Skip to content

Commit

Permalink
Consistently capitalize Worker, Job, etc, when they refer to eHive co…
Browse files Browse the repository at this point in the history
…mponents
  • Loading branch information
muffato committed Apr 8, 2018
1 parent 5987f09 commit ac8bf38
Show file tree
Hide file tree
Showing 11 changed files with 107 additions and 107 deletions.
4 changes: 2 additions & 2 deletions docs/advanced_usage/mpi.rst
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ Resource Class in your pipeline.
}
}

2. You need to add the analysis to your PipeConfig:
2. You need to add the Analysis to your PipeConfig:

::

Expand Down Expand Up @@ -159,7 +159,7 @@ define the correct Resource Class and command lines in eHive.
times. The memory requested is allocated for each _ptile_ (so
64/4*16GB=256GB in total in the example).

2. You need to add the analysis to your PipeConfig:
2. You need to add the Analysis to your PipeConfig:

::

Expand Down
66 changes: 33 additions & 33 deletions scripts/beekeeper.pl
Original file line number Diff line number Diff line change
Expand Up @@ -263,7 +263,7 @@ sub main {
if($reset_job_id) { $queen->reset_job_by_dbID_and_sync($reset_job_id); }

if($job_id_for_output) {
printf("===== job output\n");
printf("===== Job output\n");
my $job = $self->{'dba'}->get_AnalysisJobAdaptor->fetch_by_dbID($job_id_for_output);
print $job->toString. "\n";
}
Expand Down Expand Up @@ -341,7 +341,7 @@ sub main {
my $has_task = ($reset_all_jobs || $reset_failed_jobs || $reset_done_jobs || $unblock_semaphored_jobs || $forgive_failed_jobs || $discard_ready_jobs);
if($reset_all_jobs || $reset_failed_jobs || $reset_done_jobs) {
if (($reset_all_jobs || $reset_done_jobs) and not $self->{'analyses_pattern'}) {
log_and_die($self, "Beekeeper : do you really want to reset *all* the jobs ? If yes, add \"-analyses_pattern '%'\" to the command line\n");
log_and_die($self, "Beekeeper : do you really want to reset *all* the Jobs ? If yes, add \"-analyses_pattern '%'\" to the command line\n");
}
my $statuses_to_reset = $reset_failed_jobs ? [ 'FAILED' ] : ($reset_done_jobs ? [ 'DONE', 'PASSED_ON' ] : [ 'DONE', 'FAILED', 'PASSED_ON' ]);
$self->{'dba'}->get_AnalysisJobAdaptor->reset_jobs_for_analysis_id( $list_of_analyses, $statuses_to_reset );
Expand Down Expand Up @@ -390,7 +390,7 @@ sub main {
Bio::EnsEMBL::Hive::Scheduler::schedule_workers_resync_if_necessary($queen, $valley, $list_of_analyses); # show what would be submitted, but do not actually submit

if($show_failed_jobs) {
print("===== failed jobs\n");
print("===== failed Jobs\n");
my $failed_job_list = $self->{'dba'}->get_AnalysisJobAdaptor->fetch_all_by_analysis_id_status( $list_of_analyses , 'FAILED');

foreach my $job (@{$failed_job_list}) {
Expand Down Expand Up @@ -469,7 +469,7 @@ sub register_beekeeper {

$self->{'dba'}->get_BeekeeperAdaptor->store($beekeeper);
unless ($self->{'beekeeper_id'} = $beekeeper->dbID) {
die "There was a problem registering this beekeeper with the eHive database.";
die "There was a problem registering this Beekeeper with the eHive database.";
}
return $beekeeper;
}
Expand Down Expand Up @@ -502,8 +502,8 @@ sub run_autonomously {

