktop kernel: [ 1592]     0  1592     2256      330   0       0             0 cupsd
Jan  4 15:23:44 figo-desktop kernel: [ 1597]    89  1597    29903     2812   1       0             0 mysqld
Jan  4 15:23:44 figo-desktop kernel: [ 1598]     0  1598     1652      147   1     -17         -1000 sshd
Jan  4 15:23:44 figo-desktop kernel: [ 1612]     0  1612     6263      508   1       0             0 polkitd
Jan  4 15:23:44 figo-desktop kernel: [ 1613]     0  1613     2015      123   1       0             0 vmware-usbarbit
Jan  4 15:23:44 figo-desktop kernel: [ 1617]     0  1617     2887     1600   1       0             0 cntlm
Jan  4 15:23:44 figo-desktop kernel: [ 1620]     0  1620     4398      366   0       0             0 gdm-simple-slav
Jan  4 15:23:44 figo-desktop kernel: [ 1636]     0  1636    37333     9882   1       0             0 Xorg
Jan  4 15:23:44 figo-desktop kernel: [ 1638]     0  1638     1248       88   0       0             0 wpa_supplicant
Jan  4 15:23:44 figo-desktop kernel: [ 1720]     0  1720     4789     1537   1       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [ 1722]     0  1722      488       93   0       0             0 dhcpcd
Jan  4 15:23:44 figo-desktop kernel: [ 1732]     0  1732      519       62   1       0             0 vmnet-bridge
Jan  4 15:23:44 figo-desktop kernel: [ 1750]     0  1750     4922      304   1       0             0 smbd
Jan  4 15:23:44 figo-desktop kernel: [ 1764]     0  1764      655       39   1       0             0 vmnet-dhcpd
Jan  4 15:23:44 figo-desktop kernel: [ 1772]     0  1772      513       15   0       0             0 vmnet-netifup
Jan  4 15:23:44 figo-desktop kernel: [ 1774]     0  1774      655       39   0       0             0 vmnet-dhcpd
Jan  4 15:23:44 figo-desktop kernel: [ 1776]     0  1776     4922      225   0       0             0 smbd
Jan  4 15:23:44 figo-desktop kernel: [ 1778]     0  1778      634       44   0       0             0 vmnet-natd
Jan  4 15:23:44 figo-desktop kernel: [ 1780]     0  1780      513       14   1       0             0 vmnet-netifup
Jan  4 15:23:44 figo-desktop kernel: [ 1796]     0  1796     6677      329   0       0             0 console-kit-dae
Jan  4 15:23:44 figo-desktop kernel: [ 1899]   120  1899     6587      598   0       0             0 polkit-gnome-au
Jan  4 15:23:44 figo-desktop kernel: [ 1903]     0  1903     3905      245   0       0             0 gdm-session-wor
Jan  4 15:23:44 figo-desktop kernel: [ 1906]     0  1906     3677      314   1       0             0 upowerd
Jan  4 15:23:44 figo-desktop kernel: [ 1974]  1000  1974    10963     1248   0       0             0 gnome-keyring-d
Jan  4 15:23:44 figo-desktop kernel: [ 1993]  1000  1993     9253      776   0       0             0 gnome-session
Jan  4 15:23:44 figo-desktop kernel: [ 2012]  1000  2012      796      103   0       0             0 dbus-launch
Jan  4 15:23:44 figo-desktop kernel: [ 2013]  1000  2013     5854     4969   0       0             0 dbus-daemon
Jan  4 15:23:44 figo-desktop kernel: [ 2015]  1000  2015      887       54   1       0             0 ssh-agent
Jan  4 15:23:44 figo-desktop kernel: [ 2022]  1000  2022    10904     4786   1       0             0 fcitx
Jan  4 15:23:44 figo-desktop kernel: [ 2032]  1000  2032    41764     1981   1       0             0 gnome-settings-
Jan  4 15:23:44 figo-desktop kernel: [ 2036]  1000  2036     2367      416   0       0             0 gvfsd
Jan  4 15:23:44 figo-desktop kernel: [ 2039]  1000  2039    85188    26593   0       0             0 metacity
Jan  4 15:23:44 figo-desktop kernel: [ 2049]  1000  2049    14162      280   1       0             0 gvfs-fuse-daemo
Jan  4 15:23:44 figo-desktop kernel: [ 2053]  1000  2053    76657     3497   0       0             0 gnome-panel
Jan  4 15:23:44 figo-desktop kernel: [ 2056]  1000  2056    10978      563   0       0             0 gvfs-gdu-volume
Jan  4 15:23:44 figo-desktop kernel: [ 2058]     0  2058     5767      465   1       0             0 udisks-daemon
Jan  4 15:23:44 figo-desktop kernel: [ 2059]     0  2059     1291       72   1       0             0 udisks-daemon
Jan  4 15:23:44 figo-desktop kernel: [ 2069]  1000  2069   168292    50767   0       0             0 nautilus
Jan  4 15:23:44 figo-desktop kernel: [ 2071]  1000  2071    12907      223   0       0             0 bonobo-activati
Jan  4 15:23:44 figo-desktop kernel: [ 2081]  1000  2081     1633      136   0       0             0 sh
Jan  4 15:23:44 figo-desktop kernel: [ 2082]  1000  2082     1666      136   1       0             0 thunderbird
Jan  4 15:23:44 figo-desktop kernel: [ 2084]  1000  2084    46718     3364   0       0             0 wnck-applet
Jan  4 15:23:44 figo-desktop kernel: [ 2086]  1000  2086    42862     1443   0       0             0 polkit-gnome-au
Jan  4 15:23:44 figo-desktop kernel: [ 2087]  1000  2087   285933     1529   0       0             0 nm-applet
Jan  4 15:23:44 figo-desktop kernel: [ 2104]  1000  2104     5056      756   1       0             0 gdu-notificatio
Jan  4 15:23:44 figo-desktop kernel: [ 2107]  1000  2107     1666      142   1       0             0 run-mozilla.sh
Jan  4 15:23:44 figo-desktop kernel: [ 2108]  1000  2108    39395      941   0       0             0 gnome-power-man
Jan  4 15:23:44 figo-desktop kernel: [ 2109]  1000  2109     7886      709   0       0             0 vino-server
Jan  4 15:23:44 figo-desktop kernel: [ 2110]  1000  2110    10764      791   1       0             0 evolution-alarm
Jan  4 15:23:44 figo-desktop kernel: [ 2114]  1000  2114   167865    29566   1       0             0 thunderbird-bin
Jan  4 15:23:44 figo-desktop kernel: [ 2121]  1000  2121    42098     1946   0       0             0 notify-osd
Jan  4 15:23:44 figo-desktop kernel: [ 2125]  1000  2125    42488     1203   1       0             0 cpufreq-applet
Jan  4 15:23:44 figo-desktop kernel: [ 2126]  1000  2126    41394     1148   1       0             0 multiload-apple
Jan  4 15:23:44 figo-desktop kernel: [ 2129]  1000  2129    64405     1758   0       0             0 mixer_applet2
Jan  4 15:23:44 figo-desktop kernel: [ 2131]  1000  2131    75346     2389   1       0             0 clock-applet
Jan  4 15:23:44 figo-desktop kernel: [ 2132]  1000  2132    41163      930   1       0             0 notification-ar
Jan  4 15:23:44 figo-desktop kernel: [ 2149]  1000  2149    15325      697   1       0             0 e-calendar-fact
Jan  4 15:23:44 figo-desktop kernel: [ 2153]  1000  2153     7497     1008   1       0             0 gnome-screensav
Jan  4 15:23:44 figo-desktop kernel: [ 2155]  1000  2155     3848      202   1       0             0 pxgconf
Jan  4 15:23:44 figo-desktop kernel: [ 2163]  1000  2163     1781      342   0       0             0 mission-control
Jan  4 15:23:44 figo-desktop kernel: [ 2173]  1000  2173     4486      427   0       0             0 gvfsd-trash
Jan  4 15:23:44 figo-desktop kernel: [ 2186]     0  2186     3543      192   1       0             0 system-tools-ba
Jan  4 15:23:44 figo-desktop kernel: [ 2210]  1000  2210     2202      238   0       0             0 gvfsd-burn
Jan  4 15:23:44 figo-desktop kernel: [ 2245]  1000  2245     3895     1728   0       0             0 gvfsd-metadata
Jan  4 15:23:44 figo-desktop kernel: [ 2274]  1000  2274    22823      424   1       0             0 conky
Jan  4 15:23:44 figo-desktop kernel: [ 2281]     0  2281     3295     2278   0       0             0 SystemToolsBack
Jan  4 15:23:44 figo-desktop kernel: [ 2663]  1000  2663    68807     2944   1       0             0 gnome-terminal
Jan  4 15:23:44 figo-desktop kernel: [ 2683]  1000  2683      451       76   0       0             0 gnome-pty-helpe
