Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Building A Firehose - PHPNW
Search
Ian Barber
October 06, 2012
Technology
2
980
Building A Firehose - PHPNW
#phpnw12 version of my talk on building firehose style streaming data systems
Ian Barber
October 06, 2012
Tweet
Share
More Decks by Ian Barber
See All by Ian Barber
Crossing Platforms With Google+ Sign-In
ianbarber
0
170
How Google Builds Webservices
ianbarber
3
350
Mobile & Social
ianbarber
2
180
Event Stream Processing In PHP
ianbarber
6
2.4k
Clojure for PHP Developers
ianbarber
6
2k
Building a Firehose
ianbarber
5
1.5k
Taking Sites Mobile
ianbarber
1
600
The Cookie Law
ianbarber
1
960
Teaching Your Machine To Find Fraudsters
ianbarber
3
1.1k
Other Decks in Technology
See All in Technology
From Natural Language to K8s Operations: The MCP Architecture and Practice of kubectl-ai
appleboy
0
160
Observability for the system understanding and curious by developers
maruloop
0
110
ソースを読むプロセスの例
sat
PRO
15
9.9k
スタートアップの現場で実践しているテストマネジメント #jasst_kyushu
makky_tyuyan
0
110
[VPoE Global Summit] サービスレベル目標による信頼性への投資最適化
satos
0
230
初めてのDatabricks Apps開発
taka_aki
1
260
Biz職でもDifyでできる! 「触らないAIワークフロー」を実現する方法
igarashikana
3
2.8k
名刺メーカーDevグループ 紹介資料
sansan33
PRO
0
940
Introduction to Sansan, inc / Sansan Global Development Center, Inc.
sansan33
PRO
0
2.8k
難しいセキュリティ用語をわかりやすくしてみた
yuta3110
0
380
[2025年10月版] Databricks Data + AI Boot Camp
databricksjapan
1
250
Introduction to Bill One Development Engineer
sansan33
PRO
0
300
Featured
See All Featured
Reflections from 52 weeks, 52 projects
jeffersonlam
353
21k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
657
61k
Gamification - CAS2011
davidbonilla
81
5.5k
Designing Experiences People Love
moore
142
24k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
990
The Pragmatic Product Professional
lauravandoore
36
7k
Context Engineering - Making Every Token Count
addyosmani
8
300
Testing 201, or: Great Expectations
jmmastey
45
7.7k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Thoughts on Productivity
jonyablonski
70
4.9k
Building a Scalable Design System with Sketch
lauravandoore
463
33k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
23
1.5k
Transcript
+Ian Barber -
[email protected]
- @ianbarber https://github.com/ianbarber/Firehose-PHP-Talk BUILDING A FIREHOSE
FILTERABLE REAL TIME STREAMING DATA
SELLING DATA ANALYSIS & DECISIONS USER TOOLS $£¥ ☑☒
DATA SOURCES COMPOSE latency AUGMENT STORE FILTER STREAM
EVENT SAMPLE order tweet temperature snapshot
Data Source Data Source Data Source Output
Data Source Data Source Data Source Output Output
Data Source Data Source Data Source Output Messaging Batch HTTP
Logs HTTP Chunked Websockets Batched POST
APACHE PHP APACHE PHP NODE.JS PUSH ZEROMQ PULL HTTP POST
WEBSOCKETS
APACHE PHP APACHE PHP HTTP POST function sendPos() { navigator.geolocation.getCurrentPosition(
function(pos) { $.ajax({ type: 'POST', url:'http://firehose.com/input.php', data: {lat: pos.coords.latitude, lon: pos.coords.longitude}}); }); setTimeout(sendPos, 60000); } sendPos(); location.php
APACHE PHP APACHE PHP PUSH ZEROMQ WEBSOCKETS $ctx = new
ZMQContext(); $sock = $ctx->getSocket(ZMQ::SOCKET_PUSH); $sock->connect("tcp://localhost:5566"); $data = array( 'id' => get_next_msg_id(), 'uid' => $_COOKIE['uid'], 'lat' => $_POST['lat'], 'lon' => $_POST['lon'] ); $sock->send(json_encode($data)); input.php
APACHE PHP APACHE PHP NODE.JS ZEROMQ PULL WEBSOCKETS app=require('http').createServer(handler), io
= require('socket.io').listen(app), zmq = require('zmq'), sock = zmq.socket('pull'); app.listen(8080); sock.bind('tcp://*:5566'); sock.on('message', function (msg) { var data = JSON.parse(msg); // send to all clients io.sockets.emit("position", event); }); output.js
PHP DAEMON PHP DAEMON NODE.JS PUSH ZEROMQ PULL HTTP STREAM
WEBSOCKETS $fh = fopen("https://".$user.":". $pass."@stream.twitter.com/1/statuses/ filter.json?track=".$search, "r"); while(!feof($fh)) { $d = fgets($fh); if(strlen($d) > 4) { $sock->send($d); } } twitter.php
Data Source Data Source Output Assemble Process Process
SOURCE ASSEMBLE PHP PHP ZEROMQ PUB SUB SUB SUB REDIS
ZEROMQ PUSH
SOURCE PHP ZEROMQ PUB SUB REDIS $ctx = new ZMQContext();