if (($loop_until eq 'JOB_FAILURE') &&
(scalar(@job_fail_statuses)) > 0) {
print "Beekeeper : last loop because at least one job failed and loop-until mode is '$loop_until'\n";
print "Beekeeper : details from analyses with failed jobs:\n";
print "Beekeeper : last loop because at least one Job failed and loop-until mode is '$loop_until'\n";
print "Beekeeper : details from analyses with failed Jobs:\n";
print join("\n", map {$_->{'message'}} @job_fail_statuses) . "\n";
$found_reason_to_exit = 1;
last BKLOOP;
Expand All @@ -521,7 +521,7 @@ sub run_autonomously {
# loop_until_mode is either job_failure or analysis_failure, and both of these exit on analysis failure
unless ($found_reason_to_exit) {
print "Beekeeper : last loop because at least one analysis failed and loop-until mode is '$loop_until'\n";
print "Beekeeper : details from analyses with failed jobs:\n";
print "Beekeeper : details from analyses with failed Jobs:\n";
print join("\n", map {$_->{'message'}} @analysis_fail_statuses) . "\n";
$found_reason_to_exit = 1;
last BKLOOP;
Expand Down Expand Up @@ -627,7 +627,7 @@ sub run_autonomously {
$self->{'beekeeper'}->adaptor->bury_other_beekeepers($self->{'beekeeper'});
if ($self->{'beekeeper'}->check_if_blocked()) {
print "Beekeeper : We have been blocked !\n".
"This can happen if a job has explicitly required beekeeper to stop (have a look at log_message).\n".
"This can happen if a Job has explicitly required the Beekeeper to stop (have a look at log_message).\n".
"It may also happen if someone has set is_blocked=1 in the beekeeper table for beekeeper_id=".$self->{'beekeeper_id'}.".\n";
} else {
last;
Expand Down Expand Up @@ -707,11 +707,11 @@ =head1 NAME
=head1 DESCRIPTION
The Beekeeper is in charge of interfacing between the eHive database a compute resource or 'compute farm'.
Its job is to synchronise both, to assess the compute requirements of the pipeline
Its Job is to synchronise both, to assess the compute requirements of the pipeline
and to send the requested number of workers to open machines via the runWorker.pl script.
It is also responsible for identifying workers which died
unexpectedly so that dead workers can be released and unfinished jobs reclaimed.
unexpectedly so that dead workers can be released and unfinished Jobs reclaimed.
=head1 USAGE EXAMPLES
Expand All @@ -730,10 +730,10 @@ =head1 USAGE EXAMPLES
# Restrict the normal execution to one iteration only - can be used for testing a newly set up pipeline
beekeeper.pl -url mysql://username:secret@hostname:port/long_mult_test -run
# Reset failed 'buggy_analysis' jobs to 'READY' state, so that they can be run again
# Reset failed 'buggy_analysis' Jobs to 'READY' state, so that they can be run again
beekeeper.pl -url mysql://username:secret@hostname:port/long_mult_test -analyses_pattern buggy_analysis -reset_failed_jobs
# Do a cleanup: find and bury dead workers, reclaim their jobs
# Do a cleanup: find and bury dead workers, reclaim their Jobs
beekeeper.pl -url mysql://username:secret@hostname:port/long_mult_test -dead
=head1 OPTIONS
Expand Down Expand Up @@ -784,21 +784,21 @@ =head2 Looping control
=item --loop_until
sets the level of event that will cause the beekeeper to stop looping:
sets the level of event that will cause the Beekeeper to stop looping:
=over
=item JOB_FAILURE
stop looping if any job fails
stop looping if any Job fails
=item ANALYSIS_FAILURE
stop looping if any analysis has job failures exceeding its fault tolerance
stop looping if any Analysis has Job failures exceeding its fault tolerance
=item NO_WORK
ignore job and analysis failures, keep looping until there is no work
ignore Job and Analysis failures, keep looping until there is no work
=item FOREVER
Expand All @@ -812,7 +812,7 @@ =head2 Looping control
=item --max_loops <num>
perform max this # of loops in autonomous mode. The beekeeper will stop when