Jan  4 15:23:44 figo-desktop kernel: [ 2685]  1000  2685     2072      570   0       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [ 2885]     0  2885     1489      119   0       0             0 sudo
Jan  4 15:23:44 figo-desktop kernel: [ 2886]     0  2886     6273      355   1       0             0 vim
Jan  4 15:23:44 figo-desktop kernel: [ 2887]  1000  2887      472       84   0       0             0 ping
Jan  4 15:23:44 figo-desktop kernel: [ 2892]  1000  2892      472       83   1       0             0 ping
Jan  4 15:23:44 figo-desktop kernel: [ 2894]  1000  2894    76113     5872   0       0             0 vmware
Jan  4 15:23:44 figo-desktop kernel: [ 2919]  1000  2919    51497     3266   1       0             0 vmware-tray
Jan  4 15:23:44 figo-desktop kernel: [ 2954]  1000  2954    48676     1589   0       0             0 vmware-unity-he
Jan  4 15:23:44 figo-desktop kernel: [ 2988]  1000  2988   190471    42604   1       0             0 vmware-vmx
Jan  4 15:23:44 figo-desktop kernel: [ 3207]  1000  3207     4377      362   1       0             0 gvfsd-computer
Jan  4 15:23:44 figo-desktop kernel: [ 3211]  1000  3211     9920      509   0       0             0 gvfsd-smb-brows
Jan  4 15:23:44 figo-desktop kernel: [ 3217]  1000  3217     9876      569   0       0             0 gvfsd-smb
Jan  4 15:23:44 figo-desktop kernel: [15186]  1000 15186     2069      558   1       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [17451]  1000 17451     5679      503   0       0             0 dconf-service
Jan  4 15:23:44 figo-desktop kernel: [19085]  1000 19085     1576      149   0       0             0 ssh
Jan  4 15:23:44 figo-desktop kernel: [19261]  1000 19261     1682      967   1       0             0 wineserver
Jan  4 15:23:44 figo-desktop kernel: [19266]  1000 19266   399085      212   0       0             0 services.exe
Jan  4 15:23:44 figo-desktop kernel: [19269]  1000 19269   399117      158   1       0             0 winedevice.exe
Jan  4 15:23:44 figo-desktop kernel: [19342]  1000 19342   404518      620   0       0             0 explorer.exe
Jan  4 15:23:44 figo-desktop kernel: [19344]  1000 19344   550020    10921   0       0             0 insight3.exe
Jan  4 15:23:44 figo-desktop kernel: [  360]  1000   360     2069      541   1       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [ 9821]  1000  9821   166228     2835   0       0             0 stardict
Jan  4 15:23:44 figo-desktop kernel: [14614]  1000 14614     2040      523   1       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [17002]  1000 17002     2069      541   0       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [18612]     0 18612     1536      125   1       0             0 sudo
Jan  4 15:23:44 figo-desktop kernel: [18613]     0 18613     1988      607   0       0             0 minicom
Jan  4 15:23:44 figo-desktop kernel: [21183]  1000 21183     2041      517   1       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [21194]  1000 21194     1611      125   0       0             0 ssh
Jan  4 15:23:44 figo-desktop kernel: [22451]  1000 22451     2069      578   1       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [23428]  1000 23428     6475      554   1       0             0 vim
Jan  4 15:23:44 figo-desktop kernel: [23484]  1000 23484     6501      594   1       0             0 vim
Jan  4 15:23:44 figo-desktop kernel: [23549]  1000 23549     6501      594   0       0             0 vim
Jan  4 15:23:44 figo-desktop kernel: [23642]  1000 23642     9865      594   0       0             0 gvfsd-smb
Jan  4 15:23:44 figo-desktop kernel: [26358]  1000 26358   407339     4819   1       0             0 insight3.exe
Jan  4 15:23:44 figo-desktop kernel: [29711]  1000 29711     9943      617   0       0             0 gvfsd-smb
Jan  4 15:23:44 figo-desktop kernel: [26156]  1000 26156    61269     9261   0       0             0 skype
Jan  4 15:23:44 figo-desktop kernel: [32490]  1000 32490     2647      678   1       0             0 gconfd-2
Jan  4 15:23:44 figo-desktop kernel: [10622]  1000 10622     2072      741   1       0             0 bash
Jan  4 15:23:44 figo-desktop kernel: [10634]  1000 10634     1576      156   0       0             0 ssh
Jan  4 15:23:44 figo-desktop kernel: [15410]  1000 15410    76559    12077   0       0             0 evince
Jan  4 15:23:44 figo-desktop kernel: [15415]  1000 15415     5490      217   1       0             0 evinced
Jan  4 15:23:44 figo-desktop kernel: [16754]  1000 16754     9899      485   0       0             0 gvfsd-smb
Jan  4 15:23:44 figo-desktop kernel: [16772]  1000 16772     9900      500   0       0             0 gvfsd-smb
Jan  4 15:23:44 figo-desktop kernel: [25390]  1000 25390   407306     2127   1       0             0 insight3.exe
Jan  4 15:23:44 figo-desktop kernel: [ 2127]  1000  2127     1609      125   0       0             0 ssh
Jan  4 15:23:44 figo-desktop kernel: [10661]    33 10661     4775     1510   1       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [10662]    33 10662     4823     1567   0       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [10663]    33 10663     4823     1568   0       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [10664]    33 10664     4823     1567   0       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [10665]    33 10665     4823     1567   0       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [10666]    33 10666     4823     1567   1       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [32159]  1000 32159   166096    39444   1       0             0 firefox
Jan  4 15:23:44 figo-desktop kernel: [32228]    33 32228     4823     1510   0       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [32233]    33 32233     4857     1594   1       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [32234]    33 32234     4857     1595   1       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [32241]    33 32241     4789     1534   1       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [32246]    33 32246     4789     1534   0       0             0 httpd
Jan  4 15:23:44 figo-desktop kernel: [32268]  1000 32268    27543     4273   1       0             0 plugin-containe
Jan  4 15:23:44 figo-desktop kernel: [32320]  1000 32320    16230     1445   1       0             0 GoogleTalkPlugi
Jan  4 15:23:44 figo-desktop kernel: [  970]  1000   970   407197     2621   0       0             0 insight3.exe
Jan  4 15:23:44 figo-desktop kernel: [ 1240]  1000  1240      601      116   1       0             0 top
Jan  4 15:23:44 figo-desktop kernel: [ 2038]  1000  2038   407785     2796   1       0             0 insight3.exe
Jan  4 15:23:44 figo-desktop kernel: [12415]     0 12415      543      242   1     -17         -1000 udevd
Jan  4 15:23:44 figo-desktop kernel: [12416]     0 12416      580      195   1     -17         -1000 udevd
Jan  4 15:23:44 figo-desktop kernel: [13911]     0 13911      719      269   0       0             0 sh
Jan  4 15:23:44 figo-desktop kernel: [13914]     0 13914      719      268   0       0             0 sh
Jan  4 15:23:44 figo-desktop kernel: [13916]     0 13916     1187      188   1       0             0 git
Jan  4 15:23:44 figo-desktop kernel: [13918]     0 13918      719      313   0       0             0 git-pull
Jan  4 15:23:44 figo-desktop kernel: [13952]     0 13952     1189      263   1       0             0 git
Jan  4 15:23:44 figo-desktop kernel: [13954]     0 13954     1575      460   1       0             0 ssh
Jan  4 15:23:44 figo-desktop kernel: [13960]     0 13960     1488      224   1       0             0 sudo
Jan  4 15:23:44 figo-desktop kernel: [13962]     0 13962     1386      130   0       0             0 swapoff
Quoted 33 lines · Figo.zhang