$sub = $ctx->getSocket(ZMQ::SOCKET_SUB); $sub->setSockOpt(ZMQ::SOCKOPT_SUBSCRIBE,""); $sub->connect("tcp://localhost:5577"); while( $dat = $sub->recv() ) { $aug = augment(json_decode($dat,true),$obj); $redis->lpush($dat['id'],json_encode($aug)); } augmentor.php
$mongo = new Mongo(); $collection = $m->starbucks->locations; function augment($data, $collection)
{ $loc = array((float) $data['lon'], (float) $data['lat']); $res = $collection->findOne(array( 'loc' => array('$near' => $loc))); return array('name' => 'starbucks', 'val' => $res['street']); } SOURCE PHP REDIS starbucks.php DB
$ld = new Text_LanguageDetect(); $ld->setNameMode(2); function augment($data, $ld) { /*
["en"]=> float(0.24702222222222) */ $names = $ld->detect($data['text'], 1); return array('name' => 'lang', 'val' => key($names)); } SOURCE PHP REDIS langdetect.php
$zk = new Zookeeper(); $zk->connect("localhost:2181"); SOURCE ASSEMBLE PHP PHP REDIS
PHP ZOOKEEPER COUNT OF SERVICES
$zk->create( $path . "/" . uniqid(), NULL, array( array( "perms"
=> Zookeeper::PERM_ALL, "scheme" => "world", "id" => "anyone")), Zookeeper::EPHEMERAL); PHP ZOOKEEPER augmentor.php
REASSEMBLE SOURCE REDIS ZOOKEEPER define("TIMEOUT", 5); $ch = $zk->getChildren("/services"); $servs
= count($ch); COUNT
REASSEMBLE while($dat = $sub->recv()){ do { $start = microtime(true); $aug
= $redis->brpop($dat['id'],$time)); if(count($aug)) $dat['aug'][] = $aug; $time -= microtime(true) - $start; } while($time > 0 && count($dat['aug']) != $servs); $out->send(json_encode($dat)); //forward } COUNT reassemble.php
Data Source Data Source Output Assemble Process Process Filter Filter
Filter
FILTER ELASTIC SEARCH QUERY - NAME QUERY - NAME MSG
? ? MSG ZEROMQ SUB ZEROMQ PUB TOPIC MSG TOPIC MSG TOPIC MSG ZEROMQ PULL QUERY - NAME MSG HTTP / REST
ELASTIC SEARCH QUERY - NAME QUERY - NAME MSG MSG
HTTP / REST function escall($server, $path, $param) { $context = stream_context_create( array('http' => $http)); $result = file_get_contents( $serv.'/'.$path, NULL, $context); return json_decode( $result ); } elasticsearch.php
ELASTIC SEARCH QUERY - NAME QUERY - NAME MSG MSG
HTTP / REST function percolate($host, $path, $tweet) { $path = "/twitter/tweet/_percolate"; $tweet = array('doc' => array( 'tweet' => $tweet['text'])); $match = escall($host, $path, array('content' => json_encode($tweet))); return $match['matches']; } elasticsearch.php
// snip... creating in, ctl, out ZMQ socks $poll =
new ZMQPoll(); $poll->add($in, ZMQ::POLL_IN); $poll->add($ctl, ZMQ::POLL_IN); $read = $write = array(); FILTER MSG ZEROMQ PULL QUERY - NAME ZEROMQ SUB elasticsearch.php
while(true) { $ev = $poll->poll($read, $write, -1); if($read[0] === $in)
{ $msg = json_decode( $in->recv() ); $matches = percolate($host, $msg); foreach($matches as $match) { $out->sendMulti(array($match, $msg)); } } else if($read[0] === $ctl) { $q = json_decode($ctl->recv()); $name = $q['name']; $query = $q['query']; add_query($host, $name,$query); } } elasticsearch.php
Data Source Output Queue Process Filter Data Store Data Store
STORE PHP KAFKA TOPIC TOPIC 1 2 3 4 1
2 3 4 SUB APACHE PHP CLIENT HTTP GET TOPIC - OFFSET
PHP KAFKA TOPIC TOPIC 1 2 3 4 1 2
3 4 SUB $k = new Kafka_Producer("localhost", 9092); while ($data = $in->recvMulti()) { $topic = $data[0]; $msg = $data[1]; $bytes = $k->send(array($msg), $topic); } kafkastore.php
$consumer = new Kafka_SimpleConsumer( 'localhost', 9092, 1, $max); do {
$msgs = $consumer->fetch( new Kafka_FetchRequest($top,0,$os,$max) ); foreach($msgs as $msg) echo $msg->payload(), "\n"; $offset += $msgs->validBytes(); } while($msgs->validBytes() > 0); echo json_encode(array("offset"=>$offset)); kafkaconsume.php KAFKA TOPIC TOPIC 1 2 3 4 1 2 3 4 APACHE PHP CLIENT GET
OPS
JSON & MSGPACK $data = array('id'=>1,'a'=>'a','b'=>'xyz', 'c' => array(1, 2,
"abcdefg", array(5, 7, 8))); $enc = json_encode($data); var_dump( json_decode($enc) ); $enc = msgpack_pack($data); var_dump( msgpack_unpack($enc) ); JSON MSGPACK MSGPACK JSON
Data Source Output Queue Process Filter Data Store Tap Trace
Trace Trace
Data Source Output See Also: http://slidesha.re/JaWE78
+Ian Barber -
[email protected]
- @ianbarber https://github.com/ianbarber/Firehose-PHP-Talk THANKS!