Added 'meadow_user' to Worker object+schema which is now routinely recorded....

Added 'meadow_user' to Worker object+schema which is now routinely recorded. Also renamed 'host' to 'meadow_host' for consistency

modules/Bio/EnsEMBL/Hive/Queen.pm

@@ -115,9 +115,9 @@ sub create_new_worker {
     my $self    = shift @_;
     my %flags   = @_;
 
-    my ($meadow_type, $meadow_name, $process_id, $exec_host, $resource_class_id, $resource_class_name,
+    my ($meadow_type, $meadow_name, $process_id, $meadow_host, $meadow_user, $resource_class_id, $resource_class_name,
         $no_write, $debug, $worker_log_dir, $hive_log_dir, $job_limit, $life_span, $no_cleanup, $retry_throwing_jobs, $can_respecialize)
-     = @flags{qw(-meadow_type -meadow_name -process_id -exec_host -resource_class_id -resource_class_name
+     = @flags{qw(-meadow_type -meadow_name -process_id -meadow_host -meadow_user -resource_class_id -resource_class_name
             -no_write -debug -worker_log_dir -hive_log_dir -job_limit -life_span -no_cleanup -retry_throwing_jobs -can_respecialize)};
 
     foreach my $prev_worker_incarnation (@{ $self->fetch_all( "status!='DEAD' AND meadow_type='$meadow_type' AND meadow_name='$meadow_name' AND process_id='$process_id'" ) }) {
@@ -145,7 +145,8 @@ sub create_new_worker {
     my $worker = Bio::EnsEMBL::Hive::Worker->new(
         'meadow_type'       => $meadow_type,
         'meadow_name'       => $meadow_name,
-        'host'              => $exec_host,
+        'meadow_host'       => $meadow_host,
+        'meadow_user'       => $meadow_user,
         'process_id'        => $process_id,
         'resource_class'    => $resource_class,
     );

modules/Bio/EnsEMBL/Hive/Valley.pm

@@ -35,7 +35,7 @@ package Bio::EnsEMBL::Hive::Valley;
 
 use strict;
 use warnings;
-use Sys::Hostname;
+use Sys::Hostname ('hostname');
 use Bio::EnsEMBL::Hive::Utils ('find_submodules');
 use Bio::EnsEMBL::Hive::Limiter;
 
@@ -147,9 +147,10 @@ sub whereami {
         die "Could not determine the Meadow, please investigate";
     }
 
-    my $exechost = hostname();
+    my $meadow_host = hostname();
+    my $meadow_user = $ENV{'USER'} || getpwuid($<);
 
-    return ($meadow_type, $meadow_name, $pid, $exechost);
+    return ($meadow_type, $meadow_name, $pid, $meadow_host, $meadow_user);
 }
 
 

modules/Bio/EnsEMBL/Hive/Worker.pm

@@ -126,10 +126,17 @@ sub meadow_name {
 }
 
 
-sub host {
+sub meadow_host {
     my $self = shift;
-    $self->{'_host'} = shift if(@_);
-    return $self->{'_host'};
+    $self->{'_meadow_host'} = shift if(@_);
+    return $self->{'_meadow_host'};
+}
+
+
+sub meadow_user {
+    my $self = shift;
+    $self->{'_meadow_user'} = shift if(@_);
+    return $self->{'_meadow_user'};
 }
 
 
@@ -406,7 +413,7 @@ sub toString {
             $include_analysis ? ( 'analysis='.($current_role ? $current_role->analysis->logic_name.'('.$current_role->analysis_id.')' : 'UNSPECIALIZED') ) : (),
             'resource_class_id='.($self->resource_class_id // 'NULL'),
             'meadow='.$self->meadow_type.'/'.$self->meadow_name,
-            'process='.$self->process_id.'@'.$self->host,
+            'process='.$self->meadow_user.'@'.$self->meadow_host.'#'.$self->process_id,
             'last_check_in='.($self->last_check_in // 'NEVER'),
             'batch_size='.($current_role ? $current_role->analysis->stats->get_or_estimate_batch_size() : 'UNSPECIALIZED'),
             'job_limit='.($self->job_limiter->available_capacity() // 'NONE'),

scripts/runWorker.pl

@@ -104,14 +104,15 @@ sub main {
 
     my $queen = $hive_dba->get_Queen();
 
-    my ($meadow_type, $meadow_name, $process_id, $exec_host) = Bio::EnsEMBL::Hive::Valley->new()->whereami();
+    my ($meadow_type, $meadow_name, $process_id, $meadow_host, $meadow_user) = Bio::EnsEMBL::Hive::Valley->new()->whereami();
 
     my $worker = $queen->create_new_worker(
           # Worker identity:
              -meadow_type           => $meadow_type,
              -meadow_name           => $meadow_name,
              -process_id            => $process_id,
-             -exec_host             => $exec_host,
+             -meadow_host           => $meadow_host,
+             -meadow_user           => $meadow_user,
              -resource_class_id     => $resource_class_id,
              -resource_class_name   => $resource_class_name,
 

