September 2014 - discuss - mailman3.cels.anl.gov

Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling
by Abhishek Bhat 17 Sep '14

17 Sep '14

Pavan, The application works when there is a less resource intensive runs (larger grid with larger grid spacing). The issue occurs when we have nested grid runs. Also the application works without any issues for less than 7 processes (1 I/O and 6 nodes). Thank You Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant -----Original Message----- From: Balaji, Pavan [mailto:[email protected]] Sent: Wednesday, September 17, 2014 12:59 PM To: <discuss(a)mpich.org> Cc: Abhishek Bhat Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling I’m not sure the logs will be useful. This seems to be an application issue, not an MPICH issue. The application process is terminating abruptly. — Pavan On Sep 17, 2014, at 12:56 PM, Seo, Sangmin <sseo(a)anl.gov> wrote: > I have looked into your log file, but it seems that the real error happened in other process, not rank 0. The socket of rank 0 was closed because the other process died. Can you send us log files of other processes? > > And, can you also send us the execution result with > "-print-all-exitcodes” option? For example, mpiexec -machinefile nodes > -np $NUMPROCS -print-all-exitcodes $EXEC -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose -print-all-exitcodes option will show the exit codes for each process. > > Regards, > Sangmin > > > On Sep 17, 2014, at 12:33 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: > >> Any luck on finding solution on the error in the log file provided? >> >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Abhishek Bhat >> Sent: Tuesday, September 16, 2014 11:36 AM >> To: <discuss(a)mpich.org> >> Cc: 'sseo(a)anl.gov' >> Subject: RE: [mpich-discuss] Error Running MPICH for Photochemical >> Modeling >> >> Sangmin, >> >> Sorry for the confusion, I was looking in the wrong location. Please find attached the splice of the debug file 0 where the Error is occurring. >> >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Tuesday, September 16, 2014 11:12 AM >> To: Abhishek Bhat >> Cc: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical >> Modeling >> >> The log files should be found in the directory where you execute the application. Did you run the application with debug options, -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose? >> >> — Sangmin >> >> >> On Sep 16, 2014, at 11:05 AM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> Sangmin, >> >> I configured the MPICH with revised code and included the additional options as described. Where should I be looking for the log files? >> I cannot see any files generated. >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Monday, September 15, 2014 12:43 PM >> To: Abhishek Bhat >> Cc: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical >> Modeling >> >> Sorry, “./make” should have been “make” >> >> — Sangmin >> >> On Sep 15, 2014, at 12:40 PM, Seo, Sangmin <sseo(a)anl.gov> wrote: >> >> >> >> Did you run dmesg on the node which executed the rank failed? I don't see any error message from your log file. >> >> Anyway, let's try with MPICH DEBUG messages. As described >> inhttps://wiki.mpich.org/mpich/index.php/Debug_Event_Logging, first >> configure MPICH with "--enable-g=dbg,log" to enable event logging and >> built it. For example, $ ./configure --prefix=$INSTALL_DIR >> --enable-g=dbg,log $ ./make -j8 $ ./make install >> >> Then, execute your application with additional options, "-mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose." With the recent MPICH, you don't need to use mpdboot. Just execute your application with mpiexec like: >> mpiexec -machinefile nodes -np $NUMPROCS $EXEC -mpich-dbg=file >> -mpich-dbg-class=all -mpich-dbg-level=verbose >> >> This will generate log files, such as dbg0-xxxx.log, dbg1-xxxx.log, etc. Since the log files may be large, it would be difficult to send them to us. If so, please take a look at each file, find error messages, and send the error message to us. >> >> And, if you can reproduce the same error with small code, it will be really helpful to figure out your problem. Could you write a simplified code and send us the code? >> >> Regards, >> Sangmin >> >> >> On Sep 15, 2014, at 10:58 AM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> Sangmin, >> >> Please see attached the logs from demsg. I apologies but I am not a computer expert so it’s all Greek to me.. Can you please see if you can find any error or reason for the failure? >> >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Monday, September 15, 2014 9:21 AM >> To: Abhishek Bhat >> Cc: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical >> Modeling >> >> Can you run dmesg on the node of rank 1, which is killed by signal 9, after you execute your application? You can find the reason that the process is killed at the end of dmesg output, e.g., out of memory. >> >> — Sangmin >> >> >> On Sep 14, 2014, at 12:37 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> >> Because the application works when less intensive runs and fails for more intensive runs, it is likely that the application is requesting too many resources. When\where should I run ulimit –a and dmesg, after I get the error? If that is true, is there any way to change the environment in MPI to increase the capacity so that the increased resources can be accommodated? >> >> If I run it in new terminal – here is what I get >> >> core file size (blocks, -c) 0 >> data seg size (kbytes, -d) unlimited >> scheduling priority (-e) 0 >> file size (blocks, -f) unlimited >> pending signals (-i) 250598 >> max locked memory (kbytes, -l) 64 >> max memory size (kbytes, -m) unlimited >> open files (-n) 1024 >> pipe size (512 bytes, -p) 8 >> POSIX message queues (bytes, -q) 819200 >> real-time priority (-r) 0 >> stack size (kbytes, -s) 10240 >> cpu time (seconds, -t) unlimited >> max user processes (-u) 1024 >> virtual memory (kbytes, -v) unlimited >> file locks (-x) unlimited >> >> in my job, I try to set the stack size to – unlimited but I guess it is not working. >> >> Let me know. Thank you for all the help. >> Abhishek >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Sunday, September 14, 2014 11:16 AM >> To: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical >> Modeling >> >> Abhishek, >> >> Signal 9 is caused by many reasons, e.g., CPU time, out of memory, etc., but it is mostly because the application requests too many resources. You can check the environment settings with ulimit -a. And, you may find some information about your error from dmesg. >> >> Thanks, >> Sangmin >> >> >> On Sep 12, 2014, at 5:51 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> >> >> Sangmin. >> >> I updated to mpich3 and getting the following error >> >> Fatal error in MPI_Recv: A process has failed, error stack: >> MPI_Recv(187).............: MPI_Recv(buf=0x7fff93840c30, >> count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, >> status=0x7fff94444f20) failed >> dequeue_and_set_error(865): Communication error with rank 1 >> rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks >> exit status of rank 1: killed by signal 9 >> >> Same situation, successful runs for smaller resource runs and for up >> to 7 processes. Error at more than 7. Here is the mpich command I >> am using to run from my job file… >> >> cat << ieof > nodes >> dfw-camx:1 >> dfw-camx-n1:1 >> dfw-camx-n2:1 >> dfw-camx-n3:1 >> dfw-camx-n4:1 >> dfw-camx-n5:1 >> dfw-camx-n6:1 >> dfw-camx-n7:1 >> ieof >> set NUMPROCS = 8 >> set RING = `wc -l nodes | awk '{print $1}'` mpdboot -n $RING -f nodes >> –verbose >> >> if( ! { mpiexec -machinefile nodes -np $NUMPROCS $EXEC } ) then >> mpdallexit >> exit >> endif >> >> >> For a successful run the NUMPROCS has to be < = 7. >> >> Any help is much appreciated. >> >> Thank You >> Abhishek >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Friday, September 12, 2014 1:11 PM >> To: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical >> Modeling >> >> Hi Abhishek, >> >> Can you try with the recent MPICH release to see if the same error happens? You can download the recent release, 3.1.2, from http://www.mpich.org/downloads/. >> >> Thanks, >> Sangmin >> >> >> On Sep 12, 2014, at 12:59 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> >> >> >> I am running a photochemical modeling on Linux cluster (CentOS_64 bit) with 1 master and 8 slave nodes with quad core (intel i7) on each node. I have two scenarios, in first scenario, I am running less data intensive run on all 8 nodes (NUMPROCS = 9) and the run will go fine. When running same configuration for a more intense run, I am getting following error. >> >> Fatal error in MPI_Recv: Other MPI error, error stack: >> MPI_Recv(187).....................: MPI_Recv(buf=0x7fff989d53b0, >> count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, >> status=0x7fff995d96a0) failed >> MPIDI_CH3I_Progress(150)..........: >> MPID_nem_mpich2_blocking_recv(948): >> MPID_nem_tcp_connpoll(1720).......: >> state_commrdy_handler(1556).......: >> MPID_nem_tcp_recv_handler(1446)...: socket closed >> rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks >> exit status of rank 1: killed by signal 9 >> >> If I run the program with smaller nodes (smaller than 7 NUMPROCS) the run goes fine. >> >> It appears that the rank 1 (my first node) is collectively causing >> all the ranks, but I could identify why. I tried following solutions >> – >> >> 1. Increased master memory to 32 gb >> 2. Increased all nodes memory to 32 gb >> 3. Exchanged the rank 1 to different node in the parallel. >> >> In all situations, I am getting this error. Surprisingly, when I am running smaller (less data intensive runs), I am not getting this error even if I increase the NUMPROCS to 32 processes. >> >> Any help will be highly appreciated. >> >> I am running mpich 1.4 >> >> Thank You >> Abhishek >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> Trinity Consultants >> 12770 Merit Drive, Suite 900 | Dallas, Texas 75251 >> >> Office: 972-661-8100| Mobile: 806-281-7617 >> Email: abhat(a)trinityconsultants.com | LinkedIn: >> www.linkedin.com/in/abhattrinityconsultants >> >> Stay current on environmental issues. Subscribe today to receive Trinity's free Environmental Quarterly. >> Learn about Trinity’s courses for environmental professionals. >> >> <image001.gif> <image002.gif> <image003.gif> <image004.gif> >> >> <image005.jpg> >> >> >> _____________________________________________________________________ >> ____ >> >> The information transmitted is intended only for the person or entity >> to which it is addressed and may contain confidential and/or >> privileged material. Any review, retransmission, dissemination or >> other use of, or taking of any action in reliance upon, this >> information by persons or entities other than the intended recipient >> is prohibited. If you received this in error, please contact the >> sender and delete the material from any computer. >> _____________________________________________________________________ >> ____ _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss >> >> >> _____________________________________________________________________ >> ____ >> >> The information transmitted is intended only for the person or entity >> to which it is addressed and may contain confidential and/or >> privileged material. Any review, retransmission, dissemination or >> other use of, or taking of any action in reliance upon, this >> information by persons or entities other than the intended recipient >> is prohibited. If you received this in error, please contact the >> sender and delete the material from any computer. >> _____________________________________________________________________ >> ____ _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss >> >> >> _____________________________________________________________________ >> ____ >> >> The information transmitted is intended only for the person or entity >> to which it is addressed and may contain confidential and/or >> privileged material. Any review, retransmission, dissemination or >> other use of, or taking of any action in reliance upon, this >> information by persons or entities other than the intended recipient >> is prohibited. If you received this in error, please contact the >> sender and delete the material from any computer. >> _____________________________________________________________________ >> ____ >> >> >> _____________________________________________________________________ >> ____ >> >> The information transmitted is intended only for the person or entity >> to which it is addressed and may contain confidential and/or >> privileged material. Any review, retransmission, dissemination or >> other use of, or taking of any action in reliance upon, this >> information by persons or entities other than the intended recipient >> is prohibited. If you received this in error, please contact the >> sender and delete the material from any computer. >> _____________________________________________________________________ >> ____ >> <dmesg3.txt><messages.txt> >> >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss >> >> >> _____________________________________________________________________ >> ____ >> >> The information transmitted is intended only for the person or entity >> to which it is addressed and may contain confidential and/or >> privileged material. Any review, retransmission, dissemination or >> other use of, or taking of any action in reliance upon, this >> information by persons or entities other than the intended recipient >> is prohibited. If you received this in error, please contact the >> sender and delete the material from any computer. >> _____________________________________________________________________ >> ____ >> >> >> _____________________________________________________________________ >> ____ >> >> The information transmitted is intended only for the person or entity >> to which it is addressed and may contain confidential and/or >> privileged material. Any review, retransmission, dissemination or >> other use of, or taking of any action in reliance upon, this >> information by persons or entities other than the intended recipient >> is prohibited. If you received this in error, please contact the >> sender and delete the material from any computer. >> _____________________________________________________________________ >> ____ > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss -- Pavan Balaji ✉️ http://www.mcs.anl.gov/~balaji -- _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling
by Balaji, Pavan 17 Sep '14

