f280123d0b
Spelling fixes (found by codespell)
2020-07-03 09:16:30 +02:00
5a5b90cdaa
Run existing check to allow only supported backends in mdtest.
2020-06-30 11:17:46 +01:00
03dbb20594
MDTest changed verification pattern. Read now always checks the first byte/8 bytes for the signature (item number).
...
Added also --verify-write option which performs a read immediately after a write. Supports #206
2020-06-29 20:15:14 +01:00
df3f7082d8
MDTest: Added warnings/errors for errorneous read pattern #206
2020-06-28 17:21:24 +01:00
0bffd14de7
Added --warningAsErrors option to IOR and MDTest and refactored WARNINGs in IOR. #174
2020-06-24 11:13:12 +01:00
b4a54c34e8
Merge branch 'master' into fix-modules
...
Conflicts:
src/aiori-DAOS.c
src/aiori-DFS.c
2020-06-11 19:55:23 +00:00
eb2cd27fac
Removed offset from IOR structure.
2020-06-10 17:47:07 +01:00
c828a0f32c
mdtest: use correct number of bytes for posix_memalign of read buffer
...
Fixes a typo in initial posix_memalign commit for DirectIO support.
2020-06-03 01:22:44 +03:00
3eb488939d
mdtest: allocate aligned buffers to support DirectIO
2020-06-03 00:30:38 +03:00
5663593919
Moved generic IOR information to "hint" structure. Backends should only use the "hints" if set.
2020-05-31 12:50:03 +01:00
8098c3740a
Refactored fd into aiori_fd_t for type safety.
2020-05-31 12:12:49 +01:00
294b8891e6
Created dummy option type to provide type safety. Fixed various call issues for options.
2020-05-31 11:50:15 +01:00
e91b79cea0
Moved Lustre/GPFS/BeeGFS options into POSIX backend. Needs testing. Additional minor fixes.
2020-05-30 20:09:37 +01:00
aa9e2ad815
MDTest updated for AIORI changes.
2020-05-30 18:30:26 +01:00
1890aaaeb0
Started to move IOR specific knowledge out of AIORI.
...
For now, and compatibility, IOR options can still be set/internally accessed using the backends init_xfer_options.
This should be removed in the long run to strip away this dependency.
2020-05-30 18:19:48 +01:00
153b7aa60f
Critical bugfix for ior API (used e.g. in IO500)
...
TODO: Check potential issue when using IOR scripts with different backends.
2020-05-28 21:18:44 +01:00
f97090a86b
Typo fix.
2020-05-28 20:11:52 +01:00
4b417ef1f3
IOR shouldn't fail if it cannot determine file system sizes but warn. Functionality should presumably be moved into AIORI backends.
2020-05-28 19:05:41 +01:00
c702a98376
Strict prototypes for AIORI
2019-12-22 11:21:40 +00:00
9da36abaca
Fix confusing output of mknod
...
Context: mknod does not return a file descriptor.
2019-12-16 14:55:26 +01:00
4409082064
Merge pull request #188 from pkoutoupis/feature-global_default_dir_layout
...
Enable global default dir layout for subdirs in Lustre
2019-10-28 10:43:56 -07:00
b3ecd756ce
Implemented AC_CHECK_HEADERS fix in style of #190
2019-09-30 04:25:59 -07:00
604598ab2f
Merge pull request #182 from jschwartz-cray/fix-181
...
Fix #181 .
2019-09-19 16:53:41 +01:00
fe9d76ddf3
fix segfault when no API is specified to mdtest
...
Signed-off-by: Mohamad Chaarawi <mohamad.chaarawi@intel.com>
2019-09-09 22:03:55 +00:00
e9dd5fe15e
Merge branch 'master' into daos-devel
...
Signed-off-by: Mohamad Chaarawi <mohamad.chaarawi@intel.com>
Conflicts:
configure.ac
src/Makefile.am
src/aiori-MPIIO.c
src/aiori.c
src/aiori.h
src/ior.c
src/mdtest.c
src/option.c
2019-09-09 19:55:56 +00:00
0921556456
Merge pull request #184 from hpc/feature-aiori
...
Feature aiori
2019-09-09 15:20:43 +01:00
36d13d3b97
Enable global default dir layout for subdirs in Lustre
2019-09-02 22:26:12 -07:00
ced9b0183f
Merge pull request #172 from hpc/fix-168
...
