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         public function getDbType() {
  30                 return Maintenance::DB_ADMIN;
  31         }
  32
  33         public function execute() {
  34                 $this->slaveIndexes = array();
  35                 for ( $i = 1; $i < wfGetLB()->getServerCount(); $i++ ) {
  36                         if ( wfGetLB()->isNonZeroLoad( $i ) ) {
  37                                 $this->slaveIndexes[] = $i;
  38                         }
  39                 }
  40
  41                 if ( $this->hasArg() ) {
  42                         $this->desyncFixPage( $this->getArg() );
  43                 } else {
  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
  70                 foreach ( $this->slaveIndexes as $i ) {
  71                         $db = wfGetDB( $i );
  72                         $res = $db->select( 'page', array( 'page_id', 'page_latest' ), array( 'page_id<6054123' ), __METHOD__ );
  73                         foreach ( $res as $row ) {
  74                                 if ( isset( $masterIDs[$row->page_id] ) && $masterIDs[$row->page_id] != $row->page_latest ) {
  75                                         $desync[$row->page_id] = true;
  76                                         $this->output( $row->page_id . "\t" );
  77                                 }
  78                         }
  79                 }
  80                 $this->output( "\n" );
  81                 return $desync;
  82         }
  83
  84         /**
  85          * Fix a broken page entry
  86          * @param $pageID int The page_id to fix
  87          */
  88         private function desyncFixPage( $pageID ) {
  89                 # Check for a corrupted page_latest
  90                 $dbw = wfGetDB( DB_MASTER );
  91                 $dbw->begin();
  92                 $realLatest = $dbw->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ),
  93                         __METHOD__, 'FOR UPDATE' );
  94                 # list( $masterFile, $masterPos ) = $dbw->getMasterPos();
  95                 $found = false;
  96                 foreach ( $this->slaveIndexes as $i ) {
  97                         $db = wfGetDB( $i );
  98                         /*
  99                         if ( !$db->masterPosWait( $masterFile, $masterPos, 10 ) ) {
 100                                    $this->output( "Slave is too lagged, aborting\n" );
 101                                    $dbw->commit();
 102                                    sleep(10);
 103                                    return;
 104                         }*/
 105                         $latest = $db->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ), __METHOD__ );
 106                         $max = $db->selectField( 'revision', 'MAX(rev_id)', false, __METHOD__ );
 107                         if ( $latest != $realLatest && $realLatest < $max ) {
 108                                 $this->output( "page_latest corrupted in page $pageID, server $i\n" );
 109                                 $found = true;
 110                                 break;
 111                         }
 112                 }
 113                 if ( !$found ) {
 114                         $this->output( "page_id $pageID seems fine\n" );
 115                         $dbw->commit();
 116                         return;
 117                 }
 118
 119                 # Find the missing revisions
 120                 $res = $dbw->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ),
 121                         __METHOD__, 'FOR UPDATE' );
 122                 $masterIDs = array();
 123                 foreach ( $res as $row ) {
 124                         $masterIDs[] = $row->rev_id;
 125                 }
 126
 127                 $res = $dbw->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ), __METHOD__ );
 128                 $slaveIDs = array();
 129                 foreach ( $res as $row ) {
 130                         $slaveIDs[] = $row->rev_id;
 131                 }
 132                 if ( count( $masterIDs ) < count( $slaveIDs ) ) {
 133                         $missingIDs = array_diff( $slaveIDs, $masterIDs );
 134                         if ( count( $missingIDs ) ) {
 135                                 $this->output( "Found " . count( $missingIDs ) . " lost in master, copying from slave... " );
 136                                 $dbFrom = $dbw;
 137                                 $found = true;
 138                                 $toMaster = true;
 139                         } else {
 140                                 $found = false;
 141                         }
 142                 } else {
 143                         $missingIDs = array_diff( $masterIDs, $slaveIDs );
 144                         if ( count( $missingIDs ) ) {
 145                                 $this->output( "Found " . count( $missingIDs ) . " missing revision(s), copying from master... " );
 146                                 $dbFrom = $dbw;
 147                                 $found = true;
 148                                 $toMaster = false;
 149                         } else {
 150                                 $found = false;
 151                         }
 152                 }
 153
 154                 if ( $found ) {
 155                         foreach ( $missingIDs as $rid ) {
 156                                 $this->output( "$rid " );
 157                                 # Revision
 158                                 $row = $dbFrom->selectRow( 'revision', '*', array( 'rev_id' => $rid ), __METHOD__ );
 159                                 if ( $toMaster ) {
 160                                         $id = $dbw->selectField( 'revision', 'rev_id', array( 'rev_id' => $rid ),
 161                                                 __METHOD__, 'FOR UPDATE' );
 162                                         if ( $id ) {
 163                                                 $this->output( "Revision already exists\n" );
 164                                                 $found = false;
 165                                                 break;
 166                                         } else {
 167                                                 $dbw->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 168                                         }
 169                                 } else {
 170                                         foreach ( $this->slaveIndexes as $i ) {
 171                                                 $db = wfGetDB( $i );
 172                                                 $db->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 173                                         }
 174                                 }
 175
 176                                 # Text
 177                                 $row = $dbFrom->selectRow( 'text', '*', array( 'old_id' => $row->rev_text_id ), __METHOD__ );
 178                                 if ( $toMaster ) {
 179                                         $dbw->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 180                                 } else {
 181                                         foreach ( $this->slaveIndexes as $i ) {
 182                                                 $db = wfGetDB( $i );
 183                                                 $db->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
 184                                         }
 185                                 }
 186                         }
 187                         $this->output( "done\n" );
 188                 }
 189
 190                 if ( $found ) {
 191                         $this->output( "Fixing page_latest... " );
 192                         if ( $toMaster ) {
 193                                 # $dbw->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
 194                         } else {
 195                                 foreach ( $this->slaveIndexes as $i ) {
 196                                         $db = wfGetDB( $i );
 197                                         $db->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
 198                                 }
 199                         }
 200                         $this->output( "done\n" );
 201                 }
 202                 $dbw->commit();
 203         }
 204 }
 205
 206 $maintClass = "FixSlaveDesync";
 207 require_once( RUN_MAINTENANCE_IF_MAIN );