November 2017 - discuss - mailman3.cels.anl.gov

Re: [mpich-discuss] MPI_Rget + MPI_Testall fails with success
by Min Si 28 Nov '17

28 Nov '17

Hi Joseph, Thanks for reporting this issue and the reproducer program. I just confirmed this is a bug in MPICH request-based RMA routine. I will fix it soon and add your reproducer into our test suite. You can check the status through the ticket: https://github.com/pmodels/mpich/issues/2880 Thanks, Min On 11/28/17 5:48 AM, Joseph Schuchart wrote: > All, > > I am running into a problem with MPI_Rget in combination with > MPI_Testall, where the call to MPI_Testall fails with the error > hinting at more information in the status' MPI_ERROR fields. However, > these fields only signal success: > > [0] MPI_Testall failed: > See the MPI_ERROR field in MPI_Status for the error code (17) > [0] Request error: No MPI error (0) > [0] Request error: No MPI error (0) > > I am attaching a small reproducer. I should note that the application > succeeds if I am using MPI_Test on the individual requests instead of > MPI_Testall. > > Please let me know if my usage of MPI_Rget and MPI_Testall is > erroneous for some reason. I can reproduce this error with both MPICH > 3.2 and 3.2.1 as well as Intel MPI 2017 even when running with a > single process. > > Many thanks in advance, > Joseph > > > _______________________________________________ > 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

MPI_Rget + MPI_Testall fails with success
by Joseph Schuchart 28 Nov '17

28 Nov '17

All, I am running into a problem with MPI_Rget in combination with MPI_Testall, where the call to MPI_Testall fails with the error hinting at more information in the status' MPI_ERROR fields. However, these fields only signal success: [0] MPI_Testall failed: See the MPI_ERROR field in MPI_Status for the error code (17) [0] Request error: No MPI error (0) [0] Request error: No MPI error (0) I am attaching a small reproducer. I should note that the application succeeds if I am using MPI_Test on the individual requests instead of MPI_Testall. Please let me know if my usage of MPI_Rget and MPI_Testall is erroneous for some reason. I can reproduce this error with both MPICH 3.2 and 3.2.1 as well as Intel MPI 2017 even when running with a single process. Many thanks in advance, Joseph _______________________________________________ discuss mailing list discuss(a)mpich.org To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

how to run jobs using IPv6?
by Carlos 22 Nov '17

22 Nov '17

Is it possible to use mpich (3.3) with IPv6-only? We tried it here and got Fatal error in MPI_Init: Other MPI error, error stack: MPIR_Init_thread(506)..............: MPID_Init(211).....................: channel initialization failed MPIDI_CH3_Init(89).................: MPID_nem_init(324).................: MPID_nem_tcp_init(178).............: MPID_nem_tcp_get_business_card(425): ckpt_restart(384)..................: gethostbyname failed, zuratkul (errno 4) ************* This shows that mpich doesn't run without IPv4, which is our case... Is there a way to make it work in this situation? _______________________________________________ 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] Worries with ROMIO on NFS since commit b4ab2f118d
by Eric Chamberland 21 Nov '17

21 Nov '17

Hi M. Latham, I have more information now. When I try to run my example on NFS, I have the following error code: error #812707360 Other I/O error , error stack: ADIOI_NFS_READSTRIDED(523): Other I/O error Success that is returned by MPI_File_read_all_begin When I try on a local disk, everything is fine. Here are all files about my actual build: http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.21.05h40m02s_con… http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.21.05h40m02s_c.t… http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.21.05h40m02s_m.t… http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.21.05h40m02s_mi.… http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.21.05h40m02s_mpl… http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.21.05h40m02s_pm_… http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.21.05h40m02s_mpi… Hope this help to dig further into this issue. Thanks, Eric On 15/11/17 03:55 PM, Eric Chamberland wrote: > Hi, > > We are compiling with mpich/master each night since august 2016... > > since nov 8, the mpich/master branch is buggy with our nighlty build tests. > > Here is the nov 8 config.log: > > http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.08.05h36m02s_con… > > > For nov 7 the configure log: > > http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.07.05h36m01s_con… > > > > Since nov 8, on a specific ROMIO test, it is hanging indefinitely in > optimized mode, and into DEBUG mode, I have a strange (yet to be > debugged) assertion in our code. > > I reran the test manually, and when I wrote the results on a local disk, > everything is fine. > > However, when I write over *NFS*, the test is faulty. > > I have not yet debugged enough through this, but, I suspect something > related with one of: > > MPI_File_write_all_begin > MPI_File_write_all_end > MPI_File_read_all_begin > MPI_File_read_all_end > MPI_File_set_view > MPI_Type_free > > Am I alone to see these problems? > > Thanks, > Eric > > _______________________________________________ > 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] MPICH compilation error
by Min Si 17 Nov '17

