Merge lp:~lucio.torre/txstatsd/add-redis-to-distinct-plugin into lp:~txstatsd-dev/txstatsd/distinct-plugin

[Lucio Torre]

Use redis for realtime stats.

yes? please?

[Sidnei da Silva (sidnei)]

review: Approve

=== added file 'Makefile'
--- Makefile	1970-01-01 00:00:00 +0000
+++ Makefile	2012-02-07 13:11:25 +0000
@@ -0,0 +1,26 @@
+
+trial:
+	trial distinctdb/
+
+start-database: 
+	./bin/start-database.sh
+	psql -h `pwd`/tmp/db1 -d distinct < bin/schema.sql
+
+stop-database:
+	./bin/stop-database.sh
+
+start-redis:
+	./bin/start-redis.sh
+
+stop-redis:
+	./bin/stop-redis.sh
+
+start: start-database start-redis
+
+stop: stop-redis stop-database
+
+clean:
+	rm -rf ./tmp/
+test: start trial stop clean
+
+.PHONY: trial test start-database stop-database start-redis stop-redis start stop

=== added file 'bin/redis.conf'
--- bin/redis.conf	1970-01-01 00:00:00 +0000
+++ bin/redis.conf	2012-02-07 13:11:25 +0000
@@ -0,0 +1,213 @@
+# Redis configuration file example
+
+# Note on units: when memory size is needed, it is possible to specifiy
+# it in the usual form of 1k 5GB 4M and so forth:
+#
+# 1k => 1000 bytes
+# 1kb => 1024 bytes
+# 1m => 1000000 bytes
+# 1mb => 1024*1024 bytes
+# 1g => 1000000000 bytes
+# 1gb => 1024*1024*1024 bytes
+#
+# units are case insensitive so 1GB 1Gb 1gB are all the same.
+
+# By default Redis does not run as a daemon. Use 'yes' if you need it.
+# Note that Redis will write a pid file in /var/run/redis.pid when daemonized.
+daemonize no
+
+# When running daemonized, Redis writes a pid file in /var/run/redis.pid by
+# default. You can specify a custom pid file location here.
+# pidfile ./tmp/redis.pid
+
+# Accept connections on the specified port, default is 6379
+port 16379
+
+# If you want you can bind a single interface, if the bind option is not
+# specified all the interfaces will listen for incoming connections.
+#
+bind 127.0.0.1
+
+# Close the connection after a client is idle for N seconds (0 to disable)
+timeout 300
+
+# Set server verbosity to 'debug'
+# it can be one of:
+# debug (a lot of information, useful for development/testing)
+# verbose (many rarely useful info, but not a mess like the debug level)
+# notice (moderately verbose, what you want in production probably)
+# warning (only very important / critical messages are logged)
+loglevel debug
+
+# Specify the log file name. Also 'stdout' can be used to force
+# Redis to log on the standard output. Note that if you use standard
+# output for logging but daemonize, logs will be sent to /dev/null
+logfile tmp/redis/redis-server.log
+
+# Set the number of databases. The default database is DB 0, you can select
+# a different one on a per-connection basis using SELECT <dbid> where
+# dbid is a number between 0 and 'databases'-1
+databases 16
+
+################################ SNAPSHOTTING  #################################
+#
+# Save the DB on disk:
+#
+#   save <seconds> <changes>
+#
+#   Will save the DB if both the given number of seconds and the given
+#   number of write operations against the DB occurred.
+#
+#   In the example below the behaviour will be to save:
+#   after 900 sec (15 min) if at least 1 key changed
+#   after 300 sec (5 min) if at least 10 keys changed
+#   after 60 sec if at least 10000 keys changed
+#
+#   Note: you can disable saving at all commenting all the "save" lines.
+
+save 900 1
+save 300 10
+save 60 10000
+
+# Compress string objects using LZF when dump .rdb databases?
+# For default that's set to 'yes' as it's almost always a win.
+# If you want to save some CPU in the saving child set it to 'no' but
+# the dataset will likely be bigger if you have compressible values or keys.
+rdbcompression yes
+
+# The filename where to dump the DB
+dbfilename dump.rdb
+
+# The working directory.
+#
+# The DB will be written inside this directory, with the filename specified
+# above using the 'dbfilename' configuration directive.
+#
+# Also the Append Only File will be created inside this directory.
+#
+# Note that you must specify a directory here, not a file name.
+dir tmp/redis
+
+################################# REPLICATION #################################
+
+# Master-Slave replication. Use slaveof to make a Redis instance a copy of
+# another Redis server. Note that the configuration is local to the slave
+# so for example it is possible to configure the slave to save the DB with a
+# different interval, or to listen to another port, and so on.
+#
+# slaveof <masterip> <masterport>
+
+# If the master is password protected (using the "requirepass" configuration
+# directive below) it is possible to tell the slave to authenticate before
+# starting the replication synchronization process, otherwise the master will
+# refuse the slave request.
+#
+# masterauth <master-password>
+
+################################## SECURITY ###################################
+
+# Require clients to issue AUTH <PASSWORD> before processing any other
