Charm++ parallel programming system

[Gengbin Zheng <zhenggb AT gmail.com>]

Hmm, this is interesting. Looks like some thread issues.
Unfortunately we don't have access to a system with gcc 4.5.3.
Any way we can have an account to test on the system?

One thing to try is to link megatest with "-thread context" and see if it 
works.

Gengbin

On Sun, Oct 30, 2011 at 10:24 PM, Thomas Albers 
<talbers AT binghamton.edu>
 wrote:
> Hello!
>
> When charm++ is build with ibverbs and with the --with-production
> option, like so
> ta@michelin
>  ~/NAMD_2.8_Source/charm-6.3.2 $ ./build charm++
> net-linux-x86_64 ibverbs --with-production
> the megatest suite fails.  Please see output below.
>
> This is on a recent Gentoo Linux system with gcc.
> ta@michelin
>  ~ $ uname -a
> Linux michelin 2.6.39-gentoo-r3 #7 SMP Mon Oct 17 19:48:44 EDT 2011
> x86_64 AMD Phenom(tm) II X6 1090T Processor AuthenticAMD GNU/Linux
> ta@michelin
>  ~ $ gcc --version
> gcc (Gentoo 4.5.3-r1 p1.0, pie-0.4.5) 4.5.3
>
> When charm++ is built without --with-production the test suite
> completes uneventfully. The net-linux-x86_64 (without ibverbs) version
> works fine as well, both with and without --with-production.
>
> Is this more likely to be a compiler bug, or a bug within Charm?
> Please let me know if any further information is needed.
>
> Regards,
> Thomas
>
>
>
> ta@michelin
>  
> ~/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest
> $ ./charmrun +p4 pgm
> Charmrun> IBVERBS version of charmrun
> Charmrun> started all node programs in 1.251 seconds.
> Charm++> scheduler running in netpoll mode.
> Charm++> Running on 4 unique compute nodes (6-way SMP).
> Charm++> cpu topology info is gathered in 0.001 seconds.
> Megatest is running on 4 nodes 4 processors.
> test 0: initiated [completion_test (phil)]
> Starting test
> Created detector, starting first detection
> Started first test
> Finished second test
> Started third test
> test 0: completed (0.00 sec)
> test 1: initiated [inlineem (phil)]
> test 1: completed (0.00 sec)
> test 2: initiated [callback (olawlor)]
> *** longjmp causes uninitialized stack frame ***:
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm
> terminated
> ======= Backtrace: =========
> /lib64/libc.so.6(__fortify_fail+0x37)[0x7f9a2b271c07]
> /lib64/libc.so.6(+0xeab99)[0x7f9a2b271b99]
> /lib64/libc.so.6(__longjmp_chk+0x33)[0x7f9a2b271b03]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(setJcontext+0x31)[0x51567a]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(swapJcontext+0x20)[0x51572a]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(CthResume+0xc9)[0x515929]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(CthResumeNormalThread+0x1f)[0x571155]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(CmiHandleMessage+0x21)[0x5722f8]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(CsdScheduleForever+0x4e)[0x57245c]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(CsdScheduler+0xd)[0x57260a]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(ConverseInit+0x1153)[0x570eb7]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm(main+0x2d)[0x524da1]
