<div dir="ltr"><div><div><div>Sorry, I found that this discussion email cannot add figure or attachment.<br><br></div>the backtrace information is below:<br><br></div>processes Location PC Host Rank ID Status<br>
</div>7 _start 0x00402399<br><div>`-7 _libc_start_main 0x3685c1ecdd <br></div><div> `-7 main 0x00402474 <br>
</div><div> `-7 dkm ...<br></div><div><div> |-6 image_rms 0x004029bb<br></div><div> | `-6 rms 0x00402d44<br>
</div><div> | `-6 PMPI_Win_fence 0x0040c389<br></div><div><div><div><div class="gmail_extra"> | `-6 MPIDI_Win_fence 0x004a45f4<br></div>
<div class="gmail_extra"> | `-6 MPIDI_CH3I_RMAListComplete 0x004a27d3<br></div><div class="gmail_extra"> | `-6 MPIDI_CH3I_Progress ...<br></div><div class="gmail_extra">
`-1 udp 0x004035cf<br></div><div class="gmail_extra"> `-1 PMPI_Win_fence 0x0040c389<br></div><div class="gmail_extra">
`-1 MPIDI_Win_fence 0x004a45a0<br></div><div class="gmail_extra"> `-1 MPIDI_CH3I_Progress 0x004292f5<br></div><div class="gmail_extra"> `-1 MPIDI_CH3_PktHandler_Get 0x0049f3f9<br>
</div><div class="gmail_extra"> `-1 MPIDI_CH3_iSendv 0x004aa67c<br></div><div class="gmail_extra"> `- memcpy 0x3685c89329 164.54.54.122 0 20.1-13994 Stopped <br>
</div><div class="gmail_extra"><br><br><br></div><div class="gmail_extra"><div class="gmail_quote">On Wed, Jul 10, 2013 at 11:39 AM, <span dir="ltr"><<a href="mailto:discuss-request@mpich.org" target="_blank">discuss-request@mpich.org</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Send discuss mailing list submissions to<br>
<a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
<br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
<a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
or, via email, send a message with subject or body 'help' to<br>
<a href="mailto:discuss-request@mpich.org">discuss-request@mpich.org</a><br>
<br>
You can reach the person managing the list at<br>
<a href="mailto:discuss-owner@mpich.org">discuss-owner@mpich.org</a><br>
<br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of discuss digest..."<br>
<br>
<br>
Today's Topics:<br>
<br>
1. Re: MPI_Win_fence failed (Sufeng Niu)<br>
<br>
<br>
----------------------------------------------------------------------<br>
<br>
Message: 1<br>
Date: Wed, 10 Jul 2013 11:39:39 -0500<br>
From: Sufeng Niu <<a href="mailto:sniu@hawk.iit.edu">sniu@hawk.iit.edu</a>><br>
To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
Subject: Re: [mpich-discuss] MPI_Win_fence failed<br>
Message-ID:<br>
<CAFNNHkz8pBfX33icn=+3rdXvqDfWqeu58odpd=<a href="mailto:mOXLciysHgfg@mail.gmail.com">mOXLciysHgfg@mail.gmail.com</a>><br>
Content-Type: text/plain; charset="iso-8859-1"<br>
<br>
Sorry I forget to add screen shot for backtrace. the screen shot is<br>
attached.<br>
<br>
Thanks a lot!<br>
<br>
Sufeng<br>
<br>
<br>
<br>
On Wed, Jul 10, 2013 at 11:30 AM, <<a href="mailto:discuss-request@mpich.org">discuss-request@mpich.org</a>> wrote:<br>
<br>
> Send discuss mailing list submissions to<br>
> <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
><br>
> To subscribe or unsubscribe via the World Wide Web, visit<br>
> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> or, via email, send a message with subject or body 'help' to<br>
> <a href="mailto:discuss-request@mpich.org">discuss-request@mpich.org</a><br>
><br>
> You can reach the person managing the list at<br>
> <a href="mailto:discuss-owner@mpich.org">discuss-owner@mpich.org</a><br>
><br>
> When replying, please edit your Subject line so it is more specific<br>
> than "Re: Contents of discuss digest..."<br>
><br>
><br>
> Today's Topics:<br>
><br>
> 1. Re: MPI_Win_fence failed (Sufeng Niu)<br>
><br>
><br>
> ----------------------------------------------------------------------<br>
><br>
> Message: 1<br>
> Date: Wed, 10 Jul 2013 11:30:36 -0500<br>
