gnu-social/classes/Memcached_DataObject.php

534 lines
15 KiB
PHP
Raw Normal View History

<?php
/*
2009-08-25 23:14:12 +01:00
* StatusNet - the distributed open-source microblogging tool
* Copyright (C) 2008, 2009, StatusNet, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
if (!defined('STATUSNET') && !defined('LACONICA')) { exit(1); }
class Memcached_DataObject extends Safe_DataObject
{
/**
* Wrapper for DB_DataObject's static lookup using memcached
* as backing instead of an in-process cache array.
*
* @param string $cls classname of object type to load
* @param mixed $k key field name, or value for primary key
* @param mixed $v key field value, or leave out for primary key lookup
* @return mixed Memcached_DataObject subtype or false
*/
function &staticGet($cls, $k, $v=null)
{
if (is_null($v)) {
$v = $k;
# XXX: HACK!
$i = new $cls;
$keys = $i->keys();
$k = $keys[0];
unset($i);
}
$i = Memcached_DataObject::getcached($cls, $k, $v);
if ($i === false) { // false == cache miss
$i = DB_DataObject::factory($cls);
if (empty($i)) {
$i = false;
return $i;
}
$result = $i->get($k, $v);
if ($result) {
// Hit!
$i->encache();
} else {
// save the fact that no such row exists
$c = self::memcache();
if (!empty($c)) {
$ck = self::cachekey($cls, $k, $v);
$c->set($ck, null);
}
$i = false;
}
}
return $i;
}
/**
* @fixme Should this return false on lookup fail to match staticGet?
*/
function pkeyGet($cls, $kv)
{
$i = Memcached_DataObject::multicache($cls, $kv);
if ($i !== false) { // false == cache miss
return $i;
} else {
$i = DB_DataObject::factory($cls);
if (empty($i)) {
return false;
}
foreach ($kv as $k => $v) {
$i->$k = $v;
}
if ($i->find(true)) {
$i->encache();
} else {
$i = null;
$c = self::memcache();
if (!empty($c)) {
$ck = self::multicacheKey($cls, $kv);
$c->set($ck, null);
}
}
return $i;
}
}
function insert()
{
$result = parent::insert();
if ($result) {
$this->fixupTimestamps();
$this->encache(); // in case of cached negative lookups
}
return $result;
}
function update($orig=null)
{
if (is_object($orig) && $orig instanceof Memcached_DataObject) {
$orig->decache(); # might be different keys
}
$result = parent::update($orig);
if ($result) {
$this->fixupTimestamps();
$this->encache();
}
return $result;
}
function delete()
{
$this->decache(); # while we still have the values!
return parent::delete();
}
static function memcache() {
return common_memcache();
}
static function cacheKey($cls, $k, $v) {
if (is_object($cls) || is_object($k) || is_object($v)) {
$e = new Exception();
common_log(LOG_ERR, __METHOD__ . ' object in param: ' .
str_replace("\n", " ", $e->getTraceAsString()));
}
return common_cache_key(strtolower($cls).':'.$k.':'.$v);
}
static function getcached($cls, $k, $v) {
$c = Memcached_DataObject::memcache();
if (!$c) {
return false;
} else {
$obj = $c->get(Memcached_DataObject::cacheKey($cls, $k, $v));
if (0 == strcasecmp($cls, 'User')) {
// Special case for User
if (is_object($obj) && is_object($obj->id)) {
common_log(LOG_ERR, "User " . $obj->nickname . " was cached with User as ID; deleting");
$c->delete(Memcached_DataObject::cacheKey($cls, $k, $v));
return false;
}
}
return $obj;
}
}
function keyTypes()
{
// ini-based classes return number-indexed arrays. handbuilt
// classes return column => keytype. Make this uniform.
$keys = $this->keys();
$keyskeys = array_keys($keys);
if (is_string($keyskeys[0])) {
return $keys;
}
global $_DB_DATAOBJECT;
if (!isset($_DB_DATAOBJECT['INI'][$this->_database][$this->__table."__keys"])) {
$this->databaseStructure();
}
return $_DB_DATAOBJECT['INI'][$this->_database][$this->__table."__keys"];
}
function encache()
{
$c = $this->memcache();
if (!$c) {
return false;
} else if ($this->tableName() == 'user' && is_object($this->id)) {
// Special case for User bug
$e = new Exception();
common_log(LOG_ERR, __METHOD__ . ' caching user with User object as ID ' .