> /lib64/libc.so.6(__libc_start_main+0xfd)[0x7f9a2b1a8e9d]
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm[0x4b2e89]
> ======= Memory map: ========
> 00400000-005f0000 r-xp 00000000 09:00 70035716
>  
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm
> 007ef000-007f0000 r--p 001ef000 09:00 70035716
>  
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm
> 007f0000-00801000 rw-p 001f0000 09:00 70035716
>  
> /home/ta/NAMD_2.8_Source/charm-6.3.2/net-linux-x86_64-ibverbs/tests/charm++/megatest/pgm
> 00801000-00820000 rw-p 00000000 00:00 0
> 01941000-01c08000 rw-p 00000000 00:00 0                                  
> [heap]
> 7f9a285a6000-7f9a285b2000 r-xp 00000000 08:03 9707825
>  /lib64/libnss_files-2.12.2.so
> 7f9a285b2000-7f9a287b1000 ---p 0000c000 08:03 9707825
>  /lib64/libnss_files-2.12.2.so
> 7f9a287b1000-7f9a287b2000 r--p 0000b000 08:03 9707825
>  /lib64/libnss_files-2.12.2.so
> 7f9a287b2000-7f9a287b3000 rw-p 0000c000 08:03 9707825
>  /lib64/libnss_files-2.12.2.so
> 7f9a287bd000-7f9a2ad61000 rw-p 00000000 00:00 0
> 7f9a2ad61000-7f9a2ad69000 r-xp 00000000 08:03 344761
>  /usr/lib64/libmthca-rdmav2.so
> 7f9a2ad69000-7f9a2af68000 ---p 00008000 08:03 344761
>  /usr/lib64/libmthca-rdmav2.so
> 7f9a2af68000-7f9a2af69000 r--p 00007000 08:03 344761
>  /usr/lib64/libmthca-rdmav2.so
> 7f9a2af69000-7f9a2af6a000 rw-p 00008000 08:03 344761
>  /usr/lib64/libmthca-rdmav2.so
> 7f9a2af6a000-7f9a2af82000 r-xp 00000000 08:03 9707538
>  /lib64/libpthread-2.12.2.so
> 7f9a2af82000-7f9a2b181000 ---p 00018000 08:03 9707538
>  /lib64/libpthread-2.12.2.so
> 7f9a2b181000-7f9a2b182000 r--p 00017000 08:03 9707538
>  /lib64/libpthread-2.12.2.so
> 7f9a2b182000-7f9a2b183000 rw-p 00018000 08:03 9707538
>  /lib64/libpthread-2.12.2.so
> 7f9a2b183000-7f9a2b187000 rw-p 00000000 00:00 0
> 7f9a2b187000-7f9a2b2e9000 r-xp 00000000 08:03 9707551
>  /lib64/libc-2.12.2.so
> 7f9a2b2e9000-7f9a2b4e8000 ---p 00162000 08:03 9707551
>  /lib64/libc-2.12.2.so
> 7f9a2b4e8000-7f9a2b4ec000 r--p 00161000 08:03 9707551
>  /lib64/libc-2.12.2.so
> 7f9a2b4ec000-7f9a2b4ed000 rw-p 00165000 08:03 9707551
>  /lib64/libc-2.12.2.so
> 7f9a2b4ed000-7f9a2b4f2000 rw-p 00000000 00:00 0
> 7f9a2b4f2000-7f9a2b507000 r-xp 00000000 08:03 9707530
>  /lib64/libgcc_s.so.1
> 7f9a2b507000-7f9a2b706000 ---p 00015000 08:03 9707530
>  /lib64/libgcc_s.so.1
> 7f9a2b706000-7f9a2b707000 r--p 00014000 08:03 9707530
>  /lib64/libgcc_s.so.1
> 7f9a2b707000-7f9a2b708000 rw-p 00015000 08:03 9707530
>  /lib64/libgcc_s.so.1
> 7f9a2b708000-7f9a2b789000 r-xp 00000000 08:03 9707527
>  /lib64/libm-2.12.2.so
> 7f9a2b789000-7f9a2b988000 ---p 00081000 08:03 9707527
>  /lib64/libm-2.12.2.so
> 7f9a2b988000-7f9a2b989000 r--p 00080000 08:03 9707527