17 Nov '17

Hi, Thanks for the bug report. This looks like a mistake when we picked the commit from the master branch. Here is a fix patch based on the mpich-3.2.1 release. https://github.com/pmodels/mpich/pull/2872/commits/63385b77c6edf3fe10c9f400… Regards, Min On 11/17/17 5:04 AM, Marcus Calhoun-Lopez wrote: > In [1], the signature of pkt_CTS_handler wash changed in the file > src/mpid/ch3/channels/nemesis/src/mpid_nem_lmt.c. > However, the declaration and definition seem to be inconsistent: > +static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void > *data, MPIDI_msg_sz_t *buflen, MPID_Request **rreqp); > +static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void > *data, intptr_t *buflen, MPID_Request **rreqp) > > Is the patch below the correct solution? > > [1] http://git.mpich.org/mpich.git/commitdiff/2f8fe118fed12357e6f9401e644cc650e… > > > --- src/mpid/ch3/channels/nemesis/src/mpid_nem_lmt.c.orig 2017-11-10 > 19:19:44.000000000 -0700 > +++ src/mpid/ch3/channels/nemesis/src/mpid_nem_lmt.c 2017-11-17 > 04:23:52.000000000 -0700 > @@ -299,7 +299,7 @@ > #define FUNCNAME pkt_CTS_handler > #undef FCNAME > #define FCNAME MPL_QUOTE(FUNCNAME) > -static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void > *data, intptr_t *buflen, MPID_Request **rreqp) > +static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void > *data, MPIDI_msg_sz_t *buflen, MPID_Request **rreqp) > { > MPID_nem_pkt_lmt_cts_t * const cts_pkt = (MPID_nem_pkt_lmt_cts_t *)pkt; > MPID_Request *sreq; > _______________________________________________ > 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

MPICH compilation error
by Marcus Calhoun-Lopez 17 Nov '17

17 Nov '17

In [1], the signature of pkt_CTS_handler wash changed in the file src/mpid/ch3/channels/nemesis/src/mpid_nem_lmt.c. However, the declaration and definition seem to be inconsistent: +static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void *data, MPIDI_msg_sz_t *buflen, MPID_Request **rreqp); +static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void *data, intptr_t *buflen, MPID_Request **rreqp) Is the patch below the correct solution? [1] http://git.mpich.org/mpich.git/commitdiff/2f8fe118fed12357e6f9401e644cc650e… --- src/mpid/ch3/channels/nemesis/src/mpid_nem_lmt.c.orig 2017-11-10 19:19:44.000000000 -0700 +++ src/mpid/ch3/channels/nemesis/src/mpid_nem_lmt.c 2017-11-17 04:23:52.000000000 -0700 @@ -299,7 +299,7 @@ #define FUNCNAME pkt_CTS_handler #undef FCNAME #define FCNAME MPL_QUOTE(FUNCNAME) -static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void *data, intptr_t *buflen, MPID_Request **rreqp) +static int pkt_CTS_handler(MPIDI_VC_t *vc, MPIDI_CH3_Pkt_t *pkt, void *data, MPIDI_msg_sz_t *buflen, MPID_Request **rreqp) { MPID_nem_pkt_lmt_cts_t * const cts_pkt = (MPID_nem_pkt_lmt_cts_t *)pkt; MPID_Request *sreq; _______________________________________________ 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] mpich-3.2.1 configure with orangefs-2.9
by Weihao Liang 15 Nov '17

