maintenance/storage/moveToExternal.php

   1 <?php
   2 /**
   3  * Move revision's text to external storage
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Maintenance ExternalStorage
  22  */
  23
  24 define( 'REPORTING_INTERVAL', 1 );
  25
  26 if ( !defined( 'MEDIAWIKI' ) ) {
  27         $optionsWithArgs = [ 'e', 's' ];
  28         require_once __DIR__ . '/../commandLine.inc';
  29         require_once 'resolveStubs.php';
  30
  31         $fname = 'moveToExternal';
  32
  33         if ( !isset( $args[0] ) ) {
  34                 print "Usage: php moveToExternal.php [-s <startid>] [-e <endid>] <cluster>\n";
  35                 exit;
  36         }
  37
  38         $cluster = $args[0];
  39         $dbw = wfGetDB( DB_MASTER );
  40
  41         $maxID = $options['e'] ?? $dbw->selectField( 'text', 'MAX(old_id)', '', $fname );
  42         $minID = $options['s'] ?? 1;
  43
  44         moveToExternal( $cluster, $maxID, $minID );
  45 }
  46
  47 function moveToExternal( $cluster, $maxID, $minID = 1 ) {
  48         $fname = 'moveToExternal';
  49         $dbw = wfGetDB( DB_MASTER );
  50         $dbr = wfGetDB( DB_REPLICA );
  51
  52         $count = $maxID - $minID + 1;
  53         $blockSize = 1000;
  54         $numBlocks = ceil( $count / $blockSize );
  55         print "Moving text rows from $minID to $maxID to external storage\n";
  56         $ext = new ExternalStoreDB;
  57         $numMoved = 0;
  58
  59         for ( $block = 0; $block < $numBlocks; $block++ ) {
  60                 $blockStart = $block * $blockSize + $minID;
  61                 $blockEnd = $blockStart + $blockSize - 1;
  62
  63                 if ( !( $block % REPORTING_INTERVAL ) ) {
  64                         print "oldid=$blockStart, moved=$numMoved\n";
  65                         wfWaitForSlaves();
  66                 }
  67
  68                 $res = $dbr->select( 'text', [ 'old_id', 'old_flags', 'old_text' ],
  69                         [
  70                                 "old_id BETWEEN $blockStart AND $blockEnd",
  71                                 'old_flags NOT ' . $dbr->buildLike( $dbr->anyString(), 'external', $dbr->anyString() ),
  72                         ], $fname );
  73                 foreach ( $res as $row ) {
  74                         # Resolve stubs
  75                         $text = $row->old_text;
  76                         $id = $row->old_id;
  77                         if ( $row->old_flags === '' ) {
  78                                 $flags = 'external';
  79                         } else {
  80                                 $flags = "{$row->old_flags},external";
  81                         }
  82
  83                         if ( strpos( $flags, 'object' ) !== false ) {
  84                                 $obj = unserialize( $text );
  85                                 $className = strtolower( get_class( $obj ) );
  86                                 if ( $className == 'historyblobstub' ) {
  87                                         # resolveStub( $id, $row->old_text, $row->old_flags );
  88                                         # $numStubs++;
  89                                         continue;
  90                                 } elseif ( $className == 'historyblobcurstub' ) {
  91                                         $text = gzdeflate( $obj->getText() );
  92                                         $flags = 'utf-8,gzip,external';
  93                                 } elseif ( $className == 'concatenatedgziphistoryblob' ) {
  94                                         // Do nothing
  95                                 } else {
  96                                         print "Warning: unrecognised object class \"$className\"\n";
  97                                         continue;
  98                                 }
  99                         } else {
 100                                 $className = false;
 101                         }
 102
 103                         if ( strlen( $text ) < 100 && $className === false ) {
 104                                 // Don't move tiny revisions
 105                                 continue;
 106                         }
 107
 108                         # print "Storing "  . strlen( $text ) . " bytes to $url\n";
 109                         # print "old_id=$id\n";
 110
 111                         $url = $ext->store( $cluster, $text );
 112                         if ( !$url ) {
 113                                 print "Error writing to external storage\n";
 114                                 exit;
 115                         }
 116                         $dbw->update( 'text',
 117                                 [ 'old_flags' => $flags, 'old_text' => $url ],
 118                                 [ 'old_id' => $id ], $fname );
 119                         $numMoved++;
 120                 }
 121         }
 122 }