- 20 Oct, 2016 1 commit
-
-
Shane Snyder authored
-
- 17 Oct, 2016 1 commit
-
-
Cong Xu authored
Signed-off-by:
Cong Xu <cong.xu@intel.com>
-
- 14 Oct, 2016 2 commits
-
-
Cong Xu authored
1. At log parsing time, pass Lustre striping information to DXLT module a. Obtain Lustre striping information in Lustre Module. b. Cache file striping information and map it to file name. c. Pass file striping information to DXLT module for each file. 2. In DXLT module, print Lustre striping and OST information if file system type is Lustre. Signed-off-by:
Cong Xu <cong.xu@intel.com>
-
Cong Xu authored
2. Refactor DXLT to be a generic IO tracing tool for files on any file system. 3. Add file type information in DXLT log parser. Next steps: 1. Based on the file type information in DXLT log parser, add information for specific file types. (For instance, add OST information for files on Lustre) 2. In the process of parsing DXLT logs, figure out how to obtain Lustre striping information from Lustre module. 3. Rename DXLT to be "Darshan eXtended Tracing (DXT)" or "Darshan eXtended IO Tracing (DXIOT)". Signed-off-by:
Cong Xu <cong.xu@intel.com>
-
- 13 Oct, 2016 1 commit
-
-
Cong Xu authored
Signed-off-by:
Cong Xu <cong.xu@intel.com>
-
- 10 Oct, 2016 2 commits
-
-
Cong Xu authored
-
Cong Xu authored
1. Use Lustre Module in Darshan 2. Integrate DXLT IO tracing code into one module 3. Add hooks in POSIX and MPI Modules 4. Add Intel copyright Signed-off-by:
Cong Xu <cong.xu@intel.com>
-
- 04 Oct, 2016 1 commit
-
-
Cong Xu authored
1. Use Lustre Module in Darshan 2. Integrate DXLT IO tracing code into one module 3. Add hooks in POSIX and MPI Modules 4. Add Intel copyright Signed-off-by:
Cong Xu <cong.xu@intel.com>
-
- 30 Sep, 2016 5 commits
-
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
- 27 Sep, 2016 1 commit
-
-
Shane Snyder authored
-
- 26 Sep, 2016 2 commits
-
-
Shane Snyder authored
The stdio module stores names for the default streams (stdin, stderr, stdout) in the following format: <STDERR>. The '<' and '>' symbols require proper escape characters in order to be properly interpretated by the darshan-job-summary (perl) script.
-
Shane Snyder authored
-
- 23 Sep, 2016 9 commits
-
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
- 22 Sep, 2016 3 commits
-
-
Shane Snyder authored
-
Shane Snyder authored
POSIX_F_OPEN_TIMESTAMP is now POSIX_F_OPEN_START_TIMESTAMP POSIX_F_CLOSE_TIMESTAMP is now POSIX_F_CLOSE_END_TIMESTAMP I also added POSIX_F_OPEN_END_TIMESTAMP and POSIX_F_CLOSE_START_TIMESTAMP, so we can better understand how long open and close phases are for some applications.
-
Shane Snyder authored
-
- 21 Sep, 2016 2 commits
-
-
Shane Snyder authored
We don't currently have a system to try this out on, but just wanted to make sure something was there as a failsafe. The current implementation should be able to correctly aggregate all counters in BGQ records, except for BGQ_INODES.
-
Shane Snyder authored
-
- 20 Sep, 2016 6 commits
-
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
-
Shane Snyder authored
this includes defining an example logutils function for aggregating null records into a single shared null record (needed for darshan-merge utility)
-
Shane Snyder authored
-
Shane Snyder authored
-
- 19 Sep, 2016 2 commits
-
-
Shane Snyder authored
-
Shane Snyder authored
also, bug fix to avoid any attempt of reading log file for modules with no data present in the log
-
- 18 Sep, 2016 2 commits
-
-
Philip Carns authored
-
Philip Carns authored
-