1. 06 Aug, 2020 1 commit
  2. 18 Jun, 2020 2 commits
  3. 17 Jun, 2020 2 commits
  4. 08 May, 2020 1 commit
  5. 14 Apr, 2020 1 commit
  6. 07 Jan, 2020 1 commit
  7. 06 Dec, 2019 2 commits
  8. 02 Dec, 2019 8 commits
  9. 16 Nov, 2019 7 commits
    • Volodymyr Nikolaichuk's avatar
      Remove unused include dir · fabfdf9c
      Volodymyr Nikolaichuk authored
      fabfdf9c
    • Volodymyr Nikolaichuk's avatar
      Fix building heaptrack_inject · 1e15381f
      Volodymyr Nikolaichuk authored
      Prepares the build for Android
      1e15381f
    • Volodymyr Nikolaichuk's avatar
      Add heaptrack_{pause,resume}() API · e65e358c
      Volodymyr Nikolaichuk authored
      This can be used by client applications to optimize getting to a
      place that should be recorded by avoiding collecting traces and
      logging.
      e65e358c
    • Volodymyr Nikolaichuk's avatar
      Check for valloc in stdlib.h · ae54d99a
      Volodymyr Nikolaichuk authored
      ae54d99a
    • Volodymyr Nikolaichuk's avatar
    • Volodymyr Nikolaichuk's avatar
      Optionally use unwind_tables instead of libunwind · 8023779f
      Volodymyr Nikolaichuk authored
      This can then be used on platforms with no libunwind available. This
      makes heaptrack functional, but the performance is really bad:
      
      With unwind_tables:
      
      ```
      $ perf stat ./bin/heaptrack ./tests/manual/threaded
      heaptrack output will be written to "/home/milian/projects/src/heaptrack/build-unwind-tables/heaptrack.threaded.8761.zst"
      starting application, this might take some time...
      heaptrack stats:
              allocations:            403359
              leaked allocations:     0
              temporary allocations:  0
      Heaptrack finished! Now run the following to investigate the data:
      
        heaptrack --analyze "/home/milian/projects/src/heaptrack/build-unwind-tables/heaptrack.threaded.8761.zst"
      
       Performance counter stats for './bin/heaptrack ./tests/manual/threaded':
      
               10.563,39 msec task-clock:u              #    3,828 CPUs utilized
                       0      context-switches:u        #    0,000 K/sec
                       0      cpu-migrations:u          #    0,000 K/sec
                  11.483      page-faults:u             #    0,001 M/sec
          13.180.119.787      cycles:u                  #    1,248 GHz
          11.499.050.817      instructions:u            #    0,87  insn per cycle
           2.617.513.665      branches:u                #  247,791 M/sec
              41.612.348      branch-misses:u           #    1,59% of all branches
      
             2,759435712 seconds time elapsed
      
             6,641991000 seconds user
             3,927803000 seconds sys
      ```
      
      With libunwind:
      
      ```
      $ perf stat heaptrack ./tests/manual/threaded
      heaptrack output will be written to "/home/milian/projects/build/heaptrack/heaptrack.threaded.7136.zst"
      starting application, this might take some time...
      heaptrack stats:
              allocations:            403293
              leaked allocations:     0
              temporary allocations:  0
      Heaptrack finished! Now run the following to investigate the data:
      
        heaptrack --analyze "/home/milian/projects/build/heaptrack/heaptrack.threaded.7136.zst"
      
       Performance counter stats for 'heaptrack ./tests/manual/threaded':
      
                1.336,98 msec task-clock:u              #    2,730 CPUs utilized
                       0      context-switches:u        #    0,000 K/sec
                       0      cpu-migrations:u          #    0,000 K/sec
                  36.905      page-faults:u             #    0,028 M/sec
           1.909.003.446      cycles:u                  #    1,428 GHz
           2.485.908.851      instructions:u            #    1,30  insn per cycle
             448.570.458      branches:u                #  335,510 M/sec
               4.876.436      branch-misses:u           #    1,09% of all branches
      
             0,489731820 seconds time elapsed
      
             0,798096000 seconds user
             0,564706000 seconds sys
      ```
      
      As can be seen, using libunwind is roughly 5x faster for heaptrack
      and this test case on my machine here.
      8023779f
    • Volodymyr Nikolaichuk's avatar
  10. 20 Oct, 2019 2 commits
  11. 15 Oct, 2019 2 commits
  12. 13 Oct, 2019 1 commit
  13. 09 Oct, 2019 1 commit
  14. 03 Oct, 2019 3 commits
  15. 24 Sep, 2019 1 commit
  16. 22 Sep, 2019 1 commit
    • David Faure's avatar
      Add unittest for Parser · b2d80620
      David Faure authored
      Summary:
      to make sure optimizations don't break the actual parsing
      (I will neither confirm nor deny that there was bug in operator== of
      the commit that ports to unordered_map at some point, due to || instead
      of &&...)
      
      Reviewers: mwolff
      
      Reviewed By: mwolff
      
      Differential Revision: https://phabricator.kde.org/D24105
      b2d80620
  17. 20 Sep, 2019 3 commits
  18. 18 Sep, 2019 1 commit