17 Sep '14

I’m not sure the logs will be useful. This seems to be an application issue, not an MPICH issue. The application process is terminating abruptly. — Pavan On Sep 17, 2014, at 12:56 PM, Seo, Sangmin <sseo(a)anl.gov> wrote: > I have looked into your log file, but it seems that the real error happened in other process, not rank 0. The socket of rank 0 was closed because the other process died. Can you send us log files of other processes? > > And, can you also send us the execution result with "-print-all-exitcodes” option? For example, > mpiexec -machinefile nodes -np $NUMPROCS -print-all-exitcodes $EXEC -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose > -print-all-exitcodes option will show the exit codes for each process. > > Regards, > Sangmin > > > On Sep 17, 2014, at 12:33 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: > >> Any luck on finding solution on the error in the log file provided? >> >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Abhishek Bhat >> Sent: Tuesday, September 16, 2014 11:36 AM >> To: <discuss(a)mpich.org> >> Cc: 'sseo(a)anl.gov' >> Subject: RE: [mpich-discuss] Error Running MPICH for Photochemical Modeling >> >> Sangmin, >> >> Sorry for the confusion, I was looking in the wrong location. Please find attached the splice of the debug file 0 where the Error is occurring. >> >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Tuesday, September 16, 2014 11:12 AM >> To: Abhishek Bhat >> Cc: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling >> >> The log files should be found in the directory where you execute the application. Did you run the application with debug options, -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose? >> >> — Sangmin >> >> >> On Sep 16, 2014, at 11:05 AM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> Sangmin, >> >> I configured the MPICH with revised code and included the additional options as described. Where should I be looking for the log files? >> I cannot see any files generated. >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Monday, September 15, 2014 12:43 PM >> To: Abhishek Bhat >> Cc: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling >> >> Sorry, “./make” should have been “make” >> >> — Sangmin >> >> On Sep 15, 2014, at 12:40 PM, Seo, Sangmin <sseo(a)anl.gov> wrote: >> >> >> >> Did you run dmesg on the node which executed the rank failed? I don't see any error message from your log file. >> >> Anyway, let's try with MPICH DEBUG messages. As described inhttps://wiki.mpich.org/mpich/index.php/Debug_Event_Logging, first configure MPICH with "--enable-g=dbg,log" to enable event logging and built it. For example, >> $ ./configure --prefix=$INSTALL_DIR --enable-g=dbg,log >> $ ./make -j8 >> $ ./make install >> >> Then, execute your application with additional options, "-mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose." With the recent MPICH, you don't need to use mpdboot. Just execute your application with mpiexec like: >> mpiexec -machinefile nodes -np $NUMPROCS $EXEC -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose >> >> This will generate log files, such as dbg0-xxxx.log, dbg1-xxxx.log, etc. Since the log files may be large, it would be difficult to send them to us. If so, please take a look at each file, find error messages, and send the error message to us. >> >> And, if you can reproduce the same error with small code, it will be really helpful to figure out your problem. Could you write a simplified code and send us the code? >> >> Regards, >> Sangmin >> >> >> On Sep 15, 2014, at 10:58 AM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> Sangmin, >> >> Please see attached the logs from demsg. I apologies but I am not a computer expert so it’s all Greek to me.. Can you please see if you can find any error or reason for the failure? >> >> >> Thank You >> Abhishek >> >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Monday, September 15, 2014 9:21 AM >> To: Abhishek Bhat >> Cc: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling >> >> Can you run dmesg on the node of rank 1, which is killed by signal 9, after you execute your application? You can find the reason that the process is killed at the end of dmesg output, e.g., out of memory. >> >> — Sangmin >> >> >> On Sep 14, 2014, at 12:37 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> >> Because the application works when less intensive runs and fails for more intensive runs, it is likely that the application is requesting too many resources. When\where should I run ulimit –a and dmesg, after I get the error? If that is true, is there any way to change the environment in MPI to increase the capacity so that the increased resources can be accommodated? >> >> If I run it in new terminal – here is what I get >> >> core file size (blocks, -c) 0 >> data seg size (kbytes, -d) unlimited >> scheduling priority (-e) 0 >> file size (blocks, -f) unlimited >> pending signals (-i) 250598 >> max locked memory (kbytes, -l) 64 >> max memory size (kbytes, -m) unlimited >> open files (-n) 1024 >> pipe size (512 bytes, -p) 8 >> POSIX message queues (bytes, -q) 819200 >> real-time priority (-r) 0 >> stack size (kbytes, -s) 10240 >> cpu time (seconds, -t) unlimited >> max user processes (-u) 1024 >> virtual memory (kbytes, -v) unlimited >> file locks (-x) unlimited >> >> in my job, I try to set the stack size to – unlimited but I guess it is not working. >> >> Let me know. Thank you for all the help. >> Abhishek >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Sunday, September 14, 2014 11:16 AM >> To: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling >> >> Abhishek, >> >> Signal 9 is caused by many reasons, e.g., CPU time, out of memory, etc., but it is mostly because the application requests too many resources. You can check the environment settings with ulimit -a. And, you may find some information about your error from dmesg. >> >> Thanks, >> Sangmin >> >> >> On Sep 12, 2014, at 5:51 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> >> >> Sangmin. >> >> I updated to mpich3 and getting the following error >> >> Fatal error in MPI_Recv: A process has failed, error stack: >> MPI_Recv(187).............: MPI_Recv(buf=0x7fff93840c30, count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, status=0x7fff94444f20) failed >> dequeue_and_set_error(865): Communication error with rank 1 >> rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks >> exit status of rank 1: killed by signal 9 >> >> Same situation, successful runs for smaller resource runs and for up to 7 processes. Error at more than 7. Here is the mpich command I am using to run from my job file… >> >> cat << ieof > nodes >> dfw-camx:1 >> dfw-camx-n1:1 >> dfw-camx-n2:1 >> dfw-camx-n3:1 >> dfw-camx-n4:1 >> dfw-camx-n5:1 >> dfw-camx-n6:1 >> dfw-camx-n7:1 >> ieof >> set NUMPROCS = 8 >> set RING = `wc -l nodes | awk '{print $1}'` >> mpdboot -n $RING -f nodes –verbose >> >> if( ! { mpiexec -machinefile nodes -np $NUMPROCS $EXEC } ) then >> mpdallexit >> exit >> endif >> >> >> For a successful run the NUMPROCS has to be < = 7. >> >> Any help is much appreciated. >> >> Thank You >> Abhishek >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> >> From: Seo, Sangmin [mailto:[email protected]] >> Sent: Friday, September 12, 2014 1:11 PM >> To: <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling >> >> Hi Abhishek, >> >> Can you try with the recent MPICH release to see if the same error happens? You can download the recent release, 3.1.2, from http://www.mpich.org/downloads/. >> >> Thanks, >> Sangmin >> >> >> On Sep 12, 2014, at 12:59 PM, Abhishek Bhat <abhat(a)trinityconsultants.com> wrote: >> >> >> >> >> >> >> I am running a photochemical modeling on Linux cluster (CentOS_64 bit) with 1 master and 8 slave nodes with quad core (intel i7) on each node. I have two scenarios, in first scenario, I am running less data intensive run on all 8 nodes (NUMPROCS = 9) and the run will go fine. When running same configuration for a more intense run, I am getting following error. >> >> Fatal error in MPI_Recv: Other MPI error, error stack: >> MPI_Recv(187).....................: MPI_Recv(buf=0x7fff989d53b0, count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, status=0x7fff995d96a0) failed >> MPIDI_CH3I_Progress(150)..........: >> MPID_nem_mpich2_blocking_recv(948): >> MPID_nem_tcp_connpoll(1720).......: >> state_commrdy_handler(1556).......: >> MPID_nem_tcp_recv_handler(1446)...: socket closed >> rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks >> exit status of rank 1: killed by signal 9 >> >> If I run the program with smaller nodes (smaller than 7 NUMPROCS) the run goes fine. >> >> It appears that the rank 1 (my first node) is collectively causing all the ranks, but I could identify why. I tried following solutions – >> >> 1. Increased master memory to 32 gb >> 2. Increased all nodes memory to 32 gb >> 3. Exchanged the rank 1 to different node in the parallel. >> >> In all situations, I am getting this error. Surprisingly, when I am running smaller (less data intensive runs), I am not getting this error even if I increase the NUMPROCS to 32 processes. >> >> Any help will be highly appreciated. >> >> I am running mpich 1.4 >> >> Thank You >> Abhishek >> …………………………………………………………………………………………………. >> Abhishek Bhat, PhD, EPI, >> Senior Consultant >> >> Trinity Consultants >> 12770 Merit Drive, Suite 900 | Dallas, Texas 75251 >> >> Office: 972-661-8100| Mobile: 806-281-7617 >> Email: abhat(a)trinityconsultants.com | LinkedIn: www.linkedin.com/in/abhattrinityconsultants >> >> Stay current on environmental issues. Subscribe today to receive Trinity's free Environmental Quarterly. >> Learn about Trinity’s courses for environmental professionals. >> >> <image001.gif> <image002.gif> <image003.gif> <image004.gif> >> >> <image005.jpg> >> >> >> _________________________________________________________________________ >> >> The information transmitted is intended only for the person or entity to >> which it is addressed and may contain confidential and/or privileged >> material. Any review, retransmission, dissemination or other use of, or >> taking of any action in reliance upon, this information by persons or >> entities other than the intended recipient is prohibited. If you received >> this in error, please contact the sender and delete the material from any >> computer. >> _________________________________________________________________________ >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss >> >> >> _________________________________________________________________________ >> >> The information transmitted is intended only for the person or entity to >> which it is addressed and may contain confidential and/or privileged >> material. Any review, retransmission, dissemination or other use of, or >> taking of any action in reliance upon, this information by persons or >> entities other than the intended recipient is prohibited. If you received >> this in error, please contact the sender and delete the material from any >> computer. >> _________________________________________________________________________ >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss >> >> >> _________________________________________________________________________ >> >> The information transmitted is intended only for the person or entity to >> which it is addressed and may contain confidential and/or privileged >> material. Any review, retransmission, dissemination or other use of, or >> taking of any action in reliance upon, this information by persons or >> entities other than the intended recipient is prohibited. If you received >> this in error, please contact the sender and delete the material from any >> computer. >> _________________________________________________________________________ >> >> >> _________________________________________________________________________ >> >> The information transmitted is intended only for the person or entity to >> which it is addressed and may contain confidential and/or privileged >> material. Any review, retransmission, dissemination or other use of, or >> taking of any action in reliance upon, this information by persons or >> entities other than the intended recipient is prohibited. If you received >> this in error, please contact the sender and delete the material from any >> computer. >> _________________________________________________________________________ >> <dmesg3.txt><messages.txt> >> >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss >> >> >> _________________________________________________________________________ >> >> The information transmitted is intended only for the person or entity to >> which it is addressed and may contain confidential and/or privileged >> material. Any review, retransmission, dissemination or other use of, or >> taking of any action in reliance upon, this information by persons or >> entities other than the intended recipient is prohibited. If you received >> this in error, please contact the sender and delete the material from any >> computer. >> _________________________________________________________________________ >> >> >> _________________________________________________________________________ >> >> The information transmitted is intended only for the person or entity to >> which it is addressed and may contain confidential and/or privileged >> material. Any review, retransmission, dissemination or other use of, or >> taking of any action in reliance upon, this information by persons or >> entities other than the intended recipient is prohibited. If you received >> this in error, please contact the sender and delete the material from any >> computer. >> _________________________________________________________________________ > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss -- Pavan Balaji ✉️ http://www.mcs.anl.gov/~balaji _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling
by Seo, Sangmin 17 Sep '14