perform max this # of loops in autonomous mode. The Beekeeper will stop when
it has performed max_loops loops, even in FOREVER mode
=item --job_id <job_id>
Expand Down Expand Up @@ -861,11 +861,11 @@ =head2 Worker control
=item --analyses_pattern <string>
restrict the sync operation, printing of stats or looping of the beekeeper to the specified subset of analyses
restrict the sync operation, printing of stats or looping of the Beekeeper to the specified subset of analyses
=item --can_respecialize <0|1>
allow workers to re-specialise into another analysis (within resource_class) after their previous analysis was exhausted
allow workers to re-specialise into another Analysis (within resource_class) after their previous Analysis was exhausted
=item --force
Expand All @@ -881,11 +881,11 @@ =head2 Worker control
=item --job_limit <num>
#jobs to run before Worker can die naturally
Number of Jobs to run before Worker can die naturally
=item --retry_throwing_jobs <0|1>
if a job dies *knowingly*, should we retry it by default?
if a Job dies *knowingly*, should we retry it by default?
=item --hive_log_dir <path>
Expand Down Expand Up @@ -919,63 +919,63 @@ =head2 Other commands/options
=item --dead
detect all unaccounted dead workers and reset their jobs for resubmission
detect all unaccounted dead workers and reset their Jobs for resubmission
=item --sync
re-synchronise the ehive
=item --unkwn
detect all workers in UNKWN state and reset their jobs for resubmission (careful, they *may* reincarnate!)
detect all workers in UNKWN state and reset their Jobs for resubmission (careful, they *may* reincarnate!)
=item --alldead
tell the database all workers are dead (no checks are performed in this mode, so be very careful!)
=item --balance_semaphores
set all semaphore_counts to the numbers of unDONE fan jobs (emergency use only)
set all Semaphore counters to the numbers of unDONE fan Jobs (emergency use only)
=item --worker_stats
show status of each running Worker
=item --failed_jobs
show all failed jobs
show all failed Jobs
=item --job_output <job_id>
print details for one job
print details for one Job
=item --reset_job_id <num>
reset a job back to READY so it can be rerun
reset a Job back to READY so it can be rerun
=item --reset_failed_jobs
reset FAILED jobs of analyses matching -analyses_pattern back to READY so they can be rerun
reset FAILED Jobs of analyses matching -analyses_pattern back to READY so they can be rerun
=item --reset_done_jobs
reset DONE and PASSED_ON jobs of analyses matching -analyses_pattern back to READY so they can be rerun
reset DONE and PASSED_ON Jobs of analyses matching -analyses_pattern back to READY so they can be rerun
=item --reset_all_jobs
reset FAILED, DONE and PASSED_ON jobs of analyses matching -analyses_pattern back to READY so they can be rerun
reset FAILED, DONE and PASSED_ON Jobs of analyses matching -analyses_pattern back to READY so they can be rerun
=item --forgive_failed_jobs
mark FAILED jobs of analyses matching -analyses_pattern as DONE, and update their semaphores. NOTE: This does not make them dataflow
mark FAILED Jobs of analyses matching -analyses_pattern as DONE, and update their Semaphores. NOTE: This does not make them dataflow
=item --discard_ready_jobs
mark READY jobs of analyses matching -analyses_pattern as DONE, and update their semaphores. NOTE: This does not make them dataflow
mark READY Jobs of analyses matching -analyses_pattern as DONE, and update their Semaphores. NOTE: This does not make them dataflow
=item --unblock_semaphored_jobs
set SEMAPHORED jobs of analyses matching -analyses_pattern to READY so they can start
set SEMAPHORED Jobs of analyses matching -analyses_pattern to READY so they can start
=back
Expand Down
2 changes: 1 addition & 1 deletion scripts/dev/simple_init.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
## Minimalistic init system required for Docker containers
##