> From: Sufeng Niu <<a href="mailto:sniu@hawk.iit.edu">sniu@hawk.iit.edu</a>><br>
> To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> Subject: Re: [mpich-discuss] MPI_Win_fence failed<br>
> Message-ID:<br>
> <<br>
> <a href="mailto:CAFNNHkyLj8CbYMmc_w2DA9_%2Bq2Oe3kyus%2Bg6c99ShPk6ZXVkdA@mail.gmail.com">CAFNNHkyLj8CbYMmc_w2DA9_+q2Oe3kyus+g6c99ShPk6ZXVkdA@mail.gmail.com</a>><br>
> Content-Type: text/plain; charset="iso-8859-1"<br>
><br>
> Hi Jim,<br>
><br>
> Thanks a lot for your reply. the basic way for me to debugging is<br>
> barrier+printf, right now I only have an evaluation version of totalview.<br>
> the backtrace using totalview shown below. the udp is the udp collection<br>
> and create RMA window, image_rms doing MPI_Get to access the window<br>
><br>
> There is a segment violation, but I don't know why the program stopped at<br>
> MPI_Win_fence.<br>
><br>
> Thanks a lot!<br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
> On Wed, Jul 10, 2013 at 10:12 AM, <<a href="mailto:discuss-request@mpich.org">discuss-request@mpich.org</a>> wrote:<br>
><br>
> > Send discuss mailing list submissions to<br>
> > <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> ><br>
> > To subscribe or unsubscribe via the World Wide Web, visit<br>
> > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > or, via email, send a message with subject or body 'help' to<br>
> > <a href="mailto:discuss-request@mpich.org">discuss-request@mpich.org</a><br>
> ><br>
> > You can reach the person managing the list at<br>
> > <a href="mailto:discuss-owner@mpich.org">discuss-owner@mpich.org</a><br>
> ><br>
> > When replying, please edit your Subject line so it is more specific<br>
> > than "Re: Contents of discuss digest..."<br>
> ><br>
> ><br>
> > Today's Topics:<br>
> ><br>
> > 1. Re: MPICH3.0.4 make fails with "No rule to make target..."<br>
> > (Wesley Bland)<br>
> > 2. Re: Error in MPI_Finalize on a simple ring test over TCP<br>
> > (Wesley Bland)<br>
> > 3. Restrict number of cores, not threads (Bob Ilgner)<br>
> > 4. Re: Restrict number of cores, not threads (Wesley Bland)<br>
> > 5. Re: Restrict number of cores, not threads (Wesley Bland)<br>
> > 6. Re: Error in MPI_Finalize on a simple ring test over TCP<br>
> > (Thomas Ropars)<br>
> > 7. MPI_Win_fence failed (Sufeng Niu)<br>
> > 8. Re: MPI_Win_fence failed (Jim Dinan)<br>
> ><br>
> ><br>
> > ----------------------------------------------------------------------<br>
> ><br>
> > Message: 1<br>
> > Date: Wed, 10 Jul 2013 08:29:06 -0500<br>
> > From: Wesley Bland <<a href="mailto:wbland@mcs.anl.gov">wbland@mcs.anl.gov</a>><br>
> > To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > Subject: Re: [mpich-discuss] MPICH3.0.4 make fails with "No rule to<br>
> > make target..."<br>
> > Message-ID: <<a href="mailto:F48FC916-31F7-4F82-95F8-2D6A6C45264F@mcs.anl.gov">F48FC916-31F7-4F82-95F8-2D6A6C45264F@mcs.anl.gov</a>><br>
> > Content-Type: text/plain; charset="iso-8859-1"<br>
> ><br>
> > Unfortunately, due to the lack of developer resources and interest, the<br>
> > last version of MPICH which was supported on Windows was 1.4.1p. You can<br>
> > find that version on the downloads page:<br>
> ><br>
> > <a href="http://www.mpich.org/downloads/" target="_blank">http://www.mpich.org/downloads/</a><br>
> ><br>
> > Alternatively, Microsoft maintains a derivative of MPICH which should<br>
> > provide the features you need. You also find a link to that on the<br>
> > downloads page above.<br>
> ><br>
> > Wesley<br>
> ><br>
> > On Jul 10, 2013, at 1:16 AM, Don Warren <<a href="mailto:don.warren@gmail.com">don.warren@gmail.com</a>> wrote:<br>
> ><br>
> > > Hello,<br>
> > ><br>
> > > As requested in the installation guide, I'm informing this list of a<br>
