Initial import

4 files changed, 472 insertions, 0 deletions

diff --git a/.SRCINFO b/.SRCINFO
new file mode 100644
index 000000000000..eccc5922b977
--- /dev/null
+++ b/.SRCINFO
@@ -0,0 +1,33 @@
+# Generated by mksrcinfo v8
+# Sun Jan 31 21:15:40 UTC 2016
+pkgbase = python2-carbon
+	pkgdesc = Backend data caching and persistence daemon for Graphite
+	pkgver = 0.9.15
+	pkgrel = 1
+	url = https://github.com/graphite-project/carbon
+	arch = any
+	license = Apache
+	makedepends = python2-setuptools
+	depends = python2
+	depends = python2-twisted>=13.2.0
+	depends = python2-whisper>=0.9.15
+	depends = python2-txamqp
+	options = !emptydirs
+	backup = etc/carbon/aggregation-rules.conf
+	backup = etc/carbon/blacklist.conf
+	backup = etc/carbon/carbon.amqp.conf
+	backup = etc/carbon/carbon.conf
+	backup = etc/carbon/relay-rules.conf
+	backup = etc/carbon/rewrite-rules.conf
+	backup = etc/carbon/storage-aggregation.conf
+	backup = etc/carbon/storage-schemas.conf
+	backup = etc/carbon/whitelist.conf
+	source = https://github.com/graphite-project/carbon/archive/0.9.15.tar.gz
+	source = carbon.service
+	source = carbon.conf
+	md5sums = 1962b92b8b672b33d99b00c303fdd5aa
+	md5sums = 0baa839a459430e58177351cab0ba394
+	md5sums = 4be791bd13db60510f7459c47afc1e5d
+
+pkgname = python2-carbon
+
diff --git a/PKGBUILD b/PKGBUILD
new file mode 100644
index 000000000000..17ed2d75d702
--- /dev/null
+++ b/PKGBUILD
@@ -0,0 +1,33 @@
+## Initial Maintainer: Augusto F. Hack <hack.augusto@gmail.com>
+Maintainer='Gilles Hamel <hamelg@laposte.net>'
+pkgname=python2-carbon
+pkgver=0.9.15
+pkgrel=1
+pkgdesc='Backend data caching and persistence daemon for Graphite'
+arch=('any')
+url='https://github.com/graphite-project/carbon'
+license=('Apache')
+groups=()
+depends=('python2' 'python2-twisted>=13.2.0'  'python2-whisper>=0.9.15' 'python2-txamqp')
+makedepends=('python2-setuptools')
+options=(!emptydirs)
+source=("https://github.com/graphite-project/carbon/archive/$pkgver.tar.gz" carbon.service carbon.conf)
+md5sums=(1962b92b8b672b33d99b00c303fdd5aa 0baa839a459430e58177351cab0ba394 4be791bd13db60510f7459c47afc1e5d)
+backup=(etc/carbon/aggregation-rules.conf etc/carbon/blacklist.conf etc/carbon/carbon.amqp.conf etc/carbon/carbon.conf etc/carbon/relay-rules.conf etc/carbon/rewrite-rules.conf etc/carbon/storage-aggregation.conf etc/carbon/storage-schemas.conf etc/carbon/whitelist.conf)
+
+package() {
+  cd "$srcdir/carbon-$pkgver"
+  python2 setup.py install --root="$pkgdir/" --install-lib=/usr/lib/python2.7/site-packages --install-data=/var/lib/graphite --install-scripts=/usr/bin --optimize=1
+  install -D -m644 $srcdir/carbon.service $pkgdir/usr/lib/systemd/system/carbon.service
+
+  # change the directory of the config files
+  ls conf | while read conf; do
+    install -D -m644 conf/$conf $pkgdir/etc/carbon/${conf/.example}
+  done;
+  rm -r $pkgdir/var
+
+  # use our config with FHS
+  install -D -m644 $srcdir/carbon.conf $pkgdir/etc/carbon/carbon.conf
+}
+
+# vim:set ts=2 sw=2 et:
\ No newline at end of file
diff --git a/carbon.conf b/carbon.conf
new file mode 100644
index 000000000000..43326039da48
--- /dev/null
+++ b/carbon.conf
@@ -0,0 +1,397 @@
+[cache]
+# Configure carbon directories.
