GitLab

cron daily, on the fs node (ops) as root. Uses lots of configure variables
so that it does the right thing in any installation, without any
customization.

One possible caveat regarding quotas: If FS_NODE != USERNODE, they don't
have a login on the fs machine. So checking their quota won't work unless
the rpc.rquotad(8) daemon is running on FS_NODE, which we currently don't
do.

In order to do this right, I had to add a new configure var,
FS_WITH_QUOTAS, that has a space separated list of file systems that have
quotas enabled. (Ie the default is 'FS_WITH_QUOTAS="/q /users"'.) It
doesn't have any default, since I couldn't come up with a reasonable one.
All the defs files have been updated appropriately to define this new
variable.

When a user tries to create an imageid without
specifying a node to suck the image from, they are given
a warning screen explaining their situation,
with "confirm" and "back" buttons.

(also made the confirmation mechanism general so if we
 need to add more warning conditions, it'll be no problem.)

Make use of all available memory via the -M option to frisbee

Changed form respit error message:
"no such group" --> "group 'foo' is not in project 'bar'".

hopefully never to return again!

A couple of the changes Jay wanted:

 - move 'Node to Create Image From' above OS Features
 - make all Node Types default to checked

Also cleaned up footnotes a touch.

1. Implement PREQUEST message which passes a bit map of desired blocks.
   We still use the REQUEST message (start block + number of blocks) for
   full chunk requests as that is more efficient.  This message also
   includes a flag indicating whether it is a retry of a request we
   originally made or not.  This gives the server more accurate loss info.

2. More stats and tracing goo.


Frisbee client:

1. Add 'C' and 'W' command line options to specify amount of memory
   for chunk buffers (network buffering) and for write buffers (disk
   buffering).  The Emulab frisbee startup script uses these to partition
   up all the available memory on a machine.  Previously we were just
   using a fixed ~128MB even though our machines have 256 or 512MB of
   memory.  Also add the 'M' option which specifies the overall memory,
   internally dividing it up between chunk buffers and write buffers.

2. Add 'S' command line option to explicitly specify the server.  This
   allows us to make a feeb...um, "lightweight" authentication check
   on incoming messages.

3. Use the common BlockMap data struct to track which pieces of a chunk
   we have received.  This is easily inverted to make PREQUESTS and it is
   also smaller than the older byte-per-block technique.

4. Allow partial request-ahead.  Previously, we only issued request-ahead
   if there were enough empty chunk buffers for a maximum (2) request-ahead.

Frisbee server:

1. Use BlockMap for workQ elements.  An easy way to allow a complete merge
   of incoming requests with existing ones.

2. Check for overlap of incoming requests with the request currently
   being serviced.  This happens surprisingly often.

3. Dubious: burst gap becomes burst interval.  The latter takes into
   account the time required to read data, etc., in other words, we now
   have variable-sized gaps and put out bursts at specific times rather
   than having fixed gaps and putting out bursts at variable times.
   This gives us more accurate pacing over shorter time periods.  I
   thought this might be important for dynamic pacing.

4. Add 'W' command line option to specify a target bandwidth.  Frisbeed
   will use this to calculate a burst size/interval.

5. Rewrote the dynamic pacing code.  It is now easily as bad as before
   if not worse.  But it does have fewer magic constants!  Needs to be
   redone by someone who understands the TCP-friendly rate equation.

Imagezip:

1. add 'R' option to specify one or more partitions for which to force
   raw (naive) compression even if the FS format is understood.  Useful
   for benchmarking.

2. add 'D' option to allow "dangerous" writes.  In this mode, we don't
   do the fsync's or retries of failed writes.  Overrides the hack we put
   in for NFS.  Use this if writing to a local filesystem (or /dev/null).

3. Eliminate an extra copy of every chunk header.

Imageunzip:

1. Eliminate extra copy of decompressed data that we were doing between
   the single decompression buffer and the disk buffers.  Helps on slow
   machines (like gatech's 300Mhz machines with 66MHz memory bus).

2. Allow dynamic number of variable-sized write buffers.  Total memory
   not to exceed the writebufmem limit.  Previously we had a small number
   of fixed-size (256K) buffers.

3. Add debugging 'C' option to just compute a single CRC of the decompressed
   image.  Back-ported to older imageunzip and used to make sure my write
   buffer changes were correct.  Maybe handy for similar massive changes
   in the future.

request counter.

It means nothing and just takes up space and may cause confusion, and is
easy to reenable as soon as we want to.

Added processor type, location, inet connection type to widearea listing.

blog.

start, but was a dope!

(webidlecheck was removed in a separate commit.)

idletimes is the new commandline tool for checking idleness. It shows a
table like this:

PID          EID          Nodes  HrsIdle     Last Activity     Act. type
------------------------------------------------------------------------
AVQ          Tunnel           4   15.18   2003-04-07 21:18:20  tty
pces         toy              1    3.92   2003-04-08 08:34:02  tty
Spinglass    fawaz            1   13.76   2003-04-07 22:43:48  tty
TempleSCTP   FTP-REAL         1   26.40   2003-04-07 10:05:18  tty,net
testbed      bvclass          4   24.58   2003-04-07 11:54:13  net
testbed      ltest            1   14.37   2003-04-07 22:07:02  tty
testbed      ron-image        1  501.88   2003-03-18 13:36:28  cpu,ext,tty,net
testbed      Tone             1  501.88   2003-03-18 13:36:30  cpu,ext,tty,net

By default it only shows things that are over an idleness threshold. It
also has a mode to show all expts. Also can show idleness/activity by node
instead of by expt, which has a slightly different table. (s/Nodes/NodeID/)

idlemail isn't finished yet, but I don't want it to hold up idletimes and
the other changes any longer. It doesn't get used by anything yet, of
course.

as well commit it!). This is the new ipfw syntax that allows matching
on the nexthop destination chosen by ip_output.

so it is misleading.

in email.

	proc tb-use-endnodeshaping {onoff} {}
	proc tb-force-endnodeshaping {onoff} {}
	proc tb-set-multiplexed {link onoff} {}
	proc tb-set-endnodeshaping {link onoff} {}
	proc tb-set-noshaping {link onoff} {}

they go to the widearea_register page to get an account and fill in
the node info. Changed the registration page to take key,IP args so
that those fields can be embedded in the link we give them, and pre
entered into the form.

Negative times must die!!!

Modify os_setup return codes to enable "intelligent" retry;

Now os_setup returns:
  0 on success
  1 on one or more retry-friendly errors
 -1 on no-retry errors

tbswap.in checks os_setup's return code,
and will only retry on 1.

the number of hours correctly. (Was using idlehours mod 24.)

Axed a bunch of broken links.

the RHL image for the testbed.

* Now removes process accounting files
* Now removes backup files in /etc (files w/ a ~ or - appended)