diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..45d62d8 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +*.sw? diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0f7922 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +# Test Cassandra+replayer deployment + +Deploys a small Cassandra cluster on our desktops + a replayer that pulls +from the production Kafka into the Cassandra cluster. +All processes are orchestrated with `systemctl --user`. + +## Structure + +Each of the desktops runs three things: + +* a Cassandra node (multi-thread, uses lots of CPU and RAM) +* `N` rpc server instances (each mono-thread, uses lots of CPU) +* `N` replayer instances (light on both CPU and RAM) + +There is a one-to-one relationship between rpc servers and replayers on +each computer, to simplify the config (a single async replayer per computer +would be possible, but harder). + +Replayers pull from Kafka, push to rpc servers. rpc servers run the +`cassandra-driver` library, which connects to all Cassandra servers, +and pushes objects directly to the one which will hold it long-term. + +Communication between Cassandra servers should be minimal, because in +our config they don't need to exchange data with each other. + +## Hosts + +The `hosts` files contains declaration of all hosts (our four desktops), +how to connect to them, and computer-specific Cassandra config + +## Playbooks + +### `playbooks/install-cassandra.yml` + +Pulls a Cassandra binary tarball, runs it as a systemd +unit + +### `playbooks/install-storage.yml` + +Clones the [swh-storage branch with Cassandra support](https://forge.softwareheritage.org/source/swh-storage-cassandra/), +runs its `setup.py`, runs the rpc server as a systemd unit + +### `playbooks/install-replayer.yml` + +Clones swh-journal, applies a local patch (to ignore corrupt origin-visit +objects [generated by the backfiller](https://forge.softwareheritage.org/D1742), +runs its `setup.py`, runs the replayer as a systemd unit + +Replayers are started after a random delay, in order to avoid stressing +the Kafka servers too much, which causes the consumers to crash. +(TODO: investigate this) + +## Monitoring + +Running the playbooks in the above order should start everything after +approximately two minutes. + +On each computer, connecting as `vlorentz` or `vlorentz-cassandra` and +running `journalctl --user -u "replayer@*.service" -f` shows the logs +of all the replayers. + +Getting counts of each object type: +`cqlsh 128.93.66.190 -e "select * from swh_test.object_count;"` + +Getting info on the local node: +`/home/vlorentz*/apache-cassandra-3.11.4/bin/nodetool info` + +Getting info on the whole cluster: +`/home/vlorentz*/apache-cassandra-3.11.4/bin/nodetool status swh_test` diff --git a/ansible.cfg b/ansible.cfg new file mode 100644 index 0000000..c3f042f --- /dev/null +++ b/ansible.cfg @@ -0,0 +1,362 @@ +# config file for ansible -- http://ansible.com/ +# ============================================== + +# nearly all parameters can be overridden in ansible-playbook +# or with command line flags. ansible will read ANSIBLE_CONFIG, +# ansible.cfg in the current working directory, .ansible.cfg in +# the home directory or /etc/ansible/ansible.cfg, whichever it +# finds first + +[defaults] + +# some basic default values... + +inventory = ./hosts +#library = /usr/share/my_modules/ +#remote_tmp = ~/.ansible/tmp +#local_tmp = ~/.ansible/tmp +#forks = 5 +#poll_interval = 15 +#sudo_user = root +#ask_sudo_pass = True +#ask_pass = True +#transport = smart +#remote_port = 22 +#module_lang = C +#module_set_locale = False + +# plays will gather facts by default, which contain information about +# the remote system. +# +# smart - gather by default, but don't regather if already gathered +# implicit - gather by default, turn off with gather_facts: False +# explicit - do not gather by default, must say gather_facts: True +#gathering = implicit + +# by default retrieve all facts subsets +# all - gather all subsets +# network - gather min and network facts +# hardware - gather hardware facts (longest facts to retrieve) +# virtual - gather min and virtual facts +# facter - import facts from facter +# ohai - import facts from ohai +# You can combine them using comma (ex: network,virtual) +# You can negate them using ! (ex: !hardware,!facter,!ohai) +# A minimal set of facts is always gathered. +#gather_subset = all + +# some hardware related facts are collected +# with a maximum timeout of 10 seconds. This +# option lets you increase or decrease that +# timeout to something more suitable for the +# environment. +# gather_timeout = 10 + +# additional paths to search for roles in, colon separated +#roles_path = /etc/ansible/roles + +# uncomment this to disable SSH key host checking +#host_key_checking = False + +# change the default callback +#stdout_callback = skippy +# enable additional callbacks +#callback_whitelist = timer, mail + +# Determine whether includes in tasks and handlers are "static" by +# default. As of 2.0, includes are dynamic by default. Setting these +# values to True will make includes behave more like they did in the +# 1.x versions. +#task_includes_static = True +#handler_includes_static = True + +# Controls if a missing handler for a notification event is an error or a warning +#error_on_missing_handler = True + +# change this for alternative sudo implementations +#sudo_exe = sudo + +# What flags to pass to sudo +# WARNING: leaving out the defaults might create unexpected behaviours +#sudo_flags = -H -S -n + +# SSH timeout +#timeout = 10 + +# default user to use for playbooks if user is not specified +# (/usr/bin/ansible will use current user as default) +#remote_user = root + +# logging is off by default unless this path is defined +# if so defined, consider logrotate +#log_path = /var/log/ansible.log + +# default module name for /usr/bin/ansible +#module_name = command + +# use this shell for commands executed under sudo +# you may need to change this to bin/bash in rare instances +# if sudo is constrained +#executable = /bin/sh + +# if inventory variables overlap, does the higher precedence one win +# or are hash values merged together? The default is 'replace' but +# this can also be set to 'merge'. +#hash_behaviour = replace + +# by default, variables from roles will be visible in the global variable +# scope. To prevent this, the following option can be enabled, and only +# tasks and handlers within the role will see the variables there +#private_role_vars = yes + +# list any Jinja2 extensions to enable here: +#jinja2_extensions = jinja2.ext.do,jinja2.ext.i18n + +# if set, always use this private key file for authentication, same as +# if passing --private-key to ansible or ansible-playbook +#private_key_file = /path/to/file + +# If set, configures the path to the Vault password file as an alternative to +# specifying --vault-password-file on the command line. +#vault_password_file = /path/to/vault_password_file + +# format of string {{ ansible_managed }} available within Jinja2 +# templates indicates to users editing templates files will be replaced. +# replacing {file}, {host} and {uid} and strftime codes with proper values. +#ansible_managed = Ansible managed: {file} modified on %Y-%m-%d %H:%M:%S by {uid} on {host} +# {file}, {host}, {uid}, and the timestamp can all interfere with idempotence +# in some situations so the default is a static string: +#ansible_managed = Ansible managed + +# by default, ansible-playbook will display "Skipping [host]" if it determines a task +# should not be run on a host. Set this to "False" if you don't want to see these "Skipping" +# messages. NOTE: the task header will still be shown regardless of whether or not the +# task is skipped. +#display_skipped_hosts = True + +# by default, if a task in a playbook does not include a name: field then +# ansible-playbook will construct a header that includes the task's action but +# not the task's args. This is a security feature because ansible cannot know +# if the *module* considers an argument to be no_log at the time that the +# header is printed. If your environment doesn't have a problem securing +# stdout from ansible-playbook (or you have manually specified no_log in your +# playbook on all of the tasks where you have secret information) then you can +# safely set this to True to get more informative messages. +#display_args_to_stdout = False + +# by default (as of 1.3), Ansible will raise errors when attempting to dereference +# Jinja2 variables that are not set in templates or action lines. Uncomment this line +# to revert the behavior to pre-1.3. +#error_on_undefined_vars = False + +# by default (as of 1.6), Ansible may display warnings based on the configuration of the +# system running ansible itself. This may include warnings about 3rd party packages or +# other conditions that should be resolved if possible. +# to disable these warnings, set the following value to False: +#system_warnings = True + +# by default (as of 1.4), Ansible may display deprecation warnings for language +# features that should no longer be used and will be removed in future versions. +# to disable these warnings, set the following value to False: +#deprecation_warnings = True + +# (as of 1.8), Ansible can optionally warn when usage of the shell and +# command module appear to be simplified by using a default Ansible module +# instead. These warnings can be silenced by adjusting the following +# setting or adding warn=yes or warn=no to the end of the command line +# parameter string. This will for example suggest using the git module +# instead of shelling out to the git command. +# command_warnings = False + + +# set plugin path directories here, separate with colons +#action_plugins = /usr/share/ansible/plugins/action +#cache_plugins = /usr/share/ansible/plugins/cache +#callback_plugins = /usr/share/ansible/plugins/callback +#connection_plugins = /usr/share/ansible/plugins/connection +#lookup_plugins = /usr/share/ansible/plugins/lookup +#inventory_plugins = /usr/share/ansible/plugins/inventory +#vars_plugins = /usr/share/ansible/plugins/vars +#filter_plugins = /usr/share/ansible/plugins/filter +#test_plugins = /usr/share/ansible/plugins/test +#strategy_plugins = /usr/share/ansible/plugins/strategy + +# by default callbacks are not loaded for /bin/ansible, enable this if you +# want, for example, a notification or logging callback to also apply to +# /bin/ansible runs +#bin_ansible_callbacks = False + + +# don't like cows? that's unfortunate. +# set to 1 if you don't want cowsay support or export ANSIBLE_NOCOWS=1 +#nocows = 1 + +# set which cowsay stencil you'd like to use by default. When set to 'random', +# a random stencil will be selected for each task. The selection will be filtered +# against the `cow_whitelist` option below. +#cow_selection = default +#cow_selection = random + +# when using the 'random' option for cowsay, stencils will be restricted to this list. +# it should be formatted as a comma-separated list with no spaces between names. +# NOTE: line continuations here are for formatting purposes only, as the INI parser +# in python does not support them. +#cow_whitelist=bud-frogs,bunny,cheese,daemon,default,dragon,elephant-in-snake,elephant,eyes,\ +# hellokitty,kitty,luke-koala,meow,milk,moofasa,moose,ren,sheep,small,stegosaurus,\ +# stimpy,supermilker,three-eyes,turkey,turtle,tux,udder,vader-koala,vader,www + +# don't like colors either? +# set to 1 if you don't want colors, or export ANSIBLE_NOCOLOR=1 +#nocolor = 1 + +# if set to a persistent type (not 'memory', for example 'redis') fact values +# from previous runs in Ansible will be stored. This may be useful when +# wanting to use, for example, IP information from one group of servers +# without having to talk to them in the same playbook run to get their +# current IP information. +#fact_caching = memory + + +# retry files +# When a playbook fails by default a .retry file will be created in ~/ +# You can disable this feature by setting retry_files_enabled to False +# and you can change the location of the files by setting retry_files_save_path + +#retry_files_enabled = False +#retry_files_save_path = ~/.ansible-retry + +# squash actions +# Ansible can optimise actions that call modules with list parameters +# when looping. Instead of calling the module once per with_ item, the +# module is called once with all items at once. Currently this only works +# under limited circumstances, and only with parameters named 'name'. +#squash_actions = apk,apt,dnf,homebrew,package,pacman,pkgng,yum,zypper + +# prevents logging of task data, off by default +#no_log = False + +# prevents logging of tasks, but only on the targets, data is still logged on the master/controller +#no_target_syslog = False + +# controls whether Ansible will raise an error or warning if a task has no +# choice but to create world readable temporary files to execute a module on +# the remote machine. This option is False by default for security. Users may +# turn this on to have behaviour more like Ansible prior to 2.1.x. See +# https://docs.ansible.com/ansible/become.html#becoming-an-unprivileged-user +# for more secure ways to fix this than enabling this option. +#allow_world_readable_tmpfiles = False + +# controls the compression level of variables sent to +# worker processes. At the default of 0, no compression +# is used. This value must be an integer from 0 to 9. +#var_compression_level = 9 + +# controls what compression method is used for new-style ansible modules when +# they are sent to the remote system. The compression types depend on having +# support compiled into both the controller's python and the client's python. +# The names should match with the python Zipfile compression types: +# * ZIP_STORED (no compression. available everywhere) +# * ZIP_DEFLATED (uses zlib, the default) +# These values may be set per host via the ansible_module_compression inventory +# variable +#module_compression = 'ZIP_DEFLATED' + +# This controls the cutoff point (in bytes) on --diff for files +# set to 0 for unlimited (RAM may suffer!). +#max_diff_size = 1048576 + +[privilege_escalation] +#become=True +#become_method=sudo +#become_user=root +#become_ask_pass=False + +[paramiko_connection] + +# uncomment this line to cause the paramiko connection plugin to not record new host +# keys encountered. Increases performance on new host additions. Setting works independently of the +# host key checking setting above. +#record_host_keys=False + +# by default, Ansible requests a pseudo-terminal for commands executed under sudo. Uncomment this +# line to disable this behaviour. +#pty=False + +[ssh_connection] + +# ssh arguments to use +# Leaving off ControlPersist will result in poor performance, so use +# paramiko on older platforms rather than removing it, -C controls compression use +#ssh_args = -C -o ControlMaster=auto -o ControlPersist=60s + +# The path to use for the ControlPath sockets. This defaults to +# "%(directory)s/ansible-ssh-%%h-%%p-%%r", however on some systems with +# very long hostnames or very long path names (caused by long user names or +# deeply nested home directories) this can exceed the character limit on +# file socket names (108 characters for most platforms). In that case, you +# may wish to shorten the string below. +# +# Example: +# control_path = %(directory)s/%%h-%%r +#control_path = %(directory)s/ansible-ssh-%%h-%%p-%%r +control_path = %(directory)s/%%h + +# Enabling pipelining reduces the number of SSH operations required to +# execute a module on the remote server. This can result in a significant +# performance improvement when enabled, however when using "sudo:" you must +# first disable 'requiretty' in /etc/sudoers +# +# By default, this option is disabled to preserve compatibility with +# sudoers configurations that have requiretty (the default on many distros). +# +#pipelining = False + +# Control the mechanism for transfering files +# * smart = try sftp and then try scp [default] +# * True = use scp only +# * False = use sftp only +#scp_if_ssh = smart + +# if False, sftp will not use batch mode to transfer files. This may cause some +# types of file transfer failures impossible to catch however, and should +# only be disabled if your sftp version has problems with batch mode +#sftp_batch_mode = False + +[accelerate] +#accelerate_port = 5099 +#accelerate_timeout = 30 +#accelerate_connect_timeout = 5.0 + +# The daemon timeout is measured in minutes. This time is measured +# from the last activity to the accelerate daemon. +#accelerate_daemon_timeout = 30 + +# If set to yes, accelerate_multi_key will allow multiple +# private keys to be uploaded to it, though each user must +# have access to the system via SSH to add a new key. The default +# is "no". +#accelerate_multi_key = yes + +[selinux] +# file systems that require special treatment when dealing with security context +# the default behaviour that copies the existing context or uses the user default +# needs to be changed to use the file system dependent context. +#special_context_filesystems=nfs,vboxsf,fuse,ramfs + +# Set this to yes to allow libvirt_lxc connections to work without SELinux. +#libvirt_lxc_noseclabel = yes + +[colors] +#highlight = white +#verbose = blue +#warn = bright purple +#error = red +#debug = dark gray +#deprecate = purple +#skip = cyan +#unreachable = red +#ok = green +#changed = yellow +#diff_add = green +#diff_remove = red +#diff_lines = cyan diff --git a/hosts b/hosts new file mode 100644 index 0000000..aaa4de9 --- /dev/null +++ b/hosts @@ -0,0 +1,42 @@ +test-machines: + hosts: + vlorentz-desktop: + ansible_host: vlorentz-desktop.internal.softwareheritage.org + ansible_user: vlorentz-cassandra + cassandra_data_root: /srv/softwareheritage/cassandra-test-0 + cassandra_max_heap_size: 8G + cassandra_heap_newsize: 1200M + listen_address: 128.93.66.190 + swh_storage_ports: [12301, 12302, 12303, 12304, 12305, 12306, 12307, 12308] + ardumont-desktop: + ansible_host: ardumont-desktop.internal.softwareheritage.org + ansible_user: vlorentz-cassandra + cassandra_data_root: /data + cassandra_max_heap_size: 8G + cassandra_heap_newsize: 1200M + listen_address: 128.93.66.187 + swh_storage_ports: [12301, 12302, 12303, 12304, 12305, 12306] + ddouard-desktop: + ansible_host: ddouard-desktop.internal.softwareheritage.org + ansible_user: vlorentz + cassandra_data_root: /data/vlorentz + cassandra_max_heap_size: 8G + cassandra_heap_newsize: 1200M + listen_address: 128.93.66.191 + swh_storage_ports: [12301, 12302, 12303, 12304, 12305, 12306] + seirl-desktop: + ansible_host: grand-palais.internal.softwareheritage.org + ansible_user: vlorentz + cassandra_data_root: /mnt/cassandra-test-0 + cassandra_max_heap_size: 8G + cassandra_heap_newsize: 800M + listen_address: 128.93.64.42 + swh_storage_ports: [12301, 12302, 12303, 12304, 12305, 12306] + +cassandra-servers: + children: + test-machines + +cassandra-clients: + children: + test-machines diff --git a/playbooks/files/replay.py b/playbooks/files/replay.py new file mode 100644 index 0000000..b4f264c --- /dev/null +++ b/playbooks/files/replay.py @@ -0,0 +1,100 @@ +# Copyright (C) 2019 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from time import time +import logging +from concurrent.futures import ThreadPoolExecutor + +from swh.storage import HashCollision +from swh.model.hashutil import hash_to_hex +from swh.objstorage.objstorage import ID_HASH_ALGO +from swh.core.statsd import statsd + +logger = logging.getLogger(__name__) + + +def process_replay_objects(all_objects, *, storage): + for (object_type, objects) in all_objects.items(): + _insert_objects(object_type, objects, storage) + + +def _insert_objects(object_type, objects, storage): + if object_type == 'content': + # TODO: insert 'content' in batches + for object_ in objects: + try: + storage.content_add_metadata([object_]) + except HashCollision as e: + logger.error('Hash collision: %s', e.args) + elif object_type in ('directory', 'revision', 'release', + 'snapshot', 'origin'): + # TODO: split batches that are too large for the storage + # to handle? + method = getattr(storage, object_type + '_add') + method(objects) + elif object_type == 'origin_visit': + for visit in objects: + if isinstance(visit['origin'], str): + # old format + visit['origin'] = {'url': visit['origin']} + else: + storage.origin_add_one(visit['origin']) + if 'type' not in visit: + # old format + visit['type'] = visit['origin']['type'] + + # filter out buggy objects produced by the backfiller + # see https://forge.softwareheritage.org/D1742 + objects = [visit for visit in objects + if 'visit' in visit] + + storage.origin_visit_upsert(objects) + else: + logger.warning('Received a series of %s, this should not happen', + object_type) + + +def copy_object(obj_id, src, dst): + statsd_name = 'swh_journal_content_replayer_%s_duration_seconds' + try: + with statsd.timed(statsd_name % 'get'): + obj = src.get(obj_id) + with statsd.timed(statsd_name % 'put'): + dst.add(obj, obj_id=obj_id, check_presence=False) + logger.debug('copied %s', hash_to_hex(obj_id)) + statsd.increment( + 'swh_journal_content_replayer_bytes_total', + len(obj)) + except Exception: + obj = '' + logger.exception('Failed to copy %s', hash_to_hex(obj_id)) + return len(obj) + + +def process_replay_objects_content(all_objects, *, src, dst, concurrency=8): + vol = [] + t0 = time() + with ThreadPoolExecutor(max_workers=concurrency) as executor: + for (object_type, objects) in all_objects.items(): + if object_type != 'content': + logger.warning( + 'Received a series of %s, this should not happen', + object_type) + continue + for obj in objects: + obj_id = obj[ID_HASH_ALGO] + if obj['status'] == 'visible': + fut = executor.submit(copy_object, obj_id, src, dst) + fut.add_done_callback(lambda fn: vol.append(fn.result())) + else: + logger.debug('skipped %s (%s)', + hash_to_hex(obj_id), obj['status']) + dt = time() - t0 + logger.info( + 'processed %s content objects in %.1fsec ' + '(%.1f obj/sec, %.1fMB/sec) - %s failures', + len(vol), dt, + len(vol)/dt, + sum(vol)/1024/1024/dt, len([x for x in vol if not x])) diff --git a/playbooks/install-cassandra.retry b/playbooks/install-cassandra.retry new file mode 100644 index 0000000..b7ff7fd --- /dev/null +++ b/playbooks/install-cassandra.retry @@ -0,0 +1,4 @@ +ardumont-desktop +ddouard-desktop +seirl-desktop +vlorentz-desktop diff --git a/playbooks/install-cassandra.yml b/playbooks/install-cassandra.yml