+#
+# OS environment variables can be used to tell carbon where graphite is
+# installed, where to read configuration from and where to write data.
+#
+#   GRAPHITE_ROOT        - Root directory of the graphite installation.
+#                          Defaults to ../
+#   GRAPHITE_CONF_DIR    - Configuration directory (where this file lives).
+#                          Defaults to $GRAPHITE_ROOT/conf/
+#   GRAPHITE_STORAGE_DIR - Storage directory for whisper/rrd/log/pid files.
+#                          Defaults to $GRAPHITE_ROOT/storage/
+#
+# To change other directory paths, add settings to this file. The following
+# configuration variables are available with these default values:
+#
+
+CONF_DIR = /etc/carbon/
+GRAPHITE_CONF_DIR = /etc/carbon/
+LOG_DIR = /var/log/carbon/
+PID_DIR = /var/run/
+
+STORAGE_DIR = /var/lib/carbon/
+GRAPHITE_STORAGE_DIR = /var/lib/carbon/
+LOCAL_DATA_DIR = /var/lib/carbon/whisper/
+WHITELISTS_DIR = /var/lib/carbon/lists/
+
+# Enable daily log rotation. If disabled, carbon will automatically re-open
+# the file if it's rotated out of place (e.g. by logrotate daemon)
+ENABLE_LOGROTATION = True
+
+# Specify the user to drop privileges to
+# If this is blank carbon runs as the user that invokes it
+# This user must have write access to the local data directory
+USER =
+#
+# NOTE: The above settings must be set under [relay] and [aggregator]
+#       to take effect for those daemons as well
+
+# Limit the size of the cache to avoid swapping or becoming CPU bound.
+# Sorts and serving cache queries gets more expensive as the cache grows.
+# Use the value "inf" (infinity) for an unlimited cache size.
+MAX_CACHE_SIZE = inf
+
+# Limits the number of whisper update_many() calls per second, which effectively
+# means the number of write requests sent to the disk. This is intended to
+# prevent over-utilizing the disk and thus starving the rest of the system.
+# When the rate of required updates exceeds this, then carbon's caching will
+# take effect and increase the overall throughput accordingly.
+MAX_UPDATES_PER_SECOND = 500
+
+# If defined, this changes the MAX_UPDATES_PER_SECOND in Carbon when a
+# stop/shutdown is initiated.  This helps when MAX_UPDATES_PER_SECOND is
+# relatively low and carbon has cached a lot of updates; it enables the carbon
+# daemon to shutdown more quickly.
+# MAX_UPDATES_PER_SECOND_ON_SHUTDOWN = 1000
+
+# Softly limits the number of whisper files that get created each minute.
+# Setting this value low (e.g. 50) is a good way to ensure that your carbon
+# system will not be adversely impacted when a bunch of new metrics are
+# sent to it. The trade off is that any metrics received in excess of this
+# value will be silently dropped, and the whisper file will not be created
+# until such point as a subsequent metric is received and fits within the
+# defined rate limit. Setting this value high (like "inf" for infinity) will
+# cause carbon to create the files quickly but at the risk of increased I/O.
+MAX_CREATES_PER_MINUTE = 50
+
+# Set the interface and port for the line (plain text) listener.  Setting the
+# interface to 0.0.0.0 listens on all interfaces.  Port can be set to 0 to
+# disable this listener if it is not required.
+LINE_RECEIVER_INTERFACE = 0.0.0.0
+LINE_RECEIVER_PORT = 2003
+
+# Set the TCP backlog for the listen socket created by the line receiver. You
+# shouldn't change this unless you know what you're doing.
+# LINE_RECEIVER_BACKLOG = 1024
+
+# Set this to True to enable the UDP listener. By default this is off
+# because it is very common to run multiple carbon daemons and managing
+# another (rarely used) port for every carbon instance is not fun.
