1. 10 Apr, 2001 5 commits
  2. 09 Apr, 2001 10 commits
  3. 06 Apr, 2001 4 commits
  4. 05 Apr, 2001 6 commits
  5. 04 Apr, 2001 7 commits
  6. 02 Apr, 2001 2 commits
  7. 30 Mar, 2001 5 commits
    • Mike Hibler's avatar
      Big Ass Hack(tm): · 05456fd2
      Mike Hibler authored
      Add a "log" message which allows a client to send some text to TMCD which
      in turns appends it to a project/experiment specific log file.  Adds all new
      DoS routes to TMCD, and should perhaps be split off into its own daemon,
      but for now it gives a way for console-less sharks to report what they did.
    • Mike Hibler's avatar
    • Mac Newbold's avatar
      Fixed root user time limiting. · 19f7b393
      Mac Newbold authored
    • Leigh B. Stoller's avatar
      Reloading daemon. Looks for free nodes that have not been reloaded · 74d21844
      Leigh B. Stoller authored
      since the last reservation (as determined by last_reservation table).
      Picks one (randomly) from that set of nodes, and calls sched_reload on
      it. Then waits until the node has finished reloading, as determined by
      the reserved table, which gets cleared by the tmcd when the node first
      reboots after a scheduled reload. Sleeps 30 seconds, and then goes
      around again. So at most one node is tied up in a reload at a time,
      which seems like a good balance between trying to keep the machines in
      a pristine state, and having nodes available for use.
      The advantage of this approach is that instead of calling sched_reload
      on 40 nodes (after generating a new image) and watching the network
      meltdown, we can let the nodes reload at a slower pace. We could call
      sched_reload on allocated nodes so that they will load when freed, but
      we run into the problem of big experiments ending and causing meltdown.
      The downside is that this approach is a little too aggressive. Nodes
      will end up reloading after just a single experiment. Need finer grain
      control over when to reload, but I will leave that as an exercise for
    • Leigh B. Stoller's avatar
      Add -f (force) flag that says that if the node is reserved, don't do · f82712b4
      Leigh B. Stoller authored
      anything (don't put an entry in the reloads table). Just exit with non
      zero status to indicate that the node could not be loaded immediately.
      This is for use by the reloading daemon that I am writing up.
      Also did some house cleaning and removed lots of old cruft.
  8. 29 Mar, 2001 1 commit