Merge branch 'master' of git@github.com:engineyard/ey-cloud-recipes

cookbooks/delayed_job/recipes/default.rb

@@ -35,7 +35,7 @@
     end
 
     execute "monit-reload-restart" do
-       command "sleep 30 && monit quit"
+       command "sleep 30 && monit reload"
        action :run
     end
 

cookbooks/main/recipes/default.rb

@@ -35,12 +35,12 @@
 # require_recipe "sunspot"
 #
 #uncomment to run the exim recipe
-exim_auth "auth" do
-  my_hostname "my_hostname.com"
-  smtp_host "smtp.sendgrid.com"
-  username "username"
-  password "password"
-end
+#exim_auth "auth" do
+#  my_hostname "my_hostname.com"
+#  smtp_host "smtp.sendgrid.com"
+#  username "username"
+#  password "password"
+#end
 #require_recipe "exim"
 
 #uncomment to run the exim::auth recipe

cookbooks/redis/recipes/default.rb

@@ -11,11 +11,11 @@
 end
 
 enable_package "dev-db/redis" do
-  version "1.3.12_pre1"
+  version "2.0.1"
 end
 
 package "dev-db/redis" do
-  version "1.3.12_pre1"
+  version "2.0.1"
   action :install
 end
 

cookbooks/redis/templates/default/redis.conf.erb

@@ -1,33 +1,46 @@
 # 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 yes
 
-# When run as a daemon, Redis write a pid file in /var/run/redis.pid by default.
-# You can specify a custom pid file location here.
+# 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 <%= @pidfile %>
 
 # Accept connections on the specified port, default is 6379
 port <%= @port %>
 
 # If you want you can bind a single interface, if the bind option is not
-# specified all the interfaces will listen for connections.
+# specified all the interfaces will listen for incoming connections.
 #
-# bind 127.0.0.1
+#bind 127.0.0.1
 
 # Close the connection after a client is idle for N seconds (0 to disable)
 timeout <%= @timeout %>
 
 # 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 <%= @loglevel %>
 
 # Specify the log file name. Also 'stdout' can be used to force
-# the demon to log on the standard output. Note that if you use standard
+# 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 <%= @logfile %>
 
@@ -49,6 +62,9 @@ databases 16
 #   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
@@ -57,13 +73,19 @@ save 60 10000
 # 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.
-# FOR 1.2.1
-#rdbcompression yes
+rdbcompression yes
 
 # The filename where to dump the DB
-dbfilename redis_state.rdb
+dbfilename /db/redis/dump.rdb
 
-# For default save/load DB in/from the working directory
+# 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 <%= @basedir %>
 
 ################################# REPLICATION #################################
@@ -90,14 +112,18 @@ dir <%= @basedir %>
 #
 # 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 limts.
+# 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'.
 #
@@ -129,21 +155,21 @@ dir <%= @basedir %>
 # 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.log. This file will
+# 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.
 #
-# The name of the append only file is "appendonly.log"
-#
 # IMPORTANT: Check the BGREWRITEAOF to check how to rewrite the append
 # log file in background when it gets too big.
 
-# FOR 1.2.1
-#appendonly no
+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 
@@ -155,35 +181,133 @@ dir <%= @basedir %>
 # 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 "always" that's the safer of the options. It's up to you to
-# understand if you can relax this to "everysec" that will fsync every second
-# or to "no" that will let the operating system flush the output buffer when
-# it want, for better performances (but if you can live with the idea of
-# some data loss consider the default persistence mode that's snapshotting).
+# 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
-# FOR 1.2.1
-#appendfsync everysec
+appendfsync everysec
 # appendfsync no
 
+################################ VIRTUAL MEMORY ###############################
+
+# Virtual Memory allows Redis to work with datasets bigger than the actual
+# amount of RAM needed to hold the whole dataset in memory.
+# In order to do so very used keys are taken in memory while the other keys
+# are swapped into a swap file, similarly to what operating systems do
+# with memory pages.
+#
+# To enable VM just set 'vm-enabled' to yes, and set the following three
+# VM parameters accordingly to your needs.
+
+vm-enabled no
+# vm-enabled yes
+
+# This is the path of the Redis swap file. As you can guess, swap files
+# can't be shared by different Redis instances, so make sure to use a swap
+# file for every redis process you are running. Redis will complain if the
+# swap file is already in use.
+#
+# The best kind of storage for the Redis swap file (that's accessed at random) 
+# is a Solid State Disk (SSD).
+#
+# *** WARNING *** if you are using a shared hosting the default of putting
+# the swap file under /tmp is not secure. Create a dir with access granted
+# only to Redis user and configure Redis to create the swap file there.
+vm-swap-file /mnt/redis.swap
+
+# vm-max-memory configures the VM to use at max the specified amount of
+# RAM. Everything that deos not fit will be swapped on disk *if* possible, that
+# is, if there is still enough contiguous space in the swap file.
+#
+# With vm-max-memory 0 the system will swap everything it can. Not a good
+# default, just specify the max amount of RAM you can in bytes, but it's
+# better to leave some margin. For instance specify an amount of RAM
+# that's more or less between 60 and 80% of your free RAM.
+vm-max-memory 0
+
+# Redis swap files is split into pages. An object can be saved using multiple
+# contiguous pages, but pages can't be shared between different objects.
+# So if your page is too big, small objects swapped out on disk will waste
+# a lot of space. If you page is too small, there is less space in the swap
+# file (assuming you configured the same number of total swap file pages).
+#
+# If you use a lot of small objects, use a page size of 64 or 32 bytes.
+# If you use a lot of big objects, use a bigger page size.
+# If unsure, use the default :)
+vm-page-size 32
+
+# Number of total memory pages in the swap file.
+# Given that the page table (a bitmap of free/used pages) is taken in memory,
+# every 8 pages on disk will consume 1 byte of RAM.
+#
+# The total swap size is vm-page-size * vm-pages
+#
+# With the default of 32-bytes memory pages and 134217728 pages Redis will
+# use a 4 GB swap file, that will use 16 MB of RAM for the page table.
+#
+# It's better to use the smallest acceptable value for your application,
+# but the default is large in order to work in most conditions.
+vm-pages 134217728
+
+# Max number of VM I/O threads running at the same time.
+# This threads are used to read/write data from/to swap file, since they
+# also encode and decode objects from disk to memory or the reverse, a bigger
+# number of threads can help with big objects even if they can't help with
+# I/O itself as the physical device may not be able to couple with many
+# reads/writes operations at the same time.
+#
+# The special value of 0 turn off threaded I/O and enables the blocking
+# Virtual Memory implementation.
+vm-max-threads 4
+
 ############################### 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
 
-# Use object sharing. Can save a lot of memory if you have many common
-# string in your dataset, but performs lookups against the shared objects
-# pool so it uses more CPU and can be a bit slower. Usually it's a good
-# idea.
+# Hashes are encoded in a special way (much more memory efficient) when they
+# have at max a given numer of elements, and the biggest element does not
+# exceed a given threshold. You can configure this limits with the following
+# configuration directives.
+hash-max-zipmap-entries 64
+hash-max-zipmap-value 512
+
+# Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in
+# order to help rehashing the main Redis hash table (the one mapping top-level
+# keys to values). The hash table implementation redis uses (see dict.c)
+# performs a lazy rehashing: the more operation you run into an hash table
+# that is rhashing, the more rehashing "steps" are performed, so if the
+# server is idle the rehashing is never complete and some more memory is used
+# by the hash table.
+# 
+# The default is to use this millisecond 10 times every second in order to
+# active rehashing the main dictionaries, freeing memory when possible.
 #
-# When object sharing is enabled (shareobjects yes) you can use
-# shareobjectspoolsize to control the size of the pool used in order to try
-# object sharing. A bigger pool size will lead to better sharing capabilities.
-# In general you want this value to be at least the double of the number of
-# very common strings you have in your dataset.
+# If unsure:
+# use "activerehashing no" if you have hard latency requirements and it is
+# not a good thing in your environment that Redis can reply form time to time
+# to queries with 2 milliseconds delay.
 #
-# WARNING: object sharing is experimental, don't enable this feature
-# in production before of Redis 1.0-stable. Still please try this feature in
-# your development environment so that we can test it better.
+# use "activerehashing yes" if you don't have such hard requirements but
+# want to free memory asap when possible.
+activerehashing 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
+

cookbooks/solr/recipes/default.rb

@@ -5,7 +5,7 @@
 # We specify what version we want below.
 solr_desiredversion = 1.4
 if ['solo', 'util'].include?(node[:instance_role])
-  if solr_desiredverison = 1.3
+  if solr_desiredverison == 1.3
     solr_file = "apache-solr-1.3.0.tgz"
     solr_dir = "apache-solr-1.3.0"
     solr_url = "http://mirror.its.uidaho.edu/pub/apache/lucene/solr/1.3.0/apache-solr-1.3.0.tgz"

cookbooks/sphinx/README.md

@@ -0,0 +1,59 @@
+ey-cloud-recipes/sphinx
+========================
+
+A chef recipe for enabling sphinx on the EY AppCloud.
+
+Dependencies
+============
+
+If you're using the ultrasphinx flavor in this recipe, you'll need to make sure
+you install the chronic gem in your environment (this is not handled by the recipe).
+
+As previously mentioned, your application needs to have the appropriate plugin installed
+already.
+
+For thinking_sphinx:
+
+    script/plugin install git://github.com/freelancing-god/thinking-sphinx.git
+
+For ultrasphinx:
+
+    script/plugin install git://github.com/fauna/ultrasphinx.git
+
+Also note that searchd won't actually start unless you've already specified indexes
+in your application.
+
+Using it
+========
+
+Edit the recipe, changing the appropriate fields as annotated in recipes/default.rb.
+Namely:
+
+  * Add your application name.
+  * Uncomment the flavor you want to use (thinking_sphinx or ultrasphinx).
+  * Set the cron_interval to specify how frequently you want to reindex.
+
+Add the following before_migrate.rb [deploy hooks](http://docs.engineyard.com/appcloud/howtos/deployment/use-deploy-hooks-with-engine-yard-appcloud):
+
+    run "ln -nfs #{shared_path}/config/sphinx #{release_path}/config/sphinx"
+    run "ln -nfs #{shared_path}/config/sphinx.yml #{release_path}/config/sphinx.yml"
+
+By default, the recipe will install and run sphinx on all app instances. If you want to
+use a dedicated utility instance, just set the "utility_name" variable to the name of
+your utility instance. By default this is set to nil.
+
+Caveats
+========
+If you have multiple app slaves or are installing to a dedicated utility instance, the it's
+likely that the recipe run will fail on those instances the very first run because the database
+migrations will not have run yet on your application master. If this occurs, simply deploy again
+and the recipe should succeed the second time around. This should only occur going forward
+if you set new indexes on fields that are in migrations that have to be run.
+
+Additional Resources
+========
+
+You can get additional information on sphinx configuration and setup here:
+
+  * [thinking_sphinx](http://freelancing-god.github.com/ts/en/)
+  * [ultrasphinx](http://blog.evanweaver.com/files/doc/fauna/ultrasphinx/files/README.html)