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                 global $slaveIndexes, $wgDBservers;
  32                 $slaveIndexes = array();
  33                 for ( $i = 1; $i < count( $wgDBservers ); $i++ ) {
  34                         if ( wfGetLB()->isNonZeroLoad( $i ) ) {
  35                                 $slaveIndexes[] = $i;
  36                         }
  37                 }
  38
  39                 if ( $this->hasArg() ) {
  40                         $this->desyncFixPage( $this->getArg() );
  41                 } else {
  42                         $dbw = wfGetDB( DB_MASTER );
  43                         $maxPage = $dbw->selectField( 'page', 'MAX(page_id)', false, __METHOD__ );
  44                         $corrupt = $this->findPageLatestCorruption();
  45                         foreach ( $corrupt as $id => $dummy ) {
  46                                 $this->desyncFixPage( $id );
  47                         }
  48                 }
  49         }
  50
  51         /**
  52          * Find all pages that have a corrupted page_latest
  53          * @return array
  54          */
  55         private function findPageLatestCorruption() {
  56                 $desync = array();
  57                 $n = 0;
  58                 $dbw = wfGetDB( DB_MASTER );
  59                 $masterIDs = array();
  60                 $res = $dbw->select( 'page', array( 'page_id', 'page_latest' ), array( 'page_id<6054123' ), __METHOD__ );
  61                 $this->output( "Number of pages: " . $dbw->numRows( $res ) . "\n" );
  62                 foreach ( $res as $row ) {
  63                         $masterIDs[$row->page_id] = $row->page_latest;
  64                         if ( !( ++$n % 10000 ) ) {
  65                                 $this->output( "$n\r" );
  66                         }
  67                 }
  68                 $this->output( "\n" );
  69                 $dbw->freeResult( $res );
  70
  71                 global $slaveIndexes;
  72                 foreach ( $slaveIndexes as $i ) {
  73                         $db = wfGetDB( $i );
  74                         $res = $db->select( 'page', array( 'page_id', 'page_latest' ), array( 'page_id<6054123' ), __METHOD__ );
  75                         foreach ( $res as $row ) {
  76                                 if ( isset( $masterIDs[$row->page_id] ) && $masterIDs[$row->page_id] != $row->page_latest ) {
  77                                         $desync[$row->page_id] = true;
  78                                         $this->output( $row->page_id . "\t" );
  79                                 }
  80                         }
  81                         $db->freeResult( $res );
  82                 }
  83                 $this->output( "\n" );
  84                 return $desync;
  85         }
  86
  87         /**
  88          * Fix a broken page entry
  89          * @param $pageID int The page_id to fix
  90          */
  91         private function desyncFixPage( $pageID ) {
  92                 global $slaveIndexes;
  93
  94                 # Check for a corrupted page_latest
  95                 $dbw = wfGetDB( DB_MASTER );
  96                 $dbw->begin();
  97                 $realLatest = $dbw->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ),
  98                         __METHOD__, 'FOR UPDATE' );
  99                 # list( $masterFile, $masterPos ) = $dbw->getMasterPos();
 100                 $found = false;
 101                 foreach ( $slaveIndexes as $i ) {
 102                         $db = wfGetDB( $i );
 103                         /*
 104                         if ( !$db->masterPosWait( $masterFile, $masterPos, 10 ) ) {
 105                                    $this->output( "Slave is too lagged, aborting\n" );
 106                                    $dbw->commit();
 107                                    sleep(10);
 108                                    return;
 109                         }*/
 110                         $latest = $db->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ), __METHOD__ );
 111                         $max = $db->selectField( 'revision', 'MAX(rev_id)', false, __METHOD__ );
 112                         if ( $latest != $realLatest && $realLatest < $max ) {
 113                                 $this->output( "page_latest corrupted in page $pageID, server $i\n" );
 114                                 $found = true;
 115                                 break;
 116                         }
 117                 }
 118                 if ( !$found ) {
 119                         $this->output( "page_id $pageID seems fine\n" );
 120                         $dbw->commit();
 121                         return;
 122                 }
 123
 124                 # Find the missing revisions
 125                 $res = $dbw->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ),
 126                         __METHOD__, 'FOR UPDATE' );
 127                 $masterIDs = array();
 128                 foreach ( $res as $row ) {
 129                         $masterIDs[] = $row->rev_id;
 130                 }
 131                 $dbw->freeResult( $res );
 132
 133                 $res = $db->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ), __METHOD__ );
 134                 $slaveIDs = array();
 135                 foreach ( $res as $row ) {
 136                         $slaveIDs[] = $row->rev_id;
 137                 }
 138                 $db->freeResult( $res );
 139                 if ( count( $masterIDs ) < count( $slaveIDs ) ) {
 140                         $missingIDs = array_diff( $slaveIDs, $masterIDs );
 141                         if ( count( $missingIDs ) ) {
 142                                 $this->output( "Found " . count( $missingIDs ) . " lost in master, copying from slave... " );
 143                                 $dbFrom = $db;
 144                                 $found = true;
 145                                 $toMaster = true;
 146                         } else {
 147                                 $found = false;
 148                         }
 149                 } else {
 150                         $missingIDs = array_diff( $masterIDs, $slaveIDs );
 151                         if ( count( $missingIDs ) ) {
 152                                 $this->output( "Found " . count( $missingIDs ) . " missing revision(s), copying from master... " );
 153                                 $dbFrom = $dbw;
 154                                 $found = true;
 155                                 $toMaster = false;
 156                         } else {
 157                                 $found = false;
 158                         }
 159                 }
 160
 161                 if ( $found ) {
 162                         foreach ( $missingIDs as $rid ) {
 163                                 $this->output( "$rid " );
 164                                 # Revision
 165                                 $row = $dbFrom->selectRow( 'revision', '*', array( 'rev_id' => $rid ), __METHOD__ );
 166                                 if ( $toMaster ) {
 167                                         $id = $dbw->selectField( 'revision', 'rev_id', array( 'rev_id' => $rid ),
 168                                                 __METHOD__, 'FOR UPDATE' );
 169                                         if ( $id ) {
 170                                                 $this->output( "Revision already exists\n" );
 171                                                 $found = false;
 172                                                 break;
 173                                         } else {
 174                                                 $dbw->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 175                                         }
 176                                 } else {
 177                                         foreach ( $slaveIndexes as $i ) {
 178                                                 $db = wfGetDB( $i );
 179                                                 $db->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 180                                         }
 181                                 }
 182
 183                                 # Text
 184                                 $row = $dbFrom->selectRow( 'text', '*', array( 'old_id' => $row->rev_text_id ), __METHOD__ );
 185                                 if ( $toMaster ) {
 186                                         $dbw->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 187                                 } else {
 188                                         foreach ( $slaveIndexes as $i ) {
 189                                                 $db = wfGetDB( $i );
 190                                                 $db->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 191                                         }
 192                                 }
 193                         }
 194                         $this->output( "done\n" );
 195                 }
 196
 197                 if ( $found ) {
 198                         $this->output( "Fixing page_latest... " );
 199                         if ( $toMaster ) {
 200                                 # $dbw->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
 201                         } else {
 202                                 foreach ( $slaveIndexes as $i ) {
 203                                         $db = wfGetDB( $i );
 204                                         $db->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
 205                                 }
 206                         }
 207                         $this->output( "done\n" );
 208                 }
 209                 $dbw->commit();
 210         }
 211 }
 212
 213 $maintClass = "FixSlaveDesync";
 214 require_once( DO_MAINTENANCE );