Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Treddy debug gh 830 #23

Closed
wants to merge 17 commits into from
Closed

Treddy debug gh 830 #23

wants to merge 17 commits into from

Conversation

tylerjereddy
Copy link
Owner

No description provided.

shanedsnyder and others added 16 commits November 15, 2022 13:03
* add struct timespec start/end times to job struct
* add custom MPI reduction ops for max/min values of
  struct timespecs
* add logutils code for extracting start/end timespecs
* update some analysis utilities to use new timespec values
method for calculating this depends on log format version,
so a helper routine seems useful for utilities
* new logutils function (`darshan_log_get_job_runtime`) to
  calculate job runtime as a floating point value
  * for pre 3.41 logs, this is end-start+1 (i.e., runtime
    rounded up to nearest integer)
  * for 3.41+ logs, this is exact runtime to nsec precision
* CFFI definition updates of job types, type sizes
* CFFI bindings updates to extract new job timers and runtime
* updates to summary and report interfaces to use new job timers
  and runtime values
* updates to plotting code to use new job timers and runtime
  values
  * `plot_dxt_heatmap.py` in particular had some code removed
    that tried to correct for a calculated runtime of 0
* updates to tests to accommodate new changes to various
  interfaces and record formats
  * `test_plot_dxt_heatmap.py` has changes to avoid need for
    rounding up calculated runtime
  * new ior-PNETCF/ior-HDF5 log files are included as previous
    ones are no longer valid due to log format changes
* based on analysis of test memory usage with `pytest-monitor`,
try temporarily xfailing one of the more expensive cases
in `test_vertical_resize()`
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants