Re: [bgl-discuss] Can BGL jobs wind up working with corrupted memory?

[Susan Coghlan <smc@xxxxxxxxxxx>]

Steve,

I forwarded on your complaint about it to IBM.  I got back two responses:

"There is a -qxflag=stacksize flag that will generate information in the
.lst file giving the size in bytes for each procedure."


With the XL compilers there is an option, -qdebug=function_trace, that
instruments the entry and exit of each routine with calls to routines that
you can provide.  So upon function entry, we check sbrk(0) to get the top
of the heap, and we check the address of a local variable to get the
current stack pointer; and you do the same thing on function exit, for
absolutely every function.  What I have at the moment will print an error
message and report the routine names, source file and line number, if the
stack and heap overlap.  Depending on what one thinks is going on, you may
want to do different things in these entry points.  For example, they
could be used to identify a memory leak.  It is possible that a memory
leak is responsible for the overlap condition, in which case it would be
more important to find the leak than to name the routine where the first
overlap occurred.

I don't know if either of these will be truly helpful or not.

Susan.

On Thu, 19 May 2005, Steven Pieper wrote:

> Does this help me with my Fortran application?
>
> Even if it does, is IBM being complained to?  I find it completely unacceptable
> if the user has to monitor that the operating system is mismanaging memory.
>
> Thanks
> Steve
>
> >>> Hi Pete,
> >>> > Last week the TAU folks visited, and we discussed a new memory tool
> >>> >which could give you a "headroom" measurement over the life of your
> >>> >program, essentially looking at the difference between the stack and
> >>> >heap and how much you have left.  You could then see which routines
> >>> >put you closest to overflow.
> >>>
> >>> >Such a tool is in the works....
> >>> >
> >>> >-Pete
> >>> 	We're released TAU v2.14.4 with support for memory headroom evaluation options.
> >>> 	I've enclosed a description of the various options below.
> >>> 	http://www.cs.uoregon.edu/research/paracomp/tau
> >>> 	Thanks,
> >>> 	- Sameer
> >>>
>
> - --------------------------------------------------------------------
> To add or remove yourself from this mailing list, use the 'notifyme'
> command on any BGL machine. To remove: notifyme -n, to add: notifyme -y.
>
>

- --------------------------------------------------------------------
To add or remove yourself from this mailing list, use the 'notifyme'
command on any BGL machine. To remove: notifyme -n, to add: notifyme -y.