> > failure to correctly make MPICH3.0.4 on a Win7 system. The specific<br>
> error<br>
> > encountered is<br>
> > > "make[2]: *** No rule to make target<br>
> > `/cygdrive/c/FLASH/mpich-3.0.4/src/mpi/romio/Makefile.am', needed by<br>
> > `/cygdrive/c/FLASH/mpich-3.0.4/src/mpi/romio/Makefile.in'. Stop."<br>
> > ><br>
> > > I have confirmed that both Makefile.am and Makefile.in exist in the<br>
> > directory listed. I'm attaching the c.txt and the m.txt files.<br>
> > ><br>
> > > Possibly of interest is that the command "make clean" fails at exactly<br>
> > the same folder, with exactly the same error message as shown in m.txt<br>
> and<br>
> > above.<br>
> > ><br>
> > > Any advice you can give would be appreciated. I'm attempting to get<br>
> > FLASH running on my computer, which seems to require MPICH.<br>
> > ><br>
> > > Regards,<br>
> > > Don Warren<br>
> > ><br>
> <config-make-outputs.zip>_______________________________________________<br>
> > > discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > > To manage subscription options or unsubscribe:<br>
> > > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> ><br>
> > -------------- next part --------------<br>
> > An HTML attachment was scrubbed...<br>
> > URL: <<br>
> ><br>
> <a href="http://lists.mpich.org/pipermail/discuss/attachments/20130710/69b497f1/attachment-0001.html" target="_blank">http://lists.mpich.org/pipermail/discuss/attachments/20130710/69b497f1/attachment-0001.html</a><br>
> > ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 2<br>
> > Date: Wed, 10 Jul 2013 08:39:47 -0500<br>
> > From: Wesley Bland <<a href="mailto:wbland@mcs.anl.gov">wbland@mcs.anl.gov</a>><br>
> > To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > Subject: Re: [mpich-discuss] Error in MPI_Finalize on a simple ring<br>
> > test over TCP<br>
> > Message-ID: <<a href="mailto:D5999106-2A75-4091-8B0F-EAFA22880862@mcs.anl.gov">D5999106-2A75-4091-8B0F-EAFA22880862@mcs.anl.gov</a>><br>
> > Content-Type: text/plain; charset=us-ascii<br>
> ><br>
> > The value of previous for rank 0 in your code is -1. MPICH is complaining<br>
> > because all of the requests to receive a message from -1 are still<br>
> pending<br>
> > when you try to finalize. You need to make sure that you are receiving<br>
> from<br>
> > valid ranks.<br>
> ><br>
> > On Jul 10, 2013, at 7:50 AM, Thomas Ropars <<a href="mailto:thomas.ropars@epfl.ch">thomas.ropars@epfl.ch</a>><br>
> wrote:<br>
> ><br>
> > > Yes sure. Here it is.<br>
> > ><br>
> > > Thomas<br>
> > ><br>
> > > On 07/10/2013 02:23 PM, Wesley Bland wrote:<br>
> > >> Can you send us the smallest chunk of code that still exhibits this<br>
> > error?<br>
> > >><br>
> > >> Wesley<br>
> > >><br>
> > >> On Jul 10, 2013, at 6:54 AM, Thomas Ropars <<a href="mailto:thomas.ropars@epfl.ch">thomas.ropars@epfl.ch</a>><br>
> > wrote:<br>
> > >><br>
> > >>> Hi all,<br>
> > >>><br>
> > >>> I get the following error when I try to run a simple application<br>
> > implementing a ring (each process sends to rank+1 and receives from<br>
> > rank-1). More precisely, the error occurs during the call to<br>
> MPI_Finalize():<br>
> > >>><br>
> > >>> Assertion failed in file<br>
> > src/mpid/ch3/channels/nemesis/netmod/tcp/socksm.c at line 363:<br>
> sc->pg_is_set<br>
> > >>> internal ABORT - process 0<br>
> > >>><br>
> > >>> Does anybody else also noticed the same error?<br>
> > >>><br>
> > >>> Here are all the details about my test:<br>
> > >>> - The error is generated with mpich-3.0.2 (but I noticed the exact<br>
> > same error with mpich-3.0.4)<br>
> > >>> - I am using IPoIB for communication between nodes (The same thing<br>
> > happens over Ethernet)<br>
> > >>> - The problem comes from TCP links. When all processes are on the<br>
> same<br>
> > node, there is no error. As soon as one process is on a remote node, the<br>
