- 20 Sep, 2006 1 commit
-
-
Leigh B. Stoller authored
doing a Start Run. On the web page, there is a new checkbox, and on ops, template_startrun takes a new -m option. Caveat: You cannot specify a new NS file, yet. The original file is reparsed, and the idea is that a change in the template parameters will result in a change to the topology. I will add the ability to specify a new NS file in the next revision of this change. If you really really want to change the NS file, go to /proj/$pid/exp/$eid/archive/nsdata and edit nsfile.ns ... In addtion, DATASTORE is now defined while parsing the NS file. This turned to be quite the headache!
-
- 19 Sep, 2006 19 commits
-
-
Robert Ricci authored
tell it where the file is.
-
Robert Ricci authored
-
Robert Ricci authored
than the EWMA client. Also, fix an awkward ordering issue with the event system when initial condidtions are in use.
-
Robert Ricci authored
throughput numbers until we get an authoritative measurement. Note: I've left an XXX for Jon with this commit.
-
Kirk Webb authored
Minor fix to Rob's fix.
-
Robert Ricci authored
there would be exactly one instance of = on each line (which just look like shell environment variable declarlations.) Fixed this by forcing the line to be split in two - everything after the first = is part of the second string. Note that this does not handle 'escaped' =s in an sane way. Thus, if you have an environment variable with a = in its name, it will get split incorrectly. We'll worry about this one if we see it. :)
-
Leigh B. Stoller authored
swapped out event when endrun fails for some reason.
-
Leigh B. Stoller authored
-
Mike Hibler authored
output to the Sacred File <foo>.xmit, which as the name would imply, contains both transmit and receive packets.
-
Leigh B. Stoller authored
-
Mike Hibler authored
Fix a couple of typos. Fix a couple of spellos.
-
Leigh B. Stoller authored
-
Mike Hibler authored
-
Leigh B. Stoller authored
created by assign wrapper for linktrace.
-
Mike Hibler authored
Seems more intuitive that taking a snapshot does overwrite previous snapshots. Does admit the possibility of excessive logfile buildup. Nit-picky cleanups.
-
Mike Hibler authored
(i.e. not one for each direction). Creates a single ".both" file rather than ".recv" and ".xmit"
-
Leigh B. Stoller authored
stopping!
-
Leigh B. Stoller authored
-
Leigh B. Stoller authored
creating masses of duplicates that are probably confusing the hell out of the event scheduler.
-
- 18 Sep, 2006 2 commits
-
-
Kirk Webb authored
Modify the monitor to use the event system directly via the python SWIG wrapper object (requested by Rob). The monitor no longer forks and execs tevc for set_link operations. Tested the additional code here by transplanting it into a test script. Works as expected there, but has not been tested in situ.
-
Mike Hibler authored
Rob added code to let you put plab nodes in a LAN (with protocol "ipv4") so that the LAN could be traced. Meanwhile, Leigh has been adding completion events for various event types and creating various combo event groups for addressing all elements of a LAN, all LANs, etc. For pelab we have a link "reset" event which is sent to the "__all_lans" event group to reset the shaping of all links/lans. Unfortunately, plab nodes don't run a delay agent, so link events sent there fall on deaf ears. Ergo, the event scheduler waits for completions from all agents it send the "reset" to, but the plab nodes will never respond since there are no link agents.
-
- 16 Sep, 2006 1 commit
-
-
Leigh B. Stoller authored
event groups, not an implicit group handled by the agent.
-
- 15 Sep, 2006 5 commits
-
-
Jonathon Duerig authored
LeastSquaresThroughput now stores the last reported measurement to the monitor. It will send an authoritative report if the slope indicates saturation and the new measurement is different from the old. And it will send a tentative report of the slope indicates no saturation and the new measurement is greater than the old. Moderately tested(only in replay).
-
Mike Hibler authored
* generate the initial conditions for monitors to pass into the stubs (must use -i to start-experiment to do this) * make sure install-tarball does not return til tarballs are installed! (or til timeout) * move ip mapping and initial conditions files to /local/logs so they become part of the record * fix up exit status' returned by auto-* stubs so program-agent can detect real failures
-
Mike Hibler authored
script will work on nodes and not just ops. Add the -r option for calling from a remote (non-ops) node.
-
Mike Hibler authored
-
Leigh B. Stoller authored
-
- 14 Sep, 2006 12 commits
-
-
Robert Ricci authored
command-line.
-
Robert Ricci authored
elab nodes for the simple model - when no real plab nodes are being used.
-
Leigh B. Stoller authored
reload and halt events send proper completion events. This is required for stoprun and startrun to work correctly. On stoprun the logs are not collected until the programs have stopped, and on startrun we do not want to proceed until all the agents have reloaded their environments.
-
Mike Hibler authored
-
Leigh B. Stoller authored
to wait for the completion event.
-
Mike Hibler authored
-
Leigh B. Stoller authored
to tevc to wait for the reset to complete: tevc -w -e testbed/TT now link0 reset or tevc -w -e testbed/TT now __all_lans reset where __all_lans in another internally created event group.
-
Leigh B. Stoller authored
knows when the logfiles are actually rolled. Event groups complicated things a bit. To make this work properly, we no longer subscribe to the link-tracemon event, but instead use a real event group, created by assign wrapper for all of the linktrace agents. So, you can know do things like this: tevc -w -e testbed/TT now link0_tracemon snapshot or tevc -w -e testbed/TT now __all_tracemon snapshot where __all_tracemon is a group of all tracemon agents for all links and lans. I plan to change loghole to use this.
-
Mike Hibler authored
-
Mike Hibler authored
Make a single call to delaysetup with the new -r (restart) option. Only subscribe to the lan-reset event if there are lan objects.
-
Mike Hibler authored
* sync the are-we-running-the-right-kernel? code with rc.<whateveritis> so that it behaves with a 5.x delay kernel * modify to support a -r "restart" option so we don't have to invoke twice
-
Jonathon Duerig authored
Added better monitoring of replay save/load format. Changed census function to reduce the possibility of future size errors. New monitoring is hierarchical and should be essentially free as long as the #define in saveload.cc is commented out. Added LeastSquaresThroughput to the sensorlist and the definitions in monitor.py. A couple of miscellaneous fixes.
-