[Einstein Toolkit] #1271: hwloc is segfaulting

List overview All Threads
Download

newer

older

[Einstein Toolkit] #1341: Add a...

[Einstein Toolkit] #1339: Memory...

Einstein Toolkit

27 Feb 2013 27 Feb '13

4:20 p.m.

#1271: hwloc is segfaulting ---------------------+------------------------------------------------------ Reporter: sbrandt | Owner: Type: defect | Status: new Priority: major | Milestone: ET_2013_05 Component: Other | Version: development version Keywords: | ---------------------+------------------------------------------------------ My efforts to run the ET testsuite fail when system_topology.cc attempts to bind threads to CPUs because hwloc_get_obj_by_depth(topology, pu_depth, pu_num) returns NULL. In the attached patch I check for a null return value and print a warning, then skip setting the affinity.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Show replies by date

Einstein Toolkit

27 Feb 27 Feb

5:31 p.m.

#1271: hwloc is segfaulting ----------------------+----------------------------------------------------- Reporter: sbrandt | Owner: Type: defect | Status: new Priority: major | Milestone: ET_2013_05 Component: Other | Version: development version Resolution: | Keywords: ----------------------+-----------------------------------------------------

Comment (by eschnett):

What system is this? What version of hwloc is this?

Is a NULL return value documented as error return, or did we find an error in hwloc here? (I'm asking because the hwloc developers are very keen on receiving bug reports.)

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:1 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

28 Feb 28 Feb

10:46 a.m.

Comment (by sbrandt):

This is my IBM w520 laptop. I used the built-in Cactus hwloc. It is a documented error value that indicates that either 0, or 2+ objects of the requested type exist. I confess I didn't delve into which case it was.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:2 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

11:41 a.m.

Comment (by eschnett):

I don't see NULL as documented error value... I find "Returns the topology object at logical index idx from depth depth." as documentation for hwloc_get_obj_by_depth.

What are the values of "pu_depth" and "pu_num"? Can you post the output of "lstopo" for your system? I assume you are running this under Linux? Is this a virtual machine?

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:3 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

11:45 a.m.

Comment (by knarf):

http://linux.die.net/man/3/hwloc_get_obj_by_depth says: "If no object for that type exists, NULL is returned. If there are several levels with objects of that type, NULL is returned and ther caller may fallback to hwloc_get_obj_by_depth(). "

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:4 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

11:47 a.m.

Comment (by knarf):

Replying to [comment:4 knarf]:

...

http://linux.die.net/man/3/hwloc_get_obj_by_depth says: "and ther caller

may fallback to hwloc_get_obj_by_depth(). "

Which is odd - because that is the man page of that very same function.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:5 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

11:49 a.m.

Comment (by sbrandt):

When I said documented error value, I meant the condition that Frank just quoted.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:6 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

1:02 p.m.

Comment (by eschnett):

This page documents two functions, as many man pages do. The error code is for the second function only.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:7 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

4 Mar 4 Mar

8:44 p.m.

Comment (by eschnett):

I just looked at this error again. This error occurs when hwloc_get_obj_by_depth is called for the second time. I assume that one of its arguments is wrong. Can you output its arguments pu_depth and pu_num? If pu_num<0 or pu_num>=8, can you also output core_num, smt_multiplier, and pu_offset? thread_offset, thread_num_in_proc, and thread_num would also be interesting.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:8 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

8 Apr 8 Apr

10:43 a.m.

Comment (by sbrandt):

So I modified my code to look for these conditions, print a more useful error message, then abort. Since doing that, the error has not recurred. Not sure why. Maybe we can close the ticket.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:9 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

29 Apr 29 Apr

10:12 a.m.

#1271: hwloc is segfaulting -------------------------+-------------------------------------------------- Reporter: sbrandt | Owner: Type: defect | Status: closed Priority: major | Milestone: ET_2013_05 Component: Other | Version: development version Resolution: worksforme | Keywords: -------------------------+-------------------------------------------------- Changes (by sbrandt):

* status: new => closed * resolution: => worksforme

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/1271#comment:10 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

4911

Age (days ago)

4972

Last active (days ago)

trac@lists.einsteintoolkit.org

10 comments

1 participants

tags (0)

participants (1)

Einstein Toolkit