the victim should not directly access hardware devices like Xorg server, because the hardware could be left in an unpredictable state, although user-application can set /proc/pid/oom_score_adj to protect it. so i think those processes should get bonus for protection.

in v2, fix the incorrect comment.
in v3, change the divided the badness score by 4, like old heuristic for protection. we just want the oom_killer don't select Root/RESOURCE/RAWIO process as possible.

suppose that if a user process A such as email cleint "evolution" and a process B with ditecly hareware access such as "Xorg", they have eat the equal memory (the badness score is the same),so which process are you want to kill? so in new heuristic, it will kill the process B. but in reality, we want to kill process A.

---
mm/oom_kill.c | 9 +++++++++

  1 files changed, 9 insertions(+), 0 deletions(-)
mm/oom_kill.c +2 -0
index 4029583..f43d759 100644
@@ -202,6 +202,15 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
  		points -= 30;
 
  	/*
+	 * Root and direct hareware access processes are usually more
+	 * important, so they should get bonus for protection.

mm/oom_kill.c unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, · line 216

Quoted 10 lines
mm/oom_kill.c +7 -0
+	 */
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE) ||
+	    has_capability_noaudit(p, CAP_SYS_RAWIO))
+		points /= 4;
+
+	/*
  	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
  	 * either completely disable oom killing or always prefer a certain
  	 * task.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#42 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

Quoted 7 lines · On Tue, 04 Jan 2011 15:51:44 +0800 "Figo.zhang"…

i had send the patch to protect the hardware access processes for oom-killer before, but rientjes have not agree with me.

but today i catch log from my desktop. oom-killer have kill my "minicom" and "Xorg". so i think it should add protection about it.