17 Sep '14

I have looked into your log file, but it seems that the real error happened in other process, not rank 0. The socket of rank 0 was closed because the other process died. Can you send us log files of other processes? And, can you also send us the execution result with "-print-all-exitcodes” option? For example, mpiexec -machinefile nodes -np $NUMPROCS -print-all-exitcodes $EXEC -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose -print-all-exitcodes option will show the exit codes for each process. Regards, Sangmin On Sep 17, 2014, at 12:33 PM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Any luck on finding solution on the error in the log file provided? Thank You Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant From: Abhishek Bhat Sent: Tuesday, September 16, 2014 11:36 AM To: <discuss(a)mpich.org<mailto:[email protected]>> Cc: 'sseo(a)anl.gov<mailto:[email protected]>' Subject: RE: [mpich-discuss] Error Running MPICH for Photochemical Modeling Sangmin, Sorry for the confusion, I was looking in the wrong location. Please find attached the splice of the debug file 0 where the Error is occurring. Thank You Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Tuesday, September 16, 2014 11:12 AM To: Abhishek Bhat Cc: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling The log files should be found in the directory where you execute the application. Did you run the application with debug options, -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose? — Sangmin On Sep 16, 2014, at 11:05 AM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Sangmin, I configured the MPICH with revised code and included the additional options as described. Where should I be looking for the log files? I cannot see any files generated. Thank You Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Monday, September 15, 2014 12:43 PM To: Abhishek Bhat Cc: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Sorry, “./make” should have been “make” — Sangmin On Sep 15, 2014, at 12:40 PM, Seo, Sangmin <sseo(a)anl.gov<mailto:[email protected]>> wrote: Did you run dmesg on the node which executed the rank failed? I don't see any error message from your log file. Anyway, let's try with MPICH DEBUG messages. As described inhttps://wiki.mpich.org/mpich/index.php/Debug_Event_Logging, first configure MPICH with "--enable-g=dbg,log" to enable event logging and built it. For example, $ ./configure --prefix=$INSTALL_DIR --enable-g=dbg,log $ ./make -j8 $ ./make install Then, execute your application with additional options, "-mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose." With the recent MPICH, you don't need to use mpdboot. Just execute your application with mpiexec like: mpiexec -machinefile nodes -np $NUMPROCS $EXEC -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose This will generate log files, such as dbg0-xxxx.log, dbg1-xxxx.log, etc. Since the log files may be large, it would be difficult to send them to us. If so, please take a look at each file, find error messages, and send the error message to us. And, if you can reproduce the same error with small code, it will be really helpful to figure out your problem. Could you write a simplified code and send us the code? Regards, Sangmin On Sep 15, 2014, at 10:58 AM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Sangmin, Please see attached the logs from demsg. I apologies but I am not a computer expert so it’s all Greek to me.. Can you please see if you can find any error or reason for the failure? Thank You Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Monday, September 15, 2014 9:21 AM To: Abhishek Bhat Cc: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Can you run dmesg on the node of rank 1, which is killed by signal 9, after you execute your application? You can find the reason that the process is killed at the end of dmesg output, e.g., out of memory. — Sangmin On Sep 14, 2014, at 12:37 PM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Because the application works when less intensive runs and fails for more intensive runs, it is likely that the application is requesting too many resources. When\where should I run ulimit –a and dmesg, after I get the error? If that is true, is there any way to change the environment in MPI to increase the capacity so that the increased resources can be accommodated? If I run it in new terminal – here is what I get core file size (blocks, -c) 0 data seg size (kbytes, -d) unlimited scheduling priority (-e) 0 file size (blocks, -f) unlimited pending signals (-i) 250598 max locked memory (kbytes, -l) 64 max memory size (kbytes, -m) unlimited open files (-n) 1024 pipe size (512 bytes, -p) 8 POSIX message queues (bytes, -q) 819200 real-time priority (-r) 0 stack size (kbytes, -s) 10240 cpu time (seconds, -t) unlimited max user processes (-u) 1024 virtual memory (kbytes, -v) unlimited file locks (-x) unlimited in my job, I try to set the stack size to – unlimited but I guess it is not working. Let me know. Thank you for all the help. Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Sunday, September 14, 2014 11:16 AM To: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Abhishek, Signal 9 is caused by many reasons, e.g., CPU time, out of memory, etc., but it is mostly because the application requests too many resources. You can check the environment settings with ulimit -a. And, you may find some information about your error from dmesg. Thanks, Sangmin On Sep 12, 2014, at 5:51 PM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Sangmin. I updated to mpich3 and getting the following error Fatal error in MPI_Recv: A process has failed, error stack: MPI_Recv(187).............: MPI_Recv(buf=0x7fff93840c30, count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, status=0x7fff94444f20) failed dequeue_and_set_error(865): Communication error with rank 1 rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks exit status of rank 1: killed by signal 9 Same situation, successful runs for smaller resource runs and for up to 7 processes. Error at more than 7. Here is the mpich command I am using to run from my job file… cat << ieof > nodes dfw-camx:1 dfw-camx-n1:1 dfw-camx-n2:1 dfw-camx-n3:1 dfw-camx-n4:1 dfw-camx-n5:1 dfw-camx-n6:1 dfw-camx-n7:1 ieof set NUMPROCS = 8 set RING = `wc -l nodes | awk '{print $1}'` mpdboot -n $RING -f nodes –verbose if( ! { mpiexec -machinefile nodes -np $NUMPROCS $EXEC } ) then mpdallexit exit endif For a successful run the NUMPROCS has to be < = 7. Any help is much appreciated. Thank You Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Friday, September 12, 2014 1:11 PM To: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Hi Abhishek, Can you try with the recent MPICH release to see if the same error happens? You can download the recent release, 3.1.2, from http://www.mpich.org/downloads/. Thanks, Sangmin On Sep 12, 2014, at 12:59 PM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: I am running a photochemical modeling on Linux cluster (CentOS_64 bit) with 1 master and 8 slave nodes with quad core (intel i7) on each node. I have two scenarios, in first scenario, I am running less data intensive run on all 8 nodes (NUMPROCS = 9) and the run will go fine. When running same configuration for a more intense run, I am getting following error. Fatal error in MPI_Recv: Other MPI error, error stack: MPI_Recv(187).....................: MPI_Recv(buf=0x7fff989d53b0, count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, status=0x7fff995d96a0) failed MPIDI_CH3I_Progress(150)..........: MPID_nem_mpich2_blocking_recv(948): MPID_nem_tcp_connpoll(1720).......: state_commrdy_handler(1556).......: MPID_nem_tcp_recv_handler(1446)...: socket closed rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks exit status of rank 1: killed by signal 9 If I run the program with smaller nodes (smaller than 7 NUMPROCS) the run goes fine. It appears that the rank 1 (my first node) is collectively causing all the ranks, but I could identify why. I tried following solutions – 1. Increased master memory to 32 gb 2. Increased all nodes memory to 32 gb 3. Exchanged the rank 1 to different node in the parallel. In all situations, I am getting this error. Surprisingly, when I am running smaller (less data intensive runs), I am not getting this error even if I increase the NUMPROCS to 32 processes. Any help will be highly appreciated. I am running mpich 1.4 Thank You Abhishek …………………………………………………………………………………………………. Abhishek Bhat, PhD, EPI, Senior Consultant Trinity Consultants 12770 Merit Drive, Suite 900 | Dallas, Texas 75251 Office: 972-661-8100| Mobile: 806-281-7617 Email: abhat(a)trinityconsultants.com<mailto:[email protected]> | LinkedIn: www.linkedin.com/in/abhattrinityconsultants<http://www.linkedin.com/in/abhattrinityconsultants> Stay current on environmental issues. Subscribe<http://www.trinityconsultants.com/Subscribe/> today to receive Trinity's free Environmental Quarterly<http://www.trinityconsultants.com/EnvironmentalQuarterly/>. Learn about Trinity’s courses<http://www.trinityconsultants.com/Training/> for environmental professionals. <image001.gif><http://www.linkedin.com/company/trinity-consultants> <image002.gif><http://www.facebook.com/TrinityConsults> <image003.gif><http://twitter.com/trinityconsults> <image004.gif><http://www.youtube.com/trinityconsultants> <image005.jpg> _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _______________________________________________ discuss mailing list discuss(a)mpich.org<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _______________________________________________ discuss mailing list discuss(a)mpich.org<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ <dmesg3.txt><messages.txt> _______________________________________________ discuss mailing list discuss(a)mpich.org<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] MPI log via MPE on CRAY XC30 machine
by Balaji, Pavan 17 Sep '14