+# commands.  This might be useful in environments in which you do not trust
+# others with access to the host running redis-server.
+#
+# This should stay commented out for backward compatibility and because most
+# people do not need auth (e.g. they run their own servers).
+#
+# Warning: since Redis is pretty fast an outside user can try up to
+# 150k passwords per second against a good box. This means that you should
+# use a very strong password otherwise it will be very easy to break.
+#
+# requirepass foobared
+
+################################### LIMITS ####################################
+
+# Set the max number of connected clients at the same time. By default there
+# is no limit, and it's up to the number of file descriptors the Redis process
+# is able to open. The special value '0' means no limits.
+# Once the limit is reached Redis will close all the new connections sending
+# an error 'max number of clients reached'.
+#
+# maxclients 128
+
+# Don't use more memory than the specified amount of bytes.
+# When the memory limit is reached Redis will try to remove keys with an
+# EXPIRE set. It will try to start freeing keys that are going to expire
+# in little time and preserve keys with a longer time to live.
+# Redis will also try to remove objects from free lists if possible.
+#
+# If all this fails, Redis will start to reply with errors to commands
+# that will use more memory, like SET, LPUSH, and so on, and will continue
+# to reply to most read-only commands like GET.
+#
+# WARNING: maxmemory can be a good idea mainly if you want to use Redis as a
+# 'state' server or cache, not as a real DB. When Redis is used as a real
+# database the memory usage will grow over the weeks, it will be obvious if
+# it is going to use too much memory in the long run, and you'll have the time
+# to upgrade. With maxmemory after the limit is reached you'll start to get
+# errors for write operations, and this may even lead to DB inconsistency.
+#
+# maxmemory <bytes>
+
+############################## APPEND ONLY MODE ###############################
+
+# By default Redis asynchronously dumps the dataset on disk. If you can live
+# with the idea that the latest records will be lost if something like a crash
+# happens this is the preferred way to run Redis. If instead you care a lot
+# about your data and don't want to that a single record can get lost you should
+# enable the append only mode: when this mode is enabled Redis will append
+# every write operation received in the file appendonly.aof. This file will
+# be read on startup in order to rebuild the full dataset in memory.
+#
+# Note that you can have both the async dumps and the append only file if you
+# like (you have to comment the "save" statements above to disable the dumps).
+# Still if append only mode is enabled Redis will load the data from the
+# log file at startup ignoring the dump.rdb file.
+#
+# IMPORTANT: Check the BGREWRITEAOF to check how to rewrite the append
+# log file in background when it gets too big.
+
+appendonly no
+
+# The name of the append only file (default: "appendonly.aof")
+# appendfilename appendonly.aof
+
+# The fsync() call tells the Operating System to actually write data on disk
+# instead to wait for more data in the output buffer. Some OS will really flush
+# data on disk, some other OS will just try to do it ASAP.
+#
+# Redis supports three different modes:
+#
+# no: don't fsync, just let the OS flush the data when it wants. Faster.
+# always: fsync after every write to the append only log . Slow, Safest.
+# everysec: fsync only if one second passed since the last fsync. Compromise.
+#
+# The default is "everysec" that's usually the right compromise between
+# speed and data safety. It's up to you to understand if you can relax this to
+# "no" that will will let the operating system flush the output buffer when
+# it wants, for better performances (but if you can live with the idea of
+# some data loss consider the default persistence mode that's snapshotting),
+# or on the contrary, use "always" that's very slow but a bit safer than
+# everysec.
+#
+# If unsure, use "everysec".
+
+# appendfsync always
+appendfsync everysec
+# appendfsync no
+
+############################### ADVANCED CONFIG ###############################
+
+# Glue small output buffers together in order to send small replies in a
+# single TCP packet. Uses a bit more CPU but most of the times it is a win
+# in terms of number of queries per second. Use 'yes' if unsure.
+glueoutputbuf yes
+
+################################## INCLUDES ###################################
+
+# Include one or more other config files here.  This is useful if you
+# have a standard template that goes to all redis server but also need
+# to customize a few per-server settings.  Include files can include
+# other files, so use this wisely.
+#
+# include /path/to/local.conf
+# include /path/to/other.conf