str_replace("\n", " ", $e->getTraceAsString()));
return false;
} else {
$keys = $this->_allCacheKeys();
foreach ($keys as $key) {
$c->set($key, $this);
}
}
}
function decache()
{
$c = $this->memcache();
if (!$c) {
return false;
}
$keys = $this->_allCacheKeys();
foreach ($keys as $key) {
$c->delete($key, $this);
}
}
function _allCacheKeys()
{
$ckeys = array();
$types = $this->keyTypes();
ksort($types);
$pkey = array();
$pval = array();
foreach ($types as $key => $type) {
assert(!empty($key));
if ($type == 'U') {
if (empty($this->$key)) {
continue;
}
$ckeys[] = $this->cacheKey($this->tableName(), $key, $this->$key);
} else if ($type == 'K' || $type == 'N') {
$pkey[] = $key;
$pval[] = $this->$key;
} else {
throw new Exception("Unknown key type $key => $type for " . $this->tableName());
}
}
assert(count($pkey) > 0);
// XXX: should work for both compound and scalar pkeys
$pvals = implode(',', $pval);
$pkeys = implode(',', $pkey);
$ckeys[] = $this->cacheKey($this->tableName(), $pkeys, $pvals);
return $ckeys;
}
function multicache($cls, $kv)
{
ksort($kv);
$c = self::memcache();
if (!$c) {
return false;
} else {
return $c->get(self::multicacheKey($cls, $kv));
}
}
static function multicacheKey($cls, $kv)
{
ksort($kv);
$pkeys = implode(',', array_keys($kv));
$pvals = implode(',', array_values($kv));
return self::cacheKey($cls, $pkeys, $pvals);
}
function getSearchEngine($table)
{
require_once INSTALLDIR.'/lib/search_engines.php';
static $search_engine;
if (!isset($search_engine)) {
if (Event::handle('GetSearchEngine', array($this, $table, &$search_engine))) {
if ('mysql' === common_config('db', 'type')) {
$type = common_config('search', 'type');
if ($type == 'like') {
$search_engine = new MySQLLikeSearch($this, $table);
} else if ($type == 'fulltext') {
$search_engine = new MySQLSearch($this, $table);
} else {
throw new ServerException('Unknown search type: ' . $type);
}
} else {
$search_engine = new PGSearch($this, $table);
}
}
}
return $search_engine;
}
static function cachedQuery($cls, $qry, $expiry=3600)
{
$c = Memcached_DataObject::memcache();
if (!$c) {
$inst = new $cls();
$inst->query($qry);
return $inst;
}
$key_part = common_keyize($cls).':'.md5($qry);
$ckey = common_cache_key($key_part);
$stored = $c->get($ckey);
if ($stored !== false) {
return new ArrayWrapper($stored);
}
$inst = new $cls();
$inst->query($qry);
$cached = array();
while ($inst->fetch()) {
$cached[] = clone($inst);
}
$inst->free();
$c->set($ckey, $cached, MEMCACHE_COMPRESSED, $expiry);
2009-01-22 20:16:19 +00:00
return new ArrayWrapper($cached);
}
/**
* sends query to database - this is the private one that must work
* - internal functions use this rather than $this->query()
*
* Overridden to do logging.
*
* @param string $string
* @access private
* @return mixed none or PEAR_Error
*/
function _query($string)
{
$start = microtime(true);
$result = parent::_query($string);
$delta = microtime(true) - $start;
$limit = common_config('db', 'log_slow_queries');
if (($limit > 0 && $delta >= $limit) || common_config('db', 'log_queries')) {
$clean = $this->sanitizeQuery($string);
common_log(LOG_DEBUG, sprintf("DB query (%0.3fs): %s", $delta, $clean));
}
return $result;
}
// Sanitize a query for logging
// @fixme don't trim spaces in string literals
function sanitizeQuery($string)
{
$string = preg_replace('/\s+/', ' ', $string);
$string = trim($string);
return $string;
}
// We overload so that 'SET NAMES "utf8"' is called for
// each connection
function _connect()
{
global $_DB_DATAOBJECT;
$sum = $this->_getDbDsnMD5();
if (!empty($_DB_DATAOBJECT['CONNECTIONS'][$sum]) &&
!PEAR::isError($_DB_DATAOBJECT['CONNECTIONS'][$sum])) {
$exists = true;
} else {
$exists = false;
}
Major refactoring of queue handlers to support running multiple sites in one daemon. Key changes: * Initialization code moved from common.php to StatusNet class; can now switch configurations during runtime. * As a consequence, configuration files must now be idempotent... Be careful with constant, function or class definitions. * Control structure for daemons/QueueManager/QueueHandler has been refactored; the run loop is now managed by IoMaster run via scripts/queuedaemon.php IoManager subclasses are woken to handle socket input or polling, and may cover multiple sites. * Plugins can implement notice queue handlers more easily by registering a QueueHandler class; no more need to add a daemon. The new QueueDaemon runs from scripts/queuedaemon.php: * This replaces most of the old *handler.php scripts; they've been refactored to the bare handler classes. * Spawns multiple child processes to spread load; defaults to CPU count on Linux and Mac OS X systems, or override with --threads=N * When multithreaded, child processes are automatically respawned on failure. * Threads gracefully shut down and restart when passing a soft memory limit (defaults to 90% of memory_limit), limiting damage from memory leaks. * Support for UDP-based monitoring: http://www.gitorious.org/snqmon Rough control flow diagram: QueueDaemon -> IoMaster -> IoManager QueueManager [listen or poll] -> QueueHandler XmppManager [ping & keepalive] XmppConfirmManager [poll updates] Todo: * Respawning features not currently available running single-threaded. * When running single-site, configuration changes aren't picked up. * New sites or config changes affecting queue subscriptions are not yet handled without a daemon restart. * SNMP monitoring output to integrate with general tools (nagios, ganglia) * Convert XMPP confirmation message sends to use stomp queue instead of polling * Convert xmppdaemon.php to IoManager? * Convert Twitter status, friends import polling daemons to IoManager * Clean up some error reporting and failure modes * May need to adjust queue priorities for best perf in backlog/flood cases Detailed code history available in my daemon-work branch: http://www.gitorious.org/~brion/statusnet/brion-fixes/commits/daemon-work
2010-01-13 03:57:15 +00:00
// @fixme horrible evil hack!