>  /lib64/libm-2.12.2.so
> 7f9a2b989000-7f9a2b98a000 rw-p 00081000 08:03 9707527
>  /lib64/libm-2.12.2.so
> 7f9a2b98a000-7f9a2ba76000 r-xp 00000000 08:03 15385417
>  /usr/lib64/gcc/x86_64-pc-linux-gnu/4.5.3/libstdc++.so.6.0.14
> 7f9a2ba76000-7f9a2bc75000 ---p 000ec000 08:03 15385417
>  /usr/lib64/gcc/x86_64-pc-linux-gnu/4.5.3/libstdc++.so.6.0.14
> 7f9a2bc75000-7f9a2bc7d000 r--p 000eb000 08:03 15385417
>  /usr/lib64/gcc/x86_64-pc-linux-gnu/4.5.3/libstdc++.so.6.0.14
> 7f9a2bc7d000-7f9a2bc7f000 rw-p 000f3000 08:03 15385417
>  /usr/lib64/gcc/x86_64-pc-linux-gnu/4.5.3/libstdc++.so.6.0.14
> 7f9a2bc7f000-7f9a2bc94000 rw-p 00000000 00:00 0
> 7f9a2bc94000-7f9a2bc96000 r-xp 00000000 08:03 9707829
>  /lib64/libdl-2.12.2.so
> 7f9a2bc96000-7f9a2be96000 ---p 00002000 08:03 9707829
>  /lib64/libdl-2.12.2.so
> 7f9a2be96000-7f9a2be97000 r--p 00002000 08:03 9707829
>  /lib64/libdl-2.12.2.so
> 7f9a2be97000-7f9a2be98000 rw-p 00003000 08:03 9707829
>  /lib64/libdl-2.12.2.so
> 7f9a2be98000-7f9a2bea6000 r-xp 00000000 08:03 344819
>  /usr/lib64/libibverbs.so.1.0.0
> 7f9a2bea6000-7f9a2c0a5000 ---p 0000e000 08:03 344819
>  /usr/lib64/libibverbs.so.1.0.0
> 7f9a2c0a5000-7f9a2c0a6000 r--p 0000d000 08:03 344819
>  /usr/lib64/libibverbs.so.1.0.0
> 7f9a2c0a6000-7f9a2c0a7000 rw-p 0000e000 08:03 344819
>  /usr/lib64/libibverbs.so.1.0.0
> 7f9a2c0a7000-7f9a2c0c5000 r-xp 00000000 08:03 9707833
>  /lib64/ld-2.12.2.so
> 7f9a2c0ca000-7f9a2c2b9000 rw-p 00000000 00:00 0
> 7f9a2c2c2000-7f9a2c2c3000 -w-s d3803000 00:10 4351
>  /dev/infiniband/uverbs0
> 7f9a2c2c3000-7f9a2c2c4000 rw-p 00000000 00:00 0
> 7f9a2c2c4000-7f9a2c2c5000 r--p 0001d000 08:03 9707833
>  /lib64/ld-2.12.2.so
> 7f9a2c2c5000-7f9a2c2c6000 rw-p 0001e000 08:03 9707833
>  /lib64/ld-2.12.2.so
> 7f9a2c2c6000-7f9a2c2c7000 rw-p 00000000 00:00 0
> 7fffa8110000-7fffa8131000 rw-p 00000000 00:00 0                          
> [stack]
> 7fffa81ff000-7fffa8200000 r-xp 00000000 00:00 0                          
> [vdso]
> ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0
>  [vsyscall]
> ------------- Processor 0 Exiting: Caught Signal ------------
> Signal: unknown signal
> [0] Stack Traceback:
>  [0:0] +0x35960  [0x7f9a2b1bc960]
>  [0:1] gsignal+0x35  [0x7f9a2b1bc8e5]
>  [0:2] abort+0x186  [0x7f9a2b1bdd66]
>  [0:3] +0x70483  [0x7f9a2b1f7483]
>  [0:4] __fortify_fail+0x37  [0x7f9a2b271c07]
>  [0:5] +0xeab99  [0x7f9a2b271b99]
>  [0:6] __longjmp_chk+0x33  [0x7f9a2b271b03]
>  [0:7] setJcontext+0x31  [0x51567a]
>  [0:8] swapJcontext+0x20  [0x51572a]
>  [9] Charm++ Runtime: Resumed thread (CthResume+0xc9  [0x515929])
> Fatal error on PE 0> unknown signal
> _______________________________________________
> charm mailing list
> charm AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/charm
> _______________________________________________
> ppl mailing list
> ppl AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/ppl
>