maintenance/fixSlaveDesync.php

   1 <?php
   2 /**
   3  * This program is free software; you can redistribute it and/or modify
   4  * it under the terms of the GNU General Public License as published by
   5  * the Free Software Foundation; either version 2 of the License, or
   6  * (at your option) any later version.
   7  *
   8  * This program is distributed in the hope that it will be useful,
   9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  11  * GNU General Public License for more details.
  12  *
  13  * You should have received a copy of the GNU General Public License along
  14  * with this program; if not, write to the Free Software Foundation, Inc.,
  15  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  16  * http://www.gnu.org/copyleft/gpl.html
  17  *
  18  * @ingroup Maintenance
  19  */
  20
  21 require_once( dirname( __FILE__ ) . '/Maintenance.php' );
  22
  23 class FixSlaveDesync extends Maintenance {
  24         public function __construct() {
  25                 parent::__construct();
  26                 $this->mDescription = "";
  27
  28         }
  29
  30         public function execute() {
  31                 $this->slaveIndexes = array();
  32                 for ( $i = 1; $i < wfGetLB()->getServerCount(); $i++ ) {
  33                         if ( wfGetLB()->isNonZeroLoad( $i ) ) {
  34                                 $this->slaveIndexes[] = $i;
  35                         }
  36                 }
  37
  38                 if ( $this->hasArg() ) {
  39                         $this->desyncFixPage( $this->getArg() );
  40                 } else {
  41                         $dbw = wfGetDB( DB_MASTER );
  42                         $maxPage = $dbw->selectField( 'page', 'MAX(page_id)', false, __METHOD__ );
  43                         $corrupt = $this->findPageLatestCorruption();
  44                         foreach ( $corrupt as $id => $dummy ) {
  45                                 $this->desyncFixPage( $id );
  46                         }
  47                 }
  48         }
  49
  50         /**
  51          * Find all pages that have a corrupted page_latest
  52          * @return array
  53          */
  54         private function findPageLatestCorruption() {
  55                 $desync = array();
  56                 $n = 0;
  57                 $dbw = wfGetDB( DB_MASTER );
  58                 $masterIDs = array();
  59                 $res = $dbw->select( 'page', array( 'page_id', 'page_latest' ), array( 'page_id<6054123' ), __METHOD__ );
  60                 $this->output( "Number of pages: " . $dbw->numRows( $res ) . "\n" );
  61                 foreach ( $res as $row ) {
  62                         $masterIDs[$row->page_id] = $row->page_latest;
  63                         if ( !( ++$n % 10000 ) ) {
  64                                 $this->output( "$n\r" );
  65                         }
  66                 }
  67                 $this->output( "\n" );
  68
  69                 foreach ( $this->slaveIndexes as $i ) {
  70                         $db = wfGetDB( $i );
  71                         $res = $db->select( 'page', array( 'page_id', 'page_latest' ), array( 'page_id<6054123' ), __METHOD__ );
  72                         foreach ( $res as $row ) {
  73                                 if ( isset( $masterIDs[$row->page_id] ) && $masterIDs[$row->page_id] != $row->page_latest ) {
  74                                         $desync[$row->page_id] = true;
  75                                         $this->output( $row->page_id . "\t" );
  76                                 }
  77                         }
  78                 }
  79                 $this->output( "\n" );
  80                 return $desync;
  81         }
  82
  83         /**
  84          * Fix a broken page entry
  85          * @param $pageID int The page_id to fix
  86          */
  87         private function desyncFixPage( $pageID ) {
  88                 # Check for a corrupted page_latest
  89                 $dbw = wfGetDB( DB_MASTER );
  90                 $dbw->begin();
  91                 $realLatest = $dbw->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ),
  92                         __METHOD__, 'FOR UPDATE' );
  93                 # list( $masterFile, $masterPos ) = $dbw->getMasterPos();
  94                 $found = false;
  95                 foreach ( $this->slaveIndexes as $i ) {
  96                         $db = wfGetDB( $i );
  97                         /*
  98                         if ( !$db->masterPosWait( $masterFile, $masterPos, 10 ) ) {
  99                                    $this->output( "Slave is too lagged, aborting\n" );
 100                                    $dbw->commit();
 101                                    sleep(10);
 102                                    return;
 103                         }*/
 104                         $latest = $db->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ), __METHOD__ );
 105                         $max = $db->selectField( 'revision', 'MAX(rev_id)', false, __METHOD__ );
 106                         if ( $latest != $realLatest && $realLatest < $max ) {
 107                                 $this->output( "page_latest corrupted in page $pageID, server $i\n" );
 108                                 $found = true;
 109                                 break;