15 Nov '17

Thank you! It is very helpful and solved my problem. Vinson On Tue, Nov 14, 2017 at 9:27 PM, Wei-keng Liao <wkliao(a)eecs.northwestern.edu > wrote: > Try the following configure command, by adding the PVFS2 include path to > CPPFLAGS, > library path to LDFLAGS and -lpvfs2 to LIBS. > > ./configure --prefix=/path/to/install \ > --enable-romio \ > --with-file-system=ufs+pvfs2 \ > CPPFLAGS="-I/opt/orangefs/include" \ > LDFLAGS="-L/opt/orangefs/lib" \ > LIBS="-lpvfs2" > > Wei-keng > > On Nov 14, 2017, at 9:16 PM, Weihao Liang wrote: > > > Thank you. I have tried the LD_LIBRARY_PATH way and adding > "-L/opt/orangefs/lib -lpvfs2" to the link command line but the errors > still happen. So i think maybe still is there something wrong when i built > the MPICH? > > > > Vinson. > > On Tue, Nov 14, 2017 at 9:04 PM, Jeff Hammond <jeff.science(a)gmail.com> > wrote: > > The PVFS library needs to be in LD_LIBRARY_PATH or otherwise visible to > the linker. > > > > Jeff > > > > On Tue, Nov 14, 2017 at 7:00 PM Weihao Liang <lwhvinson1990(a)gmail.com> > wrote: > > Thanks, I have sucessfully built MPICH with configure command line > "CFLAGS+='/opt/orangefs/include' ./configure --enable-romio > --with-file-system=pvfs2". But when I link the the .o file with mpicc there > are many errors as below: > > ============================= > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_FLOAT' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_indexed' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_CHAR' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_hvector' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_resized' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_finalize' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_dist_setparam' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_perror' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED_CHAR' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_wait' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_truncate' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_free' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_flush' > > /usr/local/lib/libmpi.so: undefined reference to > `PVFS_debug_eventlog_to_mask' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_LONG' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_lookup' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_DOUBLE' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_SHORT' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_create' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_remove' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_BYTE' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_util_resolve' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_dist_lookup' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_io' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_vector' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_INT' > > /usr/local/lib/libmpi.so: undefined reference to > `PVFS_Request_contiguous' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_testsome' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_LONG_DOUBLE' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_struct' > > /usr/local/lib/libmpi.so: undefined reference to > `PVFS_util_init_defaults' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_hindexed' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED_LONG' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_isys_io' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED' > > /usr/local/lib/libmpi.so: undefined reference to > `PVFS_util_gen_credential_defaults' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_getparent' > > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_getattr' > > collect2: error: ld returned 1 exit status > > =============================================== > > > > Vinson > > > > On Tue, Nov 14, 2017 at 6:08 PM, Latham, Robert J. <robl(a)mcs.anl.gov> > wrote: > > On Tue, 2017-11-14 at 16:54 -0600, Weihao Liang wrote: > > > Hi, all > > > > > > I have a question is that how to configure mpich-3.2.1 with orangefs- > > > 2.9 (pvfs2)? I just want to enable the MPI-IO ability when running > > > MPI program on pvfs2 filesystem. > > > > The process is still the same it has always been. OrangeFS is a > > rebranding of what we used to call PVFS v2 : > > > > Configure MPICH with the `--with-file-system=pvfs2` flag. > > > > If you want to configure other file systems, add them with '+': > > > > `configure --prefix=/usr/local/whatever --with-file-system=pvfs2+ufs` > > > > ==rob > > _______________________________________________ > > 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 > > -- > > Jeff Hammond > > jeff.science(a)gmail.com > > http://jeffhammond.github.io/ > > > > _______________________________________________ > > 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 > > _______________________________________________ > 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

Worries with ROMIO on NFS since commit b4ab2f118d
by Eric Chamberland 15 Nov '17

15 Nov '17

Hi, We are compiling with mpich/master each night since august 2016... since nov 8, the mpich/master branch is buggy with our nighlty build tests. Here is the nov 8 config.log: http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.08.05h36m02s_con… For nov 7 the configure log: http://www.giref.ulaval.ca/~cmpgiref/dernier_mpich/2017.11.07.05h36m01s_con… Since nov 8, on a specific ROMIO test, it is hanging indefinitely in optimized mode, and into DEBUG mode, I have a strange (yet to be debugged) assertion in our code. I reran the test manually, and when I wrote the results on a local disk, everything is fine. However, when I write over *NFS*, the test is faulty. I have not yet debugged enough through this, but, I suspect something related with one of: MPI_File_write_all_begin MPI_File_write_all_end MPI_File_read_all_begin MPI_File_read_all_end MPI_File_set_view MPI_Type_free Am I alone to see these problems? Thanks, Eric _______________________________________________ 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] mpich-3.2.1 configure with orangefs-2.9
by Wei-keng Liao 14 Nov '17

