Tweak RefreshLinksJob cache logic

* Make this actually use the cache beyond edge cases
  by making the page_touched check less strict. The
  final check on the cache timestamp is good enough.
* Log metrics to statsd to give visibility.

Change-Id: I14c14846a7b68d079e1a29c6d50e354a3c1926d6

diff --git a/includes/jobqueue/jobs/RefreshLinksJob.php b/includes/jobqueue/jobs/RefreshLinksJob.php
index c297715..b7653be 100644 (file)
--- a/includes/jobqueue/jobs/RefreshLinksJob.php
+++ b/includes/jobqueue/jobs/RefreshLinksJob.php
@@ -20,6 +20,7 @@
  * @file
  * @ingroup JobQueue
  */
+use MediaWiki\MediaWikiServices;
 
 /**
  * Job to update link tables for pages
@@ -149,14 +150,16 @@ class RefreshLinksJob extends Job {
                        $revision = Revision::newFromTitle( $title, false, Revision::READ_LATEST );
                }
 
+               $stats = MediaWikiServices::getInstance()->getStatsdDataFactory();
+
                if ( !$revision ) {
+                       $stats->increment( 'refreshlinks.rev_not_found' );
                        $this->setLastError( "Revision not found for {$title->getPrefixedDBkey()}" );
                        return false; // just deleted?
-               }
-
-               if ( !$revision->isCurrent() ) {
+               } elseif ( !$revision->isCurrent() ) {
                        // If the revision isn't current, there's no point in doing a bunch
                        // of work just to fail at the lockAndGetLatest() check later.
+                       $stats->increment( 'refreshlinks.rev_not_current' );
                        $this->setLastError( "Revision {$revision->getId()} is not current" );
                        return false;
                }
@@ -188,12 +191,12 @@ class RefreshLinksJob extends Job {
 
                        if ( $page->getLinksTimestamp() > $skewedTimestamp ) {
                                // Something already updated the backlinks since this job was made
+                               $stats->increment( 'refreshlinks.update_skipped' );
                                return true;
                        }
 
-                       if ( $page->getTouched() >= $skewedTimestamp || $opportunistic ) {
-                               // Something bumped page_touched since this job was made or the cache is
-                               // otherwise suspected to be up-to-date. As long as the cache rev ID matches
+                       if ( $page->getTouched() >= $this->params['rootJobTimestamp'] || $opportunistic ) {
+                               // Cache is suspected to be up-to-date. As long as the cache rev ID matches
                                // and it reflects the job's triggering change, then it is usable.
                                $parserOutput = ParserCache::singleton()->getDirty( $page, $parserOptions );
                                if ( !$parserOutput
@@ -206,7 +209,9 @@ class RefreshLinksJob extends Job {
                }
 
                // Fetch the current revision and parse it if necessary...
-               if ( !$parserOutput ) {
+               if ( $parserOutput ) {
+                       $stats->increment( 'refreshlinks.parser_cached' );
+               } else {
                        $start = microtime( true );
                        // Revision ID must be passed to the parser output to get revision variables correct
                        $parserOutput = $content->getParserOutput(
@@ -224,6 +229,7 @@ class RefreshLinksJob extends Job {
                                        $parserOutput, $page, $parserOptions, $ctime, $revision->getId()
                                );
                        }
+                       $stats->increment( 'refreshlinks.parser_uncached' );
                }
 
                $updates = $content->getSecondaryDataUpdates(
@@ -257,6 +263,7 @@ class RefreshLinksJob extends Job {
                        // serialized, it would be OK to update links based on older revisions since it
                        // would eventually get to the latest. Since that is not the case (by design),
                        // only update the link tables to a state matching the current revision's output.
+                       $stats->increment( 'refreshlinks.rev_cas_failure' );
                        $this->setLastError( "page_latest changed from {$revision->getId()} to $latestNow" );
                        return false;
                }