I've been seeing an intermittent (once every 4 hours looping on a quick
initialization program) segv with the following stack trace.
=>[1] mca_btl_sm_add_procs(btl = 0xfd7ffdb67ef0, nprocs = 2U, procs
= 0x591560, peers = 0x591580, reachability = 0xfd7fffdff000), line
519 in "btl_sm.c"
Terry,
We use the feature defined by POSIX mmap where the area should be zero-
filled when the file length is extended. What OS you're using when you
see such problems ?
Just in case, here is a patch that set the beginning of the mmaped
region to zero, in case this is not done
IIRC, bzero is a gnu-ism. We should probably use memset instead.
On Aug 21, 2008, at 5:40 AM, George Bosilca wrote:
Terry,
We use the feature defined by POSIX mmap where the area should be
zero-filled when the file length is extended. What OS you're using
when you see such problems ?
bzero is not a gnu-ism -- it's in POSIX.1. Either bzero or memset is
correct and used throughout OMPI.
Brian
On Thu, 21 Aug 2008, Jeff Squyres wrote:
IIRC, bzero is a gnu-ism. We should probably use memset instead.
On Aug 21, 2008, at 5:40 AM, George Bosilca wrote:
Terry,
We use the
bzero() function conforms to IEEE Std 1003.1-2001 (``POSIX.1'')
memset() function conforms to ISO/IEC 9899:1990 (``ISO C90'')
Both functions are in the libc, so it's definitively difficult to see
which one is better.
george.
On Aug 21, 2008, at 3:32 PM, Jeff Squyres wrote:
IIRC, bzero
Actually, bzero() is POSIX. Here is the history section of the bzero man page
on Mac OS X 10.4:
A bzero() function appeared in 4.3BSD. Its prototype existed previously
in before it was moved to for IEEE Std 1003.1-2001
(``POSIX.1'') compliance.
Hmmm, but the Linux man page says it
George Bosilca wrote:
Terry,
We use the feature defined by POSIX mmap where the area should be
zero-filled when the file length is extended. What OS you're using
when you see such problems ?
So far I've only tested this on Solaris. We'll try out the bzero to see
if this goes away.
--td
A little google searching, and the best I can find is that
memset is part of the C89/C90 standard, while bzero isn't.
Thus memset would/should be supported even on non-POSIX
systems. Also, the opengroup claims that the bzero is LEGACY
and "This function may be withdrawn in a future version."