//
// In multisite configuration we don't want to keep around a separate
// connection for every database; we could end up with thousands of
// connections open per thread. In an ideal world we might keep
// a connection per server and select different databases, but that'd
// be reliant on having the same db username/pass as well.
//
// MySQL connections are cheap enough we're going to try just
// closing out the old connection and reopening when we encounter
// a new DSN.
//
// WARNING WARNING if we end up actually using multiple DBs at a time
// we'll need some fancier logic here.
if (!$exists && !empty($_DB_DATAOBJECT['CONNECTIONS']) && php_sapi_name() == 'cli') {
Major refactoring of queue handlers to support running multiple sites in one daemon. Key changes: * Initialization code moved from common.php to StatusNet class; can now switch configurations during runtime. * As a consequence, configuration files must now be idempotent... Be careful with constant, function or class definitions. * Control structure for daemons/QueueManager/QueueHandler has been refactored; the run loop is now managed by IoMaster run via scripts/queuedaemon.php IoManager subclasses are woken to handle socket input or polling, and may cover multiple sites. * Plugins can implement notice queue handlers more easily by registering a QueueHandler class; no more need to add a daemon. The new QueueDaemon runs from scripts/queuedaemon.php: * This replaces most of the old *handler.php scripts; they've been refactored to the bare handler classes. * Spawns multiple child processes to spread load; defaults to CPU count on Linux and Mac OS X systems, or override with --threads=N * When multithreaded, child processes are automatically respawned on failure. * Threads gracefully shut down and restart when passing a soft memory limit (defaults to 90% of memory_limit), limiting damage from memory leaks. * Support for UDP-based monitoring: http://www.gitorious.org/snqmon Rough control flow diagram: QueueDaemon -> IoMaster -> IoManager QueueManager [listen or poll] -> QueueHandler XmppManager [ping & keepalive] XmppConfirmManager [poll updates] Todo: * Respawning features not currently available running single-threaded. * When running single-site, configuration changes aren't picked up. * New sites or config changes affecting queue subscriptions are not yet handled without a daemon restart. * SNMP monitoring output to integrate with general tools (nagios, ganglia) * Convert XMPP confirmation message sends to use stomp queue instead of polling * Convert xmppdaemon.php to IoManager? * Convert Twitter status, friends import polling daemons to IoManager * Clean up some error reporting and failure modes * May need to adjust queue priorities for best perf in backlog/flood cases Detailed code history available in my daemon-work branch: http://www.gitorious.org/~brion/statusnet/brion-fixes/commits/daemon-work
2010-01-13 03:57:15 +00:00
foreach ($_DB_DATAOBJECT['CONNECTIONS'] as $index => $conn) {
if (!empty($conn)) {
$conn->disconnect();
}
unset($_DB_DATAOBJECT['CONNECTIONS'][$index]);
}
}
$result = parent::_connect();
if ($result && !$exists) {
$DB = &$_DB_DATAOBJECT['CONNECTIONS'][$this->_database_dsn_md5];
if (common_config('db', 'type') == 'mysql' &&
common_config('db', 'utf8')) {
$conn = $DB->connection;
if (!empty($conn)) {
if ($DB instanceof DB_mysqli) {
mysqli_set_charset($conn, 'utf8');
} else if ($DB instanceof DB_mysql) {
mysql_set_charset('utf8', $conn);
}
}
}
}
return $result;
}
// XXX: largely cadged from DB_DataObject
function _getDbDsnMD5()
{
if ($this->_database_dsn_md5) {
return $this->_database_dsn_md5;
}
$dsn = $this->_getDbDsn();
if (is_string($dsn)) {
$sum = md5($dsn);
} else {
/// support array based dsn's
$sum = md5(serialize($dsn));
}
return $sum;
}
function _getDbDsn()
{
global $_DB_DATAOBJECT;
if (empty($_DB_DATAOBJECT['CONFIG'])) {
DB_DataObject::_loadConfig();
}
$options = &$_DB_DATAOBJECT['CONFIG'];
// if the databse dsn dis defined in the object..