=== added file 'bin/start-redis.sh'
--- bin/start-redis.sh	1970-01-01 00:00:00 +0000
+++ bin/start-redis.sh	2012-02-07 13:11:25 +0000
@@ -0,0 +1,5 @@
+#!/bin/bash
+
+mkdir -p tmp/redis
+/sbin/start-stop-daemon --start -b -m -d . -p tmp/redis.pid --exec /usr/bin/redis-server -- `pwd`/bin/redis.conf
+

=== added file 'bin/stop-redis.sh'
--- bin/stop-redis.sh	1970-01-01 00:00:00 +0000
+++ bin/stop-redis.sh	2012-02-07 13:11:25 +0000
@@ -0,0 +1,3 @@
+#!/bin/bash
+
+/sbin/start-stop-daemon --stop -p tmp/redis.pid --exec /usr/bin/redis-server -- `pwd`/bin/redis.conf

=== modified file 'distinctdb/distinctmetric.py'
--- distinctdb/distinctmetric.py	2011-12-09 14:47:23 +0000
+++ distinctdb/distinctmetric.py	2012-02-07 13:11:25 +0000
@@ -1,12 +1,16 @@
 import time
+import threading
 
 import psycopg2
+import redis
 
 from zope.interface import implements
-from twisted.internet.threads import deferToThread
+from twisted.internet import reactor
 from txstatsd.itxstatsd import IMetric
 
-ONEDAY = 60 * 60 * 24
+ONE_MINUTE = 60
+ONE_HOUR = 60 * ONE_MINUTE
+ONE_DAY = 24 * ONE_HOUR
 
 
 class DistinctMetricReporter(object):
@@ -16,8 +20,10 @@
     """
     implements(IMetric)
 
+    periods = [5 * ONE_MINUTE, ONE_HOUR, ONE_DAY]
+
     def __init__(self, name, wall_time_func=time.time, prefix="",
-            bucket_size=ONEDAY, dsn=None):
+            bucket_size=ONE_DAY, dsn=None, redis_host=None, redis_port=None):
         """Construct a metric we expect to be periodically updated.
 
         @param name: Indicates what is being instrumented.
@@ -32,8 +38,17 @@
         self.prefix = prefix
         self.bucket_size = bucket_size
         self.dsn = dsn
+        self.redis_host = redis_host
+        if redis_port is None:
+            redis.port = 6379
+        self.redis_port = redis_port
         self.metric_id = None
         self.build_bucket()
+        self.redis_flush_lock = threading.Lock()
+        self.redis_count = {}
+
+        if redis_host != None:
+            self.redis = redis.client.Redis(host=redis_host, port=redis_port)
 
     def build_bucket(self, timestamp=None):
         self.max = 0
@@ -55,6 +70,40 @@
         if value > self.max:
             self.max = value
 