Off topic.

In this log, I found

Quoted 3 lines
Quoted 3 lines
Jan  4 15:22:55 figo-desktop kernel: Free swap  = -1636kB
Jan  4 15:22:55 figo-desktop kernel: Total swap = 0kB
Jan  4 15:22:55 figo-desktop kernel: 515070 pages RAM

... This means total_swap_pages = 0 while pages are read-in at swapoff.

Let's see 'points' for oom
==
points = (get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS)) * 1000 /

                        totalpages;

==

Here, totalpages = total_ram + total_swap but totalswap is 0 here.

So, points can be > 1000, easily.
(This seems not to be related to the Xorg's death itself)

Thanks,
-Kame

#43 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

Quoted 24 lines · KAMEZAWA Hiroyuki
Quoted 7 lines · On Tue, 04 Jan 2011 15:51:44 +0800 "Figo.zhang"<[email protected]>…

i had send the patch to protect the hardware access processes for oom-killer before, but rientjes have not agree with me.

but today i catch log from my desktop. oom-killer have kill my "minicom" and "Xorg". so i think it should add protection about it.

Off topic.

In this log, I found

Quoted 3 lines
Quoted 3 lines
Jan  4 15:22:55 figo-desktop kernel: Free swap  = -1636kB
Jan  4 15:22:55 figo-desktop kernel: Total swap = 0kB
Jan  4 15:22:55 figo-desktop kernel: 515070 pages RAM

... This means total_swap_pages = 0 while pages are read-in at swapoff.

Let's see 'points' for oom
==
points = (get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS)) * 1000 /

Quoted 7 lines
                         totalpages;

==

Here, totalpages = total_ram + total_swap but totalswap is 0 here.

So, points can be> 1000, easily.
(This seems not to be related to the Xorg's death itself)

total_swap is 0, so
totalpages = total_ram,
get_mm_counter(p->mm, MM_SWAPENTS) = 0,

so
points = (get_mm_rss(p->mm)) * 1000 / totalpages;

so points canot larger than 1000.

Quoted 7 lines

Thanks,
-Kame

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#44 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

Quoted 33 lines · On Tue, 04 Jan 2011 16:56:47 +0800 "Figo.zhang"…
Quoted 24 lines · KAMEZAWA Hiroyuki
Quoted 7 lines · On Tue, 04 Jan 2011 15:51:44 +0800 "Figo.zhang"<[email protected]>…

i had send the patch to protect the hardware access processes for oom-killer before, but rientjes have not agree with me.

but today i catch log from my desktop. oom-killer have kill my "minicom" and "Xorg". so i think it should add protection about it.

Off topic.

In this log, I found

Quoted 3 lines
Quoted 3 lines
Jan  4 15:22:55 figo-desktop kernel: Free swap  = -1636kB
Jan  4 15:22:55 figo-desktop kernel: Total swap = 0kB
Jan  4 15:22:55 figo-desktop kernel: 515070 pages RAM

... This means total_swap_pages = 0 while pages are read-in at swapoff.

Let's see 'points' for oom
==
points = (get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS)) * 1000 /

Quoted 7 lines
                         totalpages;

==

Here, totalpages = total_ram + total_swap but totalswap is 0 here.

So, points can be> 1000, easily.
(This seems not to be related to the Xorg's death itself)

Quoted 8 lines

total_swap is 0, so
totalpages = total_ram,
get_mm_counter(p->mm, MM_SWAPENTS) = 0,

so
points = (get_mm_rss(p->mm)) * 1000 / totalpages;

so points canot larger than 1000.

mm_counter's swap count is reduced only when swapents are removed from page table. But total_swap is reduced to be 0 before try_to_unuse().

Thanks,
-Kame

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

#45 lore raw

Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus

In reply to Figo.zhang
Quoted 3 lines · Figo.zhang

i had send the patch to protect the hardware access processes for oom-killer before, but rientjes have not agree with me.

My objection wasn't just limited to CAP_SYS_RAWIO but rather to all arbitrary heuristics that make the badness scoring less than predictable. oom_badness()'s sole responsibility as implemented is to identify the most memory-hogging task that is eligible for kill in the current context and adding additional heuristics on top of that beyond CAP_SYS_ADMIN will slowly make it evolve into what we had before. It also depreciates the unit of the new userspace tunable.

Quoted 3 lines

but today i catch log from my desktop. oom-killer have kill my "minicom" and "Xorg". so i think it should add protection about it.

Because Xorg was killed does necessarily mean we need to add more heursitics to the oom killer. In fact, if you are to again suggest the 3% memory bonus for these tasks, you should be able to show that the same result cannot happen even with your patch. I don't believe you've made a case for that and making all CAP_SYS_RAWIO tasks immune from oom killing as a default choice would be inappropriate.

If the kernel is killing Xorg, that means it is the most memory-hogging task on the system and it is following the heuristic's core principle:
kill the most memory-hogging task to free a large amount of memory to prevent additional oom kills in the near future if allowed by userspace. The kernel doesn't realize that Xorg is important to you and me, it needs to tell it using /proc/pid/oom_score_adj. Throwing additional heuristics for things like CAP_SYS_RAWIO is short-sighted, however, because the capability itself doesn't have any direct correlation to a memory quantity or oom killing preference.