sql/patch_2015-01-13.mysql

+
+    -- First, rename 'host' to 'meadow_host' for consistency:
+ALTER TABLE worker CHANGE COLUMN host meadow_host VARCHAR(255) NOT NULL;
+
+    -- Then allow each Worker to register the username that is running the process on the meadow_host:
+ALTER TABLE worker ADD COLUMN meadow_user VARCHAR(255) DEFAULT NULL AFTER meadow_host;
+
+    -- UPDATE hive_sql_schema_version
+UPDATE hive_meta SET meta_value=63 WHERE meta_key='hive_sql_schema_version' AND meta_value='62';
+

sql/patch_2015-01-13.pgsql

+
+    -- First, rename 'host' to 'meadow_host' for consistency:
+ALTER TABLE worker RENAME COLUMN host TO meadow_host;
+
+    -- Then allow each Worker to register the username that is running the process on the meadow_host:
+ALTER TABLE worker ADD COLUMN meadow_user VARCHAR(255) DEFAULT NULL;
+
+    -- UPDATE hive_sql_schema_version
+UPDATE hive_meta SET meta_value=63 WHERE meta_key='hive_sql_schema_version' AND meta_value='62';
+

sql/tables.mysql

@@ -439,8 +439,9 @@ CREATE TABLE analysis_data (
 
 @column worker_id           unique ID of the Worker
 @column meadow_type         type of the Meadow it is running on
-@column meadow_name         name of the Meadow it is running on (for 'LOCAL' type is the same as host)
-@column host                execution host name
+@column meadow_name         name of the Meadow it is running on (for meadow_type=='LOCAL' it is the same as meadow_host)
+@column meadow_host         execution host name
+@column meadow_user         scheduling/execution user name (within the Meadow)
 @column process_id          identifies the Worker process on the Meadow (for 'LOCAL' is the OS PID)
 @column resource_class_id   links to Worker's resource class
 @column work_done           how many jobs the Worker has completed successfully
@@ -456,7 +457,8 @@ CREATE TABLE worker (
     worker_id               INTEGER     NOT NULL PRIMARY KEY AUTO_INCREMENT,
     meadow_type             VARCHAR(255) NOT NULL,
     meadow_name             VARCHAR(255) NOT NULL,
-    host                    VARCHAR(255) NOT NULL,
+    meadow_host             VARCHAR(255) NOT NULL,
+    meadow_user             VARCHAR(255)         DEFAULT NULL,
     process_id              VARCHAR(255) NOT NULL,
     resource_class_id       INTEGER              DEFAULT NULL,
 

sql/tables.pgsql

@@ -444,8 +444,9 @@ CREATE INDEX ON analysis_data (data);
 
 @column worker_id           unique ID of the Worker
 @column meadow_type         type of the Meadow it is running on
-@column meadow_name         name of the Meadow it is running on (for 'LOCAL' type is the same as host)
-@column host                execution host name
+@column meadow_name         name of the Meadow it is running on (for meadow_type=='LOCAL' it is the same as meadow_host)
+@column meadow_host         execution host name
+@column meadow_user         scheduling/execution user name (within the Meadow)
 @column process_id          identifies the Worker process on the Meadow (for 'LOCAL' is the OS PID)
 @column resource_class_id   links to Worker's resource class
 @column work_done           how many jobs the Worker has completed successfully
@@ -462,7 +463,8 @@ CREATE TABLE worker (
     worker_id               SERIAL PRIMARY KEY,
     meadow_type             VARCHAR(255) NOT NULL,
     meadow_name             VARCHAR(255) NOT NULL,
-    host                    VARCHAR(255) NOT NULL,
+    meadow_host             VARCHAR(255) NOT NULL,
+    meadow_user             VARCHAR(255)         DEFAULT NULL,
     process_id              VARCHAR(255) NOT NULL,
     resource_class_id       INTEGER              DEFAULT NULL,
     work_done               INTEGER     NOT NULL DEFAULT 0,

sql/tables.sqlite

@@ -435,8 +435,9 @@ CREATE        INDEX analysis_data_idx ON analysis_data (data);
 
 @column worker_id           unique ID of the Worker
 @column meadow_type         type of the Meadow it is running on
-@column meadow_name         name of the Meadow it is running on (for 'LOCAL' type is the same as host)
-@column host                execution host name
+@column meadow_name         name of the Meadow it is running on (for meadow_type=='LOCAL' it is the same as meadow_host)
+@column meadow_host         execution host name
+@column meadow_user         scheduling/execution user name (within the Meadow)
 @column process_id          identifies the Worker process on the Meadow (for 'LOCAL' is the OS PID)
 @column resource_class_id   links to Worker's resource class
 @column work_done           how many jobs the Worker has completed successfully
@@ -452,7 +453,8 @@ CREATE TABLE worker (
     worker_id               INTEGER     NOT NULL PRIMARY KEY AUTOINCREMENT,
     meadow_type             VARCHAR(255) NOT NULL,
     meadow_name             VARCHAR(255) NOT NULL,
-    host                    VARCHAR(255) NOT NULL,
+    meadow_host             VARCHAR(255) NOT NULL,
+    meadow_user             VARCHAR(255)         DEFAULT NULL,
     process_id              VARCHAR(255) NOT NULL,
     resource_class_id       INTEGER              DEFAULT NULL,
     work_done               INTEGER     NOT NULL DEFAULT 0,