new file mode 100644 index 0000000..93a138d --- /dev/null +++ b/playbooks/install-cassandra.yml @@ -0,0 +1,60 @@ +- hosts: cassandra-servers + tasks: + - name: "get seed ipv4 address" + set_fact: + cassandra_seed_ip: 128.93.66.190 + + - name: "stat data dir" + stat: + path: "{{cassandra_data_root}}" + register: stat_data_dir + - name: "check data dir is owned by me" + fail: + msg: "data dir {{cassandra_data_root}} is owned by {{stat_data_dir.stat.pw_name}}, not by {{ansible_user}}" + when: "stat_data_dir.stat.pw_name != '{{ansible_user}}'" + + - name: "download cassandra bin" + get_url: + dest: "/home/{{ansible_user}}/apache-cassandra-3.11.4-bin.tar.gz" + url: "http://apache.mirrors.ovh.net/ftp.apache.org/dist/cassandra/3.11.4/apache-cassandra-3.11.4-bin.tar.gz" + checksum: "sha256:5d598e23c3ffc4db0301ec2b313061e3208fae0f9763d4b47888237dd9069987" + - name: "unarchive cassandra bin" + unarchive: + src: "/home/{{ansible_user}}/apache-cassandra-3.11.4-bin.tar.gz" + dest: "/home/{{ansible_user}}/" + remote_src: true + keep_newer: true + - name: "set cassandra install dir" + set_fact: + cassandra_install_path: /home/{{ansible_user}}/apache-cassandra-3.11.4 + + - name: "install config files" + template: + src: "cassandra.yaml" + dest: "{{cassandra_install_path}}/conf/{{item}}" + with_items: [cassandra.yaml, jvm.options] + - name: "create log dir" + file: + path: "{{cassandra_install_path}}/logs" + state: directory + + - name: "create systemd unit dir" + file: + path: "/home/{{ansible_user}}/.config/systemd/user/" + state: directory + - name: "install systemd unit" + template: + src: "cassandra.service" + dest: "/home/{{ansible_user}}/.config/systemd/user/cassandra.service" + - name: "enable systemd unit" + systemd: + name: "cassandra.service" + enabled: yes + user: yes + daemon_reload: yes # https://github.com/ansible/ansible/issues/36585 + - name: "start cassandra" + systemd: + name: "cassandra.service" + state: started + user: yes + diff --git a/playbooks/install-replayer.retry b/playbooks/install-replayer.retry new file mode 100644 index 0000000..b7ff7fd --- /dev/null +++ b/playbooks/install-replayer.retry @@ -0,0 +1,4 @@ +ardumont-desktop +ddouard-desktop +seirl-desktop +vlorentz-desktop diff --git a/playbooks/install-replayer.yml b/playbooks/install-replayer.yml new file mode 100644 index 0000000..95068e8 --- /dev/null +++ b/playbooks/install-replayer.yml @@ -0,0 +1,56 @@ +- hosts: cassandra-clients + tasks: + - name: "set journal source location" + set_fact: + journal_source: "/home/{{ansible_user}}/swh-journal" + + - name: "get swh-journal's source" + git: + dest: "{{journal_source}}" + repo: "https://forge.softwareheritage.org/source/swh-journal.git" + force: yes + + - name: "fix 'replay' command for recent versions of click" + shell: "sed -i \"s/'--group-id', '--consumer-id'/'--group-id'/\" {{journal_source}}/swh/journal/cli.py" + - name: "update replayer" + copy: + src: replay.py + dest: "{{journal_source}}/swh/journal/replay.py" + + - name: "write dummy version file" + # to please vcversioner + copy: + content: "0.0.0-foo-bar" + dest: "{{journal_source}}/version.txt" + + - name: "install swh-journal" + shell: "python3 setup.py develop --user" + args: + chdir: "{{journal_source}}" + + - name: "copy replayer config file" + template: + src: "replayer.yml" + dest: "/home/{{ansible_user}}/replayer_{{item}}.yml" + vars: + rpc_port: "{{item}}" + with_items: "{{swh_storage_ports}}" + + - name: "install replayer systemd unit" + template: + src: "replayer@.service" + dest: "/home/{{ansible_user}}/.config/systemd/user/replayer@.service" + - name: "enable systemd unit" + systemd: + name: "replayer@{{item}}.service" + enabled: yes + user: yes + daemon_reload: yes # https://github.com/ansible/ansible/issues/36585 + with_items: "{{swh_storage_ports}}" + - name: "restart replayer" + systemd: + name: "replayer@{{item}}.service" + state: restarted + user: yes + with_items: "{{swh_storage_ports}}" + diff --git a/playbooks/install-storage.retry b/playbooks/install-storage.retry new file mode 100644 index 0000000..b7ff7fd --- /dev/null +++ b/playbooks/install-storage.retry @@ -0,0 +1,4 @@ +ardumont-desktop +ddouard-desktop +seirl-desktop +vlorentz-desktop diff --git a/playbooks/install-storage.yml b/playbooks/install-storage.yml new file mode 100644 index 0000000..2b21def --- /dev/null +++ b/playbooks/install-storage.yml @@ -0,0 +1,46 @@ +- hosts: cassandra-clients + tasks: + - name: "set rpc server source location" + set_fact: + storage_source: "/home/{{ansible_user}}/swh-storage" + + - name: "get swh-storage-cassandra's source" + git: + dest: "{{storage_source}}" + repo: "https://forge.softwareheritage.org/source/swh-storage-cassandra.git" + version: "cassandra-backend2" + remote: "origin-cassandra" + + - name: "write dummy version file" + # to please vcversioner + copy: + content: "0.0.999999--" + dest: "{{storage_source}}/version.txt" + + - name: "install swh-storage-cassandra" + shell: "python3 setup.py develop --user" + args: + chdir: "{{storage_source}}" + + - name: "copy rpc server config file" + template: + src: "storage_cassandra.yml" + dest: "/home/{{ansible_user}}/storage_cassandra.yml" + + - name: "install swh-storage-cassandra systemd unit" + template: + src: "swh-storage-cassandra@.service" + dest: "/home/{{ansible_user}}/.config/systemd/user/swh-storage-cassandra@.service" + - name: "enable systemd unit" + systemd: + name: "swh-storage-cassandra@{{item}}.service" + enabled: yes + user: yes + daemon_reload: yes # https://github.com/ansible/ansible/issues/36585 + with_items: "{{swh_storage_ports}}" + - name: "start swh-storage-cassandra" + systemd: + name: "swh-storage-cassandra@{{item}}.service" + state: restarted + user: yes + with_items: "{{swh_storage_ports}}" diff --git a/playbooks/templates/cassandra.service b/playbooks/templates/cassandra.service new file mode 100644 index 0000000..01c4e3d --- /dev/null +++ b/playbooks/templates/cassandra.service @@ -0,0 +1,15 @@ +[Unit] +Description=Cassandra server for SWH test cluster +After=network.target + +[Service] +Type=forking +ExecStart={{cassandra_install_path}}/bin/cassandra + +Environment=MAX_HEAP_SIZE={{cassandra_max_heap_size}} +Environment=HEAP_NEWSIZE={{cassandra_heap_newsize}} + +Nice=10 + +[Install] +WantedBy=default.target diff --git a/playbooks/templates/cassandra.yaml b/playbooks/templates/cassandra.yaml new file mode 100644 index 0000000..d8c29da --- /dev/null +++ b/playbooks/templates/cassandra.yaml @@ -0,0 +1,1243 @@ +# Cassandra storage config YAML + +# NOTE: +# See http://wiki.apache.org/cassandra/StorageConfiguration for +# full explanations of configuration directives +# /NOTE + +# The name of the cluster. This is mainly used to prevent machines in +# one logical cluster from joining another. +cluster_name: 'Test SWH Cluster' + +# This defines the number of tokens randomly assigned to this node on the ring +# The more tokens, relative to other nodes, the larger the proportion of data +# that this node will store. You probably want all nodes to have the same number +# of tokens assuming they have equal hardware capability. +# +# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility, +# and will use the initial_token as described below. +# +# Specifying initial_token will override this setting on the node's initial start, +# on subsequent starts, this setting will apply even if initial token is set. +# +# If you already have a cluster with 1 token per node, and wish to migrate to +# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations +num_tokens: 256 + +# Triggers automatic allocation of num_tokens tokens for this node. The allocation +# algorithm attempts to choose tokens in a way that optimizes replicated load over +# the nodes in the datacenter for the replication strategy used by the specified +# keyspace. +# +# The load assigned to each node will be close to proportional to its number of +# vnodes. +# +# Only supported with the Murmur3Partitioner. +# allocate_tokens_for_keyspace: KEYSPACE + +# initial_token allows you to specify tokens manually. While you can use it with +# vnodes (num_tokens > 1, above) -- in which case you should provide a +# comma-separated list -- it's primarily used when adding nodes to legacy clusters +# that do not have vnodes enabled. +# initial_token: + +# See http://wiki.apache.org/cassandra/HintedHandoff +# May either be "true" or "false" to enable globally +hinted_handoff_enabled: true + +# When hinted_handoff_enabled is true, a black list of data centers that will not +# perform hinted handoff +# hinted_handoff_disabled_datacenters: +# - DC1 +# - DC2 + +# this defines the maximum amount of time a dead host will have hints +# generated. After it has been dead this long, new hints for it will not be +# created until it has been seen alive and gone down again. +max_hint_window_in_ms: 10800000 # 3 hours + +# Maximum throttle in KBs per second, per delivery thread. This will be +# reduced proportionally to the number of nodes in the cluster. (If there +# are two nodes in the cluster, each delivery thread will use the maximum +# rate; if there are three, each will throttle to half of the maximum, +# since we expect two nodes to be delivering hints simultaneously.) +hinted_handoff_throttle_in_kb: 1024 + +# Number of threads with which to deliver hints; +# Consider increasing this number when you have multi-dc deployments, since +# cross-dc handoff tends to be slower +max_hints_delivery_threads: 2 + +# Directory where Cassandra should store hints. +# If not set, the default directory is $CASSANDRA_HOME/data/hints. +# hints_directory: /var/lib/cassandra/hints +hints_directory: {{cassandra_data_root}}/hints + +# How often hints should be flushed from the internal buffers to disk. +# Will *not* trigger fsync. +hints_flush_period_in_ms: 10000 + +# Maximum size for a single hints file, in megabytes. +max_hints_file_size_in_mb: 128 + +# Compression to apply to the hint files. If omitted, hints files +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +#hints_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Maximum throttle in KBs per second, total. This will be +# reduced proportionally to the number of nodes in the cluster. +batchlog_replay_throttle_in_kb: 1024 + +# Authentication backend, implementing IAuthenticator; used to identify users +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator, +# PasswordAuthenticator}. +# +# - AllowAllAuthenticator performs no checks - set it to disable authentication. +# - PasswordAuthenticator relies on username/password pairs to authenticate +# users. It keeps usernames and hashed passwords in system_auth.roles table. +# Please increase system_auth keyspace replication factor if you use this authenticator. +# If using PasswordAuthenticator, CassandraRoleManager must also be used (see below) +authenticator: AllowAllAuthenticator + +# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer, +# CassandraAuthorizer}. +# +# - AllowAllAuthorizer allows any action to any user - set it to disable authorization. +# - CassandraAuthorizer stores permissions in system_auth.role_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +authorizer: AllowAllAuthorizer + +# Part of the Authentication & Authorization