- 09 Feb, 2004 2 commits
-
-
Leigh B. Stoller authored
seconds it takes the kernel to decide the other machine is not responding (as will happens as machines are rebooting), down to 5 seconds, using a SIGARLM.
-
Leigh B. Stoller authored
used. Add .pid file creation in /var/run to kill daemon from the new rc.syncserver script in tmcd client code. Add -v flag to increase server verbosity. Add -l argument to specify where to write the log file.
-
- 06 Feb, 2004 3 commits
-
-
Mac Newbold authored
-
Mac Newbold authored
-
Leigh B. Stoller authored
Not perfect, as it takes about 30 seconds to timeout. Need to add a timer to it.
-
- 05 Feb, 2004 7 commits
-
-
Leigh B. Stoller authored
accessible.
-
Leigh B. Stoller authored
way to do this, but it will do. Sigh.
-
Leigh B. Stoller authored
inconsistent DB state. One more left ... no time to mess with it right now.
-
Robert Ricci authored
for Jon's ipassign stuff.
-
Leigh B. Stoller authored
is_info table.
-
Leigh B. Stoller authored
makefile needs to be fixed (remove fbsd/linux subdir cruft).
-
Leigh B. Stoller authored
-
- 04 Feb, 2004 4 commits
-
-
Leigh B. Stoller authored
not rebooted or reloaded, get a reconfig instead. Currently, I check the opmode of the node (NORMALv2), but that is horribly bogus. Need a better way to determine that a node can be reconfiged, probably by looking the def_boot_osid feature list. Later.
-
Leigh B. Stoller authored
vnodes (via their pnode).
-
Leigh B. Stoller authored
instead of rebooting. If the reconfig fails, fail through to reboot. A reconfig will "halt" the current vnodes (or remove ones that are no longer assigned to the node) reconfig the pnode, and then restart the vnodes that are still assigned to the node (or create new ones for newly assigned vnodes). A halt stops the vnode, but leaves the vnode filesystem intact. Not bothering to reconfig individual vnodes yet since thats pretty much like a reboot of a vnode. Difference in time is tiny. Lbs
-
longmore authored
automatically load tar files. -Henry Longmore (longmore@cs), 04 Feb 04
-
- 03 Feb, 2004 7 commits
-
-
Leigh B. Stoller authored
-
Robert Ricci authored
runtime quite a bit, because it has less scoring work to do. Add METIS as a coarsening algorithm - we shoot for making conglomerates of size 10.
-
longmore authored
"will run /proj/pid/runme.nodeA on nodeA and /proj/pid/runme.nodeA on nodeB" to will run /proj/pid/runme.nodeA on nodeA and /proj/pid/runme.nodeB on nodeB" -Henry Longmore (longmore@cs), 03 Feb 04
-
Leigh B. Stoller authored
node type, but allow it to be overridden with tb-set-jail-os().
-
Leigh B. Stoller authored
other changes to the commvirtsig branch. * Run assign with nice; when assign is cranking (or when two are cranking!) boss gets really sluggish (web, DB). * Minor change to "impotent" option; run a little longer and print out what the vlan table would look like. * Two trivial grammer changes.
-
Leigh B. Stoller authored
parser with new functions tb-set-jail-os() and tb-set-delay-os()). Prefer these over anything in the node_types table. Makes it easier to test new images in the various configurations.
-
Leigh B. Stoller authored
jail and delay node OSIDs. When set, will override anything in the node_types table. Use with caution.
-
- 02 Feb, 2004 12 commits
-
-
Jonathon Duerig authored
-
Jonathon Duerig authored
-
Leigh B. Stoller authored
for the experiments table.
-
Leigh B. Stoller authored
-
Leigh B. Stoller authored
paper effort. Note, not an osid, but an osname like we specify for a virt_node. Lookup rules are the same; first check the current project for a match, and then check emulab-ops.
-
Jonathon Duerig authored
Modified routecalc, adding a command line option to dump all route lengths to a file for statistical analysis.
-
Jonathon Duerig authored
-
Robert Ricci authored
is broken right now. Told Jon I'd do this so that he can check in - so that we have snapshots of his code, but he doesn't have to worry about breaking the build (yet.)
-
Mike Hibler authored
-
Jonathon Duerig authored
-
Leigh B. Stoller authored
anyway, so not as important anymore.
-
Jay Lepreau authored
-
- 31 Jan, 2004 1 commit
-
-
Shashi Guruprasad authored
from one pnode to another during a swapmod.
-
- 30 Jan, 2004 4 commits
-
-
Mike Hibler authored
From the code: # N.B. privnet is setup first even before the default route. # This is because the gateway for the default route is on the # privnet, but our control net interface is not (because it has # a 255.255.255.255 netmask by virtue of being an alias on the # real control interface). Thus there is no way to use the # default route until the privnet route is up (ARP complains # about "host is not on local network").
-
Robert Ricci authored
in find_best_link(), don't try plinks that already have a non-emulated link on them, when we're doing an emulated link.
-
Mike Hibler authored
- the problem with broadcast when using fake MACs instead of encapsulation - why ARP is hard in our environment
-
Shashi Guruprasad authored
-