17 Sep '14

You’ll need to download the latest version. http://www.mpich.org/static/mpe/downloads/ I’ll need to figure out the exact download tarballs and clean up the above link, but for now you can pick the latest version of MPE2. — Pavan On Sep 17, 2014, at 12:32 PM, Milind Chabbi <Milind.Chabbi(a)rice.edu> wrote: > Pavan, > > Now, I am trying MPE2 present inside mpich2-1.4.1p1. It runs into > several compilation issues (see below). Do you have any suggestions? > > Can you tell me how MPE2 achieves the logging? Does it divert MPI_ > calls through its own functions? On static libraries does it use > linker wrapping? For a large application simply changing the last > linker step to use mpecc would suffice or does it need the whole > application to be recompiled with mpecc wrapper? > > > -------------------------------------------------------- > **** Making src/wrappers .... > > make --no-print-directory build_lib_bin > > cc -I.. -I../../../../src/wrappers/include > -I/global/homes/m/mc29/software/mpich2-1.4.1p1/src/mpe2/BUILD/include > -I../../.. -I../../../../src/wrappers/../../include -c > ../../../../src/wrappers/src/log_mpi_util.c > > cc -I.. -I../../../../src/wrappers/include > -I/global/homes/m/mc29/software/mpich2-1.4.1p1/src/mpe2/BUILD/include > -I../../.. -I../../../../src/wrappers/../../include -c > ../../../../src/wrappers/src/log_mpi_core.c > > ../../../../src/wrappers/src/log_mpi_core.c: In function 'MPI_Allgather': > > ../../../../src/wrappers/src/log_mpi_core.c:1550:8: error: argument > 'sendbuf' doesn't match prototype > > void * sendbuf; > > ^ > > In file included from ../../../../src/wrappers/src/log_mpi_core.c:10:0: > > /opt/cray/mpt/6.3.1/gni/mpich2-gnu/48/include/mpi.h:945:5: error: > prototype declaration > > int MPI_Allgather(const void *sendbuf, int sendcount, MPI_Datatype > sendtype, void *recvbuf, > > ^ > -------------------------------------------------------- > > On Wed, Sep 17, 2014 at 6:20 AM, Balaji, Pavan <balaji(a)anl.gov> wrote: >> Milind, >> >> Did you try this link? >> >> http://wiki.mpich.org/mpich/index.php/MPE_by_example >> >> — Pavan >> >> On Sep 17, 2014, at 12:26 AM, Milind Chabbi <milind.chabbi(a)rice.edu> wrote: >> >>> I am trying to gather MPI logs on CRAY XC30 (Edison machine at NERSC.) >>> I built MPE 2-1.3 (ftp://ftp.mcs.anl.gov/pub/mpi/mpe/mpe2.tar.gz) with >>> the following configure command: >>> >>> ./configure MPI_CC=cc F77=ftn MPI_F77=ftn --prefix=/XXXXX/mpe2-1.3.0-install >>> >>> I compiled a simple application with the following command: >>> /XXXX/mpe2-1.3.0-install/bin/mpecc test1.cpp -mpilog >>> >>> The code compiled fine, but the execution did not generate any log files. >>> >>> I am trying to generate logs files of MPI calls to view with Jumpshot >>> on programs compiled on Cray XC30. Can you suggest the steps needed to >>> get this working? >>> >>> Thanks >>> -Milind >>> _______________________________________________ >>> discuss mailing list discuss(a)mpich.org >>> To manage subscription options or unsubscribe: >>> https://lists.mpich.org/mailman/listinfo/discuss >> >> -- >> Pavan Balaji ✉️ >> http://www.mcs.anl.gov/~balaji >> >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss -- Pavan Balaji ✉️ http://www.mcs.anl.gov/~balaji _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling
by Abhishek Bhat 17 Sep '14

