Re: OpenSM 3.3.16 at 100% CPU load, "console off"

[Hal Rosenstock <hal-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>]

Hi Sebastian,

On 10/9/2013 9:28 AM, Hal Rosenstock wrote:
> Hi Sebastian,
> 
> On 10/9/2013 7:10 AM, Sebastian Riemer wrote:
>> Hi Hal,
>>
>> we've encountered an issue with OpenSM 3.3.16 and the config option
>> "console off".
>> OpenSM processes are at 100% CPU load.
>>
>> >From strace:
>> poll([{fd=0, events=POLLIN}], 1, 1000)  = 1 ([{fd=0, revents=POLLIN}])
>> read(0, "", 4096)                       = 0
>> poll([{fd=0, events=POLLIN}], 1, 1000)  = 1 ([{fd=0, revents=POLLIN}])
>> read(0, "", 4096)                       = 0
>> poll([{fd=0, events=POLLIN}], 1, 1000)  = 1 ([{fd=0, revents=POLLIN}])
>> read(0, "", 4096)                       = 0
> 
> So this doesn't block for 1 second and that's why the CPU is 100% ?
> 
>> As far as I've seen in the code, the function osm_console() from
>> opensm/osm_console.c is the only function which uses poll().
> 
> osm_vendor_ibumad has a receiver thread polling umad under the covers of
> umad_recv but I think that uses infinite rather than 1 second.
> 
>> Is this issue already known or perhaps already fixed?
> 
> This area of the console code has not changed in quite a while.
> Any idea if this works with older versions of OpenSM ?
> 
> This is first I've heard of this issue.

Do you recall the sequence to get to this ?

Was console option changed to off and then OpenSM SIGHUP'd ? Something
else ?

Is this reproducible ?

-- Hal

> -- Hal
> 
>> Thanks,
>> Sebastian
>>
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html