Merge maintenance-work branch (now with less errors!):
[lhc/web/wiklou.git] / 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( "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 $wgUseRootUser, $wgDBservers;
32 $wgUseRootUser = true;
33
34 $slaveIndexes = array();
35 for ( $i = 1; $i < count( $wgDBservers ); $i++ ) {
36 if ( wfGetLB()->isNonZeroLoad( $i ) ) {
37 $slaveIndexes[] = $i;
38 }
39 }
40
41 if ( $this->hasArg() ) {
42 $this->desyncFixPage( $this->getArg() );
43 } else {
44 $dbw = wfGetDB( DB_MASTER );
45 $maxPage = $dbw->selectField( 'page', 'MAX(page_id)', false, __METHOD__ );
46 $corrupt = $this->findPageLatestCorruption();
47 foreach ( $corrupt as $id => $dummy ) {
48 $this->desyncFixPage( $id );
49 }
50 }
51 }
52
53 /**
54 * Find all pages that have a corrupted page_latest
55 * @return array
56 */
57 private function findPageLatestCorruption() {
58 $desync = array();
59 $n = 0;
60 $dbw = wfGetDB( DB_MASTER );
61 $masterIDs = array();
62 $res = $dbw->select( 'page', array( 'page_id', 'page_latest' ), array( 'page_id<6054123' ), __METHOD__ );
63 $this->output( "Number of pages: " . $dbw->numRows( $res ) . "\n" );
64 while ( $row = $dbw->fetchObject( $res ) ) {
65 $masterIDs[$row->page_id] = $row->page_latest;
66 if ( !( ++$n % 10000 ) ) {
67 $this->output( "$n\r" );
68 }
69 }
70 $this->output( "\n" );
71 $dbw->freeResult( $res );
72
73 global $slaveIndexes;
74 foreach ( $slaveIndexes as $i ) {
75 $db = wfGetDB( $i );
76 $res = $db->select( 'page', array( 'page_id', 'page_latest' ), array( 'page_id<6054123' ), __METHOD__ );
77 while ( $row = $db->fetchObject( $res ) ) {
78 if ( isset( $masterIDs[$row->page_id] ) && $masterIDs[$row->page_id] != $row->page_latest ) {
79 $desync[$row->page_id] = true;
80 $this->output( $row->page_id . "\t" );
81 }
82 }
83 $db->freeResult( $res );
84 }
85 $this->output( "\n" );
86 return $desync;
87 }
88
89 /**
90 * Fix a broken page entry
91 * @param $pageID int The page_id to fix
92 */
93 private function desyncFixPage( $pageID ) {
94 global $slaveIndexes;
95
96 # Check for a corrupted page_latest
97 $dbw = wfGetDB( DB_MASTER );
98 $dbw->begin();
99 $realLatest = $dbw->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ),
100 __METHOD__, 'FOR UPDATE' );
101 #list( $masterFile, $masterPos ) = $dbw->getMasterPos();
102 $found = false;
103 foreach ( $slaveIndexes as $i ) {
104 $db = wfGetDB( $i );
105 /*
106 if ( !$db->masterPosWait( $masterFile, $masterPos, 10 ) ) {
107 $this->output( "Slave is too lagged, aborting\n" );
108 $dbw->commit();
109 sleep(10);
110 return;
111 }*/
112 $latest = $db->selectField( 'page', 'page_latest', array( 'page_id' => $pageID ), __METHOD__ );
113 $max = $db->selectField( 'revision', 'MAX(rev_id)', false, __METHOD__ );
114 if ( $latest != $realLatest && $realLatest < $max ) {
115 $this->output( "page_latest corrupted in page $pageID, server $i\n" );
116 $found = true;
117 break;
118 }
119 }
120 if ( !$found ) {
121 $this->output( "page_id $pageID seems fine\n" );
122 $dbw->commit();
123 return;
124 }
125
126 # Find the missing revisions
127 $res = $dbw->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ),
128 __METHOD__, 'FOR UPDATE' );
129 $masterIDs = array();
130 while ( $row = $dbw->fetchObject( $res ) ) {
131 $masterIDs[] = $row->rev_id;
132 }
133 $dbw->freeResult( $res );
134
135 $res = $db->select( 'revision', array( 'rev_id' ), array( 'rev_page' => $pageID ), __METHOD__ );
136 $slaveIDs = array();
137 while ( $row = $db->fetchObject( $res ) ) {
138 $slaveIDs[] = $row->rev_id;
139 }
140 $db->freeResult( $res );
141 if ( count( $masterIDs ) < count( $slaveIDs ) ) {
142 $missingIDs = array_diff( $slaveIDs, $masterIDs );
143 if ( count( $missingIDs ) ) {
144 $this->output( "Found " . count( $missingIDs ) . " lost in master, copying from slave... " );
145 $dbFrom = $db;
146 $found = true;
147 $toMaster = true;
148 } else {
149 $found = false;
150 }
151 } else {
152 $missingIDs = array_diff( $masterIDs, $slaveIDs );
153 if ( count( $missingIDs ) ) {
154 $this->output( "Found " . count( $missingIDs ) . " missing revision(s), copying from master... " );
155 $dbFrom = $dbw;
156 $found = true;
157 $toMaster = false;
158 } else {
159 $found = false;
160 }
161 }
162
163 if ( $found ) {
164 foreach ( $missingIDs as $rid ) {
165 $this->output( "$rid " );
166 # Revision
167 $row = $dbFrom->selectRow( 'revision', '*', array( 'rev_id' => $rid ), __METHOD__ );
168 if ( $toMaster ) {
169 $id = $dbw->selectField( 'revision', 'rev_id', array( 'rev_id' => $rid ),
170 __METHOD__, 'FOR UPDATE' );
171 if ( $id ) {
172 $this->output( "Revision already exists\n" );
173 $found = false;
174 break;
175 } else {
176 $dbw->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
177 }
178 } else {
179 foreach ( $slaveIndexes as $i ) {
180 $db = wfGetDB( $i );
181 $db->insert( 'revision', get_object_vars( $row ), __METHOD__, 'IGNORE' );
182 }
183 }
184
185 # Text
186 $row = $dbFrom->selectRow( 'text', '*', array( 'old_id' => $row->rev_text_id ), __METHOD__ );
187 if ( $toMaster ) {
188 $dbw->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
189 } else {
190 foreach ( $slaveIndexes as $i ) {
191 $db = wfGetDB( $i );
192 $db->insert( 'text', get_object_vars( $row ), __METHOD__, 'IGNORE' );
193 }
194 }
195 }
196 $this->output( "done\n" );
197 }
198
199 if ( $found ) {
200 $this->output( "Fixing page_latest... " );
201 if ( $toMaster ) {
202 #$dbw->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
203 } else {
204 foreach ( $slaveIndexes as $i ) {
205 $db = wfGetDB( $i );
206 $db->update( 'page', array( 'page_latest' => $realLatest ), array( 'page_id' => $pageID ), __METHOD__ );
207 }
208 }
209 $this->output( "done\n" );
210 }
211 $dbw->commit();
212 }
213 }
214
215 $maintClass = "FixSlaveDesync";
216 require_once( DO_MAINTENANCE );