17 Sep '14

Any luck on finding solution on the error in the log file provided? Thank You Abhishek ................................................................................................................ Abhishek Bhat, PhD, EPI, Senior Consultant From: Abhishek Bhat Sent: Tuesday, September 16, 2014 11:36 AM To: <discuss(a)mpich.org> Cc: 'sseo(a)anl.gov' Subject: RE: [mpich-discuss] Error Running MPICH for Photochemical Modeling Sangmin, Sorry for the confusion, I was looking in the wrong location. Please find attached the splice of the debug file 0 where the Error is occurring. Thank You Abhishek ................................................................................................................ Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Tuesday, September 16, 2014 11:12 AM To: Abhishek Bhat Cc: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling The log files should be found in the directory where you execute the application. Did you run the application with debug options, -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose? - Sangmin On Sep 16, 2014, at 11:05 AM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Sangmin, I configured the MPICH with revised code and included the additional options as described. Where should I be looking for the log files? I cannot see any files generated. Thank You Abhishek ................................................................................................................ Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Monday, September 15, 2014 12:43 PM To: Abhishek Bhat Cc: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Sorry, "./make" should have been "make" - Sangmin On Sep 15, 2014, at 12:40 PM, Seo, Sangmin <sseo(a)anl.gov<mailto:[email protected]>> wrote: Did you run dmesg on the node which executed the rank failed? I don't see any error message from your log file. Anyway, let's try with MPICH DEBUG messages. As described inhttps://wiki.mpich.org/mpich/index.php/Debug_Event_Logging, first configure MPICH with "--enable-g=dbg,log" to enable event logging and built it. For example, $ ./configure --prefix=$INSTALL_DIR --enable-g=dbg,log $ ./make -j8 $ ./make install Then, execute your application with additional options, "-mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose." With the recent MPICH, you don't need to use mpdboot. Just execute your application with mpiexec like: mpiexec -machinefile nodes -np $NUMPROCS $EXEC -mpich-dbg=file -mpich-dbg-class=all -mpich-dbg-level=verbose This will generate log files, such as dbg0-xxxx.log, dbg1-xxxx.log, etc. Since the log files may be large, it would be difficult to send them to us. If so, please take a look at each file, find error messages, and send the error message to us. And, if you can reproduce the same error with small code, it will be really helpful to figure out your problem. Could you write a simplified code and send us the code? Regards, Sangmin On Sep 15, 2014, at 10:58 AM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Sangmin, Please see attached the logs from demsg. I apologies but I am not a computer expert so it's all Greek to me.. Can you please see if you can find any error or reason for the failure? Thank You Abhishek ................................................................................................................ Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Monday, September 15, 2014 9:21 AM To: Abhishek Bhat Cc: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Can you run dmesg on the node of rank 1, which is killed by signal 9, after you execute your application? You can find the reason that the process is killed at the end of dmesg output, e.g., out of memory. - Sangmin On Sep 14, 2014, at 12:37 PM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Because the application works when less intensive runs and fails for more intensive runs, it is likely that the application is requesting too many resources. When\where should I run ulimit -a and dmesg, after I get the error? If that is true, is there any way to change the environment in MPI to increase the capacity so that the increased resources can be accommodated? If I run it in new terminal - here is what I get core file size (blocks, -c) 0 data seg size (kbytes, -d) unlimited scheduling priority (-e) 0 file size (blocks, -f) unlimited pending signals (-i) 250598 max locked memory (kbytes, -l) 64 max memory size (kbytes, -m) unlimited open files (-n) 1024 pipe size (512 bytes, -p) 8 POSIX message queues (bytes, -q) 819200 real-time priority (-r) 0 stack size (kbytes, -s) 10240 cpu time (seconds, -t) unlimited max user processes (-u) 1024 virtual memory (kbytes, -v) unlimited file locks (-x) unlimited in my job, I try to set the stack size to - unlimited but I guess it is not working. Let me know. Thank you for all the help. Abhishek ................................................................................................................ Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Sunday, September 14, 2014 11:16 AM To: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Abhishek, Signal 9 is caused by many reasons, e.g., CPU time, out of memory, etc., but it is mostly because the application requests too many resources. You can check the environment settings with ulimit -a. And, you may find some information about your error from dmesg. Thanks, Sangmin On Sep 12, 2014, at 5:51 PM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: Sangmin. I updated to mpich3 and getting the following error Fatal error in MPI_Recv: A process has failed, error stack: MPI_Recv(187).............: MPI_Recv(buf=0x7fff93840c30, count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, status=0x7fff94444f20) failed dequeue_and_set_error(865): Communication error with rank 1 rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks exit status of rank 1: killed by signal 9 Same situation, successful runs for smaller resource runs and for up to 7 processes. Error at more than 7. Here is the mpich command I am using to run from my job file... cat << ieof > nodes dfw-camx:1 dfw-camx-n1:1 dfw-camx-n2:1 dfw-camx-n3:1 dfw-camx-n4:1 dfw-camx-n5:1 dfw-camx-n6:1 dfw-camx-n7:1 ieof set NUMPROCS = 8 set RING = `wc -l nodes | awk '{print $1}'` mpdboot -n $RING -f nodes -verbose if( ! { mpiexec -machinefile nodes -np $NUMPROCS $EXEC } ) then mpdallexit exit endif For a successful run the NUMPROCS has to be < = 7. Any help is much appreciated. Thank You Abhishek ................................................................................................................ Abhishek Bhat, PhD, EPI, Senior Consultant From: Seo, Sangmin [mailto:[email protected]] Sent: Friday, September 12, 2014 1:11 PM To: <discuss(a)mpich.org<mailto:[email protected]>> Subject: Re: [mpich-discuss] Error Running MPICH for Photochemical Modeling Hi Abhishek, Can you try with the recent MPICH release to see if the same error happens? You can download the recent release, 3.1.2, from http://www.mpich.org/downloads/. Thanks, Sangmin On Sep 12, 2014, at 12:59 PM, Abhishek Bhat <abhat(a)trinityconsultants.com<mailto:[email protected]>> wrote: I am running a photochemical modeling on Linux cluster (CentOS_64 bit) with 1 master and 8 slave nodes with quad core (intel i7) on each node. I have two scenarios, in first scenario, I am running less data intensive run on all 8 nodes (NUMPROCS = 9) and the run will go fine. When running same configuration for a more intense run, I am getting following error. Fatal error in MPI_Recv: Other MPI error, error stack: MPI_Recv(187).....................: MPI_Recv(buf=0x7fff989d53b0, count=644490, MPI_REAL, src=1, tag=14131, MPI_COMM_WORLD, status=0x7fff995d96a0) failed MPIDI_CH3I_Progress(150)..........: MPID_nem_mpich2_blocking_recv(948): MPID_nem_tcp_connpoll(1720).......: state_commrdy_handler(1556).......: MPID_nem_tcp_recv_handler(1446)...: socket closed rank 1 in job 1 dfw-camx_55000 caused collective abort of all ranks exit status of rank 1: killed by signal 9 If I run the program with smaller nodes (smaller than 7 NUMPROCS) the run goes fine. It appears that the rank 1 (my first node) is collectively causing all the ranks, but I could identify why. I tried following solutions - 1. Increased master memory to 32 gb 2. Increased all nodes memory to 32 gb 3. Exchanged the rank 1 to different node in the parallel. In all situations, I am getting this error. Surprisingly, when I am running smaller (less data intensive runs), I am not getting this error even if I increase the NUMPROCS to 32 processes. Any help will be highly appreciated. I am running mpich 1.4 Thank You Abhishek ................................................................................................................ Abhishek Bhat, PhD, EPI, Senior Consultant Trinity Consultants 12770 Merit Drive, Suite 900 | Dallas, Texas 75251 Office: 972-661-8100| Mobile: 806-281-7617 Email: abhat(a)trinityconsultants.com<mailto:[email protected]> | LinkedIn: www.linkedin.com/in/abhattrinityconsultants<http://www.linkedin.com/in/abhattrinityconsultants> Stay current on environmental issues. Subscribe<http://www.trinityconsultants.com/Subscribe/> today to receive Trinity's free Environmental Quarterly<http://www.trinityconsultants.com/EnvironmentalQuarterly/>. Learn about Trinity's courses<http://www.trinityconsultants.com/Training/> for environmental professionals. <image001.gif><http://www.linkedin.com/company/trinity-consultants> <image002.gif><http://www.facebook.com/TrinityConsults> <image003.gif><http://twitter.com/trinityconsults> <image004.gif><http://www.youtube.com/trinityconsultants> <image005.jpg> _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _______________________________________________ discuss mailing list discuss(a)mpich.org<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _______________________________________________ discuss mailing list discuss(a)mpich.org<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ <dmesg3.txt><messages.txt> _______________________________________________ discuss mailing list discuss(a)mpich.org<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ -- _________________________________________________________________________ The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. _________________________________________________________________________ _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] MPI log via MPE on CRAY XC30 machine
by Milind Chabbi 17 Sep '14

17 Sep '14

Pavan, Now, I am trying MPE2 present inside mpich2-1.4.1p1. It runs into several compilation issues (see below). Do you have any suggestions? Can you tell me how MPE2 achieves the logging? Does it divert MPI_ calls through its own functions? On static libraries does it use linker wrapping? For a large application simply changing the last linker step to use mpecc would suffice or does it need the whole application to be recompiled with mpecc wrapper? -------------------------------------------------------- **** Making src/wrappers .... make --no-print-directory build_lib_bin cc -I.. -I../../../../src/wrappers/include -I/global/homes/m/mc29/software/mpich2-1.4.1p1/src/mpe2/BUILD/include -I../../.. -I../../../../src/wrappers/../../include -c ../../../../src/wrappers/src/log_mpi_util.c cc -I.. -I../../../../src/wrappers/include -I/global/homes/m/mc29/software/mpich2-1.4.1p1/src/mpe2/BUILD/include -I../../.. -I../../../../src/wrappers/../../include -c ../../../../src/wrappers/src/log_mpi_core.c ../../../../src/wrappers/src/log_mpi_core.c: In function 'MPI_Allgather': ../../../../src/wrappers/src/log_mpi_core.c:1550:8: error: argument 'sendbuf' doesn't match prototype void * sendbuf; ^ In file included from ../../../../src/wrappers/src/log_mpi_core.c:10:0: /opt/cray/mpt/6.3.1/gni/mpich2-gnu/48/include/mpi.h:945:5: error: prototype declaration int MPI_Allgather(const void *sendbuf, int sendcount, MPI_Datatype sendtype, void *recvbuf, ^ -------------------------------------------------------- On Wed, Sep 17, 2014 at 6:20 AM, Balaji, Pavan <balaji(a)anl.gov> wrote: > Milind, > > Did you try this link? > > http://wiki.mpich.org/mpich/index.php/MPE_by_example > > — Pavan > > On Sep 17, 2014, at 12:26 AM, Milind Chabbi <milind.chabbi(a)rice.edu> wrote: > >> I am trying to gather MPI logs on CRAY XC30 (Edison machine at NERSC.) >> I built MPE 2-1.3 (ftp://ftp.mcs.anl.gov/pub/mpi/mpe/mpe2.tar.gz) with >> the following configure command: >> >> ./configure MPI_CC=cc F77=ftn MPI_F77=ftn --prefix=/XXXXX/mpe2-1.3.0-install >> >> I compiled a simple application with the following command: >> /XXXX/mpe2-1.3.0-install/bin/mpecc test1.cpp -mpilog >> >> The code compiled fine, but the execution did not generate any log files. >> >> I am trying to generate logs files of MPI calls to view with Jumpshot >> on programs compiled on Cray XC30. Can you suggest the steps needed to >> get this working? >> >> Thanks >> -Milind >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss > > -- > Pavan Balaji ✉️ > http://www.mcs.anl.gov/~balaji > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] GFORTRAN on MinGW doesn't link to MPICH-2
by Bland, Wesley B. 17 Sep '14

