- 03 Oct, 2012 1 commit
-
-
Kirk Webb authored
-
- 01 Oct, 2012 2 commits
-
-
Mike Hibler authored
Only works if the image file is readable since mfrisbee protocol doesn't return this info, at least not right now.
-
Leigh B Stoller authored
can wreak havoc.c
-
- 28 Sep, 2012 13 commits
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
rules to ensure that the guest cannot change their assigned IP.
-
Leigh B Stoller authored
-
Jonathon Duerig authored
-
Jonathon Duerig authored
-
Leigh B Stoller authored
on modern linux, instead of our older qdisc hacks.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
die. Mostly a workaround, since I do not know why the signal that was sent is not delivered when mkvnode unblocks them. So, just send the signal multiple times. Gack. Needs a lot more thought!
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
- 27 Sep, 2012 3 commits
-
-
Mike Hibler authored
-
Mike Hibler authored
Cannot figure out why this happened, but at least don't crash if it happens again!
-
Jonathon Duerig authored
-
- 26 Sep, 2012 7 commits
-
-
Jonathon Duerig authored
-
Jonathon Duerig authored
Conflicts: protogeni/scripts/GNUmakefile.in
-
Jonathon Duerig authored
All incoming rspecs are now validated with rspeclint. Multiple Create calls are now permitted. Slivers now have URNs at allocation time. Delete now returns a list of ex-slivers. Advertisement now specifies an operational state machine. Other minor fixes.
-
Gary Wong authored
-
Gary Wong authored
-
Gary Wong authored
-
Gary Wong authored
-
- 25 Sep, 2012 14 commits
-
-
Mike Hibler authored
Previously tb-set-node-failure-mode of "nonfatal" only applied to failures when rebooting a node. If there was an error during the disk reload phase, the experiment would still fail. This makes sense, as it is pretty dicey to let a node boot with an unloaded or partially-loaded disk. But there are situations, such as 500+ node experiments on PRObE, where it makes sense to not fail the experiment. What we do if a node fails reload, is to clear the OSIDs and partition info for the node and then force it to reboot (by setting the state to TBFAILED, for which there is a REBOOT trigger in stated). This causes the node to come up and park in pxeboot in the PXEWAIT state. It should remain in this state across reboots. The user can manually os_load the machine, or do a swap modify which will force the node to try to reload the original OS. Since this may not be for everyone, this new allow non-fatal osload failures requires that the "OsloadFailNonfatal" feature be enabled. This allows the new behavior to be global, per-group, per-experiment or per-user. The default is disabled.
-
Mike Hibler authored
-
Leigh B Stoller authored
Snapshots are done a little differently then openvz of course, since there are potentially multiple disk partitions and a kernel. The basic operation is: 1. Fire off reboot_prepare from boss. Changes to reboot_prepare result in the guest "halting" insted of rebooting. 2. Fire off the create-image client script, which will take imagezips of all of the disks (except the swap partition), and grab a copy of the kernel. A new xm.conf file is written, and then the directory is first tar'ed and then we imagezip that bundle for upload. 3. When booting a guest, we now look for guest images that are packaged in this way, although we still support the older method for backwards compatability. All of the disks are restored, and a new xm.conf created that points to the new kernel.
-
Leigh B Stoller authored
can mount the NFS filesystems. Only doing this for shared hosts at this time, to avoid driving up the number of exports too much. Might reconsider later.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
in the proper reverse map.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
of reboot since otherwise the domU just reboots and keeps running.
-
Leigh B Stoller authored
they do not have to be created at swapin. This is mostly for the tutorial sessions, where we have dozens of containers launching at the same time.
-
Leigh B Stoller authored
Works a lot better!
-