$dsn = isset($this->_database_dsn) ? $this->_database_dsn : null;
if (!$dsn) {
if (!$this->_database) {
$this->_database = isset($options["table_{$this->__table}"]) ? $options["table_{$this->__table}"] : null;
}
if ($this->_database && !empty($options["database_{$this->_database}"])) {
$dsn = $options["database_{$this->_database}"];
} else if (!empty($options['database'])) {
$dsn = $options['database'];
}
}
if (!$dsn) {
throw new Exception("No database name / dsn found anywhere");
}
return $dsn;
}
Offload inbox updates to a queue handler to speed up posting online Moved much of the writing that happens when posting a notice to a new queuehandler, distribqueuehandler. This updates tags, groups, replies and inboxes at queue time (or at Web time, if queues are disabled). To make this work well, I had to break up the monolithic Notice::blowCaches() and make cache blowing happen closer to where data is updated. Squashed commit of the following: commit 5257626c62750ac4ac1db0ce2b71410c5711cfa3 Author: Evan Prodromou <evan@status.net> Date: Mon Jan 25 14:56:41 2010 -0500 slightly better handling of blowing tag memory cache commit 8a22a3cdf6ec28685da129a0313e7b2a0837c9ef Author: Evan Prodromou <evan@status.net> Date: Mon Jan 25 01:42:56 2010 -0500 change 'distribute' to 'distrib' so not too long for dbqueue commit 7a063315b0f7fad27cb6fbd2bdd74e253af83e4f Author: Evan Prodromou <evan@status.net> Date: Mon Jan 25 01:39:15 2010 -0500 change handle_notice() to handle() in distributqueuehandler commit 1a39ccd28b9994137d7bfd21bb4f230546938e77 Author: Evan Prodromou <evan@status.net> Date: Mon Jan 25 16:05:25 2010 -0500 error with queuemanager commit e6b3bb93f305cfd2de71a6340b8aa6fb890049b7 Author: Evan Prodromou <evan@status.net> Date: Mon Jan 25 01:11:34 2010 -0500 Blow memcache at different point rather than one big function for Notice class commit 94d557cdc016187d1d0647ae1794cd94d6fb8ac8 Author: Evan Prodromou <evan@status.net> Date: Mon Jan 25 00:48:44 2010 -0500 Blow memcache at different point rather than one big function for Notice class commit 1c781dd08c88a35dafc5c01230b4872fd6b95182 Author: Evan Prodromou <evan@status.net> Date: Wed Jan 20 08:54:18 2010 -0500 move broadcasting and distributing to new queuehandler commit da3e46d26b84e4f028f34a13fd2ee373e4c1b954 Author: Evan Prodromou <evan@status.net> Date: Wed Jan 20 08:53:12 2010 -0500 Move distribution of notices to new distribute queue handler
2010-01-25 23:08:21 +00:00
static function blow()
{
$c = self::memcache();
if (empty($c)) {
return false;
}
$args = func_get_args();
$format = array_shift($args);
$keyPart = vsprintf($format, $args);
$cacheKey = common_cache_key($keyPart);
return $c->delete($cacheKey);
}
function fixupTimestamps()
{
// Fake up timestamp columns
$columns = $this->table();
foreach ($columns as $name => $type) {
if ($type & DB_DATAOBJECT_MYSQLTIMESTAMP) {
$this->$name = common_sql_now();
}
}
}
function debugDump()
{
common_debug("debugDump: " . common_log_objstring($this));
}
2010-01-28 21:26:55 +00:00
function raiseError($message, $type = null, $behaviour = null)
{
throw new ServerException("DB_DataObject error [$type]: $message");
}
static function cacheGet($keyPart)
{
$c = self::memcache();
if (empty($c)) {
return false;
}
$cacheKey = common_cache_key($keyPart);
return $c->get($cacheKey);
}
static function cacheSet($keyPart, $value)
{
$c = self::memcache();
if (empty($c)) {
return false;
}
$cacheKey = common_cache_key($keyPart);
return $c->set($cacheKey, $value);
}
}