Bits of documentation

diff --git a/NOTES b/NOTES
new file mode 100644 (file)
index 0000000..1412bf7
--- /dev/null
+++ b/NOTES
@@ -0,0 +1,48 @@
+### Structure of queue directories ###
+
+<queue>/hosts/<hostname>/      Jobs queued for the given host
+                               (they are executed in the lexicographic order of <job-id>s)
+       /<job-id>.job           Symlink to <queue>/jobs/<job-id>.job
+       /<job-id>.stat          (Optional) status of the job
+       /<job-id>.tmp           Used temporarily by brun to store the script actually
+                               sent to the host (can be inspected if something goes wrong)
+
+<queue>/jobs/<job-id>.job      All jobs issued on this queue, including those which
+                               are no longer queued for any machine
+
+<queue>/log                    Log of actions on this queue. Lines look this way:
+                               YYYY-MM-DD HH:MM:SS <host> <job-id> <status> [<msg>]
+                               <status> and <msg> correspond to "Status" and "Message"
+                               in status files.
+
+<queue>/status-fifo            FIFO used for reporting status of subprocesses by `bprun'
+
+### Job files ###
+
+Mail-like structure. First come the headers (<keyword>:<spaces><value>), keywords are
+case-sensitive, no multi-line fields allowed, then an empty line and then the body
+(i.e., commands to be executed on the remote host).
+
+Known header fields:
+
+ID: <job-id>                   Identifier of the job, unique in the scope of a queue
+Subject: <subject>             Subject to be displayed to the user
+
+### Status files ###
+
+Structure identical to job headers, but they do not contain a body.
+
+Known fields:
+
+Time: <timestamp>              UNIX timestamp of the last status change
+Status: <code>                 Machine-readable status of the job:
+                               NOPING - host does not respond to ping
+                               NOXFER - transfer of the job body to a temporary file
+                                    on the host has failed
+                               OK - job executed successfully (however, the job will
+                                    be removed from the queue immediately, so you are
+                                    not likely to see this code)
+                               FAILED - job failed to execute (i.e., it returned
+                                        a non-zero exit code)
+                               INTERR - internal error of BEX
+Message: <msg>                 (Optional) human-readable message explaining the status

diff --git a/TODO b/TODO
new file mode 100644 (file)
index 0000000..63d6f1d
--- /dev/null
+++ b/TODO
@@ -0,0 +1,11 @@
+- benq: options for specifying subject and other params
+- benq: take job from file
+- benq: requeue job
+- bprun: option for setting max # of running jobs
+- bprun --job
+- bprun --curses
+- Locking
+- rsync, rsync-only
+- Rename machine -> host
+- ssh options
+- Detector of orphans (unused queue dirs, jobs on non-existent machines, non-queued jobs)

diff --git a/brun b/brun
index aa8a51af6db6268e35725f9f2abff8d3b1cac4c8..901c7d5186536b3c997b67f3b3e9c5ffd3369972 100755 (executable)
--- a/brun
+++ b/brun
@@ -53,9 +53,6 @@ sub run_job($$$) {
        my ($job, $queue, $mach) = @_;
        my $jid = $job->{'ID'};
 
-       # FIXME: rsyncing, rsync-only jobs
-       # FIXME: Locking
-
        my $tmp = $queue->temp_file($mach, $jid);
        open T, '>', $tmp or die;
        if (defined $BEX::Config::job_prolog) {