backend, implementing IRoleManager; used +# to maintain grants and memberships between roles. +# Out of the box, Cassandra provides org.apache.cassandra.auth.CassandraRoleManager, +# which stores role information in the system_auth keyspace. Most functions of the +# IRoleManager require an authenticated login, so unless the configured IAuthenticator +# actually implements authentication, most of this functionality will be unavailable. +# +# - CassandraRoleManager stores role data in the system_auth keyspace. Please +# increase system_auth keyspace replication factor if you use this role manager. +role_manager: CassandraRoleManager + +# Validity period for roles cache (fetching granted roles can be an expensive +# operation depending on the role manager, CassandraRoleManager is one example) +# Granted roles are cached for authenticated sessions in AuthenticatedUser and +# after the period specified here, become eligible for (async) reload. +# Defaults to 2000, set to 0 to disable caching entirely. +# Will be disabled automatically for AllowAllAuthenticator. +roles_validity_in_ms: 2000 + +# Refresh interval for roles cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If roles_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as roles_validity_in_ms. +# roles_update_interval_in_ms: 2000 + +# Validity period for permissions cache (fetching permissions can be an +# expensive operation depending on the authorizer, CassandraAuthorizer is +# one example). Defaults to 2000, set to 0 to disable. +# Will be disabled automatically for AllowAllAuthorizer. +permissions_validity_in_ms: 2000 + +# Refresh interval for permissions cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If permissions_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as permissions_validity_in_ms. +# permissions_update_interval_in_ms: 2000 + +# Validity period for credentials cache. This cache is tightly coupled to +# the provided PasswordAuthenticator implementation of IAuthenticator. If +# another IAuthenticator implementation is configured, this cache will not +# be automatically used and so the following settings will have no effect. +# Please note, credentials are cached in their encrypted form, so while +# activating this cache may reduce the number of queries made to the +# underlying table, it may not bring a significant reduction in the +# latency of individual authentication attempts. +# Defaults to 2000, set to 0 to disable credentials caching. +credentials_validity_in_ms: 2000 + +# Refresh interval for credentials cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If credentials_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as credentials_validity_in_ms. +# credentials_update_interval_in_ms: 2000 + +# The partitioner is responsible for distributing groups of rows (by +# partition key) across nodes in the cluster. You should leave this +# alone for new clusters. The partitioner can NOT be changed without +# reloading all data, so when upgrading you should set this to the +# same partitioner you were already using. +# +# Besides Murmur3Partitioner, partitioners included for backwards +# compatibility include RandomPartitioner, ByteOrderedPartitioner, and +# OrderPreservingPartitioner. +# +partitioner: org.apache.cassandra.dht.Murmur3Partitioner + +# Directories where Cassandra should store data on disk. Cassandra +# will spread data evenly across them, subject to the granularity of +# the configured compaction strategy. +# If not set, the default directory is $CASSANDRA_HOME/data/data. +# data_file_directories: +# - /var/lib/cassandra/data +data_file_directories: + - {{cassandra_data_root}}/data + +# commit log. when running on magnetic HDD, this should be a +# separate spindle than the data directories. +# If not set, the default directory is $CASSANDRA_HOME/data/commitlog. +# commitlog_directory: /var/lib/cassandra/commitlog +commitlog_directory: {{cassandra_data_root}}/commitlog + +# Enable / disable CDC functionality on a per-node basis. This modifies the logic used +# for write path allocation rejection (standard: never reject. cdc: reject Mutation +# containing a CDC-enabled table if at space limit in cdc_raw_directory). +cdc_enabled: false + +# CommitLogSegments are moved to this directory on flush if cdc_enabled: true and the +# segment contains mutations for a CDC-enabled table. This should be placed on a +# separate spindle than the data directories. If not set, the default directory is +# $CASSANDRA_HOME/data/cdc_raw. +# cdc_raw_directory: /var/lib/cassandra/cdc_raw +cdc_raw_directory: {{cassandra_data_root}}/cdc_raw + +# Policy for data disk failures: +# +# die +# shut down gossip and client transports and kill the JVM for any fs errors or +# single-sstable errors, so the node can be replaced. +# +# stop_paranoid +# shut down gossip and client transports even for single-sstable errors, +# kill the JVM for errors during startup. +# +# stop +# shut down gossip and client transports, leaving the node effectively dead, but +# can still be inspected via JMX, kill the JVM for errors during startup. +# +# best_effort +# stop using the failed disk and respond to requests based on +# remaining available sstables. This means you WILL see obsolete +# data at CL.ONE! +# +# ignore +# ignore fatal errors and let requests fail, as in pre-1.2 Cassandra +disk_failure_policy: stop + +# Policy for commit disk failures: +# +# die +# shut down gossip and Thrift and kill the JVM, so the node can be replaced. +# +# stop +# shut down gossip and Thrift, leaving the node effectively dead, but +# can still be inspected via JMX. +# +# stop_commit +# shutdown the commit log, letting writes collect but +# continuing to service reads, as in pre-2.0.5 Cassandra +# +# ignore +# ignore fatal errors and let the batches fail +commit_failure_policy: stop + +# Maximum size of the native protocol prepared statement cache +# +# Valid values are either "auto" (omitting the value) or a value greater 0. +# +# Note that specifying a too large value will result in long running GCs and possbily +# out-of-memory errors. Keep the value at a small fraction of the heap. +# +# If you constantly see "prepared statements discarded in the last minute because +# cache limit reached" messages, the first step is to investigate the root cause +# of these messages and check whether prepared statements are used correctly - +# i.e. use bind markers for variable parts. +# +# Do only change the default value, if you really have more prepared statements than +# fit in the cache. In most cases it is not neccessary to change this value. +# Constantly re-preparing statements is a performance penalty. +# +# Default value ("auto") is 1/256th of the heap or 10MB, whichever is greater +prepared_statements_cache_size_mb: + +# Maximum size of the Thrift prepared statement cache +# +# If you do not use Thrift at all, it is safe to leave this value at "auto". +# +# See description of 'prepared_statements_cache_size_mb' above for more information. +# +# Default value ("auto") is 1/256th of the heap or 10MB, whichever is greater +thrift_prepared_statements_cache_size_mb: + +# Maximum size of the key cache in memory. +# +# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the +# minimum, sometimes more. The key cache is fairly tiny for the amount of +# time it saves, so it's worthwhile to use it at large numbers. +# The row cache saves even more time, but must contain the entire row, +# so it is extremely space-intensive. It's best to only use the +# row cache if you have hot rows or static rows. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(5% of Heap (in MB), 100MB)). Set to 0 to disable key cache. +key_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the key cache. Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 14400 or 4 hours. +key_cache_save_period: 14400 + +# Number of keys from the key cache to save +# Disabled by default, meaning all keys are going to be saved +# key_cache_keys_to_save: 100 + +# Row cache implementation class name. Available implementations: +# +# org.apache.cassandra.cache.OHCProvider +# Fully off-heap row cache implementation (default). +# +# org.apache.cassandra.cache.SerializingCacheProvider +# This is the row cache implementation availabile +# in previous releases of Cassandra. +# row_cache_class_name: org.apache.cassandra.cache.OHCProvider + +# Maximum size of the row cache in memory. +# Please note that OHC cache implementation requires some additional off-heap memory to manage +# the map structures and some in-flight memory during operations before/after cache entries can be +# accounted against the cache capacity. This overhead is usually small compared to the whole capacity. +# Do not specify more memory that the system can afford in the worst usual situation and leave some +# headroom for OS block level cache. Do never allow your system to swap. +# +# Default value is 0, to disable row caching. +row_cache_size_in_mb: 0 + +# Duration in seconds after which Cassandra should save the row cache. +# Caches are saved to saved_caches_directory as specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 0 to disable saving the row cache. +row_cache_save_period: 0 + +# Number of keys from the row cache to save. +# Specify 0 (which is the default), meaning all keys are going to be saved +# row_cache_keys_to_save: 100 + +# Maximum size of the counter cache in memory. +# +# Counter cache helps to reduce counter locks' contention for hot counter cells. +# In case of RF = 1 a counter cache hit will cause Cassandra to skip the read before +# write entirely. With RF > 1 a counter cache hit will still help to reduce the duration +# of the lock hold, helping with hot counter cell updates, but will not allow skipping +# the read entirely. Only the local (clock, count) tuple of a counter cell is kept +# in memory, not the whole counter, so it's relatively cheap. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(2.5% of Heap (in MB), 50MB)). Set to 0 to disable counter cache. +# NOTE: if you perform counter deletes and rely on low gcgs, you should disable the counter cache. +counter_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the counter cache (keys only). Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Default is 7200 or 2 hours. +counter_cache_save_period: 7200 + +# Number of keys from the counter cache to save +# Disabled by default, meaning all keys are going to be saved +# counter_cache_keys_to_save: 100 + +# saved caches +# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches. +# saved_caches_directory: /var/lib/cassandra/saved_caches +saved_caches_directory: {{cassandra_data_root}}/saved_caches + +# commitlog_sync may be either "periodic" or "batch." +# +# When in batch mode, Cassandra won't ack writes until the commit log +# has been fsynced to disk. It will wait +# commitlog_sync_batch_window_in_ms milliseconds between fsyncs. +# This window should be kept short because the writer threads will +# be unable to do extra work while waiting. (You may need to increase +# concurrent_writes for the same reason.) +# +# commitlog_sync: batch +# commitlog_sync_batch_window_in_ms: 2 +# +# the other option is "periodic" where writes may be acked immediately +# and the CommitLog is simply synced every commitlog_sync_period_in_ms +# milliseconds. +commitlog_sync: periodic +commitlog_sync_period_in_ms: 10000 + +# The size of the individual commitlog file segments. A commitlog +# segment may be archived, deleted, or recycled once all the data +# in it (potentially from each columnfamily in the system) has been +# flushed to sstables. +# +# The default size is 32, which is almost always fine, but if you are +# archiving commitlog segments (see commitlog_archiving.properties), +# then you probably want a finer granularity of archiving; 8 or 16 MB +# is reasonable. +# Max mutation size is also configurable via max_mutation_size_in_kb setting in +# cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024. +# This should be positive and less than 2048. +# +# NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must +# be set to at least twice the size of max_mutation_size_in_kb / 1024 +# +commitlog_segment_size_in_mb: 32 + +# Compression to apply to the commit log. If omitted, the commit log +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +# commitlog_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# any class that implements the SeedProvider interface and has a +# constructor that takes a Map of parameters will do. +seed_provider: + # Addresses of hosts that are deemed contact points. + # Cassandra nodes use this list of hosts to find each other and learn + # the topology of the ring. You must change this if you are running + # multiple nodes! + - class_name: org.apache.cassandra.locator.SimpleSeedProvider + parameters: + # seeds is actually a comma-delimited list of addresses. + # Ex: ",," + - seeds: "{{cassandra_seed_ip}}" + +# For workloads with more data than can fit in memory, Cassandra's +# bottleneck will be reads that need to fetch data from +# disk. "concurrent_reads" should be set to (16 * number_of_drives) in +# order to allow the operations to enqueue low enough in the stack +# that the OS and drives can reorder them. Same applies to +# "concurrent_counter_writes", since counter writes read the current +# values before incrementing and writing them back. +# +# On the other hand, since writes are almost never IO bound, the ideal +# number of "concurrent_writes" is dependent on the number of cores in +# your system; (8 * number_of_cores) is a good rule of thumb. +concurrent_reads: 32 +concurrent_writes: 32 +concurrent_counter_writes: 32 + +# For materialized view writes, as there is a read involved, so this should +# be limited by the less of concurrent reads or concurrent writes. +concurrent_materialized_view_writes: 32 + +# Maximum memory to use for sstable chunk cache and buffer pooling. +# 32MB of this are reserved for pooling buffers, the rest is used as an +# cache that holds uncompressed sstable chunks. +# Defaults to the smaller of 1/4 of heap or 512MB. This pool is allocated off-heap, +# so is in addition to the memory allocated for heap. The cache also has on-heap +# overhead which is roughly 128 bytes per chunk (i.e. 0.2% of the reserved size +# if the default 64k chunk size is used). +# Memory is only allocated when needed. +# file_cache_size_in_mb: 512 + +# Flag indicating whether to allocate on or off heap when the sstable buffer +# pool is exhausted, that is when it has exceeded the maximum memory +# file_cache_size_in_mb, beyond which it will not cache buffers but allocate on request. + +# buffer_pool_use_heap_if_exhausted: true + +# The strategy for optimizing disk read +# Possible values are: +# ssd (for solid state disks, the default) +# spinning (for spinning disks) +# disk_optimization_strategy: ssd + +# Total permitted memory to use for memtables. Cassandra will stop +# accepting writes when the limit is exceeded until a flush completes, +# and will trigger a flush based on memtable_cleanup_threshold +# If omitted, Cassandra will set both to 1/4 the size of the heap. +# memtable_heap_space_in_mb: 2048 +# memtable_offheap_space_in_mb: 2048 + +# memtable_cleanup_threshold is deprecated. The default calculation +# is the only reasonable choice. See the comments on memtable_flush_writers +# for more information. +# +# Ratio of occupied non-flushing memtable size to total permitted size +# that will trigger a flush of the largest memtable. Larger mct will +# mean larger flushes and hence less compaction, but also less concurrent +# flush activity which can make it difficult to keep your disks fed +# under heavy write load. +# +# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1) +# memtable_cleanup_threshold: 0.11 + +# Specify the way Cassandra allocates and manages memtable memory. +# Options are: +# +# heap_buffers +# on heap nio buffers +# +# offheap_buffers +# off heap (direct) nio buffers +# +# offheap_objects +# off heap objects +memtable_allocation_type: heap_buffers + +# Total space to use for commit logs on disk. +# +# If space gets above this value, Cassandra will flush every dirty CF +# in the oldest segment and remove it. So a small total commitlog space +# will tend to cause more flush activity on less-active columnfamilies. +# +# The default value is the smaller of 8192, and 1/4 of the total space +# of the commitlog volume. +# +# commitlog_total_space_in_mb: 8192 + +# This sets the number of memtable flush writer threads per disk +# as well as the total number of memtables that can be flushed concurrently. +# These are generally a combination of compute and IO bound. +# +# Memtable flushing is more CPU efficient than memtable ingest and a single thread +# can keep up with the ingest rate of a whole server on a single fast disk +# until it temporarily becomes IO bound under contention typically with compaction. +# At that point you need multiple flush threads. At some point in the future +# it may become CPU bound all the time. +# +# You can tell if flushing is falling behind using the MemtablePool.BlockedOnAllocation +# metric which should be 0, but will be non-zero if threads are blocked waiting on flushing +# to free memory. +# +# memtable_flush_writers defaults to two for a single data directory. +# This means that two memtables can be flushed concurrently to the single data directory. +# If you have multiple data directories the default is one memtable flushing at a time +# but the flush will use a thread per data directory so you will get two or more writers. +# +# Two is generally enough to flush on a fast disk [array] mounted as a single data directory. +# Adding more flush writers will result in smaller more frequent flushes that introduce more +# compaction overhead. +# +# There is a direct tradeoff between number of memtables that can be flushed concurrently +# and flush size and frequency. More is not better you just need enough flush writers +# to never stall waiting for flushing to free memory. +# +#memtable_flush_writers: 2 + +# Total space to use for change-data-capture logs on disk. +# +# If space gets above this value, Cassandra will throw WriteTimeoutException +# on Mutations including tables with CDC enabled. A CDCCompactor is responsible +# for parsing the raw CDC logs and deleting them when parsing is completed. +# +# The default value is the min of 4096 mb and 1/8th of the total space +# of the drive where cdc_raw_directory resides. +# cdc_total_space_in_mb: 4096 + +# When we hit our cdc_raw limit and the CDCCompactor is either running behind +# or experiencing backpressure, we check at the following interval to see if any +# new space for cdc-tracked tables has been made available. Default to 250ms +# cdc_free_space_check_interval_ms: 250 + +# A fixed memory pool size in MB for for SSTable index summaries. If left +# empty, this will default to 5% of the heap size. If the memory usage of +# all index summaries exceeds this limit, SSTables with low read rates will +# shrink their index summaries in order to meet this limit. However, this +# is a best-effort process. In extreme conditions Cassandra may need to use +# more than this amount of memory. +index_summary_capacity_in_mb: + +# How frequently index summaries should be resampled. This is done +# periodically to redistribute memory from the fixed-size pool to sstables +# proportional their recent read rates. Setting to -1 will disable this +# process, leaving existing index summaries at their current sampling level. +index_summary_resize_interval_in_minutes: 60 + +# Whether to, when doing sequential writing, fsync() at intervals in +# order to force the operating system to flush the dirty +# buffers. Enable this to avoid sudden dirty buffer flushing from +# impacting read latencies. Almost always a good idea on SSDs; not +# necessarily on platters. +trickle_fsync: true +trickle_fsync_interval_in_kb: 10240 + +# TCP port, for commands and data +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +storage_port: 7000 + +# SSL port, for encrypted communication. Unused unless enabled in +# encryption_options +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +ssl_storage_port: 7001 + +# Address or interface to bind to and tell other Cassandra nodes to connect to. +# You _must_ change this if you want multiple nodes to be able to communicate! +# +# Set listen_address OR listen_interface, not both. +# +# Leaving it blank leaves it up to InetAddress.getLocalHost(). This +# will always do the Right Thing _if_ the node is properly configured +# (hostname, name resolution, etc), and the Right Thing is to use the +# address associated with the hostname (it might not be). +# +# Setting listen_address to 0.0.0.0 is always wrong. +# +listen_address: {{listen_address}} + +# Set listen_address OR listen_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# listen_interface: eth0 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# listen_interface_prefer_ipv6: false + +# Address to broadcast to other Cassandra nodes +# Leaving this blank will set it to the same value as listen_address +# broadcast_address: 1.2.3.4 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# Please note that the address on which the native transport is bound is the +# same as the rpc_address. The port however is different and specified below. +start_native_transport: true +# port for the CQL native transport to listen for clients on +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +native_transport_port: 9042 +# Enabling native transport encryption in client_encryption_options allows you to either use +# encryption for the standard port or to use a dedicated, additional port along with the unencrypted +# standard native_transport_port. +# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption +# for native_transport_port. Setting native_transport_port_ssl to a different value +# from native_transport_port will use encryption for native_transport_port_ssl while +# keeping native_transport_port unencrypted. +# native_transport_port_ssl: 9142 +# The maximum threads for handling requests when the native transport is used. +# This is similar to rpc_max_threads though the default differs slightly (and +# there is no native_transport_min_threads, idle threads will always be stopped +# after 30 seconds). +# native_transport_max_threads: 128 +# +# The maximum size of allowed frame. Frame (requests) larger than this will +# be rejected as invalid. The default is 256MB. If you're changing this parameter, +# you may want to adjust max_value_size_in_mb accordingly. This should be positive and less than 2048. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# Whether to start the thrift rpc server. +start_rpc: false + +# The address or interface to bind the Thrift RPC service and native transport +# server to. +# +# Set rpc_address OR rpc_interface, not both. +# +# Leaving rpc_address blank has the same effect as on listen_address +# (i.e. it will be based on the configured hostname of the node). +# +# Note that unlike listen_address, you can specify 0.0.0.0, but you must also +# set broadcast_rpc_address to a value other than 0.0.0.0. +# +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +rpc_address: {{listen_address}} + +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# rpc_interface: eth1 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# rpc_interface_prefer_ipv6: false + +# port for Thrift to listen for clients on +rpc_port: 9160 + +# RPC address to broadcast to drivers and other Cassandra nodes. This cannot +# be set to 0.0.0.0. If left blank, this will be set to the value of +# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must +# be set. +# broadcast_rpc_address: 1.2.3.4 + +# enable or disable keepalive on rpc/native connections +rpc_keepalive: true + +# Cassandra provides two out-of-the-box options for the RPC Server: +# +# sync +# One thread per thrift connection. For a very large number of clients, memory +# will be your limiting factor. On a 64 bit JVM, 180KB is the minimum stack size +# per thread, and that will correspond to your use of virtual memory (but physical memory +# may be limited depending on use of stack space). +# +# hsha +# Stands for "half synchronous, half asynchronous." All thrift clients are handled +# asynchronously using a small number of threads that does not vary with the amount +# of thrift clients (and thus scales well to many clients). The rpc requests are still +# synchronous (one thread per active request). If hsha is selected then it is essential +# that rpc_max_threads is changed from the default value of unlimited. +# +# The default is sync because on Windows hsha is about 30% slower. On Linux, +# sync/hsha performance is about the same, with hsha of course using less memory. +# +# Alternatively, can provide your own RPC server by providing the fully-qualified class name +# of an o.a.c.t.TServerFactory that can create an instance of it. +rpc_server_type: sync + +# Uncomment rpc_min|max_thread to set request pool size limits. +# +# Regardless of your choice of RPC server (see above), the number of maximum requests in the +# RPC thread pool dictates how many concurrent requests are possible (but if you are using the sync +# RPC server, it also dictates the number of clients that can be connected at all). +# +# The default is unlimited and thus provides no protection against clients overwhelming the server. You are +# encouraged to set a maximum that makes sense for you in production, but do keep in mind that +# rpc_max_threads represents the maximum number of client requests this server may execute concurrently. +# +# rpc_min_threads: 16 +# rpc_max_threads: 2048 + +# uncomment to set socket buffer sizes on rpc connections +# rpc_send_buff_size_in_bytes: +# rpc_recv_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# See also: +# /proc/sys/net/core/wmem_max +# /proc/sys/net/core/rmem_max +# /proc/sys/net/ipv4/tcp_wmem +# /proc/sys/net/ipv4/tcp_wmem +# and 'man tcp' +# internode_send_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# internode_recv_buff_size_in_bytes: + +# Frame size for thrift (maximum message length). +thrift_framed_transport_size_in_mb: 15 + +# Set to true to have Cassandra create a hard link to each sstable +# flushed or streamed locally in a backups/ subdirectory of the +# keyspace data. Removing these links is the operator's +# responsibility. +incremental_backups: false + +# Whether or not to take a snapshot before each compaction. Be +# careful using this option, since Cassandra won't clean up the +# snapshots for you. Mostly useful if you're paranoid when there +# is a data format change. +snapshot_before_compaction: false + +# Whether or not a snapshot is taken of the data before keyspace truncation +# or dropping of column families. The STRONGLY advised default of true +# should be used to provide data safety. If you set this flag to false, you will +# lose data on truncation or drop. +auto_snapshot: true + +# Granularity of the collation index of rows within a partition. +# Increase if your rows are large, or if you have a very large +# number of rows per partition. The competing goals are these: +# +# - a smaller granularity means more index entries are generated +# and looking up rows withing the partition by collation column +# is faster +# - but, Cassandra will keep the collation index in memory for hot +# rows (as part of the key cache), so a larger granularity means +# you can cache more hot rows +column_index_size_in_kb: 64 + +# Per sstable indexed key cache entries (the collation index in memory +# mentioned above) exceeding this size will not be held on heap. +# This means that only partition information is held on heap and the +# index entries are read from disk. +# +# Note that this size refers to the size of the +# serialized index information and not the size of the partition. +column_index_cache_size_in_kb: 2 + +# Number of simultaneous compactions to allow, NOT including +# validation "compactions" for anti-entropy repair. Simultaneous +# compactions can help preserve read performance in a mixed read/write +# workload, by mitigating the tendency of small sstables to accumulate +# during a single long running compactions. The default is usually +# fine and if you experience problems with compaction running too +# slowly or too fast, you should look at +# compaction_throughput_mb_per_sec first. +# +# concurrent_compactors defaults to the smaller of (number of disks, +# number of cores), with a minimum of 2 and a maximum of 8. +# +# If your data directories are backed by SSD, you should increase this +# to the number of cores. +#concurrent_compactors: 1 + +# Throttles compaction to the given total throughput across the entire +# system. The faster you insert data, the faster you need to compact in +# order to keep the sstable count down, but in general, setting this to +# 16 to 32 times the rate you are inserting data is more than sufficient. +# Setting this to 0 disables throttling. Note that this account for all types +# of compaction, including validation compaction. +compaction_throughput_mb_per_sec: 16 + +# When compacting, the replacement sstable(s) can be opened before they +# are completely written, and used in place of the prior sstables for +# any range that has been written. This helps to smoothly transfer reads +# between the sstables, reducing page cache churn and keeping hot rows hot +sstable_preemptive_open_interval_in_mb: 50 + +# Throttles all outbound streaming file transfers on this node to the +# given total throughput in Mbps. This is necessary because Cassandra does +# mostly sequential IO when streaming data during bootstrap or repair, which +# can lead to saturating the network connection and degrading rpc performance. +# When unset, the default is 200 Mbps or 25 MB/s. +# stream_throughput_outbound_megabits_per_sec: 200 + +# Throttles all streaming file transfer between the datacenters, +# this setting allows users to throttle inter dc stream throughput in addition +# to throttling all network stream traffic as configured with +# stream_throughput_outbound_megabits_per_sec +# When unset, the default is 200 Mbps or 25 MB/s +# inter_dc_stream_throughput_outbound_megabits_per_sec: 200 + +# How long the coordinator should wait for read operations to complete +read_request_timeout_in_ms: 5000 +# How long the coordinator should wait for seq or index scans to complete +range_request_timeout_in_ms: 10000 +# How long the coordinator should wait for writes to complete +write_request_timeout_in_ms: 2000 +# How long the coordinator should wait for counter writes to complete +counter_write_request_timeout_in_ms: 5000 +# How long a coordinator should continue to retry a CAS operation +# that contends with other proposals for the same row +cas_contention_timeout_in_ms: 1000 +# How long the coordinator should wait for truncates to complete +# (This can be much longer, because unless auto_snapshot is disabled +# we need to flush first so we can snapshot before removing the data.) +truncate_request_timeout_in_ms: 60000 +# The default timeout for other, miscellaneous operations +request_timeout_in_ms: 10000 + +# How long before a node logs slow queries. Select queries that take longer than +# this timeout to execute, will generate an aggregated log message, so that slow queries +# can be identified. Set this value to zero to disable slow query logging. +slow_query_log_timeout_in_ms: 500 + +# Enable operation timeout information exchange between nodes to accurately +# measure request timeouts. If disabled, replicas will assume that requests +# were forwarded to them instantly by the coordinator, which means that +# under overload conditions we will waste that much extra time processing +# already-timed-out requests. +# +# Warning: before enabling this property make sure to ntp is installed +# and the times are synchronized between the nodes. +cross_node_timeout: false + +# Set keep-alive period for streaming +# This node will send a keep-alive message periodically with this period. +# If the node does not receive a keep-alive message from the peer for +# 2 keep-alive cycles the stream session times out and fail +# Default value is 300s (5 minutes), which means stalled stream +# times out in 10 minutes by default +# streaming_keep_alive_period_in_secs: 300 + +# phi value that must be reached for a host to be marked down. +# most users should never need to adjust this. +# phi_convict_threshold: 8 + +# endpoint_snitch -- Set this to a class that implements +# IEndpointSnitch. The snitch has two functions: +# +# - it teaches Cassandra enough about your network topology to route +# requests efficiently +# - it allows Cassandra to spread replicas around your cluster to avoid +# correlated failures. It does this by grouping machines into +# "datacenters" and "racks." Cassandra will do its best not to have +# more than one replica on the same "rack" (which may not actually +# be a physical location) +# +# CASSANDRA WILL NOT ALLOW YOU TO SWITCH TO AN INCOMPATIBLE SNITCH +# ONCE DATA IS INSERTED INTO THE CLUSTER. This would cause data loss. +# This means that if you start with the default SimpleSnitch, which +# locates every node on "rack1" in "datacenter1", your only options +# if you need to add another datacenter are GossipingPropertyFileSnitch +# (and the older PFS). From there, if you want to migrate to an +# incompatible snitch like Ec2Snitch you can do it by adding new nodes +# under Ec2Snitch (which will locate them in a new "datacenter") and +# decommissioning the old ones. +# +# Out of the box, Cassandra provides: +# +# SimpleSnitch: +# Treats