# Docker doesn't come with an "init" process, meaning that when beekeeper
# Docker doesn't come with an "init" process, meaning that when the Beekeeper
# submits LOCAL Workers and exits (beekeeper -run), the Workers will be
# killed by docker.

Expand Down
2 changes: 1 addition & 1 deletion scripts/generate_graph.pl
Original file line number Diff line number Diff line change
Expand Up @@ -138,7 +138,7 @@ =head1 DESCRIPTION
This program will generate a graphical representation of your eHive pipeline.
This includes visualising the flow of data from the different analyses, blocking
rules and table writers. The graph is also coloured to indicate the stage
an analysis is at. The colours and fonts used can be configured via
an Analysis is at. The colours and fonts used can be configured via
hive_config.json configuration file.
=head1 OPTIONS
Expand Down
12 changes: 6 additions & 6 deletions scripts/generate_timeline.pl
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env perl

# Gets the activity of each analysis along time, in a CSV file or in an image (see list of formats supported by GNUplot)
# Gets the activity of each Analysis along time, in a CSV file or in an image (see list of formats supported by GNUplot)

use strict;
use warnings;
Expand Down Expand Up @@ -103,7 +103,7 @@ sub main {

my %allowed_keys = (
analysis => 'Analysis',
resource_class => 'Resource class',
resource_class => 'Resource Class',
);
if ($key) {
die "Unknown key '$key'. Allowed keys are: ".join(", ", keys %allowed_keys) unless exists $allowed_keys{$key};
Expand Down Expand Up @@ -515,17 +515,17 @@ =head1 DESCRIPTION
Based on the command-line parameters "start_date" and "end_date", or on the start time of the first
Worker and end time of the last Worker (as recorded in pipeline database), it pulls the relevant data out
of the C<worker> table for accurate timing.
By default, the output is in CSV format, to allow extra analysis to be carried.
By default, the output is in CSV format, to allow extra Analysis to be carried.
You can optionally ask the script to generate an image with Gnuplot.
=head1 USAGE EXAMPLES
# Just run it the usual way: only the top 20 analysis will be reported in CSV format
# Just run it the usual way: only the top 20 Analysis will be reported in CSV format
generate_timeline.pl -url mysql://username:secret@hostname:port/database > timeline.csv
# The same, but getting the analysis that fill 99.5% of the global activity in a PNG file
# The same, but getting the Analysis that fill 99.5% of the global activity in a PNG file
generate_timeline.pl -url mysql://username:secret@hostname:port/database -top .995 -output timeline_top995.png
# Assuming you are only interested in a precise interval (in a PNG file)
Expand Down Expand Up @@ -586,7 +586,7 @@ =head2 Timeline configuration
=item --top <float>
maximum number (> 1) or fraction (< 1) of analysis to report (default: 20)
maximum number (> 1) or fraction (< 1) of Analysis to report (default: 20)
=item --output <string>
Expand Down
12 changes: 6 additions & 6 deletions scripts/hoover_pipeline.pl
Original file line number Diff line number Diff line change
Expand Up @@ -128,21 +128,21 @@ =head1 SYNOPSIS
=head1 DESCRIPTION
hoover_pipeline.pl is a script used to remove old "DONE" jobs from a continuously running pipeline database
hoover_pipeline.pl is a script used to remove old "DONE" Jobs from a continuously running pipeline database
=head1 USAGE EXAMPLES
# delete all jobs that have been "DONE" for at least a week (default threshold) :
# delete all Jobs that have been "DONE" for at least a week (default threshold) :
hoover_pipeline.pl -url "mysql://ensadmin:${ENSADMIN_PSW}@localhost:3306/lg4_long_mult"
# delete all jobs that have been "DONE" for at least a given number of days
# delete all Jobs that have been "DONE" for at least a given number of days
hoover_pipeline.pl -url "mysql://ensadmin:${ENSADMIN_PSW}@localhost:3306/lg4_long_mult" -days_ago 3
# delete all jobs "DONE" before a specific datetime:
# delete all Jobs "DONE" before a specific datetime:
hoover_pipeline.pl -url "mysql://ensadmin:${ENSADMIN_PSW}@localhost:3306/lg4_long_mult" -before_datetime "2013-02-14 15:42:50"
Expand Down Expand Up @@ -172,11 +172,11 @@ =head1 OPTIONS
=item --before_datetime <string>
delete jobs "DONE" before a specific time
delete Jobs "DONE" before a specific time
=item --days_ago <num>
delete jobs that have been "DONE" for at least <num> days
delete Jobs that have been "DONE" for at least <num> days
=item -h, --help
Expand Down

0 comments on commit ac8bf38

Please sign in to comment.