+ENABLE_UDP_LISTENER = False
+UDP_RECEIVER_INTERFACE = 0.0.0.0
+UDP_RECEIVER_PORT = 2003
+
+# Set the interface and port for the pickle listener.  Setting the interface to
+# 0.0.0.0 listens on all interfaces.  Port can be set to 0 to disable this
+# listener if it is not required.
+PICKLE_RECEIVER_INTERFACE = 0.0.0.0
+PICKLE_RECEIVER_PORT = 2004
+
+# Set the TCP backlog for the listen socket created by the pickle receiver. You
+# shouldn't change this unless you know what you're doing.
+# PICKLE_RECEIVER_BACKLOG = 1024
+
+# Set to false to disable logging of successful connections
+LOG_LISTENER_CONNECTIONS = True
+
+# Per security concerns outlined in Bug #817247 the pickle receiver
+# will use a more secure and slightly less efficient unpickler.
+# Set this to True to revert to the old-fashioned insecure unpickler.
+USE_INSECURE_UNPICKLER = False
+
+CACHE_QUERY_INTERFACE = 0.0.0.0
+CACHE_QUERY_PORT = 7002
+
+# Set the TCP backlog for the listen socket created by the cache query
+# listener. You shouldn't change this unless you know what you're doing.
+# CACHE_QUERY_BACKLOG = 1024
+
+# Set this to False to drop datapoints received after the cache
+# reaches MAX_CACHE_SIZE. If this is True (the default) then sockets
+# over which metrics are received will temporarily stop accepting
+# data until the cache size falls below 95% MAX_CACHE_SIZE.
+USE_FLOW_CONTROL = True
+
+# By default, carbon-cache will log every whisper update and cache hit. This can be excessive and
+# degrade performance if logging on the same volume as the whisper data is stored.
+LOG_UPDATES = False
+LOG_CACHE_HITS = False
+LOG_CACHE_QUEUE_SORTS = True
+
+# The thread that writes metrics to disk can use on of the following strategies
+# determining the order in which metrics are removed from cache and flushed to
+# disk. The default option preserves the same behavior as has been historically
+# available in version 0.9.10.
+#
+# sorted - All metrics in the cache will be counted and an ordered list of
+# them will be sorted according to the number of datapoints in the cache at the
+# moment of the list's creation. Metrics will then be flushed from the cache to
+# disk in that order.
+#
+# max - The writer thread will always pop and flush the metric from cache
+# that has the most datapoints. This will give a strong flush preference to
+# frequently updated metrics and will also reduce random file-io. Infrequently
+# updated metrics may only ever be persisted to disk at daemon shutdown if
+# there are a large number of metrics which receive very frequent updates OR if
+# disk i/o is very slow.
+#
+# naive - Metrics will be flushed from the cache to disk in an unordered
+# fashion. This strategy may be desirable in situations where the storage for
+# whisper files is solid state, CPU resources are very limited or deference to
+# the OS's i/o scheduler is expected to compensate for the random write
+# pattern.
+#
+CACHE_WRITE_STRATEGY = sorted
+
+# On some systems it is desirable for whisper to write synchronously.
+# Set this option to True if you'd like to try this. Basically it will
+# shift the onus of buffering writes from the kernel into carbon's cache.
+WHISPER_AUTOFLUSH = False
+
+# By default new Whisper files are created pre-allocated with the data region
+# filled with zeros to prevent fragmentation and speed up contiguous reads and
+# writes (which are common). Enabling this option will cause Whisper to create
+# the file sparsely instead. Enabling this option may allow a large increase of
+# MAX_CREATES_PER_MINUTE but may have longer term performance implications
+# depending on the underlying storage configuration.
+# WHISPER_SPARSE_CREATE = False
+
+# Only beneficial on linux filesystems that support the fallocate system call.
+# It maintains the benefits of contiguous reads/writes, but with a potentially
+# much faster creation speed, by allowing the kernel to handle the block
+# allocation and zero-ing. Enabling this option may allow a large increase of
+# MAX_CREATES_PER_MINUTE. If enabled on an OS or filesystem that is unsupported
+# this option will gracefully fallback to standard POSIX file access methods.