[snipped the first oom killer log because it was incomplete]

Quoted 398 lines
Quoted 398 lines
Jan  4 15:22:51 figo-desktop kernel: minicom invoked oom-killer:
gfp_mask=0x201da, order=0, oom_adj=0, oom_score_adj=0
Jan  4 15:22:51 figo-desktop kernel: minicom cpuset=/ mems_allowed=0
Jan  4 15:22:51 figo-desktop kernel: Pid: 18613, comm: minicom Not tainted
2.6.36-ARCH #1
Jan  4 15:22:51 figo-desktop kernel: Call Trace:
Jan  4 15:22:51 figo-desktop kernel: [<c10c11d0>]
dump_header.clone.5+0x80/0x1e0
Jan  4 15:22:51 figo-desktop kernel: [<c10c153c>]
oom_kill_process+0x5c/0x1c0
Jan  4 15:22:51 figo-desktop kernel: [<c10c171d>] ?
select_bad_process.clone.7+0x7d/0xd0
Jan  4 15:22:51 figo-desktop kernel: [<c10c1a0f>] out_of_memory+0xbf/0x1d0
Jan  4 15:22:51 figo-desktop kernel: [<c10c18d8>] ?
try_set_zonelist_oom+0xc8/0xe0
Jan  4 15:22:51 figo-desktop kernel: [<c10c5288>]
__alloc_pages_nodemask+0x5e8/0x600
Jan  4 15:22:51 figo-desktop kernel: [<c10c6c35>]
__do_page_cache_readahead+0x105/0x230
Jan  4 15:22:51 figo-desktop kernel: [<c10c6fc1>] ra_submit+0x21/0x30
Jan  4 15:22:51 figo-desktop kernel: [<c10bf31b>] filemap_fault+0x36b/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c10d637b>] __do_fault+0x3b/0x4f0
Jan  4 15:22:51 figo-desktop kernel: [<c122e619>] ?
check_modem_status+0x19/0x1d0
Jan  4 15:22:51 figo-desktop kernel: [<c10befb0>] ? filemap_fault+0x0/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c10d95c1>]
handle_mm_fault+0x111/0x970
Jan  4 15:22:51 figo-desktop kernel: [<c1172121>] ?
tomoyo_init_request_info+0x41/0x50
Jan  4 15:22:51 figo-desktop kernel: [<c1028d60>] ? do_page_fault+0x0/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c1028eb0>] do_page_fault+0x150/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c1170eb2>] ?
tomoyo_file_ioctl+0x12/0x20
Jan  4 15:22:51 figo-desktop kernel: [<c110c43f>] ? sys_ioctl+0x5f/0x80
Jan  4 15:22:51 figo-desktop kernel: [<c1028d60>] ? do_page_fault+0x0/0x3e0
Jan  4 15:22:51 figo-desktop kernel: [<c130753b>] error_code+0x67/0x6c
Jan  4 15:22:51 figo-desktop kernel: Mem-Info:
Jan  4 15:22:51 figo-desktop kernel: DMA per-cpu:
Jan  4 15:22:51 figo-desktop kernel: CPU    0: hi:    0, btch:   1 usd:   0
Jan  4 15:22:51 figo-desktop kernel: CPU    1: hi:    0, btch:   1 usd:   0
Jan  4 15:22:51 figo-desktop kernel: Normal per-cpu:
Jan  4 15:22:51 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  61
Jan  4 15:22:54 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:   1
Jan  4 15:22:54 figo-desktop kernel: HighMem per-cpu:
Jan  4 15:22:54 figo-desktop kernel: CPU    0: hi:  186, btch:  31 usd:  30
Jan  4 15:22:54 figo-desktop kernel: CPU    1: hi:  186, btch:  31 usd:  30
Jan  4 15:22:54 figo-desktop kernel: active_anon:191656 inactive_anon:101947
isolated_anon:0
Jan  4 15:22:54 figo-desktop kernel: active_file:54186 inactive_file:122506
isolated_file:0
Jan  4 15:22:54 figo-desktop kernel: unevictable:17 dirty:0 writeback:0
unstable:0
Jan  4 15:22:54 figo-desktop kernel: free:11958 slab_reclaimable:5450
slab_unreclaimable:6123
Jan  4 15:22:54 figo-desktop kernel: mapped:49649 shmem:29219
pagetables:2559 bounce:0
Jan  4 15:22:54 figo-desktop kernel: DMA free:7960kB min:64kB low:80kB

high:96kB active_anon:4772kB inactive_anon:1180kB active_file:524kB inactive_file:768kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15788kB mlocked:0kB dirty:0kB writeback:0kB mapped:592kB shmem:348kB slab_reclaimable:480kB slab_unreclaimable:112kB kernel_stack:8kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:2689 all_unreclaimable? yes

Jan  4 15:22:55 figo-desktop kernel: lowmem_reserve[]: 0 865 1980 1980
Jan  4 15:22:55 figo-desktop kernel: Normal free:39364kB min:3728kB

low:4660kB high:5592kB active_anon:224324kB inactive_anon:226020kB active_file:86076kB inactive_file:207880kB unevictable:68kB isolated(anon):0kB isolated(file):0kB present:885944kB mlocked:68kB dirty:0kB writeback:0kB mapped:57272kB shmem:42072kB slab_reclaimable:21320kB slab_unreclaimable:24380kB kernel_stack:3224kB pagetables:10236kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:445029 all_unreclaimable? yes

Jan  4 15:22:55 figo-desktop kernel: lowmem_reserve[]: 0 0 8921 8921
Jan  4 15:22:55 figo-desktop kernel: HighMem free:508kB min:512kB low:1712kB

high:2912kB active_anon:537528kB inactive_anon:180588kB active_file:130144kB inactive_file:281376kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:1141984kB mlocked:0kB dirty:0kB writeback:0kB mapped:140732kB shmem:74456kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:644938 all_unreclaimable? yes

