Hey guys and gals,
Yesterday I had one of my scientists kill one of my servers when his program ran amok and gobbled up all the memory, or forked too many processes, or I'm just not exactly sure what to be honest.
Is there something I can run manually in cron to look for rampant programs and kill them? I know that may be hard to discern but I could also include a list if "known good" programs not to kill, as well as a list of "known suspect" user IDs
Anyone ever done this? Searching the list on "OOM" does not bring up much.
thanks -Alan
* Alan McKay alan.mckay@gmail.com [07/25/2012 09:36]:
Yesterday I had one of my scientists kill one of my servers when his program ran amok and gobbled up all the memory, or forked too many processes, or I'm just not exactly sure what to be honest.
Is there something I can run manually in cron to look for rampant programs and kill them? I know that may be hard to discern but I could also include a list if "known good" programs not to kill, as well as a list of "known suspect" user IDs
Anyone ever done this? Searching the list on "OOM" does not bring up much.
I would look into disabling memory overcommit.
On our compute cluster nodes we use the following sysctls: # disable overcommit (allocation_limit=swap + overcommit_ratio/100 * phys_mem) vm.overcommit_ratio=70 vm.overcommit_memory=2
This will prevent programs to allocate more than allocation_limit of memory. In this way the program that tries to allocate the memory that would put the memory usage over the limit will be prevented to do so. The malloc will return NULL.
For the forking too many processes you can look into man limits.conf where you can limit the maximum number of processes per user.
Daniel.
Alan McKay wrote:
Hey guys and gals,
Yesterday I had one of my scientists kill one of my servers when his program ran amok and gobbled up all the memory, or forked too many processes, or I'm just not exactly sure what to be honest.
Is there something I can run manually in cron to look for rampant programs and kill them? I know that may be hard to discern but I could also include a list if "known good" programs not to kill, as well as a list of "known suspect" user IDs
Anyone ever done this? Searching the list on "OOM" does not bring up much.
Yeah, we've had that a few times, even on 64 core systems with a ridiculous amount of memory. One thing we did was to tell them to limit the number of cores they were using in the parallel processing threads. There is some kind of limit you can set up - I forget exactly what it is, but I'm not sure it will limit memory usage.
Someone suggested yesterday, in another context, giving 'em a VM of their own. Doing that, you can limit how many cores and how much memory they have, and then if they crash, it's more their problem than yours.
Or have them buy another server and make it a cluster. We use the torque package.
mark
Interesting stuff - thanks again guys. Looks like I can get what I need right here ...
From: Alan McKay alan.mckay@gmail.com
Yesterday I had one of my scientists kill one of my servers when his program ran amok and gobbled up all the memory, or forked too many processes, or I'm just not exactly sure what to be honest.
Is there something I can run manually in cron to look for rampant programs and kill them? I know that may be hard to discern but I could also include a list if "known good" programs not to kill, as well as a list of "known suspect" user IDs
What about setting limits...? /etc/security/limits.conf
JD
On 7/25/2012 7:36 AM, Alan McKay wrote:
Is there something I can run manually in cron to look for rampant programs and kill them?
You appear to be under the impression that you have a technical problem.
What you actually have is a people problem.
Go now, and kneel at the feet of the Bastard Operator From Hell (http://bofh.ntk.net/) to learn how to deal with such matters.
On Wed, Jul 25, 2012 at 1:24 PM, Warren Young warren@etr-usa.com wrote:
Go now, and kneel at the feet of the Bastard Operator From Hell (http://bofh.ntk.net/) to learn how to deal with such matters.
Well I was looking for my LART ... seem to have misplaced it over the years :-)
-
Alan McKay -
Daniel De Marco -
John Doe -
m.roth＠5-cent.us -
Warren Young