+WHISPER_FALLOCATE_CREATE = True
+
+# Enabling this option will cause Whisper to lock each Whisper file it writes
+# to with an exclusive lock (LOCK_EX, see: man 2 flock). This is useful when
+# multiple carbon-cache daemons are writing to the same files
+# WHISPER_LOCK_WRITES = False
+
+# Set this to True to enable whitelisting and blacklisting of metrics in
+# CONF_DIR/whitelist and CONF_DIR/blacklist. If the whitelist is missing or
+# empty, all metrics will pass through
+# USE_WHITELIST = False
+
+# By default, carbon itself will log statistics (such as a count,
+# metricsReceived) with the top level prefix of 'carbon' at an interval of 60
+# seconds. Set CARBON_METRIC_INTERVAL to 0 to disable instrumentation
+# CARBON_METRIC_PREFIX = carbon
+# CARBON_METRIC_INTERVAL = 60
+
+# Enable AMQP if you want to receve metrics using an amqp broker
+# ENABLE_AMQP = False
+
+# Verbose means a line will be logged for every metric received
+# useful for testing
+# AMQP_VERBOSE = False
+
+# AMQP_HOST = localhost
+# AMQP_PORT = 5672
+# AMQP_VHOST = /
+# AMQP_USER = guest
+# AMQP_PASSWORD = guest
+# AMQP_EXCHANGE = graphite
+# AMQP_METRIC_NAME_IN_BODY = False
+
+# The manhole interface allows you to SSH into the carbon daemon
+# and get a python interpreter. BE CAREFUL WITH THIS! If you do
+# something like time.sleep() in the interpreter, the whole process
+# will sleep! This is *extremely* helpful in debugging, assuming
+# you are familiar with the code. If you are not, please don't
+# mess with this, you are asking for trouble :)
+#
+# ENABLE_MANHOLE = False
+# MANHOLE_INTERFACE = 127.0.0.1
+# MANHOLE_PORT = 7222
+# MANHOLE_USER = admin
+# MANHOLE_PUBLIC_KEY = ssh-rsa AAAAB3NzaC1yc2EAAAABiwAaAIEAoxN0sv/e4eZCPpi3N3KYvyzRaBaMeS2RsOQ/cDuKv11dlNzVeiyc3RFmCv5Rjwn/lQ79y0zyHxw67qLyhQ/kDzINc4cY41ivuQXm2tPmgvexdrBv5nsfEpjs3gLZfJnyvlcVyWK/lId8WUvEWSWHTzsbtmXAF2raJMdgLTbQ8wE=
+
+# Patterns for all of the metrics this machine will store. Read more at
+# http://en.wikipedia.org/wiki/Advanced_Message_Queuing_Protocol#Bindings
+#
+# Example: store all sales, linux servers, and utilization metrics
+# BIND_PATTERNS = sales.#, servers.linux.#, #.utilization
+#
+# Example: store everything
+# BIND_PATTERNS = #
+
+# To configure special settings for the carbon-cache instance 'b', uncomment this:
+#[cache:b]
+#LINE_RECEIVER_PORT = 2103
+#PICKLE_RECEIVER_PORT = 2104
+#CACHE_QUERY_PORT = 7102
+# and any other settings you want to customize, defaults are inherited
+# from [carbon] section.
+# You can then specify the --instance=b option to manage this instance
+
+
+
+[relay]
+LINE_RECEIVER_INTERFACE = 0.0.0.0
+LINE_RECEIVER_PORT = 2013
+PICKLE_RECEIVER_INTERFACE = 0.0.0.0
+PICKLE_RECEIVER_PORT = 2014
+
+# Set to false to disable logging of successful connections
+LOG_LISTENER_CONNECTIONS = True
+
+# Carbon-relay has several options for metric routing controlled by RELAY_METHOD
+#
+# Use relay-rules.conf to route metrics to destinations based on pattern rules
+#RELAY_METHOD = rules
+#
+# Use consistent-hashing for even distribution of metrics between destinations
+#RELAY_METHOD = consistent-hashing
+#
+# Use consistent-hashing but take into account an aggregation-rules.conf shared
+# by downstream carbon-aggregator daemons. This will ensure that all metrics
+# that map to a given aggregation rule are sent to the same carbon-aggregator
+# instance.