Fix #168
2019-09-01 15:51:44 +01:00
e3db1759b2
Moded sync() to aiori backend.
2019-09-01 15:47:42 +01:00
6de1ea3176
Merge branch 'feature-sync' into feature-aiori
2019-09-01 15:39:49 +01:00
10d3db1dc8
MDTest: fixing the memset() to account for the number of iterations.
2019-08-31 17:28:08 +01:00
0e952f0f8c
Fix #181 .
...
On systems where numTasks is not evenly divisible by 'tasksPerNode' we were
seeing some nodes reading multiple files while others read none after
reordering.
Commonly all nodes have the same number of tasks but there is nothing
requiring that to be the case. Imagine having 64 tasks running against 4
nodes which can run 20 tasks each. Here you get three groups of 20 and one
group of 4. On this sytem nodes running in the group of 4 were previously
getting tasksPerNode of 4 which meant they reordered tasks differently than
the nodes which got tasksPerNode of 20.
The key to fixing this is ensuring that every node reorders tasks the same
way, which means ensuring they all use the same input values. Obviously on
systems where the number of tasks per node is inconsistent the reordering will
also be inconsistent (some tasks may end up on the same node, or not as far
separated as desired, etc.) but at least this way you'll always end up with a
1:1 reordering.
- Renamed nodes/nodeCount to numNodes
- Renamed tasksPerNode to numTasksOnNode0
- Ensured that numTasksOnNode0 will always have the same value regardless of
which node you're on
- Removed inconsistently used globals numTasksWorld and tasksPerNode and
replaced with per-test params equivalents
- Added utility functions for setting these values:
- numNodes -> GetNumNodes
- numTasks -> GetNumTasks
- numTasksOnNode0 -> GetNumNodesOnTask0
- Improved MPI_VERSION < 3 logic for GetNumNodes so it works when numTasks is
not evenly divisible by numTasksOnNode0
- Left 'nodes' and 'tasksPerNode' in output alone to not break compatibility
- Allowed command-line params to override numTasks, numNodes, and
numTasksOnNode0 but default to using the MPI-calculated values
2019-08-30 16:45:03 -06:00
4df051bf28
New option -Y to invoke the sync command.
2019-08-26 18:57:14 +01:00
0d9f46e980
MDTest re-added the -Z option for compatibility (for now) and switched back behavior.
2019-08-15 16:49:46 +01:00
de3baf8861
MDTest: Document choice of 42.
2019-08-15 16:21:30 +01:00
5e6a03442f
Merge pull request #170 from ax3l/fix-someMemleaks
...
Fix Some Memory Leaks; Thanks.
2019-08-03 09:19:08 +01:00
c4ff3d7c4e
Trivial fix for #168
2019-08-03 09:12:48 +01:00
bfff0df8fd
Fix Some Memory Leaks
...
Fixing some memory leaks :)
2019-08-02 23:33:01 -05:00
cf56715a5a
Make sure that each read buffer contains an invalid first byte.
2019-08-01 18:33:44 +01:00
ce1ae750f6
MDtest: Support to verify the read operation with a default pattern.
2019-08-01 18:29:32 +01:00
df8355a9bc
Added output of mdtest stonewall timer.
2019-08-01 17:57:45 +01:00
061b5a860f
Backmerged: New option: print rate AND time; improves debugging.
2019-08-01 17:54:11 +01:00
3890b71b54
Fixed issues and followed suggestions from Glenn's review of the PR
2019-08-01 09:42:03 +09:00
a3c37808da
Made FAIL take variable args so we can pass printf like args to it
2019-07-28 11:17:11 -06:00
0ffec67d2b
Following Julian's suggestion about better naming
2019-07-28 10:25:42 -06:00
b2d486f749
Followed Andreas suggestion to replace escape double quotes within printf's with single quotes
2019-07-28 10:07:03 -06:00
168a407793
Fixed inconsistent spacing that Andreas commented upon
2019-07-28 09:55:00 -06:00
d69957e55b
Final changes cleaning up the output messages
2019-07-27 14:31:49 -06:00
e767ef3de9
Remove extraneous print_help function that was causing people to have to edit the same string in two different locations
2019-07-27 13:26:39 -06:00
f6491fcd37
Cleaned up the verbose messages by creating a macro and a function
2019-07-27 13:22:15 -06:00
Karsten Weiss