14 Nov '17

Try the following configure command, by adding the PVFS2 include path to CPPFLAGS, library path to LDFLAGS and -lpvfs2 to LIBS. ./configure --prefix=/path/to/install \ --enable-romio \ --with-file-system=ufs+pvfs2 \ CPPFLAGS="-I/opt/orangefs/include" \ LDFLAGS="-L/opt/orangefs/lib" \ LIBS="-lpvfs2" Wei-keng On Nov 14, 2017, at 9:16 PM, Weihao Liang wrote: > Thank you. I have tried the LD_LIBRARY_PATH way and adding "-L/opt/orangefs/lib -lpvfs2" to the link command line but the errors still happen. So i think maybe still is there something wrong when i built the MPICH? > > Vinson. > On Tue, Nov 14, 2017 at 9:04 PM, Jeff Hammond <jeff.science(a)gmail.com> wrote: > The PVFS library needs to be in LD_LIBRARY_PATH or otherwise visible to the linker. > > Jeff > > On Tue, Nov 14, 2017 at 7:00 PM Weihao Liang <lwhvinson1990(a)gmail.com> wrote: > Thanks, I have sucessfully built MPICH with configure command line "CFLAGS+='/opt/orangefs/include' ./configure --enable-romio --with-file-system=pvfs2". But when I link the the .o file with mpicc there are many errors as below: > ============================= > /usr/local/lib/libmpi.so: undefined reference to `PVFS_FLOAT' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_indexed' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_CHAR' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_hvector' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_resized' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_finalize' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_dist_setparam' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_perror' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED_CHAR' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_wait' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_truncate' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_free' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_flush' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_debug_eventlog_to_mask' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_LONG' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_lookup' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_DOUBLE' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_SHORT' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_create' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_remove' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_BYTE' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_util_resolve' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_dist_lookup' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_io' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_vector' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_INT' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_contiguous' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_testsome' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_LONG_DOUBLE' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_struct' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_util_init_defaults' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_hindexed' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED_LONG' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_isys_io' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_util_gen_credential_defaults' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_getparent' > /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_getattr' > collect2: error: ld returned 1 exit status > =============================================== > > Vinson > > On Tue, Nov 14, 2017 at 6:08 PM, Latham, Robert J. <robl(a)mcs.anl.gov> wrote: > On Tue, 2017-11-14 at 16:54 -0600, Weihao Liang wrote: > > Hi, all > > > > I have a question is that how to configure mpich-3.2.1 with orangefs- > > 2.9 (pvfs2)? I just want to enable the MPI-IO ability when running > > MPI program on pvfs2 filesystem. > > The process is still the same it has always been. OrangeFS is a > rebranding of what we used to call PVFS v2 : > > Configure MPICH with the `--with-file-system=pvfs2` flag. > > If you want to configure other file systems, add them with '+': > > `configure --prefix=/usr/local/whatever --with-file-system=pvfs2+ufs` > > ==rob > _______________________________________________ > 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 > -- > Jeff Hammond > jeff.science(a)gmail.com > http://jeffhammond.github.io/ > > _______________________________________________ > 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 _______________________________________________ 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] mpich-3.2.1 configure with orangefs-2.9
by Weihao Liang 14 Nov '17

14 Nov '17

Thank you. I have tried the LD_LIBRARY_PATH way and adding "-L/opt/orangefs/lib -lpvfs2" to the link command line but the errors still happen. So i think maybe still is there something wrong when i built the MPICH? Vinson. On Tue, Nov 14, 2017 at 9:04 PM, Jeff Hammond <jeff.science(a)gmail.com> wrote: > The PVFS library needs to be in LD_LIBRARY_PATH or otherwise visible to > the linker. > > Jeff > > On Tue, Nov 14, 2017 at 7:00 PM Weihao Liang <lwhvinson1990(a)gmail.com> > wrote: > >> Thanks, I have sucessfully built MPICH with configure command line >> "CFLAGS+='/opt/orangefs/include' ./configure --enable-romio >> --with-file-system=pvfs2". But when I link the the .o file with mpicc there >> are many errors as below: >> ============================= >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_FLOAT' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_indexed' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_CHAR' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_hvector' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_resized' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_finalize' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_dist_setparam' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_perror' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED_CHAR' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_wait' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_truncate' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_free' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_flush' >> /usr/local/lib/libmpi.so: undefined reference to >> `PVFS_debug_eventlog_to_mask' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_LONG' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_lookup' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_DOUBLE' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_SHORT' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_create' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_remove' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_BYTE' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_util_resolve' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_dist_lookup' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_io' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_vector' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_INT' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_contiguous' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_testsome' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_LONG_DOUBLE' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_struct' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_util_init_defaults' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_Request_hindexed' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED_LONG' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_isys_io' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_UNSIGNED' >> /usr/local/lib/libmpi.so: undefined reference to >> `PVFS_util_gen_credential_defaults' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_getparent' >> /usr/local/lib/libmpi.so: undefined reference to `PVFS_sys_getattr' >> collect2: error: ld returned 1 exit status >> =============================================== >> >> Vinson >> >> On Tue, Nov 14, 2017 at 6:08 PM, Latham, Robert J. <robl(a)mcs.anl.gov> >> wrote: >> >>> On Tue, 2017-11-14 at 16:54 -0600, Weihao Liang wrote: >>> > Hi, all >>> > >>> > I have a question is that how to configure mpich-3.2.1 with orangefs- >>> > 2.9 (pvfs2)? I just want to enable the MPI-IO ability when running >>> > MPI program on pvfs2 filesystem. >>> >>> The process is still the same it has always been. OrangeFS is a >>> rebranding of what we used to call PVFS v2 : >>> >>> Configure MPICH with the `--with-file-system=pvfs2` flag. >>> >>> If you want to configure other file systems, add them with '+': >>> >>> `configure --prefix=/usr/local/whatever --with-file-system=pvfs2+ufs` >>> >>> ==rob >>> _______________________________________________ >>> 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 > > -- > Jeff Hammond > jeff.science(a)gmail.com > http://jeffhammond.github.io/ > > _______________________________________________ > 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