17 Sep '14

Hi Miao, I’m sorry. All we can do at this point is provide the download. We don’t have any developers left to support Windows. If you need to run MPI on Windows, we suggest using Microsoft MPI as it is still well supported. You can also use Intel MPI, but it is not free. Thanks, Wesley > On Sep 17, 2014, at 11:38 AM, Miao Li <rockymountai(a)gmail.com> wrote: > > Hello, Bland > > Thank you for your input, but 1.4.1p is exactly what I am using now, > it should be recognized by the system, I believe. > > It is downloaded from > http://www.mcs.anl.gov/research/projects/mpich2staging/goodell/downloads/in… > > On Wed, Sep 17, 2014 at 10:45 AM, <discuss-request(a)mpich.org> wrote: >> Send discuss mailing list submissions to >> discuss(a)mpich.org >> >> To subscribe or unsubscribe via the World Wide Web, visit >> https://lists.mpich.org/mailman/listinfo/discuss >> or, via email, send a message with subject or body 'help' to >> discuss-request(a)mpich.org >> >> You can reach the person managing the list at >> discuss-owner(a)mpich.org >> >> When replying, please edit your Subject line so it is more specific >> than "Re: Contents of discuss digest..." >> >> >> Today's Topics: >> >> 1. mpich-3.2a for Blue Gene /Q omits spi libraries from the >> wrappers (William Scullin) >> 2. MPI log via MPE on CRAY XC30 machine (Milind Chabbi) >> 3. Passwords on small cluster (Bob Ilgner) >> 4. Re: Passwords on small cluster (Reuti) >> 5. Re: MPI log via MPE on CRAY XC30 machine (Balaji, Pavan) >> 6. GFORTRAN on MinGW doesn't link (Miao Li) >> 7. GFORTRAN on MinGW doesn't link to MPICH-2 (Miao Li) >> 8. Re: GFORTRAN on MinGW doesn't link (Bland, Wesley B.) >> >> >> ---------------------------------------------------------------------- >> >> Message: 1 >> Date: Tue, 16 Sep 2014 16:06:11 -0500 >> From: William Scullin <wscullin(a)alcf.anl.gov> >> To: <discuss(a)mpich.org> >> Subject: [mpich-discuss] mpich-3.2a for Blue Gene /Q omits spi >> libraries from the wrappers >> Message-ID: >> <CAFmX=Zya7G_TB939v9pLnykzRUyE0O_p5p_oRn4SY0QrHz=nMA(a)mail.gmail.com> >> Content-Type: text/plain; charset="UTF-8" >> >> When building mpich-3.2a for Blue Gene /Q and following the same >> procedure used for building mpich-3.1.2 for BG/Q, the required linking >> information for spi and pami is omitted from the wrappers. I'm not >> sure if this is intentional or not. >> >> Thanks, >> William >> >> >> Patching the wrappers to reflect the required linking gives the following diff : >> >> [wscullin@vestasn1 ~]$ diff >> /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc >> /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc-postpatch >> 265c265 >> < $Show $CC $PROFILE_INCPATHS >> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib >> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir >> -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi >> $PROFILE_POSTLIB >> --- >>> $Show $CC $PROFILE_INCPATHS -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi $PROFILE_POSTLIB -lpami-gcc -lpthread -lSPI -lSPI_cnk -lrt -lstdc++ >> >> Full diff of mpich-3.1.2 versus 3.2a wrappers: >> >> [wscullin@vestasn1 ~]$ diff >> /projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/bin/mpicc >> /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc >> 30,34c30,34 >> < prefix=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7 >> < exec_prefix=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7 >> < sysconfdir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/etc >> < includedir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/include >> < libdir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/lib >> --- >>> prefix=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7 >>> exec_prefix=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7 >>> sysconfdir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/etc >>> includedir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/include >>> libdir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/lib >> 40c40 >> < MPICH_VERSION="3.1.2" >> --- >>> MPICH_VERSION="3.2a1" >> 262c262 >> < $Show $CC $PROFILE_INCPATHS >> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib >> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib >> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib >> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir >> --- >>> $Show $CC $PROFILE_INCPATHS -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir >> 265c265 >> < $Show $CC $PROFILE_INCPATHS >> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib >> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib >> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib >> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir >> -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi >> $PROFILE_POSTLIB -lpami-gcc -lpthread -lSPI -lSPI_cnk -lrt -lstdc++ >> --- >>> $Show $CC $PROFILE_INCPATHS -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi $PROFILE_POSTLIB >> >> >> ------------------------------ >> >> Message: 2 >> Date: Wed, 17 Sep 2014 00:26:05 -0500 >> From: Milind Chabbi <Milind.Chabbi(a)rice.edu> >> To: mpich-discuss(a)mcs.anl.gov >> Subject: [mpich-discuss] MPI log via MPE on CRAY XC30 machine >> Message-ID: >> <CAMmz+Y=vvO5vkwyXaKeGg1BKB+Z7zbktZJiwU3rkMjAh8Z058Q(a)mail.gmail.com> >> Content-Type: text/plain; charset=UTF-8 >> >> I am trying to gather MPI logs on CRAY XC30 (Edison machine at NERSC.) >> I built MPE 2-1.3 (ftp://ftp.mcs.anl.gov/pub/mpi/mpe/mpe2.tar.gz) with >> the following configure command: >> >> ./configure MPI_CC=cc F77=ftn MPI_F77=ftn --prefix=/XXXXX/mpe2-1.3.0-install >> >> I compiled a simple application with the following command: >> /XXXX/mpe2-1.3.0-install/bin/mpecc test1.cpp -mpilog >> >> The code compiled fine, but the execution did not generate any log files. >> >> I am trying to generate logs files of MPI calls to view with Jumpshot >> on programs compiled on Cray XC30. Can you suggest the steps needed to >> get this working? >> >> Thanks >> -Milind >> >> >> ------------------------------ >> >> Message: 3 >> Date: Wed, 17 Sep 2014 08:41:00 +0200 >> From: Bob Ilgner <bobilgner(a)gmail.com> >> To: discuss(a)mpich.org >> Subject: [mpich-discuss] Passwords on small cluster >> Message-ID: >> <CAKv15b_xROGRhPzxU3ZXka2KiC2-xz8+Vr1DHc=NYFHE-fQ6MA(a)mail.gmail.com> >> Content-Type: text/plain; charset="utf-8" >> >> Dear all, >> >> >> I am trying to run my mpi job on a small cluster with 5 nodes. When I run >> >> mpirun -n 5 --host node01,node02,node03,node04,node05 ./hesp >> >> the system requests a password for node01. >> >> if I run the job only on node05 then no pasword is requested and the job >> runs OK Is there some way I can include a password in the host file, or >> otherwise ? >> >> regards. >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: <http://lists.mpich.org/pipermail/discuss/attachments/20140917/04ab8446/atta…> >> >> ------------------------------ >> >> Message: 4 >> Date: Wed, 17 Sep 2014 13:00:32 +0200 >> From: Reuti <reuti(a)staff.uni-marburg.de> >> To: discuss(a)mpich.org >> Subject: Re: [mpich-discuss] Passwords on small cluster >> Message-ID: >> <CBCC63B9-F266-4B59-8961-EFB22FEFD635(a)staff.uni-marburg.de> >> Content-Type: text/plain; charset=us-ascii >> >> Hi, >> >> Am 17.09.2014 um 08:41 schrieb Bob Ilgner: >> >>> I am trying to run my mpi job on a small cluster with 5 nodes. When I run >>> >>> mpirun -n 5 --host node01,node02,node03,node04,node05 ./hesp >>> >>> the system requests a password for node01. >>> >>> if I run the job only on node05 then no pasword is requested and the job runs OK Is there some way I can include a password in the host file, or otherwise ? >> >> You will have to set up some kind of passwordless access, either by a passphraseless SSH-key (if you are the only user), or hostbased authentication (to make the setup one time for all users). >> >> https://www.open-mpi.org/faq/?category=rsh#ssh-keys (although this page is from the Open MPI site, the constraints are the same as in MPICH) >> >> or: >> >> https://arc.liv.ac.uk/SGE/howto/hostbased-ssh.html >> >> -- Reuti >> >> PS: You could also use an SSH-agent http://www.unixwiz.net/techtips/ssh-agent-forwarding.html which will answer all further requests for the passphrase after you entered it one time. >> >> ------------------------------ >> >> Message: 5 >> Date: Wed, 17 Sep 2014 11:20:50 +0000 >> From: "Balaji, Pavan" <balaji(a)anl.gov> >> To: "discuss(a)mpich.org" <discuss(a)mpich.org> >> Subject: Re: [mpich-discuss] MPI log via MPE on CRAY XC30 machine >> Message-ID: <77BB388D-E452-48B5-89C2-DA16D773F2CA(a)anl.gov> >> Content-Type: text/plain; charset="utf-8" >> >> Milind, >> >> Did you try this link? >> >> http://wiki.mpich.org/mpich/index.php/MPE_by_example >> >> ? Pavan >> >> On Sep 17, 2014, at 12:26 AM, Milind Chabbi <milind.chabbi(a)rice.edu> wrote: >> >>> I am trying to gather MPI logs on CRAY XC30 (Edison machine at NERSC.) >>> I built MPE 2-1.3 (ftp://ftp.mcs.anl.gov/pub/mpi/mpe/mpe2.tar.gz) with >>> the following configure