> > failure occurs.<br>
> > >>> - Note also that the failure does not occur if I run a more complex<br>
> > code (eg, a NAS benchmark).<br>
> > >>><br>
> > >>> Thomas Ropars<br>
> > >>> _______________________________________________<br>
> > >>> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > >>> To manage subscription options or unsubscribe:<br>
> > >>> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > >> _______________________________________________<br>
> > >> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > >> To manage subscription options or unsubscribe:<br>
> > >> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > >><br>
> > >><br>
> > ><br>
> > > <ring_clean.c>_______________________________________________<br>
> > > discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > > To manage subscription options or unsubscribe:<br>
> > > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> ><br>
> ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 3<br>
> > Date: Wed, 10 Jul 2013 16:41:27 +0200<br>
> > From: Bob Ilgner <<a href="mailto:bobilgner@gmail.com">bobilgner@gmail.com</a>><br>
> > To: <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
> > Subject: [mpich-discuss] Restrict number of cores, not threads<br>
> > Message-ID:<br>
> > <<br>
> > <a href="mailto:CAKv15b-QgmHkVkoiTFmP3EZXvyy6sc_QeqHQgbMUhnr3Xh9ecA@mail.gmail.com">CAKv15b-QgmHkVkoiTFmP3EZXvyy6sc_QeqHQgbMUhnr3Xh9ecA@mail.gmail.com</a>><br>
> > Content-Type: text/plain; charset="iso-8859-1"<br>
> ><br>
> > Dear all,<br>
> ><br>
> > I am working on a shared memory processor with 256 cores. I am working<br>
> from<br>
> > the command line directly.<br>
> ><br>
> > Can I restict the number of cores that I deploy.The command<br>
> ><br>
> > mpirun -n 100 myprog<br>
> ><br>
> ><br>
> > will automatically start on 100 cores. I wish to use only 10 cores and<br>
> have<br>
> > 10 threads on each core. Can I do this with mpich ? Rememebre that this<br>
> an<br>
> > smp abd I can not identify each core individually(as in a cluster)<br>
> ><br>
> > Regards, bob<br>
> > -------------- next part --------------<br>
> > An HTML attachment was scrubbed...<br>
> > URL: <<br>
> ><br>
> <a href="http://lists.mpich.org/pipermail/discuss/attachments/20130710/ec659e91/attachment-0001.html" target="_blank">http://lists.mpich.org/pipermail/discuss/attachments/20130710/ec659e91/attachment-0001.html</a><br>
> > ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 4<br>
> > Date: Wed, 10 Jul 2013 09:46:38 -0500<br>
> > From: Wesley Bland <<a href="mailto:wbland@mcs.anl.gov">wbland@mcs.anl.gov</a>><br>
> > To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > Cc: <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
> > Subject: Re: [mpich-discuss] Restrict number of cores, not threads<br>
> > Message-ID: <<a href="mailto:2FAF588E-2FBE-45E4-B53F-E6BC931E3D51@mcs.anl.gov">2FAF588E-2FBE-45E4-B53F-E6BC931E3D51@mcs.anl.gov</a>><br>
> > Content-Type: text/plain; charset=iso-8859-1<br>
> ><br>
> > Threads in MPI are not ranks. When you say you want to launch with -n<br>
> 100,<br>
> > you will always get 100 processes, not threads. If you want 10 threads on<br>
> > 10 cores, you will need to launch with -n 10, then add your threads<br>
> > according to your threading library.<br>
> ><br>
> > Note that threads in MPI do not get their own rank currently. They all<br>
> > share the same rank as the process in which they reside, so if you need<br>
> to<br>
> > be able to handle things with different ranks, you'll need to use actual<br>
> > processes.<br>
> ><br>
> > Wesley<br>
> ><br>
> > On Jul 10, 2013, at 9:41 AM, Bob Ilgner <<a href="mailto:bobilgner@gmail.com">bobilgner@gmail.com</a>> wrote:<br>
> ><br>
> > > Dear all,<br>
> > ><br>