Jan  4 15:22:55 figo-desktop kernel: lowmem_reserve[]: 0 0 0 0
Jan  4 15:22:55 figo-desktop kernel: DMA: 1500*4kB 245*8kB 0*16kB 0*32kB
0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 7960kB
Jan  4 15:22:55 figo-desktop kernel: Normal: 1399*4kB 3723*8kB 91*16kB
21*32kB 5*64kB 2*128kB 3*256kB 1*512kB 0*1024kB 0*2048kB 0*4096kB = 39364kB
Jan  4 15:22:55 figo-desktop kernel: HighMem: 27*4kB 10*8kB 18*16kB 1*32kB
0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 508kB
Jan  4 15:22:55 figo-desktop kernel: 206073 total pagecache pages
Jan  4 15:22:55 figo-desktop kernel: 151 pages in swap cache
Jan  4 15:22:55 figo-desktop kernel: Swap cache stats: add 889409, delete
889258, find 277087/391428
Jan  4 15:22:55 figo-desktop kernel: Free swap  = -1636kB
Jan  4 15:22:55 figo-desktop kernel: Total swap = 0kB
Jan  4 15:22:55 figo-desktop kernel: 515070 pages RAM
Jan  4 15:22:55 figo-desktop kernel: 287745 pages HighMem
Jan  4 15:22:55 figo-desktop kernel: 8297 pages reserved
Jan  4 15:22:55 figo-desktop kernel: 304095 pages shared
Jan  4 15:22:55 figo-desktop kernel: 306148 pages non-shared
Jan  4 15:22:55 figo-desktop kernel: [ pid ]   uid  tgid total_vm      rss
cpu oom_adj oom_score_adj name
Jan  4 15:22:55 figo-desktop kernel: [  583]     0   583      581      207
1     -17         -1000 udevd
Jan  4 15:22:55 figo-desktop kernel: [ 1303]     0  1303      868       37
0       0             0 syslog-ng
Jan  4 15:22:55 figo-desktop kernel: [ 1304]     0  1304     1604      350
0       0             0 syslog-ng
Jan  4 15:22:55 figo-desktop kernel: [ 1306]    81  1306      808      396
1       0             0 dbus-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 1309]    82  1309     3777      406
0       0             0 hald
Jan  4 15:22:55 figo-desktop kernel: [ 1310]     0  1310      903      130
1       0             0 hald-runner
Jan  4 15:22:55 figo-desktop kernel: [ 1339]     0  1339      919       90
1       0             0 hald-addon-inpu
Jan  4 15:22:55 figo-desktop kernel: [ 1357]     0  1357      919      184
1       0             0 hald-addon-stor
Jan  4 15:22:55 figo-desktop kernel: [ 1359]    82  1359      824      107
1       0             0 hald-addon-acpi
Jan  4 15:22:55 figo-desktop kernel: [ 1448]     0  1448      616      294
0       0             0 crond
Jan  4 15:22:55 figo-desktop kernel: [ 1477]     0  1477      720      108
0       0             0 mysqld_safe
Jan  4 15:22:55 figo-desktop kernel: [ 1484]     0  1484     3580      269
0       0             0 gdm-binary
Jan  4 15:22:55 figo-desktop kernel: [ 1497]     0  1497      440       67
1       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1498]     0  1498      440       67
0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1499]     0  1499      440       67
0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1500]     0  1500      440       67
1       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1501]     0  1501      440       67
0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1502]     0  1502      440       68
0       0             0 agetty
Jan  4 15:22:55 figo-desktop kernel: [ 1553]     0  1553     6607      619
0       0             0 NetworkManager
Jan  4 15:22:55 figo-desktop kernel: [ 1592]     0  1592     2256      330
0       0             0 cupsd
Jan  4 15:22:55 figo-desktop kernel: [ 1597]    89  1597    29903     2812
1       0             0 mysqld
Jan  4 15:22:55 figo-desktop kernel: [ 1598]     0  1598     1652      147
1     -17         -1000 sshd
Jan  4 15:22:55 figo-desktop kernel: [ 1612]     0  1612     6263      508
1       0             0 polkitd
Jan  4 15:22:55 figo-desktop kernel: [ 1613]     0  1613     2015      123
1       0             0 vmware-usbarbit
Jan  4 15:22:55 figo-desktop kernel: [ 1617]     0  1617     2887     1603
0       0             0 cntlm
Jan  4 15:22:55 figo-desktop kernel: [ 1620]     0  1620     4398      366
0       0             0 gdm-simple-slav
Jan  4 15:22:55 figo-desktop kernel: [ 1636]     0  1636    37298    12186
0       0             0 Xorg
Jan  4 15:22:55 figo-desktop kernel: [ 1638]     0  1638     1248       88
0       0             0 wpa_supplicant
Jan  4 15:22:55 figo-desktop kernel: [ 1720]     0  1720     4789     1555
1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [ 1722]     0  1722      488       93
0       0             0 dhcpcd
Jan  4 15:22:55 figo-desktop kernel: [ 1732]     0  1732      519       62
1       0             0 vmnet-bridge
Jan  4 15:22:55 figo-desktop kernel: [ 1750]     0  1750     4922      304
1       0             0 smbd
Jan  4 15:22:55 figo-desktop kernel: [ 1764]     0  1764      655       39
1       0             0 vmnet-dhcpd
Jan  4 15:22:55 figo-desktop kernel: [ 1772]     0  1772      513       15
0       0             0 vmnet-netifup
Jan  4 15:22:55 figo-desktop kernel: [ 1774]     0  1774      655       39
0       0             0 vmnet-dhcpd
Jan  4 15:22:55 figo-desktop kernel: [ 1776]     0  1776     4922      225
0       0             0 smbd
Jan  4 15:22:55 figo-desktop kernel: [ 1778]     0  1778      634       44
0       0             0 vmnet-natd
Jan  4 15:22:55 figo-desktop kernel: [ 1780]     0  1780      513       14
1       0             0 vmnet-netifup
Jan  4 15:22:55 figo-desktop kernel: [ 1796]     0  1796     6677      329
0       0             0 console-kit-dae
Jan  4 15:22:55 figo-desktop kernel: [ 1899]   120  1899     6587      598
0       0             0 polkit-gnome-au
Jan  4 15:22:55 figo-desktop kernel: [ 1903]     0  1903     3905      245
0       0             0 gdm-session-wor
Jan  4 15:22:55 figo-desktop kernel: [ 1906]     0  1906     3677      314
1       0             0 upowerd
Jan  4 15:22:55 figo-desktop kernel: [ 1974]  1000  1974    10963     1248
0       0             0 gnome-keyring-d
Jan  4 15:22:55 figo-desktop kernel: [ 1993]  1000  1993     9253      776
0       0             0 gnome-session