command: >>> >>> ./configure MPI_CC=cc F77=ftn MPI_F77=ftn --prefix=/XXXXX/mpe2-1.3.0-install >>> >>> I compiled a simple application with the following command: >>> /XXXX/mpe2-1.3.0-install/bin/mpecc test1.cpp -mpilog >>> >>> The code compiled fine, but the execution did not generate any log files. >>> >>> I am trying to generate logs files of MPI calls to view with Jumpshot >>> on programs compiled on Cray XC30. Can you suggest the steps needed to >>> get this working? >>> >>> Thanks >>> -Milind >>> _______________________________________________ >>> discuss mailing list discuss(a)mpich.org >>> To manage subscription options or unsubscribe: >>> https://lists.mpich.org/mailman/listinfo/discuss >> >> -- >> Pavan Balaji ?? >> http://www.mcs.anl.gov/~balaji >> >> >> ------------------------------ >> >> Message: 6 >> Date: Wed, 17 Sep 2014 10:39:35 -0500 >> From: Miao Li <rockymountai(a)gmail.com> >> To: mpich-discuss(a)mcs.anl.gov >> Subject: [mpich-discuss] GFORTRAN on MinGW doesn't link >> Message-ID: >> <CAKOfFceOwHjAvvpWe5+WPnWm9-Bjn6iXCcsNGbXtFBcuHZbGVA(a)mail.gmail.com> >> Content-Type: text/plain; charset=UTF-8 >> >> Hello, Folks >> >> Sorry to bug you guys with this but I am sure there are tons of people >> have encountered this before, I am creating a MPI program with MPICH-2 >> and gfortran on Windows 8 64 with MinGW, but for some reason the >> MPICH-2 can't be linked and errors are: >> >> hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_' >> hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_' >> hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_' >> hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_' >> hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_' >> hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_' >> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: >> C:\Users\<myid>\AppData\L >> ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame' >> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: >> final link failed: Inval >> id operation >> collect2.exe: error: ld returned 1 exit status >> >> This is just a "hello world" program and I followed the instructions >> in the README.winbin.rtf file >> >> " >> >> 2) add ?I?mpich2\include >> >> 3) add ?L?mpich2\lib >> >> " >> >> Some people believe that the "-lmpi" option should be used at the very >> end of command, I did that but doesn't help. >> >> I even tried compiling without any makefile but just a single command like: >> >>> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi >> >> But still it doesn't work for me. >> >> Did any of you guys have encountered this before? >> >> I really look forward your response, any inputs are highly appreciated!!! >> >> Thank you so much! >> >> Best Regard >> >> NOTE: >> >> Here is my simple makefile: >> >> F90 = gfortran >> MPI_DIR = /c/Program\ Files/MPICH2 >> MPI_LIB_DIR = $(MPI_DIR)/lib >> MPI_LIB_INCLUDE = $(MPI_DIR)/include >> MPI_LIB = -L$(MPI_LIB_DIR) -lmpi >> MPI_INCLUDE = -I$(MPI_LIB_INCLUDE) >> SRC = hello_mpi.f90 >> OBJ = $(SRC:.f90=.o) >> EXEC = hello >> $(EXEC): $(OBJ) >> $(F90) -o $(EXEC) $(OBJ) $(MPI_LIB) >> $(OBJ) : $(SRC) >> $(F90) $(MPI_INCLUDE) -c $< >> clean: >> rm *.o >> >> >> ------------------------------ >> >> Message: 7 >> Date: Wed, 17 Sep 2014 10:43:04 -0500 >> From: Miao Li <rockymountai(a)gmail.com> >> To: discuss(a)mpich.org >> Subject: [mpich-discuss] GFORTRAN on MinGW doesn't link to MPICH-2 >> Message-ID: >> <CAKOfFceNJnTYnzcWQgq9_qwJvpotgk8eroN=Oq--4Me-LJiG=w(a)mail.gmail.com> >> Content-Type: text/plain; charset=UTF-8 >> >> Hello, Folks >> >> Sorry to bug you guys with this but I am sure there are tons of people >> have encountered this before, I am creating a MPI program with MPICH-2 >> and gfortran on Windows 8 64 with MinGW, but for some reason the >> MPICH-2 can't be linked and errors are: >> >> hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_' >> hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_' >> hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_' >> hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_' >> hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_' >> hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_' >> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: >> C:\Users\<myid>\AppData\L >> ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame' >> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: >> final link failed: Inval >> id operation >> collect2.exe: error: ld returned 1 exit status >> >> This is just a "hello world" program and I followed the instructions >> in the README.winbin.rtf file >> >> " >> >> 2) add ?I?mpich2\include >> >> 3) add ?L?mpich2\lib >> >> " >> >> Some people believe that the "-lmpi" option should be used at the very >> end of command, I did that but doesn't help. >> >> I even tried compiling without any makefile but just a single command like: >> >>> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi >> >> But still it doesn't work for me. >> >> Did any of you guys have encountered this before? >> >> I really look forward your response, any inputs are highly appreciated!!! >> >> Thank you so much! >> >> Best Regard >> >> NOTE: >> >> Here is my simple makefile: >> >> F90 = gfortran >> MPI_DIR = /c/Program\ Files/MPICH2 >> MPI_LIB_DIR = $(MPI_DIR)/lib >> MPI_LIB_INCLUDE = $(MPI_DIR)/include >> MPI_LIB = -L$(MPI_LIB_DIR) -lmpi >> MPI_INCLUDE = -I$(MPI_LIB_INCLUDE) >> SRC = hello_mpi.f90 >> OBJ = $(SRC:.f90=.o) >> EXEC = hello >> $(EXEC): $(OBJ) >> $(F90) -o $(EXEC) $(OBJ) $(MPI_LIB) >> $(OBJ) : $(SRC) >> $(F90) $(MPI_INCLUDE) -c $< >> clean: >> rm *.o >> >> >> ------------------------------ >> >> Message: 8 >> Date: Wed, 17 Sep 2014 15:45:07 +0000 >> From: "Bland, Wesley B." <wbland(a)anl.gov> >> To: "discuss(a)mpich.org" <discuss(a)mpich.org> >> Cc: "mpich-discuss(a)mcs.anl.gov" <mpich-discuss(a)mcs.anl.gov> >> Subject: Re: [mpich-discuss] GFORTRAN on MinGW doesn't link >> Message-ID: <667114D6-5B30-4F87-8AD4-857793E47DFA(a)anl.gov> >> Content-Type: text/plain; charset="utf-8" >> >> Unfortunately, we haven't supported Windows since MPICH version 1.4.1p1. You can find out more at the FAQ page: http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can… >> >> Thanks, >> Wesley >> >>> On Sep 17, 2014, at 10:39 AM, Miao Li <rockymountai(a)gmail.com> wrote: >>> >>> Hello, Folks >>> >>> Sorry to bug you guys with this but I am sure there are tons of people >>> have encountered this before, I am creating a MPI program with MPICH-2 >>> and gfortran on Windows 8 64 with MinGW, but for some reason the >>> MPICH-2 can't be linked and errors are: >>> >>> hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_' >>> hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_' >>> hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_' >>> hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_' >>> hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_' >>> hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_' >>> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: >>> C:\Users\<myid>\AppData\L >>> ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame' >>> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: >>> final link failed: Inval >>> id operation >>> collect2.exe: error: ld returned 1 exit status >>> >>> This is just a "hello world" program and I followed the instructions >>> in the README.winbin.rtf file >>> >>> " >>> >>> 2) add ?I?mpich2\include >>> >>> 3) add ?L?mpich2\lib >>> >>> " >>> >>> Some people believe that the "-lmpi" option should be used at the very >>> end of command, I did that but doesn't help. >>> >>> I even tried compiling without any makefile but just a single command like: >>> >>>> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi >>> >>> But still it doesn't work for me. >>> >>> Did any of you guys have encountered this before? >>> >>> I really look forward your response, any inputs are highly appreciated!!! >>> >>> Thank you so much! >>> >>> Best Regard >>> >>> NOTE: >>> >>> Here is my simple makefile: >>> >>> F90 = gfortran >>> MPI_DIR = /c/Program\ Files/MPICH2 >>> MPI_LIB_DIR = $(MPI_DIR)/lib >>> MPI_LIB_INCLUDE = $(MPI_DIR)/include >>> MPI_LIB = -L$(MPI_LIB_DIR) -lmpi >>> MPI_INCLUDE = -I$(MPI_LIB_INCLUDE) >>> SRC = hello_mpi.f90 >>> OBJ = $(SRC:.f90=.o) >>> EXEC = hello >>> $(EXEC): $(OBJ) >>> $(F90) -o $(EXEC) $(OBJ) $(MPI_LIB) >>> $(OBJ) : $(SRC) >>> $(F90) $(MPI_INCLUDE) -c $< >>> clean: >>> rm *.o >>> _______________________________________________ >>> discuss mailing list discuss(a)mpich.org >>> To manage subscription options or unsubscribe: >>> https://lists.mpich.org/mailman/listinfo/discuss >> >> >> ------------------------------ >> >> _______________________________________________ >> discuss mailing list >> discuss(a)mpich.org >> https://lists.mpich.org/mailman/listinfo/discuss >> >> End of discuss Digest, Vol 23, Issue 34 >> *************************************** > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] GFORTRAN on MinGW doesn't link to MPICH-2
by Miao Li 17 Sep '14