Strategy order as proximity. This can improve cache +# locality when disabling read repair. Only appropriate for +# single-datacenter deployments. +# +# GossipingPropertyFileSnitch +# This should be your go-to snitch for production use. The rack +# and datacenter for the local node are defined in +# cassandra-rackdc.properties and propagated to other nodes via +# gossip. If cassandra-topology.properties exists, it is used as a +# fallback, allowing migration from the PropertyFileSnitch. +# +# PropertyFileSnitch: +# Proximity is determined by rack and data center, which are +# explicitly configured in cassandra-topology.properties. +# +# Ec2Snitch: +# Appropriate for EC2 deployments in a single Region. Loads Region +# and Availability Zone information from the EC2 API. The Region is +# treated as the datacenter, and the Availability Zone as the rack. +# Only private IPs are used, so this will not work across multiple +# Regions. +# +# Ec2MultiRegionSnitch: +# Uses public IPs as broadcast_address to allow cross-region +# connectivity. (Thus, you should set seed addresses to the public +# IP as well.) You will need to open the storage_port or +# ssl_storage_port on the public IP firewall. (For intra-Region +# traffic, Cassandra will switch to the private IP after +# establishing a connection.) +# +# RackInferringSnitch: +# Proximity is determined by rack and data center, which are +# assumed to correspond to the 3rd and 2nd octet of each node's IP +# address, respectively. Unless this happens to match your +# deployment conventions, this is best used as an example of +# writing a custom Snitch class and is provided in that spirit. +# +# You can use a custom Snitch by setting this to the full class name +# of the snitch, which will be assumed to be on your classpath. +endpoint_snitch: SimpleSnitch + +# controls how often to perform the more expensive part of host score +# calculation +dynamic_snitch_update_interval_in_ms: 100 +# controls how often to reset all host scores, allowing a bad host to +# possibly recover +dynamic_snitch_reset_interval_in_ms: 600000 +# if set greater than zero and read_repair_chance is < 1.0, this will allow +# 'pinning' of replicas to hosts in order to increase cache capacity. +# The badness threshold will control how much worse the pinned host has to be +# before the dynamic snitch will prefer other replicas over it. This is +# expressed as a double which represents a percentage. Thus, a value of +# 0.2 means Cassandra would continue to prefer the static snitch values +# until the pinned host was 20% worse than the fastest. +dynamic_snitch_badness_threshold: 0.1 + +# request_scheduler -- Set this to a class that implements +# RequestScheduler, which will schedule incoming client requests +# according to the specific policy. This is useful for multi-tenancy +# with a single Cassandra cluster. +# NOTE: This is specifically for requests from the client and does +# not affect inter node communication. +# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place +# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of +# client requests to a node with a separate queue for each +# request_scheduler_id. The scheduler is further customized by +# request_scheduler_options as described below. +request_scheduler: org.apache.cassandra.scheduler.NoScheduler + +# Scheduler Options vary based on the type of scheduler +# +# NoScheduler +# Has no options +# +# RoundRobin +# throttle_limit +# The throttle_limit is the number of in-flight +# requests per client. Requests beyond +# that limit are queued up until +# running requests can complete. +# The value of 80 here is twice the number of +# concurrent_reads + concurrent_writes. +# default_weight +# default_weight is optional and allows for +# overriding the default which is 1. +# weights +# Weights are optional and will default to 1 or the +# overridden default_weight. The weight translates into how +# many requests are handled during each turn of the +# RoundRobin, based on the scheduler id. +# +# request_scheduler_options: +# throttle_limit: 80 +# default_weight: 5 +# weights: +# Keyspace1: 1 +# Keyspace2: 5 + +# request_scheduler_id -- An identifier based on which to perform +# the request scheduling. Currently the only valid option is keyspace. +# request_scheduler_id: keyspace + +# Enable or disable inter-node encryption +# JVM defaults for supported SSL socket protocols and cipher suites can +# be replaced using custom encryption options. This is not recommended +# unless you have policies in place that dictate certain settings, or +# need to disable vulnerable ciphers or protocols in case the JVM cannot +# be updated. +# FIPS compliant settings can be configured at JVM level and should not +# involve changing encryption settings here: +# https://docs.oracle.com/javase/8/docs/technotes/guides/security/jsse/FIPS.html +# *NOTE* No custom encryption options are enabled at the moment +# The available internode options are : all, none, dc, rack +# +# If set to dc cassandra will encrypt the traffic between the DCs +# If set to rack cassandra will encrypt the traffic between the racks +# +# The passwords used in these options must match the passwords used when generating +# the keystore and truststore. For instructions on generating these files, see: +# http://download.oracle.com/javase/6/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore +# +server_encryption_options: + internode_encryption: none + keystore: conf/.keystore + keystore_password: cassandra + truststore: conf/.truststore + truststore_password: cassandra + # More advanced defaults below: + # protocol: TLS + # algorithm: SunX509 + # store_type: JKS + # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA] + # require_client_auth: false + # require_endpoint_verification: false + +# enable or disable client/server encryption. +client_encryption_options: + enabled: false + # If enabled and optional is set to true encrypted and unencrypted connections are handled. + optional: false + keystore: conf/.keystore + keystore_password: cassandra + # require_client_auth: false + # Set trustore and truststore_password if require_client_auth is true + # truststore: conf/.truststore + # truststore_password: cassandra + # More advanced defaults below: + # protocol: TLS + # algorithm: SunX509 + # store_type: JKS + # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA] + +# internode_compression controls whether traffic between nodes is +# compressed. +# Can be: +# +# all +# all traffic is compressed +# +# dc +# traffic between different datacenters is compressed +# +# none +# nothing is compressed. +internode_compression: dc + +# Enable or disable tcp_nodelay for inter-dc communication. +# Disabling it will result in larger (but fewer) network packets being sent, +# reducing overhead from the TCP protocol itself, at the cost of increasing +# latency if you block for cross-datacenter responses. +inter_dc_tcp_nodelay: false + +# TTL for different trace types used during logging of the repair process. +tracetype_query_ttl: 86400 +tracetype_repair_ttl: 604800 + +# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level +# This threshold can be adjusted to minimize logging if necessary +# gc_log_threshold_in_ms: 200 + +# If unset, all GC Pauses greater than gc_log_threshold_in_ms will log at +# INFO level +# UDFs (user defined functions) are disabled by default. +# As of Cassandra 3.0 there is a sandbox in place that should prevent execution of evil code. +enable_user_defined_functions: true + +# Enables scripted UDFs (JavaScript UDFs). +# Java UDFs are always enabled, if enable_user_defined_functions is true. +# Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider. +# This option has no effect, if enable_user_defined_functions is false. +enable_scripted_user_defined_functions: false + +# Enables materialized view creation on this node. +# Materialized views are considered experimental and are not recommended for production use. +enable_materialized_views: true + +# The default Windows kernel timer and scheduling resolution is 15.6ms for power conservation. +# Lowering this value on Windows can provide much tighter latency and better throughput, however +# some virtualized environments may see a negative performance impact from changing this setting +# below their system default. The sysinternals 'clockres' tool can confirm your system's default +# setting. +windows_timer_interval: 1 + + +# Enables encrypting data at-rest (on disk). Different key providers can be plugged in, but the default reads from +# a JCE-style keystore. A single keystore can hold multiple keys, but the one referenced by +# the "key_alias" is the only key that will be used for encrypt opertaions; previously used keys +# can still (and should!) be in the keystore and will be used on decrypt operations +# (to handle the case of key rotation). +# +# It is strongly recommended to download and install Java Cryptography Extension (JCE) +# Unlimited Strength Jurisdiction Policy Files for your version of the JDK. +# (current link: http://www.oracle.com/technetwork/java/javase/downloads/jce8-download-2133166.html) +# +# Currently, only the following file types are supported for transparent data encryption, although +# more are coming in future cassandra releases: commitlog, hints +transparent_data_encryption_options: + enabled: false + chunk_length_kb: 64 + cipher: AES/CBC/PKCS5Padding + key_alias: testing:1 + # CBC IV length for AES needs to be 16 bytes (which is also the default size) + # iv_length: 16 + key_provider: + - class_name: org.apache.cassandra.security.JKSKeyProvider + parameters: + - keystore: conf/.keystore + keystore_password: cassandra + store_type: JCEKS + key_password: cassandra + + +##################### +# SAFETY THRESHOLDS # +##################### + +# When executing a scan, within or across a partition, we need to keep the +# tombstones seen in memory so we can return them to the coordinator, which +# will use them to make sure other replicas also know about the deleted rows. +# With workloads that generate a lot of tombstones, this can cause performance +# problems and even exaust the server heap. +# (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets) +# Adjust the thresholds here if you understand the dangers and want to +# scan more tombstones anyway. These thresholds may also be adjusted at runtime +# using the StorageService mbean. +tombstone_warn_threshold: 1000 +tombstone_failure_threshold: 100000 + +# Log WARN on any multiple-partition batch size exceeding this value. 