> > > I am working on a shared memory processor with 256 cores. I am working<br>
> > from the command line directly.<br>
> > ><br>
> > > Can I restict the number of cores that I deploy.The command<br>
> > ><br>
> > > mpirun -n 100 myprog<br>
> > ><br>
> > ><br>
> > > will automatically start on 100 cores. I wish to use only 10 cores and<br>
> > have 10 threads on each core. Can I do this with mpich ? Rememebre that<br>
> > this an smp abd I can not identify each core individually(as in a<br>
> cluster)<br>
> > ><br>
> > > Regards, bob<br>
> > > _______________________________________________<br>
> > > discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > > To manage subscription options or unsubscribe:<br>
> > > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> ><br>
> ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 5<br>
> > Date: Wed, 10 Jul 2013 09:46:38 -0500<br>
> > From: Wesley Bland <<a href="mailto:wbland@mcs.anl.gov">wbland@mcs.anl.gov</a>><br>
> > To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > Cc: <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
> > Subject: Re: [mpich-discuss] Restrict number of cores, not threads<br>
> > Message-ID: <<a href="mailto:2FAF588E-2FBE-45E4-B53F-E6BC931E3D51@mcs.anl.gov">2FAF588E-2FBE-45E4-B53F-E6BC931E3D51@mcs.anl.gov</a>><br>
> > Content-Type: text/plain; charset=iso-8859-1<br>
> ><br>
> > Threads in MPI are not ranks. When you say you want to launch with -n<br>
> 100,<br>
> > you will always get 100 processes, not threads. If you want 10 threads on<br>
> > 10 cores, you will need to launch with -n 10, then add your threads<br>
> > according to your threading library.<br>
> ><br>
> > Note that threads in MPI do not get their own rank currently. They all<br>
> > share the same rank as the process in which they reside, so if you need<br>
> to<br>
> > be able to handle things with different ranks, you'll need to use actual<br>
> > processes.<br>
> ><br>
> > Wesley<br>
> ><br>
> > On Jul 10, 2013, at 9:41 AM, Bob Ilgner <<a href="mailto:bobilgner@gmail.com">bobilgner@gmail.com</a>> wrote:<br>
> ><br>
> > > Dear all,<br>
> > ><br>
> > > I am working on a shared memory processor with 256 cores. I am working<br>
> > from the command line directly.<br>
> > ><br>
> > > Can I restict the number of cores that I deploy.The command<br>
> > ><br>
> > > mpirun -n 100 myprog<br>
> > ><br>
> > ><br>
> > > will automatically start on 100 cores. I wish to use only 10 cores and<br>
> > have 10 threads on each core. Can I do this with mpich ? Rememebre that<br>
> > this an smp abd I can not identify each core individually(as in a<br>
> cluster)<br>
> > ><br>
> > > Regards, bob<br>
> > > _______________________________________________<br>
> > > discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > > To manage subscription options or unsubscribe:<br>
> > > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> ><br>
> ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 6<br>
> > Date: Wed, 10 Jul 2013 16:50:36 +0200<br>
> > From: Thomas Ropars <<a href="mailto:thomas.ropars@epfl.ch">thomas.ropars@epfl.ch</a>><br>
> > To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > Subject: Re: [mpich-discuss] Error in MPI_Finalize on a simple ring<br>
> > test over TCP<br>
> > Message-ID: <<a href="mailto:51DD74BC.3020009@epfl.ch">51DD74BC.3020009@epfl.ch</a>><br>
> > Content-Type: text/plain; charset=UTF-8; format=flowed<br>
> ><br>
> > Yes, you are right, sorry for disturbing.<br>
> ><br>
> > On 07/10/2013 03:39 PM, Wesley Bland wrote:<br>
> > > The value of previous for rank 0 in your code is -1. MPICH is<br>
> > complaining because all of the requests to receive a message from -1 are<br>
> > still pending when you try to finalize. You need to make sure that you<br>
> are<br>