Jan  4 15:22:55 figo-desktop kernel: [ 2012]  1000  2012      796      103
0       0             0 dbus-launch
Jan  4 15:22:55 figo-desktop kernel: [ 2013]  1000  2013     5854     4985
0       0             0 dbus-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 2015]  1000  2015      887       54
0       0             0 ssh-agent
Jan  4 15:22:55 figo-desktop kernel: [ 2022]  1000  2022    10904     4789
0       0             0 fcitx
Jan  4 15:22:55 figo-desktop kernel: [ 2032]  1000  2032    41764     2007
0       0             0 gnome-settings-
Jan  4 15:22:55 figo-desktop kernel: [ 2036]  1000  2036     2367      416
0       0             0 gvfsd
Jan  4 15:22:55 figo-desktop kernel: [ 2039]  1000  2039    85188    29636
1       0             0 metacity
Jan  4 15:22:55 figo-desktop kernel: [ 2049]  1000  2049    14162      280
1       0             0 gvfs-fuse-daemo
Jan  4 15:22:55 figo-desktop kernel: [ 2053]  1000  2053    76657     3620
0       0             0 gnome-panel
Jan  4 15:22:55 figo-desktop kernel: [ 2056]  1000  2056    10978      563
1       0             0 gvfs-gdu-volume
Jan  4 15:22:55 figo-desktop kernel: [ 2058]     0  2058     5767      503
0       0             0 udisks-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 2059]     0  2059     1291       72
0       0             0 udisks-daemon
Jan  4 15:22:55 figo-desktop kernel: [ 2069]  1000  2069   168292    50943
0       0             0 nautilus
Jan  4 15:22:55 figo-desktop kernel: [ 2071]  1000  2071    12907      223
0       0             0 bonobo-activati
Jan  4 15:22:55 figo-desktop kernel: [ 2081]  1000  2081     1633      136
0       0             0 sh
Jan  4 15:22:55 figo-desktop kernel: [ 2082]  1000  2082     1666      136
1       0             0 thunderbird
Jan  4 15:22:55 figo-desktop kernel: [ 2084]  1000  2084    46718     3501
1       0             0 wnck-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2086]  1000  2086    42862     1487
0       0             0 polkit-gnome-au
Jan  4 15:22:55 figo-desktop kernel: [ 2087]  1000  2087   285933     1584
0       0             0 nm-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2104]  1000  2104     5056      715
0       0             0 gdu-notificatio
Jan  4 15:22:55 figo-desktop kernel: [ 2107]  1000  2107     1666      142
1       0             0 run-mozilla.sh
Jan  4 15:22:55 figo-desktop kernel: [ 2108]  1000  2108    39395      973
0       0             0 gnome-power-man
Jan  4 15:22:55 figo-desktop kernel: [ 2109]  1000  2109     7886      709
0       0             0 vino-server
Jan  4 15:22:55 figo-desktop kernel: [ 2110]  1000  2110    10764      791
1       0             0 evolution-alarm
Jan  4 15:22:55 figo-desktop kernel: [ 2114]  1000  2114   167865    29673
1       0             0 thunderbird-bin
Jan  4 15:22:55 figo-desktop kernel: [ 2121]  1000  2121    42098     1965
0       0             0 notify-osd
Jan  4 15:22:55 figo-desktop kernel: [ 2125]  1000  2125    42488     1203
1       0             0 cpufreq-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2126]  1000  2126    41394     1148
1       0             0 multiload-apple
Jan  4 15:22:55 figo-desktop kernel: [ 2129]  1000  2129    64405     1827
0       0             0 mixer_applet2
Jan  4 15:22:55 figo-desktop kernel: [ 2131]  1000  2131    75346     2489
0       0             0 clock-applet
Jan  4 15:22:55 figo-desktop kernel: [ 2132]  1000  2132    41163      930
1       0             0 notification-ar
Jan  4 15:22:55 figo-desktop kernel: [ 2149]  1000  2149    15325      697
1       0             0 e-calendar-fact
Jan  4 15:22:55 figo-desktop kernel: [ 2153]  1000  2153     7497     1008
0       0             0 gnome-screensav
Jan  4 15:22:55 figo-desktop kernel: [ 2155]  1000  2155     3848      202
1       0             0 pxgconf
Jan  4 15:22:55 figo-desktop kernel: [ 2163]  1000  2163     1781      342
0       0             0 mission-control
Jan  4 15:22:55 figo-desktop kernel: [ 2173]  1000  2173     4486      428
0       0             0 gvfsd-trash
Jan  4 15:22:55 figo-desktop kernel: [ 2186]     0  2186     3543      192
1       0             0 system-tools-ba
Jan  4 15:22:55 figo-desktop kernel: [ 2210]  1000  2210     2202      238
0       0             0 gvfsd-burn
Jan  4 15:22:55 figo-desktop kernel: [ 2245]  1000  2245     3895     1730
0       0             0 gvfsd-metadata
Jan  4 15:22:55 figo-desktop kernel: [ 2274]  1000  2274    22823      424
0       0             0 conky
Jan  4 15:22:55 figo-desktop kernel: [ 2281]     0  2281     3295     2278
0       0             0 SystemToolsBack
Jan  4 15:22:55 figo-desktop kernel: [ 2663]  1000  2663    68807     3042
1       0             0 gnome-terminal
Jan  4 15:22:55 figo-desktop kernel: [ 2683]  1000  2683      451       76
0       0             0 gnome-pty-helpe
Jan  4 15:22:55 figo-desktop kernel: [ 2685]  1000  2685     2072      570
0       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [ 2885]     0  2885     1489      119
0       0             0 sudo
Jan  4 15:22:55 figo-desktop kernel: [ 2886]     0  2886     6273      355
1       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [ 2887]  1000  2887      472       84
0       0             0 ping
Jan  4 15:22:55 figo-desktop kernel: [ 2892]  1000  2892      472       83
1       0             0 ping
Jan  4 15:22:55 figo-desktop kernel: [ 2894]  1000  2894    76113     5890
0       0             0 vmware
Jan  4 15:22:55 figo-desktop kernel: [ 2919]  1000  2919    51497     3315
1       0             0 vmware-tray
Jan  4 15:22:55 figo-desktop kernel: [ 2954]  1000  2954    48676     1589
0       0             0 vmware-unity-he
Jan  4 15:22:55 figo-desktop kernel: [ 2988]  1000  2988   190471    42400
0       0             0 vmware-vmx
Jan  4 15:22:55 figo-desktop kernel: [ 3207]  1000  3207     4377      362
1       0             0 gvfsd-computer
Jan  4 15:22:55 figo-desktop kernel: [ 3211]  1000  3211     9920      509
