1. 04 Jun, 2010 1 commit
  2. 28 May, 2010 4 commits
  3. 27 May, 2010 1 commit
  4. 25 May, 2010 2 commits
  5. 24 May, 2010 1 commit
  6. 17 May, 2010 3 commits
  7. 12 May, 2010 1 commit
  8. 11 May, 2010 1 commit
  9. 10 May, 2010 5 commits
  10. 04 May, 2010 1 commit
    • Kevin Atkinson's avatar
      BUG FIX: Make parse errors "User" errors again. · 7a148ab4
      Kevin Atkinson authored
      The problem is that comit f6d81289
      (Changes from Pat Gunn at CMU: allow "at swapout"...) changed the exit
      status of parse.proxy with this line:
        -    exec("nice -15 $parser @ARGV $nsfile");
        +    exec("nice -15 $parser @ARGV $nsfile|tee $tempdir/output.txt");
      so parse-ns was not detecting that it failed.  It then processed to
      run xmlconvert which detected that the ns parse failed.
      
      The causes two problems, 1) my error handling code depends on the fact
      that parse.proxy failed in order to determine it was a user error and
      2) it causes the "Syntax Check" option to always report correct syntax
      even when it shouldn't.
      7a148ab4
  11. 27 Apr, 2010 1 commit
  12. 26 Apr, 2010 2 commits
  13. 20 Apr, 2010 2 commits
  14. 15 Apr, 2010 3 commits
  15. 14 Apr, 2010 9 commits
    • Jonathon Duerig's avatar
      Added disk image support to ptopgen and a set of 0.2 schema files which allow... · 98517b23
      Jonathon Duerig authored
      Added disk image support to ptopgen and a set of 0.2 schema files which allow disk images in the rspec..
      98517b23
    • Weibin Sun's avatar
      fix bug: in snmpit_hp module, the SNMP session with MIB returns the OID as... · a3e55dbf
      Weibin Sun authored
      fix bug: in snmpit_hp module, the SNMP session with MIB returns the OID as strings not numbers even for Openflow entry, however, the meaningful string OID cannot be used to get the next entry in MIB table! So getUsedOpenflowListenerPorts has to modify the OID of the current entry to be the numbered format.
      a3e55dbf
    • Mike Hibler's avatar
      Reduce from 3 DB queries per node to 1 total query. · e4173cfa
      Mike Hibler authored
      Reduce the running time by 50%...from 1 second to 0.5 seconds.
      A marvel of pointless optimization!  At the time it seemed like it might
      matter, but the case that is really slow (requiring a call to nalloc per
      node) is still slow.  But it was a twenty minute diversion.
      e4173cfa
    • Weibin Sun's avatar
    • Weibin Sun's avatar
    • Weibin Sun's avatar
      lock is added to snmpit.in for Openflow listener port assigning. Unlike the... · 101e059c
      Weibin Sun authored
      lock is added to snmpit.in for Openflow listener port assigning. Unlike the small locks in snmpit stack modules, the OF lock is a big lock in snmpit.in because the critical section includes both the getUsedOpenflowListenerPorts and setOpenflowListener functions and if stack/device small locks are used we have to grab multiple small locks one by one with the risk of dead lock.
      101e059c
    • Mike Hibler's avatar
      Add some useful elabinelab sitevars. · 9bb38c10
      Mike Hibler authored
      New sitevars:
        elabinelab/singlenet     set the system-wide default for cnet implementation
        elabinelab/boss_osid     default OSID for boss node
        elabinelab/ops_osid      default OSID for ops node
        elabinelab/fs_osid       default OSID for fs node
      
      Also mark the various elabinelab/*pkg* sitevars as deprecated.  Package
      versions are just too dependent on the OS running and we almost always
      wind up overriding these sitevars in rc.mkelab anyway.
      9bb38c10
    • Mike Hibler's avatar
      Changes for speeding up elabinelab server setup. · 6feda7d3
      Mike Hibler authored
      Boss/ops/fs: reboot them together after setup rather than serially.
      
      Nodes: leave them in PXEWAIT throughout the setup, until after boss has
      been rebooted.  At that point we send them the new bootinfo RESTART command
      telling pxeboot to re-DHCP and use the new info obtained (next-server) to
      contact a potentially new boss node.  This is a quick way to switch a node
      in PXEWAIT from talking to the outer boss to talking to the inner one.
      
      A significant number of rinky-dink changes were needed to do this, primarily
      adding a new state, PXELIMBO, where nodes can be sent to sit until they are
      restarted.  It turns out, just putting them in an existing state such as
      PXEWAKEUP or SHUTDOWN wouldn't work, as they tend to timeout or otherwise
      reboot.
      6feda7d3
    • Leigh B Stoller's avatar
      Fix syntax error. · a3182f39
      Leigh B Stoller authored
      a3182f39
  16. 13 Apr, 2010 3 commits