> > receiving from valid ranks.<br>
> > ><br>
> > > On Jul 10, 2013, at 7:50 AM, Thomas Ropars <<a href="mailto:thomas.ropars@epfl.ch">thomas.ropars@epfl.ch</a>><br>
> > wrote:<br>
> > ><br>
> > >> Yes sure. Here it is.<br>
> > >><br>
> > >> Thomas<br>
> > >><br>
> > >> On 07/10/2013 02:23 PM, Wesley Bland wrote:<br>
> > >>> Can you send us the smallest chunk of code that still exhibits this<br>
> > error?<br>
> > >>><br>
> > >>> Wesley<br>
> > >>><br>
> > >>> On Jul 10, 2013, at 6:54 AM, Thomas Ropars <<a href="mailto:thomas.ropars@epfl.ch">thomas.ropars@epfl.ch</a>><br>
> > wrote:<br>
> > >>><br>
> > >>>> Hi all,<br>
> > >>>><br>
> > >>>> I get the following error when I try to run a simple application<br>
> > implementing a ring (each process sends to rank+1 and receives from<br>
> > rank-1). More precisely, the error occurs during the call to<br>
> MPI_Finalize():<br>
> > >>>><br>
> > >>>> Assertion failed in file<br>
> > src/mpid/ch3/channels/nemesis/netmod/tcp/socksm.c at line 363:<br>
> sc->pg_is_set<br>
> > >>>> internal ABORT - process 0<br>
> > >>>><br>
> > >>>> Does anybody else also noticed the same error?<br>
> > >>>><br>
> > >>>> Here are all the details about my test:<br>
> > >>>> - The error is generated with mpich-3.0.2 (but I noticed the exact<br>
> > same error with mpich-3.0.4)<br>
> > >>>> - I am using IPoIB for communication between nodes (The same thing<br>
> > happens over Ethernet)<br>
> > >>>> - The problem comes from TCP links. When all processes are on the<br>
> > same node, there is no error. As soon as one process is on a remote node,<br>
> > the failure occurs.<br>
> > >>>> - Note also that the failure does not occur if I run a more complex<br>
> > code (eg, a NAS benchmark).<br>
> > >>>><br>
> > >>>> Thomas Ropars<br>
> > >>>> _______________________________________________<br>
> > >>>> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > >>>> To manage subscription options or unsubscribe:<br>
> > >>>> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > >>> _______________________________________________<br>
> > >>> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > >>> To manage subscription options or unsubscribe:<br>
> > >>> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > >>><br>
> > >>><br>
> > >> <ring_clean.c>_______________________________________________<br>
> > >> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > >> To manage subscription options or unsubscribe:<br>
> > >> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > > _______________________________________________<br>
> > > discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > > To manage subscription options or unsubscribe:<br>
> > > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > ><br>
> > ><br>
> ><br>
> ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 7<br>
> > Date: Wed, 10 Jul 2013 10:07:21 -0500<br>
> > From: Sufeng Niu <<a href="mailto:sniu@hawk.iit.edu">sniu@hawk.iit.edu</a>><br>
> > To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > Subject: [mpich-discuss] MPI_Win_fence failed<br>
> > Message-ID:<br>
> > <<br>
> > <a href="mailto:CAFNNHkz_1gC7hfpx0G9j24adO-gDabdmwZ4VuT6jip-fDMhS9A@mail.gmail.com">CAFNNHkz_1gC7hfpx0G9j24adO-gDabdmwZ4VuT6jip-fDMhS9A@mail.gmail.com</a>><br>
> > Content-Type: text/plain; charset="iso-8859-1"<br>
> ><br>
> > Hello,<br>
> ><br>
> > I used MPI RMA in my program, but the program stop at the MPI_Win_fence,<br>
> I<br>
> > have a master process receive data from udp socket. Other processes use<br>
> > MPI_Get to access data.<br>
> ><br>
> > master process:<br>
> ><br>
> > MPI_Create(...)<br>
> > for(...){<br>
> > /* udp recv operation */<br>
> ><br>
> > MPI_Barrier // to let other process know data received from udp is ready<br>
> ><br>
> > MPI_Win_fence(0, win);<br>
