[torqueusers] Memory resource limits and rlimits on Linux
chindw at wfu.edu
Fri Oct 15 07:26:25 MDT 2010
2010/10/14 "Mgr. Šimon Tóth" <SimonT at mail.muni.cz>:
>> a) I am looking at src/resmom/linux/mom_mach.c mom_over_limit().
>> The function mom_over_limit() does not check for "mem".
> Yes the logic behind this is that mom_over_limit() only checks limits
> that cannot be enforced by the underlying system.
Ah, that makes sense.
>> b) In mom_set_limits(), various rlimits are set based on
>> Torque resources:
>> line 1352 and onwards:
>> The mem and/or pmem resource causes the system limit RLIMIT_DATA
>> to be set. Linux 2.6 IGNORES RLIMIT_DATA. Try it. I used the attached
>> glom.c program, adding in appropriate setrlimit() calls. glom takes
>> one integer argument, the amount of MiB to allocate.
> Oh, if this is true, then this is definitely something the we all need
> to look into.
> I will try to allocate some time and test it myself and then report back.
> Just to make sure, if mem/pmem/vmem/pvmem limits would be enforced
> correctly (maybe not using rlimit but cgroups, or something else), would
> that solve the issue for you?
Yes, that would. I appreciate your taking time to look at it.
David Chin, Ph.D.
chindw at wfu.edu High Performance Computing Systems Analyst
Office: 336-758-2964 Wake Forest University
Mobile: 336-608-0793 Winston-Salem, NC
Email-to-txt: 3366080793 at mms.att.net
Google Talk: chindw at wfu.edu
More information about the torqueusers