- 28 May, 2013 6 commits
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
through the 172 phony router we have setup on the control node. This is silly to do for local traffic, but getting XEN guests to not do it, turned into a pit that I didn't want to enter. We want this so that arplockdown works properly; the mac address is really the client not a router. Revisit later.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Jonathon Duerig authored
-
- 24 May, 2013 1 commit
-
-
Mike Hibler authored
Take care of an iSCSI race condition in Fedora15.
-
- 23 May, 2013 6 commits
-
-
Mike Hibler authored
Not sure how I got on this side track, but it is done.
-
Kirk Webb authored
-
Kirk Webb authored
-
Kirk Webb authored
loc-bstore: local blockstore support rem-bstore: remote blockstore support Check for these when a user attaches a blockstore to a local node (local blockstores), or to a link/lan (remote blockstores). All nodes in a lan containing one or more remote blockstores must have an OS with the remote blockstores feature.
-
Leigh B Stoller authored
boot. Need a better way to figure out wait times based on the host OS.
-
Leigh B Stoller authored
boot. Need a better way to figure out wait times based on the host OS.
-
- 22 May, 2013 15 commits
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
kernel command line, according to new loadinfo variable returned from tmcd. This is so we can tailor the amount of memory per node type.
-
Leigh B Stoller authored
Mike's instruction. Faster, better, slicker then snot.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
when we get the RPC results.
-
Leigh B Stoller authored
Return the dom0mem node attribute so that slicefix can use it to set it in the grub config file. Small fix to how loadinfo determine the image for a pcvm; use the def_boot_osid joined with the partitions table, like we do for real nodes. Did not like the special case.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
- 21 May, 2013 5 commits
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
- 20 May, 2013 1 commit
-
-
Jonathon Duerig authored
-
- 18 May, 2013 2 commits
-
-
Mike Hibler authored
The "-k" option (hey, it was the best available letter!) takes a size in MB with which the frisbee client and server will first try to size their UDP socket buffers. They may still wind up with a smaller size, depending on what the OS supports. Fixed the burst logging logic so that we correctly trace overrun conditions.
-
Mike Hibler authored
The Storage Subsystem Whack-a-Mole game continues! I smack down the bugs in the LVM version, and up pops ZFS problems. Wham! Down goes ZFS, up pops Vinum...
-
- 17 May, 2013 4 commits
-
-
Leigh B Stoller authored
apod'ing the host while it is still stopping and saving containers.
-
Leigh B Stoller authored
of on ops, so that we can handle images in /usr/testbed/images.
-
Leigh B Stoller authored
Tired of messing with it in mysql.
-
Leigh B Stoller authored
lookup had failed, and it seems to be transient. No ideas why.
-