 110                         }
 111                 }
 112                 if ( !$found ) {
 113                         $this->output( "page_id $pageID seems fine\n" );
 114                         $dbw->commit();
 115                         return;
 116                 }
 117
 118                 # Find the missing revisions
 119                 $res = $dbw->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ),
 120                         __METHOD__, 'FOR UPDATE' );
 121                 $masterIDs = array();
 122                 foreach ( $res as $row ) {
 123                         $masterIDs[] = $row->rev_id;
 124                 }
 125
 126                 $res = $db->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ), __METHOD__ );
 127                 $slaveIDs = array();
 128                 foreach ( $res as $row ) {
 129                         $slaveIDs[] = $row->rev_id;
 130                 }
 131                 if ( count( $masterIDs ) < count( $slaveIDs ) ) {
 132                         $missingIDs = array_diff( $slaveIDs, $masterIDs );
 133                         if ( count( $missingIDs ) ) {
 134                                 $this->output( "Found " . count( $missingIDs ) . " lost in master, copying from slave... " );
 135                                 $dbFrom = $db;
 136                                 $found = true;
 137                                 $toMaster = true;
 138                         } else {
 139                                 $found = false;
 140                         }
 141                 } else {
 142                         $missingIDs = array_diff( $masterIDs, $slaveIDs );
 143                         if ( count( $missingIDs ) ) {
 144                                 $this->output( "Found " . count( $missingIDs ) . " missing revision(s), copying from master... " );
 145                                 $dbFrom = $dbw;
 146                                 $found = true;
 147                                 $toMaster = false;
 148                         } else {
 149                                 $found = false;
 150                         }
 151                 }
 152
 153                 if ( $found ) {
 154                         foreach ( $missingIDs as $rid ) {
 155                                 $this->output( "$rid " );
 156                                 # Revision
 157                                 $row = $dbFrom->selectRow( 'revision', '*', array( 'rev_id' => $rid ), __METHOD__ );
 158                                 if ( $toMaster ) {
 159                                         $id = $dbw->selectField( 'revision', 'rev_id', array( 'rev_id' => $rid ),
 160                                                 __METHOD__, 'FOR UPDATE' );
 161                                         if ( $id ) {
 162                                                 $this->output( "Revision already exists\n" );
 163                                                 $found = false;
 164                                                 break;
 165                                         } else {
 166                                                 $dbw->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 167                                         }
 168                                 } else {
 169                                         foreach ( $this->slaveIndexes as $i ) {
 170                                                 $db = wfGetDB( $i );
 171                                                 $db->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 172                                         }
 173                                 }
 174
 175                                 # Text
 176                                 $row = $dbFrom->selectRow( 'text', '*', array( 'old_id' => $row->rev_text_id ), __METHOD__ );
 177                                 if ( $toMaster ) {
 178                                         $dbw->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 179                                 } else {
 180                                         foreach ( $this->slaveIndexes as $i ) {
 181                                                 $db = wfGetDB( $i );
 182                                                 $db->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 183                                         }
 184                                 }
 185                         }
 186                         $this->output( "done\n" );
 187                 }
 188
 189                 if ( $found ) {
 190                         $this->output( "Fixing page_latest... " );
 191                         if ( $toMaster ) {
 192                                 # $dbw->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
 193                         } else {
 194                                 foreach ( $this->slaveIndexes as $i ) {
 195                                         $db = wfGetDB( $i );
 196                                         $db->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
 197                                 }
 198                         }
 199                         $this->output( "done\n" );
 200                 }
 201                 $dbw->commit();
 202         }
 203 }
 204
 205 $maintClass = "FixSlaveDesync";
 206 require_once( DO_MAINTENANCE );