+# Enable this for carbon-relays that send to a group of carbon-aggregators
+#RELAY_METHOD = aggregated-consistent-hashing
+RELAY_METHOD = rules
+
+# If you use consistent-hashing you can add redundancy by replicating every
+# datapoint to more than one machine.
+REPLICATION_FACTOR = 1
+
+# For REPLICATION_FACTOR >=2, set DIVERSE_REPLICAS to True to guarantee replicas
+# across distributed hosts. With this setting disabled, it's possible that replicas
+# may be sent to different caches on the same host. This has been the default 
+# behavior since introduction of 'consistent-hashing' relay method.
+# Note that enabling this on an existing pre-0.9.14 cluster will require rebalancing
+# your metrics across the cluster nodes using a tool like Carbonate.
+#DIVERSE_REPLICAS = False
+
+# This is a list of carbon daemons we will send any relayed or
+# generated metrics to. The default provided would send to a single
+# carbon-cache instance on the default port. However if you
+# use multiple carbon-cache instances then it would look like this:
+#
+# DESTINATIONS = 127.0.0.1:2004:a, 127.0.0.1:2104:b
+#
+# The general form is IP:PORT:INSTANCE where the :INSTANCE part is
+# optional and refers to the "None" instance if omitted.
+#
+# Note that if the destinations are all carbon-caches then this should
+# exactly match the webapp's CARBONLINK_HOSTS setting in terms of
+# instances listed (order matters!).
+#
+# If using RELAY_METHOD = rules, all destinations used in relay-rules.conf
+# must be defined in this list
+DESTINATIONS = 127.0.0.1:2004
+
+# This defines the maximum "message size" between carbon daemons.
+# You shouldn't need to tune this unless you really know what you're doing.
+MAX_DATAPOINTS_PER_MESSAGE = 500
+MAX_QUEUE_SIZE = 10000
+
+# This is the percentage that the queue must be empty before it will accept
+# more messages.  For a larger site, if the queue is very large it makes sense
+# to tune this to allow for incoming stats.  So if you have an average
+# flow of 100k stats/minute, and a MAX_QUEUE_SIZE of 3,000,000, it makes sense
+# to allow stats to start flowing when you've cleared the queue to 95% since
+# you should have space to accommodate the next minute's worth of stats
+# even before the relay incrementally clears more of the queue
+QUEUE_LOW_WATERMARK_PCT = 0.8
+
+# Set this to False to drop datapoints when any send queue (sending datapoints
+# to a downstream carbon daemon) hits MAX_QUEUE_SIZE. If this is True (the
+# default) then sockets over which metrics are received will temporarily stop accepting
+# data until the send queues fall below QUEUE_LOW_WATERMARK_PCT * MAX_QUEUE_SIZE.
+USE_FLOW_CONTROL = True
+
+# Set this to True to enable whitelisting and blacklisting of metrics in
+# CONF_DIR/whitelist and CONF_DIR/blacklist. If the whitelist is missing or
+# empty, all metrics will pass through
+# USE_WHITELIST = False
+
+# By default, carbon itself will log statistics (such as a count,
+# metricsReceived) with the top level prefix of 'carbon' at an interval of 60
+# seconds. Set CARBON_METRIC_INTERVAL to 0 to disable instrumentation
+# CARBON_METRIC_PREFIX = carbon
+# CARBON_METRIC_INTERVAL = 60
+
+
+[aggregator]
+LINE_RECEIVER_INTERFACE = 0.0.0.0
+LINE_RECEIVER_PORT = 2023
+
+PICKLE_RECEIVER_INTERFACE = 0.0.0.0
+PICKLE_RECEIVER_PORT = 2024
+
+# Set to false to disable logging of successful connections
+LOG_LISTENER_CONNECTIONS = True
+
+# If set true, metric received will be forwarded to DESTINATIONS in addition to
+# the output of the aggregation rules. If set false the carbon-aggregator will
+# only ever send the output of aggregation. Default value is set to false and will not forward
+FORWARD_ALL = False
+
+# Filenames of the configuration files to use for this instance of aggregator.
