1. 26 Jun, 2008 3 commits
  2. 08 Apr, 2008 1 commit
  3. 09 Feb, 2008 1 commit
    • Dan Gebhardt's avatar
      Some very basic infrastructure for generalized tools was added. · 639758e6
      Dan Gebhardt authored
      Some parts very "hacky", lots of XXX / TODOs.
      BARELY tested!!!! Don't use on the production system yet.
      Need to verify that things didn't break, especially with the automanager,
      the bgmon.pl "outage detection stuff", etc...
      See code's todos and also the file
      At this point:
       - mangerclient & automanagerclient did not change.
       - The manager, when a probe request is received, looks at the DB table
         "tool_spec" to retrieve the proper wrapperpath, formal parameter list, etc..
       - The manager assembles a message and sends it out to the appropriate
         path probers, which operate on the request as they have been
         (no major internal changes to the path probers).
       - The path probers call the toolwrapper to run the tests
       - The toolwrappers return a canonical result for that type of metric.
       - The path probers send the result and the actual parameters used by the
         tool to the data collector.
       - The data collector uses the toolname and actual parameters to get an
         idx number. This idx is stored in the "measured_by" field of this
         measurement's entry in the "pair_data" table.
  4. 07 Feb, 2008 1 commit
    • Dan Gebhardt's avatar
      Initial changes to support tool generalization. All command-line · caa4023a
      Dan Gebhardt authored
      arguments and result parsing handled by separate application wrappers.
      Currently fping and iperf supported.
      Not fully functional at this point: user interface needs extending
      to support the generalization, as well as getting the results back
      to "opsrecv".
      Also merged some of Mike's changes to allow for "private" managers
      to use during testing.
  5. 02 Feb, 2008 1 commit
    • Dan Gebhardt's avatar
      Checking in Mike's changes: · 322dbb59
      Dan Gebhardt authored
      - latency measurements under 2 second intervals now operate in "continuous"
        mode: a single "ping" process runs per destination, versus the "normal"
        approach of forking a new fping process for each measurement instance.
      - Note, that I found a bug which is not fixed in this checkin: if a latency
        test is running in continuous mode and another latency measurement request
        is received with a shorter interval, the "continuous" ping process is not
        re-initialized with the new, shorter interval.
  6. 23 Oct, 2007 1 commit
  7. 22 Oct, 2007 3 commits
  8. 19 Oct, 2007 1 commit
  9. 02 Oct, 2007 1 commit
  10. 26 Jun, 2007 3 commits
    • Sachin Goyal's avatar
      · 4f6ed4f3
      Sachin Goyal authored
      Setting the sql mode for the database session to 'STRCIT_ALL'.
      This is to handle the database setting difference between mysql on Ops
      and mysql on DataPository.
    • Sachin Goyal's avatar
      · 5ebb54de
      Sachin Goyal authored
      Added an extra layer of protection to prevent to-and-fro switching
      between different nodes on a site due to CPU USAGE difference.
      Previously if a node has less cpu load than current best node (discounted
      by a threshold of 10). Now this has to happen 2 times consecutively
      for the switching to happen.
    • Sachin Goyal's avatar
      · 9b756cf8
      Sachin Goyal authored
      Added randomness for initial starting of bw probes scheduled by
  11. 14 Jun, 2007 2 commits
    • Sachin Goyal's avatar
      · 5cbf14c3
      Sachin Goyal authored
      Added a lower limit on the bandwidth measurements frequency
    • Sachin Goyal's avatar
      · 6d2d8a38
      Sachin Goyal authored
      Updates for better handling of getstatus failures
      1 - libwanetmon.pm/sendcmd: tcp timeout is changed from 1 sec to 3 sec
      2 - Now we remove a node from measurement only if it fails two consecutive
          attempts (currently a getstatus probe happens every half an hour).
          Though if there exists multiple nodes at a single site, it can
          switch over to other node after a single getstatus failure.
  12. 13 Jun, 2007 1 commit
  13. 14 Mar, 2007 2 commits
  14. 12 Mar, 2007 3 commits
  15. 21 Feb, 2007 1 commit
  16. 12 Feb, 2007 1 commit
  17. 07 Feb, 2007 1 commit
  18. 02 Feb, 2007 1 commit
    • Mike Hibler's avatar
      The paint wasn't even dry on the last plab tarball before I have moved on... · c2570cfc
      Mike Hibler authored
      Rev 20 of the tarball has no new function, it is just slimmed down.
      I replaced our large statically linked binaries with dynamically linked ones.
      Also found and stripped a couple of other binaries.
      The resulting tarball goes from 5.7MB to 0.9MB.
      The Makefile changes are to incorporate the NOSTATIC=1 environment hack
      to enable building the dynamic binaries above.
  19. 30 Jan, 2007 1 commit
  20. 16 Jan, 2007 2 commits
  21. 12 Jan, 2007 1 commit
  22. 14 Dec, 2006 1 commit
  23. 11 Dec, 2006 2 commits
  24. 08 Dec, 2006 1 commit
  25. 06 Dec, 2006 1 commit
  26. 01 Dec, 2006 3 commits