- 31 Aug, 2017 5 commits
-
-
Artem Polyakov authored
Add new performance debugging feature to pmix plugin that allows to measure plain collectives performance on selected message sizes. This functionality is similar to a ping-pong feature. Performance results for existing point-to-point modes: size sapi dtcp ducx 1 0.002319442 0.000492334 0.000135243 2 0.002318223 0.000453552 0.000137356 4 0.00227046 0.00045832 0.000137117 8 0.002342675 0.000463539 0.000136455 16 0.00235131 0.000481208 0.00013619 32 0.002333058 0.000562986 0.000140756 64 0.002456691 0.000883791 0.000142574 128 0.002953556 0.001326429 0.000142336 256 0.003892236 0.002324766 0.000161224 512 0.006044123 0.004371988 0.000177675 1024 0.010324001 0.008485476 0.000224325 2048 0.018556118 0.016488896 0.000347243 4096 0.035331223 0.032744778 0.000481764 8192 0.06957123 0.065519465 0.001194106 16384 0.137925333 0.130130662 0.002544668 32768 0.272100422 0.259290563 0.009916888 65536 0.543431362 0.486692217 0.012841119 Signed-off-by:
Artem Polyakov <artpol84@gmail.com>
-
Artem Polyakov authored
Signed-off-by:
Artem Polyakov <artpol84@gmail.com>
-
Artem Polyakov authored
Signed-off-by:
Artem Polyakov <artpol84@gmail.com>
-
Artem Polyakov authored
Signed-off-by:
Artem Polyakov <artpol84@gmail.com>
-
Artem Polyakov authored
There were segmentation faults because of double free of a pending list when UCX comonent was trying to connect multiple times. Signed-off-by:
Artem Polyakov <artpol84@gmail.com>
-
- 30 Aug, 2017 11 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
Stop unpacking / packing it as well.
-
David Gloe authored
Statically linked Cray PMI applications still expect to use some file paths containing the old SLURM_ID_HASH format. Some Cray customers have certification requirements that make recompilation difficult. The attached patch defines a macro to convert the new SLURM_ID_HASH to the old format, and writes the files and symlinks necessary for statically linked Cray PMI applications to work. Bug 4114
-
Danny Auble authored
frequency on the batch step. Bug 4073 Also see Bug 3510
-
Danny Auble authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Bug 2346.
-
Tim Wickberg authored
Queries longer than the range will be rejected outright. Default value is INFINITE (query range is unlimited). Bug 2346.
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
This reverts commit 0581585c. Do not change permissions on files the testsuite does not "own". Bug 4118.
-
- 29 Aug, 2017 24 commits
-
-
Brian Christiansen authored
Bug 4090
-
Danny Auble authored
-
Danny Auble authored
-
Tim Wickberg authored
This reverts commit 610042bb.
-
Tim Wickberg authored
This reverts commit f9687bbc.
-
Tim Wickberg authored
Note that field_size is always reset later by _parse_token.
-
Danny Auble authored
-
Brian Christiansen authored
-
Brian Christiansen authored
as reported when compiling with optimizations (-O2).
-
Brian Christiansen authored
reported when compiling with optimizations (-O2).
-
Brian Christiansen authored
as reported when compiling with optimizations (-O2). Also check for null dereference.
-
Brian Christiansen authored
as reported when compiling with optimizations (-O2).
-
Brian Christiansen authored
as reported when compiling with optimizations (-02). Initialize the variables early since they were being initialized in their loops and later checked for -1. Technically couldn't have happened since for example, user_part_inx1 would only be set to -1 if max_backfill_job_per_user_part was set. And user_part_inx is only checked later if max_backfill_job_per_user_part is set. Same thing for part_inx, max_backfill_job_per_part and user_inx, max_backfill_job_per_user.
-
Brian Christiansen authored
reported when compiling with optimizations (-O2). The compiler ignores the (void) cast and reports the error.
-
Brian Christiansen authored
reported when compiling with optimizations (-O2). field_id may be uninitialized or the the value from the previous iteration in the while loop. The only possible values of dataset_loc->type are: typedef enum { PROFILE_FIELD_NOT_SET, PROFILE_FIELD_UINT64, PROFILE_FIELD_DOUBLE } acct_gather_profile_field_type_t; and the while loop condition ensures that PROFILE_FIELD_NOT_SET is not handled. So instead of handling PROFILE_FIELD_NOT_SET directly, just catching everything else with the "default" case statement and continuing the loop.
-
Brian Christiansen authored
when compiling with optimizations (-02) due to "size" not being set in case statement.
-
Brian Christiansen authored
when compiling with optimizations (-O2).
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
Could happen if the switch statement hit the default. Was originally this way in ca682973
-
Brian Christiansen authored
as stated in README. Was originally this way in ca682973
-
Danny Auble authored
relies on the primary to do so. There is a potential race condition if the backup DBD tries to create/check the database at the same time as the primary. This patch removes this race by not allowing the backup to do the check/create. Bug 3827
-
Morris Jette authored
Coverity CID 171481
-