17 Sep '14

Hello, Bland Thank you for your input, but 1.4.1p is exactly what I am using now, it should be recognized by the system, I believe. It is downloaded from http://www.mcs.anl.gov/research/projects/mpich2staging/goodell/downloads/in… On Wed, Sep 17, 2014 at 10:45 AM, <discuss-request(a)mpich.org> wrote: > Send discuss mailing list submissions to > discuss(a)mpich.org > > To subscribe or unsubscribe via the World Wide Web, visit > https://lists.mpich.org/mailman/listinfo/discuss > or, via email, send a message with subject or body 'help' to > discuss-request(a)mpich.org > > You can reach the person managing the list at > discuss-owner(a)mpich.org > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of discuss digest..." > > > Today's Topics: > > 1. mpich-3.2a for Blue Gene /Q omits spi libraries from the > wrappers (William Scullin) > 2. MPI log via MPE on CRAY XC30 machine (Milind Chabbi) > 3. Passwords on small cluster (Bob Ilgner) > 4. Re: Passwords on small cluster (Reuti) > 5. Re: MPI log via MPE on CRAY XC30 machine (Balaji, Pavan) > 6. GFORTRAN on MinGW doesn't link (Miao Li) > 7. GFORTRAN on MinGW doesn't link to MPICH-2 (Miao Li) > 8. Re: GFORTRAN on MinGW doesn't link (Bland, Wesley B.) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Tue, 16 Sep 2014 16:06:11 -0500 > From: William Scullin <wscullin(a)alcf.anl.gov> > To: <discuss(a)mpich.org> > Subject: [mpich-discuss] mpich-3.2a for Blue Gene /Q omits spi > libraries from the wrappers > Message-ID: > <CAFmX=Zya7G_TB939v9pLnykzRUyE0O_p5p_oRn4SY0QrHz=nMA(a)mail.gmail.com> > Content-Type: text/plain; charset="UTF-8" > > When building mpich-3.2a for Blue Gene /Q and following the same > procedure used for building mpich-3.1.2 for BG/Q, the required linking > information for spi and pami is omitted from the wrappers. I'm not > sure if this is intentional or not. > > Thanks, > William > > > Patching the wrappers to reflect the required linking gives the following diff : > > [wscullin@vestasn1 ~]$ diff > /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc > /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc-postpatch > 265c265 > < $Show $CC $PROFILE_INCPATHS > -L/bgsys/drivers/V1R2M2/ppc64/spi/lib > -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir > -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi > $PROFILE_POSTLIB > --- >> $Show $CC $PROFILE_INCPATHS -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi $PROFILE_POSTLIB -lpami-gcc -lpthread -lSPI -lSPI_cnk -lrt -lstdc++ > > Full diff of mpich-3.1.2 versus 3.2a wrappers: > > [wscullin@vestasn1 ~]$ diff > /projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/bin/mpicc > /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc > 30,34c30,34 > < prefix=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7 > < exec_prefix=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7 > < sysconfdir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/etc > < includedir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/include > < libdir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/lib > --- >> prefix=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7 >> exec_prefix=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7 >> sysconfdir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/etc >> includedir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/include >> libdir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/lib > 40c40 > < MPICH_VERSION="3.1.2" > --- >> MPICH_VERSION="3.2a1" > 262c262 > < $Show $CC $PROFILE_INCPATHS > -L/bgsys/drivers/V1R2M2/ppc64/spi/lib > -L/bgsys/drivers/V1R2M2/ppc64/comm/lib > -L/bgsys/drivers/V1R2M2/ppc64/spi/lib > -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir > --- >> $Show $CC $PROFILE_INCPATHS -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir > 265c265 > < $Show $CC $PROFILE_INCPATHS > -L/bgsys/drivers/V1R2M2/ppc64/spi/lib > -L/bgsys/drivers/V1R2M2/ppc64/comm/lib > -L/bgsys/drivers/V1R2M2/ppc64/spi/lib > -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir > -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi > $PROFILE_POSTLIB -lpami-gcc -lpthread -lSPI -lSPI_cnk -lrt -lstdc++ > --- >> $Show $CC $PROFILE_INCPATHS -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi $PROFILE_POSTLIB > > > ------------------------------ > > Message: 2 > Date: Wed, 17 Sep 2014 00:26:05 -0500 > From: Milind Chabbi <Milind.Chabbi(a)rice.edu> > To: mpich-discuss(a)mcs.anl.gov > Subject: [mpich-discuss] MPI log via MPE on CRAY XC30 machine > Message-ID: > <CAMmz+Y=vvO5vkwyXaKeGg1BKB+Z7zbktZJiwU3rkMjAh8Z058Q(a)mail.gmail.com> > Content-Type: text/plain; charset=UTF-8 > > I am trying to gather MPI logs on CRAY XC30 (Edison machine at NERSC.) > I built MPE 2-1.3 (ftp://ftp.mcs.anl.gov/pub/mpi/mpe/mpe2.tar.gz) with > the following configure command: > > ./configure MPI_CC=cc F77=ftn MPI_F77=ftn --prefix=/XXXXX/mpe2-1.3.0-install > > I compiled a simple application with the following command: > /XXXX/mpe2-1.3.0-install/bin/mpecc test1.cpp -mpilog > > The code compiled fine, but the execution did not generate any log files. > > I am trying to generate logs files of MPI calls to view with Jumpshot > on programs compiled on Cray XC30. Can you suggest the steps needed to > get this working? > > Thanks > -Milind > > > ------------------------------ > > Message: 3 > Date: Wed, 17 Sep 2014 08:41:00 +0200 > From: Bob Ilgner <bobilgner(a)gmail.com> > To: discuss(a)mpich.org > Subject: [mpich-discuss] Passwords on small cluster > Message-ID: > <CAKv15b_xROGRhPzxU3ZXka2KiC2-xz8+Vr1DHc=NYFHE-fQ6MA(a)mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > Dear all, > > > I am trying to run my mpi job on a small cluster with 5 nodes. When I run > > mpirun -n 5 --host node01,node02,node03,node04,node05 ./hesp > > the system requests a password for node01. > > if I run the job only on node05 then no pasword is requested and the job > runs OK Is there some way I can include a password in the host file, or > otherwise ? > > regards. >

1 0

Re: [mpich-discuss] GFORTRAN on MinGW doesn't link to MPICH-2
by Balaji, Pavan 17 Sep '14

17 Sep '14

Hello, Windows is not supported anymore. Sorry. http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can… — Pavan On Sep 17, 2014, at 10:43 AM, Miao Li <rockymountai(a)gmail.com> wrote: > Hello, Folks > > Sorry to bug you guys with this but I am sure there are tons of people > have encountered this before, I am creating a MPI program with MPICH-2 > and gfortran on Windows 8 64 with MinGW, but for some reason the > MPICH-2 can't be linked and errors are: > > hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_' > hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_' > hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_' > hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_' > hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_' > hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_' > c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: > C:\Users\<myid>\AppData\L > ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame' > c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: > final link failed: Inval > id operation > collect2.exe: error: ld returned 1 exit status > > This is just a "hello world" program and I followed the instructions > in the README.winbin.rtf file > > " > > 2) add –I…mpich2\include > > 3) add –L…mpich2\lib > > " > > Some people believe that the "-lmpi" option should be used at the very > end of command, I did that but doesn't help. > > I even tried compiling without any makefile but just a single command like: > >> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi > > But still it doesn't work for me. > > Did any of you guys have encountered this before? > > I really look forward your response, any inputs are highly appreciated!!! > > Thank you so much! > > Best Regard > > NOTE: > > Here is my simple makefile: > > F90 = gfortran > MPI_DIR = /c/Program\ Files/MPICH2 > MPI_LIB_DIR = $(MPI_DIR)/lib > MPI_LIB_INCLUDE = $(MPI_DIR)/include > MPI_LIB = -L$(MPI_LIB_DIR) -lmpi > MPI_INCLUDE = -I$(MPI_LIB_INCLUDE) > SRC = hello_mpi.f90 > OBJ = $(SRC:.f90=.o) > EXEC = hello > $(EXEC): $(OBJ) > $(F90) -o $(EXEC) $(OBJ) $(MPI_LIB) > $(OBJ) : $(SRC) > $(F90) $(MPI_INCLUDE) -c $< > clean: > rm *.o > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss -- Pavan Balaji ✉️ http://www.mcs.anl.gov/~balaji _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] GFORTRAN on MinGW doesn't link
by Bland, Wesley B. 17 Sep '14

17 Sep '14

Unfortunately, we haven't supported Windows since MPICH version 1.4.1p1. You can find out more at the FAQ page: http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can… Thanks, Wesley > On Sep 17, 2014, at 10:39 AM, Miao Li <rockymountai(a)gmail.com> wrote: > > Hello, Folks > > Sorry to bug you guys with this but I am sure there are tons of people > have encountered this before, I am creating a MPI program with MPICH-2 > and gfortran on Windows 8 64 with MinGW, but for some reason the > MPICH-2 can't be linked and errors are: > > hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_' > hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_' > hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_' > hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_' > hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_' > hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_' > c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: > C:\Users\<myid>\AppData\L > ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame' > c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe: > final link failed: Inval > id operation > collect2.exe: error: ld returned 1 exit status > > This is just a "hello world" program and I followed the instructions > in the README.winbin.rtf file > > " > > 2) add –I…mpich2\include > > 3) add –L…mpich2\lib > > " > > Some people believe that the "-lmpi" option should be used at the very > end of command, I did that but doesn't help. > > I even tried compiling without any makefile but just a single command like: > >> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi > > But still it doesn't work for me. > > Did any of you guys have encountered this before? > > I really look forward your response, any inputs are highly appreciated!!! > > Thank you so much! > > Best Regard > > NOTE: > > Here is my simple makefile: > > F90 = gfortran > MPI_DIR = /c/Program\ Files/MPICH2 > MPI_LIB_DIR = $(MPI_DIR)/lib > MPI_LIB_INCLUDE = $(MPI_DIR)/include > MPI_LIB = -L$(MPI_LIB_DIR) -lmpi > MPI_INCLUDE = -I$(MPI_LIB_INCLUDE) > SRC = hello_mpi.f90 > OBJ = $(SRC:.f90=.o) > EXEC = hello > $(EXEC): $(OBJ) > $(F90) -o $(EXEC) $(OBJ) $(MPI_LIB) > $(OBJ) : $(SRC) > $(F90) $(MPI_INCLUDE) -c $< > clean: > rm *.o > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0