> > MPI_Win_fence(0, win);<br>
> ><br>
> > }<br>
> ><br>
> > other processes:<br>
> ><br>
> > for(...){<br>
> ><br>
> > MPI_Barrier // sync for udp data ready<br>
> ><br>
> > MPI_Win_fence(0, win);<br>
> ><br>
> > MPI_Get();<br>
> ><br>
> > MPI_Win_fence(0, win); <-- program stopped here<br>
> ><br>
> > /* other operation */<br>
> > }<br>
> ><br>
> > I found that the program stopped at second MPI_Win_fence, the terminal<br>
> > output is:<br>
> ><br>
> ><br>
> ><br>
> ><br>
> ===================================================================================<br>
> > = BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES<br>
> > = EXIT CODE: 11<br>
> > = CLEANING UP REMAINING PROCESSES<br>
> > = YOU CAN IGNORE THE BELOW CLEANUP MESSAGES<br>
> ><br>
> ><br>
> ===================================================================================<br>
> > YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault<br>
> > (signal 11)<br>
> > This typically refers to a problem with your application.<br>
> > Please see the FAQ page for debugging suggestions<br>
> ><br>
> > Do you have any suggestions? Thank you very much!<br>
> ><br>
> > --<br>
> > Best Regards,<br>
> > Sufeng Niu<br>
> > ECASP lab, ECE department, Illinois Institute of Technology<br>
> > Tel: <a href="tel:312-731-7219" value="+13127317219">312-731-7219</a><br>
> > -------------- next part --------------<br>
> > An HTML attachment was scrubbed...<br>
> > URL: <<br>
> ><br>
> <a href="http://lists.mpich.org/pipermail/discuss/attachments/20130710/375a95ac/attachment-0001.html" target="_blank">http://lists.mpich.org/pipermail/discuss/attachments/20130710/375a95ac/attachment-0001.html</a><br>
> > ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 8<br>
> > Date: Wed, 10 Jul 2013 11:12:45 -0400<br>
> > From: Jim Dinan <<a href="mailto:james.dinan@gmail.com">james.dinan@gmail.com</a>><br>
> > To: <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > Subject: Re: [mpich-discuss] MPI_Win_fence failed<br>
> > Message-ID:<br>
> > <CAOoEU4F3hX=y3yrJKYKucNeiueQYBeR_3OQas9E+mg+GM6Rz=<br>
> > <a href="mailto:w@mail.gmail.com">w@mail.gmail.com</a>><br>
> > Content-Type: text/plain; charset="iso-8859-1"<br>
> ><br>
> > It's hard to tell where the segmentation fault is coming from. Can you<br>
> use<br>
> > a debugger to generate a backtrace?<br>
> ><br>
> > ~Jim.<br>
> ><br>
> ><br>
> > On Wed, Jul 10, 2013 at 11:07 AM, Sufeng Niu <<a href="mailto:sniu@hawk.iit.edu">sniu@hawk.iit.edu</a>> wrote:<br>
> ><br>
> > > Hello,<br>
> > ><br>
> > > I used MPI RMA in my program, but the program stop at the<br>
> MPI_Win_fence,<br>
> > I<br>
> > > have a master process receive data from udp socket. Other processes use<br>
> > > MPI_Get to access data.<br>
> > ><br>
> > > master process:<br>
> > ><br>
> > > MPI_Create(...)<br>
> > > for(...){<br>
> > > /* udp recv operation */<br>
> > ><br>
> > > MPI_Barrier // to let other process know data received from udp is<br>
> ready<br>
> > ><br>
> > > MPI_Win_fence(0, win);<br>
> > > MPI_Win_fence(0, win);<br>
> > ><br>
> > > }<br>
> > ><br>
> > > other processes:<br>
> > ><br>
> > > for(...){<br>
> > ><br>
> > > MPI_Barrier // sync for udp data ready<br>
> > ><br>
> > > MPI_Win_fence(0, win);<br>
> > ><br>
> > > MPI_Get();<br>
> > ><br>
> > > MPI_Win_fence(0, win); <-- program stopped here<br>
> > ><br>
> > > /* other operation */<br>
> > > }<br>
> > ><br>
> > > I found that the program stopped at second MPI_Win_fence, the terminal<br>
> > > output is:<br>
> > ><br>
> > ><br>
> > ><br>
> > ><br>
> ><br>
> ===================================================================================<br>
> > > = BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES<br>
> > > = EXIT CODE: 11<br>
> > > = CLEANING UP REMAINING PROCESSES<br>
