Skip to content
Snippets Groups Projects
  • Sergey Kaplun's avatar
    ccb7a649
    perf: standardize gh-7089-vclock-copy benchmark · ccb7a649
    Sergey Kaplun authored
    The output now contains items per second without the mean time in
    seconds. The number of iterations is reduced to 40 to avoid running the
    test too long. The `wal_mode` option (default is "none") is set via
    command line flags, as far as the number of nodes (default is 10). Also,
    the master nodes are set up via the `popen()` command without using any
    Makefile.
    
    Also, two new options are introduced:
    * The `--output` option allows you to specify the output file.
    * The `--output_format` option means the format for the printed output.
      The default is "console". It prints items proceeded per second to the
      stdout. The "json" format contains all the information about the
      benchmark in a format similar to Google Benchmark's.
    
    Usually, these options should be used together to dump machine-readable
    results for the benchmarks.
    
    NO_DOC=perf test
    NO_CHANGELOG=perf test
    NO_TEST=perf test
    ccb7a649
    History
    perf: standardize gh-7089-vclock-copy benchmark
    Sergey Kaplun authored
    The output now contains items per second without the mean time in
    seconds. The number of iterations is reduced to 40 to avoid running the
    test too long. The `wal_mode` option (default is "none") is set via
    command line flags, as far as the number of nodes (default is 10). Also,
    the master nodes are set up via the `popen()` command without using any
    Makefile.
    
    Also, two new options are introduced:
    * The `--output` option allows you to specify the output file.
    * The `--output_format` option means the format for the printed output.
      The default is "console". It prints items proceeded per second to the
      stdout. The "json" format contains all the information about the
      benchmark in a format similar to Google Benchmark's.
    
    Usually, these options should be used together to dump machine-readable
    results for the benchmarks.
    
    NO_DOC=perf test
    NO_CHANGELOG=perf test
    NO_TEST=perf test