+# Filenames are relative to CONF_DIR.
+#
+# AGGREGATION_RULES = aggregation-rules.conf
+# REWRITE_RULES = rewrite-rules.conf
+
+# This is a list of carbon daemons we will send any relayed or
+# generated metrics to. The default provided would send to a single
+# carbon-cache instance on the default port. However if you
+# use multiple carbon-cache instances then it would look like this:
+#
+# DESTINATIONS = 127.0.0.1:2004:a, 127.0.0.1:2104:b
+#
+# The format is comma-delimited IP:PORT:INSTANCE where the :INSTANCE part is
+# optional and refers to the "None" instance if omitted.
+#
+# Note that if the destinations are all carbon-caches then this should
+# exactly match the webapp's CARBONLINK_HOSTS setting in terms of
+# instances listed (order matters!).
+DESTINATIONS = 127.0.0.1:2004
+
+# If you want to add redundancy to your data by replicating every
+# datapoint to more than one machine, increase this.
+REPLICATION_FACTOR = 1
+
+# This is the maximum number of datapoints that can be queued up
+# for a single destination. Once this limit is hit, we will
+# stop accepting new data if USE_FLOW_CONTROL is True, otherwise
+# we will drop any subsequently received datapoints.
+MAX_QUEUE_SIZE = 10000
+
+# Set this to False to drop datapoints when any send queue (sending datapoints
+# to a downstream carbon daemon) hits MAX_QUEUE_SIZE. If this is True (the
+# default) then sockets over which metrics are received will temporarily stop accepting
+# data until the send queues fall below 80% MAX_QUEUE_SIZE.
+USE_FLOW_CONTROL = True
+
+# This defines the maximum "message size" between carbon daemons.
+# You shouldn't need to tune this unless you really know what you're doing.
+MAX_DATAPOINTS_PER_MESSAGE = 500
+
+# This defines how many datapoints the aggregator remembers for
+# each metric. Aggregation only happens for datapoints that fall in
+# the past MAX_AGGREGATION_INTERVALS * intervalSize seconds.
+MAX_AGGREGATION_INTERVALS = 5
+
+# By default (WRITE_BACK_FREQUENCY = 0), carbon-aggregator will write back
+# aggregated data points once every rule.frequency seconds, on a per-rule basis.
+# Set this (WRITE_BACK_FREQUENCY = N) to write back all aggregated data points
+# every N seconds, independent of rule frequency. This is useful, for example,
+# to be able to query partially aggregated metrics from carbon-cache without
+# having to first wait rule.frequency seconds.
+# WRITE_BACK_FREQUENCY = 0
+
+# Set this to True to enable whitelisting and blacklisting of metrics in
+# CONF_DIR/whitelist and CONF_DIR/blacklist. If the whitelist is missing or
+# empty, all metrics will pass through
+# USE_WHITELIST = False
+
+# By default, carbon itself will log statistics (such as a count,
+# metricsReceived) with the top level prefix of 'carbon' at an interval of 60
+# seconds. Set CARBON_METRIC_INTERVAL to 0 to disable instrumentation
+# CARBON_METRIC_PREFIX = carbon
+# CARBON_METRIC_INTERVAL = 60
diff --git a/carbon.service b/carbon.service
new file mode 100644
index 000000000000..14aac624d91e
--- /dev/null
+++ b/carbon.service
@@ -0,0 +1,9 @@
+[Unit]
+Description=Graphite/Carbon
+After=network.target
+
+[Service]
+ExecStart=/usr/bin/carbon-cache.py --nodaemon --config=/etc/carbon/carbon.conf start
+
+[Install]
+WantedBy=multi-user.target