oom-kill: direct hardware access processes should get bonus
Subsystems (2)
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
@@ -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 ;/*
David Rientjes
reviewerQuoted 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_adjto 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
Signed-off-by Figo.zhang <[email protected]>---
mm/oom_kill.c| 8 +++++---1 files changed, 5 insertions(+), 3 deletions(-)mm/oom_kill.c +0
-0
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.
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_RAWIOhad 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>
David Rientjes
reviewerQuoted 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_RAWIOhad 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_RAWIOwill 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>
PATCH v2 1/1 oom-kill: CAP_SYS_RESOURCE should get bonus
In reply to Figo.zhangCAP_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
@@ -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>
David Rientjes
reviewerRe: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus
Quoted 2 lines · Figo.zhang
CAP_SYS_RESOURCEalso had better get 3% bonus for protection.
Would you like to elaborate as to why?
Quoted 10 lines
Signed-off-by Figo.zhang <[email protected]>---
mm/oom_kill.c| 3 ++-1 files changed, 2 insertions(+), 1 deletions(-)mm/oom_kill.c +0
-0
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]
Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus
Quoted 13 lines · Figo.zhang
Quoted 3 lines
CAP_SYS_RESOURCEalso 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
Re:[PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus
Quoted 4 lines · Figo.zhang
Quoted 4 lines
Quoted 2 lines
CAP_SYS_RESOURCEalso 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_RESOURCEcapibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process withCAP_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.
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_RESOURCEalso 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_RESOURCEcapibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process withCAP_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_RESOURCEthreads have the ability to lower their ownoom_score_adjvalues, 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>
David Rientjes
reviewerRe: 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_RESOURCEto protection. seefs/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 smalloom_score_adj, if newoom_score_adjis 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>
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_RESOURCEto protection. seefs/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 smalloom_score_adj, if newoom_score_adjis small than now and it is not limited resource, it will not adjust, that seems not right?Tasks without
CAP_SYS_RESOURCEcannot lower their ownoom_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_adjso the oom killer prefers to kill it first.I think you may be confused:
CAP_SYS_RESOURCEoverride resource limits.
David Rientjes
reviewerRe: 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_adjwill 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 byoom_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.html2280 ? 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>
Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus
In reply to David RientjesQuoted 15 lines · Figo.zhang
Quoted 5 lines
Quoted 5 lines
Quoted 3 lines
CAP_SYS_RESOURCEalso 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_RESOURCEcapibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process withCAP_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_RESOURCEthreads have the ability to lower their ownoom_score_adjvalues, 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>
Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus
Quoted 10 lines
Quoted 9 lines
Quoted 4 lines
process with
CAP_SYS_RESOURCEcapibility which have system resource limits, like journaling resource on ext3/4 filesystem, RTC clock. so it also the same treatment as process withCAP_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_RESOURCEcondition 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>
David Rientjes
reviewerRe: [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>
David Rientjes
reviewerRe: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus
Quoted 5 lines · David Rientjes
I didn't check earlier, but
CAP_SYS_RESOURCEhasn'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 overoom_score_adjto 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).
Re: [PATCH v2]oom-kill: CAP_SYS_RESOURCE should get bonus
In reply to David RientjesQuoted 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_RESOURCEhasn'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 overoom_score_adjto 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?
David Rientjes
reviewerRe: [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_RESOURCEhasn'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 overoom_score_adjto 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_killeris 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.
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_adjto protect it. so i think those processes should get 3% bonus for protection.Signed-off-by Figo.zhang <[email protected]>
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
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>
PATCH v2 1/1 mm/oom-kill: direct hardware access processes should get bonus
In reply to Figo.zhangthe 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
@@ -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>
David Rientjes
reviewerRe: [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_adjto 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>
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_adjto 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_ADMINheuristic 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 likeCAP_SYS_RAWIOmakes 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>
Re: [PATCH v2]mm/oom-kill: direct hardware access processes should get bonus
In reply to David RientjesQuoted 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_adjto 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_ADMINheuristic 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 likeCAP_SYS_RAWIOmakes 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_RAWIOand 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 thatCAP_SYS_RAWIOrequires 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>
David Rientjes
reviewerRe: [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_RESOURCEmean 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_RAWIOmean 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>
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_ADMINthat 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_RESOURCEmean 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_RESOURCEthread 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_RESOURCEhave full control over theiroom_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_RAWIOmean 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_MINworks 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>
David Rientjes
reviewerRe: [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_ADMINthat 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_RAWIOmean 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_MINworks 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>
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_ADMINthat 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 likeoom_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_RAWIOmean 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_MINworks 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_RAWIOtask 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 foroom_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>
David Rientjes
reviewerRe: [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_ADMINthat 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!
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_ADMINthat 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_ADMINtasks 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>
David Rientjes
reviewerRe: [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_ADMINtasks 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>
PATCH v3 1/1 mm/oom-kill: direct hardware access processes should get bonus
In reply to Figo.zhangthe 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
@@ -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>
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
@@ -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>
David Rientjes
reviewerRe: [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_adjto 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 theoom_killerdon'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
Signed-off-by Figo.zhang <[email protected]>Reviewed-by KOSAKI Motohiro <[email protected]>
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@@ -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?
Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus
In reply to Figo.zhangQuoted 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_adjto 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 theoom_killerdon'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.
Signed-off-by Figo.zhang <[email protected]>Reviewed-by KOSAKI Motohiro <[email protected]>
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@@ -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>
David Rientjes
reviewerRe: [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_adjto 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 theoom_killerdon'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
Signed-off-by Figo.zhang <[email protected]>Reviewed-by KOSAKI Motohiro <[email protected]>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>
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>
David Rientjes
reviewerRe: [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_RESOURCEcondition 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/48998so you just test your new
oom_killeralgorithm 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.
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_adjjust like you did withoom_adj. Sinceoom_adjis 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>
David Rientjes
reviewerRe: [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_adjjust like you did withoom_adj. Sinceoom_adjis 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>
Re: [PATCH] Revert oom rewrite series
In reply to Alan Coxsorry 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_adjjust like you did withoom_adj. Sinceoom_adjis 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>
Re: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus
In reply to Figo.zhangi 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_adjto 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 theoom_killerdon'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.
Signed-off-by Figo.zhang<[email protected]>Reviewed-by KOSAKI Motohiro<[email protected]>---
mm/oom_kill.c| 9 +++++++++1 files changed, 9 insertions(+), 0 deletions(-)mm/oom_kill.c +2
-0@@ -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>
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
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_swapbut 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>
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_swapbut 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_swapis 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>
David Rientjes
reviewerRe: [PATCH v3]mm/oom-kill: direct hardware access processes should get bonus
In reply to Figo.zhangQuoted 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:80kBhigh: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? yesJan 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:3728kBlow: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? yesJan 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:1712kBhigh: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? yesJan 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 28420 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 1310 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.