+        now = self.wall_time_func()
+        if self.redis_host is not None:
+            reactor.callInThread(self._update_count, item, now)
+
+    def bucket_name_for(self, period):
+        return "bucket_" + str(period)
+
+    def _update_count(self, value, when):
+        for period in self.periods:
+            self.redis.zadd(self.bucket_name_for(period), value, when)
+
+    def _flush_redis(self, now):
+        if self.redis_flush_lock.acquire(False) is False:
+            return
+        try:
+            for period in self.periods:
+                bucket = self.bucket_name_for(period)
+                self.redis.zremrangebyscore(bucket, 0, now - period)
+                self.redis_count[bucket] = self.redis.zcard(bucket)
+        finally:
+            self.redis_flush_lock.release()
+
+    def count(self, period):
+        return self.redis_count.get(self.bucket_name_for(period), 0)
+
+    def count_5min(self):
+        return self.count(5 * ONE_MINUTE)
+
+    def count_1hour(self):
+        return self.count(ONE_HOUR)
+
+    def count_1day(self):
+        return self.count(ONE_DAY)
+
     def _save_bucket(self, bucket, bucket_no):
         path = self.prefix + self.name
         if self.metric_id is None:
@@ -80,7 +129,7 @@
 
     def save_bucket(self, bucket, bucket_no):
         if self.dsn is not None:
-            deferToThread(self._save_bucket, bucket, bucket_no)
+            reactor.callInThread(self._save_bucket, bucket, bucket_no)
 
     def flush(self, interval, timestamp):
         current_bucket = self.get_bucket_no(timestamp)
@@ -88,9 +137,16 @@
             self.save_bucket(self.bucket, self.bucket_no)
             self.build_bucket(timestamp)
 
+        if self.redis_host is not None:
+            reactor.callInThread(self._flush_redis, timestamp)
+
         metrics = []
-        items = {".count": len(self.bucket),
-                 ".max": self.max}
+        items = {".messages": len(self.bucket),
+                 ".max": self.max,
+                 ".count_5min": self.count_5min(),
+                 ".count_1hour": self.count_1hour(),
+                 ".count_1day": self.count_1day(),
+                 }
         for item, value in items.iteritems():
             metrics.append((self.prefix + self.name + item, value, timestamp))
         return metrics

=== modified file 'distinctdb/tests/test_distinct.py'
--- distinctdb/tests/test_distinct.py	2011-12-09 20:04:06 +0000
+++ distinctdb/tests/test_distinct.py	2012-02-07 13:11:25 +0000
@@ -5,11 +5,19 @@
 from cStringIO import StringIO
 import os
 import time
-import subprocess
+try:
+    from subprocess import check_output
+except ImportError:
+    import subprocess
+    def check_output(args):
+        return subprocess.Popen(args,
+            stdout=subprocess.PIPE).communicate()[0]
 
 import psycopg2
+import redis
 
 from twisted.trial.unittest import TestCase
+from twisted.internet import reactor
 from twisted.plugin import getPlugins
 from twisted.plugins import distinctdbplugin
 from txstatsd.itxstatsd import IMetricFactory
@@ -71,8 +79,10 @@
         dmr.update("three")
         self.assertEquals(result,
             {"bucket": {"one": 2, "two": 1}, "bucket_no": 0})
-        self.assertEquals(dmr.flush(1, day),
-            [("test.max", 1, day), ("test.count", 1, day)])
+        result = dmr.flush(1, day)
+
+        self.assertTrue(("test.max", 1, day) in result)
+        self.assertTrue(("test.messages", 1, day) in result)
 
     def test_configure(self):
         class TestOptions(service.OptionsGlue):
@@ -101,7 +111,7 @@
 class TestDatabase(TestCase):
 