> > > = YOU CAN IGNORE THE BELOW CLEANUP MESSAGES<br>
> > ><br>
> > ><br>
> ><br>
> ===================================================================================<br>
> > > YOUR APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault<br>
> > > (signal 11)<br>
> > > This typically refers to a problem with your application.<br>
> > > Please see the FAQ page for debugging suggestions<br>
> > ><br>
> > > Do you have any suggestions? Thank you very much!<br>
> > ><br>
> > > --<br>
> > > Best Regards,<br>
> > > Sufeng Niu<br>
> > > ECASP lab, ECE department, Illinois Institute of Technology<br>
> > > Tel: <a href="tel:312-731-7219" value="+13127317219">312-731-7219</a><br>
> > ><br>
> > > _______________________________________________<br>
> > > discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > > To manage subscription options or unsubscribe:<br>
> > > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> > ><br>
> > -------------- next part --------------<br>
> > An HTML attachment was scrubbed...<br>
> > URL: <<br>
> ><br>
> <a href="http://lists.mpich.org/pipermail/discuss/attachments/20130710/48c5f337/attachment.html" target="_blank">http://lists.mpich.org/pipermail/discuss/attachments/20130710/48c5f337/attachment.html</a><br>
> > ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > _______________________________________________<br>
> > discuss mailing list<br>
> > <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> > <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
> ><br>
> > End of discuss Digest, Vol 9, Issue 27<br>
> > **************************************<br>
> ><br>
><br>
><br>
><br>
> --<br>
> Best Regards,<br>
> Sufeng Niu<br>
> ECASP lab, ECE department, Illinois Institute of Technology<br>
> Tel: <a href="tel:312-731-7219" value="+13127317219">312-731-7219</a><br>
> -------------- next part --------------<br>
> An HTML attachment was scrubbed...<br>
> URL: <<br>
> <a href="http://lists.mpich.org/pipermail/discuss/attachments/20130710/57a5e76f/attachment.html" target="_blank">http://lists.mpich.org/pipermail/discuss/attachments/20130710/57a5e76f/attachment.html</a><br>
> ><br>
><br>
> ------------------------------<br>
><br>
> _______________________________________________<br>
> discuss mailing list<br>
> <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
><br>
> End of discuss Digest, Vol 9, Issue 28<br>
> **************************************<br>
><br>
<br>
<br>
<br>
--<br>
Best Regards,<br>
Sufeng Niu<br>
ECASP lab, ECE department, Illinois Institute of Technology<br>
Tel: <a href="tel:312-731-7219" value="+13127317219">312-731-7219</a><br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://lists.mpich.org/pipermail/discuss/attachments/20130710/48296a33/attachment.html" target="_blank">http://lists.mpich.org/pipermail/discuss/attachments/20130710/48296a33/attachment.html</a>><br>
-------------- next part --------------<br>
A non-text attachment was scrubbed...<br>
Name: Screenshot.png<br>
Type: image/png<br>
Size: 131397 bytes<br>
Desc: not available<br>
URL: <<a href="http://lists.mpich.org/pipermail/discuss/attachments/20130710/48296a33/attachment.png" target="_blank">http://lists.mpich.org/pipermail/discuss/attachments/20130710/48296a33/attachment.png</a>><br>
<br>
------------------------------<br>
<br>
_______________________________________________<br>
discuss mailing list<br>
<a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
<a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
<br>
End of discuss Digest, Vol 9, Issue 29<br>
**************************************<br>
</blockquote></div><br><br clear="all"><br>-- <br>Best Regards,<div>Sufeng Niu</div><div>ECASP lab, ECE department, Illinois Institute of Technology</div><div>Tel: 312-731-7219</div>
</div></div></div></div></div></div>