0       0             0 gvfsd-smb-brows
Jan  4 15:22:55 figo-desktop kernel: [ 3217]  1000  3217     9876      569
0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [15186]  1000 15186     2069      558
1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [17451]  1000 17451     5679      503
0       0             0 dconf-service
Jan  4 15:22:55 figo-desktop kernel: [19085]  1000 19085     1576      149
0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [19261]  1000 19261     1682      967
0       0             0 wineserver
Jan  4 15:22:55 figo-desktop kernel: [19266]  1000 19266   399085      212
0       0             0 services.exe
Jan  4 15:22:55 figo-desktop kernel: [19269]  1000 19269   399117      158
1       0             0 winedevice.exe
Jan  4 15:22:55 figo-desktop kernel: [19342]  1000 19342   404518      643
0       0             0 explorer.exe
Jan  4 15:22:55 figo-desktop kernel: [19344]  1000 19344   550020    11028
1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [  360]  1000   360     2069      541
1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [ 9821]  1000  9821   166228     2915
0       0             0 stardict
Jan  4 15:22:55 figo-desktop kernel: [14614]  1000 14614     2040      523
1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [17002]  1000 17002     2069      541
0       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [18612]     0 18612     1536      125
1       0             0 sudo
Jan  4 15:22:55 figo-desktop kernel: [18613]     0 18613     1988      608
1       0             0 minicom
Jan  4 15:22:55 figo-desktop kernel: [21183]  1000 21183     2041      517
1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [21194]  1000 21194     1611      125
0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [22451]  1000 22451     2069      578
1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [23428]  1000 23428     6475      554
1       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [23484]  1000 23484     6501      594
1       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [23549]  1000 23549     6501      594
0       0             0 vim
Jan  4 15:22:55 figo-desktop kernel: [23642]  1000 23642     9865      594
0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [26358]  1000 26358   407339     5019
1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [29711]  1000 29711     9943      617
0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [26156]  1000 26156    61269     9179
0       0             0 skype
Jan  4 15:22:55 figo-desktop kernel: [32490]  1000 32490     2647      684
0       0             0 gconfd-2
Jan  4 15:22:55 figo-desktop kernel: [10622]  1000 10622     2072      725
1       0             0 bash
Jan  4 15:22:55 figo-desktop kernel: [10634]  1000 10634     1576      156
0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [15410]  1000 15410    76559    12161
0       0             0 evince
Jan  4 15:22:55 figo-desktop kernel: [15415]  1000 15415     5490      217
1       0             0 evinced
Jan  4 15:22:55 figo-desktop kernel: [16754]  1000 16754     9899      485
0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [16772]  1000 16772     9900      500
0       0             0 gvfsd-smb
Jan  4 15:22:55 figo-desktop kernel: [25390]  1000 25390   407306     2164
1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [ 2127]  1000  2127     1609      125
0       0             0 ssh
Jan  4 15:22:55 figo-desktop kernel: [10661]    33 10661     4775     1510
1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10662]    33 10662     4823     1569
0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10663]    33 10663     4823     1570
0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10664]    33 10664     4823     1569
0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10665]    33 10665     4823     1569
0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [10666]    33 10666     4823     1569
1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32159]  1000 32159   166096    39479
0       0             0 firefox
Jan  4 15:22:55 figo-desktop kernel: [32228]    33 32228     4823     1512
0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32233]    33 32233     4857     1596
1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32234]    33 32234     4857     1597
1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32241]    33 32241     4789     1536
1       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32246]    33 32246     4789     1536
0       0             0 httpd
Jan  4 15:22:55 figo-desktop kernel: [32268]  1000 32268    27543     4279
1       0             0 plugin-containe
Jan  4 15:22:55 figo-desktop kernel: [32320]  1000 32320    16230     1445
1       0             0 GoogleTalkPlugi
Jan  4 15:22:55 figo-desktop kernel: [  970]  1000   970   407197     2636
1       0             0 insight3.exe
Jan  4 15:22:55 figo-desktop kernel: [ 1240]  1000  1240      601      116
1       0             0 top
Jan  4 15:22:55 figo-desktop kernel: [ 2038]  1000  2038   407786     2842

0 0 0 insight3.exe

Quoted 8 lines
Quoted 8 lines
Jan  4 15:22:55 figo-desktop kernel: [12415]     0 12415      543      232
1     -17         -1000 udevd
Jan  4 15:22:55 figo-desktop kernel: [12416]     0 12416      580      195
1     -17         -1000 udevd
Jan  4 15:22:55 figo-desktop kernel: [13904]     0 13904     1488      219
1       0             0 sudo
Jan  4 15:22:55 figo-desktop kernel: [13906]     0 13906     1386      131

0 0 0 swapoff

We don't know what task was killed here, if any, because it's not showing the "Killed process ... total-vm:...kB, anon-rss:...kB, file--rss:...kB" line that indicates anything was killed. In fact, your entire log doesn't show that. minicom simply invoking the oom killer (and Xorg later) doesn't indicate a problem.

Please post a complete log that shows the tasklist dump and which task was selected from that state.