     def setUp(self):
-        rootdir = subprocess.check_output(["bzr", "root"]).strip()
+        rootdir = check_output(["bzr", "root"]).strip()
         dsn_file = os.path.join(rootdir, "tmp", "pg.dsn")
         self.dsn = open(dsn_file).read()
         self.conn = psycopg2.connect(self.dsn)
@@ -145,3 +155,69 @@
         dmr2 = distinct.DistinctMetricReporter("test", dsn=self.dsn)
         dmr2._save_bucket({}, 0)
         self.assertEquals(dmr.metric_id, dmr2.metric_id)
+
+
+class TestRedis(TestCase):
+
+    def setUp(self):
+        reactor._initThreadPool()
+        reactor.threadpool.start()
+
+    def tearDown(self):
+        r = redis.client.Redis(host="localhost", port=16379)
+        r.flushdb()
+        reactor.threadpool.stop()
+
+    def test_connect(self):
+        r = redis.client.Redis(host="localhost", port=16379)
+        r.ping()
+
+    def test_configure(self):
+        class TestOptions(service.OptionsGlue):
+            optParameters = [["test", "t", "default", "help"]]
+            config_section = "statsd"
+
+        o = TestOptions()
+        config_file = ConfigParser.RawConfigParser()
+        config_file.readfp(StringIO("[statsd]\n\n[plugin_distinctdb]\n"
+            "redis_host = localhost\nredis_port = 16379"))
+        o.configure(config_file)
+        dmf = distinctdbplugin.DistinctMetricFactory()
+        dmf.configure(o)
+        dmr = dmf.build_metric("foo", "bar", time.time)
+        self.assertEquals(dmr.redis_host, "localhost")
+        self.assertEquals(dmr.redis_port, 16379)
+
+    def test_usage(self):
+        dmr = distinct.DistinctMetricReporter("test",
+            redis_host="localhost", redis_port=16379)
+
+        self.assertEquals(dmr.count_1hour(), 0)
+        dmr._update_count("one", 0)
+        dmr._flush_redis(1)
+        self.assertEquals(dmr.count_1hour(), 1)
+        dmr._update_count("one", 0)
+        dmr._flush_redis(1)
+        self.assertEquals(dmr.count_1hour(), 1)
+        dmr._update_count("two", 30 * distinct.ONE_MINUTE)
+        dmr._flush_redis(30 * distinct.ONE_MINUTE)
+        self.assertEquals(dmr.count_1hour(), 2)
+        dmr._flush_redis(distinct.ONE_HOUR + 10 * distinct.ONE_MINUTE)
+        self.assertEquals(dmr.count_1hour(), 1)
+
+    def test_load(self):
+        dmr = distinct.DistinctMetricReporter("test",
+            redis_host="localhost", redis_port=16379)
+        start = time.time()
+        for i in range(10000):
+            dmr.update(str(i % 1000))
+
+        while True:
+            w = len(reactor.threadpool.working)
+            if w == 0:
+                break
+            time.sleep(0.1)
+        dmr._flush_redis(time.time())
+        duration = time.time() - start
+        self.assertEquals(dmr.count_1hour(), 1000)
+        self.assertTrue(duration <  10)

=== modified file 'twisted/plugins/distinctdbplugin.py'
--- twisted/plugins/distinctdbplugin.py	2011-12-08 21:08:38 +0000
+++ twisted/plugins/distinctdbplugin.py	2012-02-07 13:11:25 +0000
@@ -2,7 +2,7 @@
 
 from twisted.plugin import IPlugin
 from txstatsd.itxstatsd import IMetricFactory
-from distinctdb.distinctmetric import DistinctMetricReporter, ONEDAY
+from distinctdb.distinctmetric import DistinctMetricReporter, ONE_DAY
 
 
 class DistinctMetricFactory(object):
@@ -19,15 +19,20 @@
         return DistinctMetricReporter(name, prefix=prefix,
                                       wall_time_func=wall_time_func,
                                       bucket_size=self.bucket_size,
-                                      dsn=self.dsn)
+                                      dsn=self.dsn, redis_host=self.redis_host,
+                                      redis_port=self.redis_port)
 
     def configure(self, options):
         self.section = dict(options.get("plugin_distinctdb", {}))
         try:
-            self.bucket_size = int(self.section.get("bucket_size", ONEDAY))
+            self.bucket_size = int(self.section.get("bucket_size", ONE_DAY))
         except ValueError:
-            self.bucket_size = ONEDAY
+            self.bucket_size = ONE_DAY
 
         self.dsn = self.section.get("dsn", None)
+        self.redis_host = self.section.get("redis_host", None)
+        self.redis_port = self.section.get("redis_port", None)
+        if self.redis_port is not None:
+            self.redis_port = int(self.redis_port)
 
 distinct_metric_factory = DistinctMetricFactory()