5kb per batch by default. +# Caution should be taken on increasing the size of this threshold as it can lead to node instability. +batch_size_warn_threshold_in_kb: 5 + +# Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default. +batch_size_fail_threshold_in_kb: 50 + +# Log WARN on any batches not of type LOGGED than span across more partitions than this limit +unlogged_batch_across_partitions_warn_threshold: 10 + +# Log a warning when compacting partitions larger than this value +compaction_large_partition_warning_threshold_mb: 100 + +# GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level +# Adjust the threshold based on your application throughput requirement +# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level +gc_warn_threshold_in_ms: 1000 + +# Maximum size of any value in SSTables. Safety measure to detect SSTable corruption +# early. Any value size larger than this threshold will result into marking an SSTable +# as corrupted. This should be positive and less than 2048. +# max_value_size_in_mb: 256 + +# Back-pressure settings # +# If enabled, the coordinator will apply the back-pressure strategy specified below to each mutation +# sent to replicas, with the aim of reducing pressure on overloaded replicas. +back_pressure_enabled: false +# The back-pressure strategy applied. +# The default implementation, RateBasedBackPressure, takes three arguments: +# high ratio, factor, and flow type, and uses the ratio between incoming mutation responses and outgoing mutation requests. +# If below high ratio, outgoing mutations are rate limited according to the incoming rate decreased by the given factor; +# if above high ratio, the rate limiting is increased by the given factor; +# such factor is usually best configured between 1 and 10, use larger values for a faster recovery +# at the expense of potentially more dropped mutations; +# the rate limiting is applied according to the flow type: if FAST, it's rate limited at the speed of the fastest replica, +# if SLOW at the speed of the slowest one. +# New strategies can be added. Implementors need to implement org.apache.cassandra.net.BackpressureStrategy and +# provide a public constructor accepting a Map. +back_pressure_strategy: + - class_name: org.apache.cassandra.net.RateBasedBackPressure + parameters: + - high_ratio: 0.90 + factor: 5 + flow: FAST + +# Coalescing Strategies # +# Coalescing multiples messages turns out to significantly boost message processing throughput (think doubling or more). +# On bare metal, the floor for packet processing throughput is high enough that many applications won't notice, but in +# virtualized environments, the point at which an application can be bound by network packet processing can be +# surprisingly low compared to the throughput of task processing that is possible inside a VM. It's not that bare metal +# doesn't benefit from coalescing messages, it's that the number of packets a bare metal network interface can process +# is sufficient for many applications such that no load starvation is experienced even without coalescing. +# There are other benefits to coalescing network messages that are harder to isolate with a simple metric like messages +# per second. By coalescing multiple tasks together, a network thread can process multiple messages for the cost of one +# trip to read from a socket, and all the task submission work can be done at the same time reducing context switching +# and increasing cache friendliness of network message processing. +# See CASSANDRA-8692 for details. + +# Strategy to use for coalescing messages in OutboundTcpConnection. +# Can be fixed, movingaverage, timehorizon, disabled (default). +# You can also specify a subclass of CoalescingStrategies.CoalescingStrategy by name. +# otc_coalescing_strategy: DISABLED + +# How many microseconds to wait for coalescing. For fixed strategy this is the amount of time after the first +# message is received before it will be sent with any accompanying messages. For moving average this is the +# maximum amount of time that will be waited as well as the interval at which messages must arrive on average +# for coalescing to be enabled. +# otc_coalescing_window_us: 200 + +# Do not try to coalesce messages if we already got that many messages. This should be more than 2 and less than 128. +# otc_coalescing_enough_coalesced_messages: 8 + +# How many milliseconds to wait between two expiration runs on the backlog (queue) of the OutboundTcpConnection. +# Expiration is done if messages are piling up in the backlog. Droppable messages are expired to free the memory +# taken by expired messages. The interval should be between 0 and 1000, and in most installations the default value +# will be appropriate. A smaller value could potentially expire messages slightly sooner at the expense of more CPU +# time and queue contention while iterating the backlog of messages. +# An interval of 0 disables any wait time, which is the behavior of former Cassandra versions. +# +# otc_backlog_expiration_interval_ms: 200 diff --git a/playbooks/templates/jvm.options b/playbooks/templates/jvm.options new file mode 100644 index 0000000..0ef35b8 --- /dev/null +++ b/playbooks/templates/jvm.options @@ -0,0 +1,257 @@ +########################################################################### +# jvm.options # +# # +# - all flags defined here will be used by cassandra to startup the JVM # +# - one flag should be specified per line # +# - lines that do not start with '-' will be ignored # +# - only static flags are accepted (no variables or parameters) # +# - dynamic flags will be appended to these on cassandra-env # +########################################################################### + +###################### +# STARTUP PARAMETERS # +###################### + +# Uncomment any of the following properties to enable specific startup parameters + +# In a multi-instance deployment, multiple Cassandra instances will independently assume that all +# CPU processors are available to it. This setting allows you to specify a smaller set of processors +# and perhaps have affinity. +#-Dcassandra.available_processors=number_of_processors + +# The directory location of the cassandra.yaml file. +#-Dcassandra.config=directory + +# Sets the initial partitioner token for a node the first time the node is started. +#-Dcassandra.initial_token=token + +# Set to false to start Cassandra on a node but not have the node join the cluster. +#-Dcassandra.join_ring=true|false + +# Set to false to clear all gossip state for the node on restart. Use when you have changed node +# information in cassandra.yaml (such as listen_address). +#-Dcassandra.load_ring_state=true|false + +# Enable pluggable metrics reporter. See Pluggable metrics reporting in Cassandra 2.0.2. +#-Dcassandra.metricsReporterConfigFile=file + +# Set the port on which the CQL native transport listens for clients. (Default: 9042) +#-Dcassandra.native_transport_port=port + +# Overrides the partitioner. (Default: org.apache.cassandra.dht.Murmur3Partitioner) +#-Dcassandra.partitioner=partitioner + +# To replace a node that has died, restart a new node in its place specifying the address of the +# dead node. The new node must not have any data in its data directory, that is, it must be in the +# same state as before bootstrapping. +#-Dcassandra.replace_address=listen_address or broadcast_address of dead node + +# Allow restoring specific tables from an archived commit log. +#-Dcassandra.replayList=table + +# Allows overriding of the default RING_DELAY (30000ms), which is the amount of time a node waits +# before joining the ring. +#-Dcassandra.ring_delay_ms=ms + +# Set the port for the Thrift RPC service, which is used for client connections. (Default: 9160) +#-Dcassandra.rpc_port=port + +# Set the SSL port for encrypted communication. (Default: 7001) +#-Dcassandra.ssl_storage_port=port + +# Enable or disable the native transport server. See start_native_transport in cassandra.yaml. +# cassandra.start_native_transport=true|false + +# Enable or disable the Thrift RPC server. (Default: true) +#-Dcassandra.start_rpc=true/false + +# Set the port for inter-node communication. (Default: 7000) +#-Dcassandra.storage_port=port + +# Set the default location for the trigger JARs. (Default: conf/triggers) +#-Dcassandra.triggers_dir=directory + +# For testing new compaction and compression strategies. It allows you to experiment with different +# strategies and benchmark write performance differences without affecting the production workload. +#-Dcassandra.write_survey=true + +# To disable configuration via JMX of auth caches (such as those for credentials, permissions and +# roles). This will mean those config options can only be set (persistently) in cassandra.yaml +# and will require a restart for new values to take effect. +#-Dcassandra.disable_auth_caches_remote_configuration=true + +# To disable dynamic calculation of the page size used when indexing an entire partition (during +# initial index build/rebuild). If set to true, the page size will be fixed to the default of +# 10000 rows per page. +#-Dcassandra.force_default_indexing_page_size=true + +######################## +# GENERAL JVM SETTINGS # +######################## + +# enable assertions. highly suggested for correct application functionality. +-ea + +# enable thread priorities, primarily so we can give periodic tasks +# a lower priority to avoid interfering with client workload +-XX:+UseThreadPriorities + +# allows lowering thread priority without being root on linux - probably +# not necessary on Windows but doesn't harm anything. +# see http://tech.stolsvik.com/2010/01/linux-java-thread-priorities-workar +#-XX:ThreadPriorityPolicy=42 + +# Enable heap-dump if there's an OOM +-XX:+HeapDumpOnOutOfMemoryError + +# Per-thread stack size. +-Xss256k + +# Larger interned string table, for gossip's benefit (CASSANDRA-6410) +-XX:StringTableSize=1000003 + +# Make sure all memory is faulted and zeroed on startup. +# This helps prevent soft faults in containers and makes +# transparent hugepage allocation more effective. +-XX:+AlwaysPreTouch + +# Disable biased locking as it does not benefit Cassandra. +-XX:-UseBiasedLocking + +# Enable thread-local allocation blocks and allow the JVM to automatically +# resize them at runtime. +-XX:+UseTLAB +-XX:+ResizeTLAB +-XX:+UseNUMA + +# http://www.evanjones.ca/jvm-mmap-pause.html +-XX:+PerfDisableSharedMem + +# Prefer binding to IPv4 network intefaces (when net.ipv6.bindv6only=1). See +# http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=6342561 (short version: +# comment out this entry to enable IPv6 support). +-Djava.net.preferIPv4Stack=true + +### Debug options + +# uncomment to enable flight recorder +#-XX:+UnlockCommercialFeatures +#-XX:+FlightRecorder + +# uncomment to have Cassandra JVM listen for remote debuggers/profilers on port 1414 +#-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=1414 + +# uncomment to have Cassandra JVM log internal method compilation (developers only) +#-XX:+UnlockDiagnosticVMOptions +#-XX:+LogCompilation + +################# +# HEAP SETTINGS # +################# + +# Heap size is automatically calculated by cassandra-env based on this +# formula: max(min(1/2 ram, 1024MB), min(1/4 ram, 8GB)) +# That is: +# - calculate 1/2 ram and cap to 1024MB +# - calculate 1/4 ram and cap to 8192MB +# - pick the max +# +# For production use you may wish to adjust this for your environment. +# If that's the case, uncomment the -Xmx and Xms options below to override the +# automatic calculation of JVM heap memory. +# +# It is recommended to set min (-Xms) and max (-Xmx) heap sizes to +# the same value to avoid stop-the-world GC pauses during resize, and +# so that we can lock the heap in memory on startup to prevent any +# of it from being swapped out. +#-Xms4G +#-Xmx4G + +# Young generation size is automatically calculated by cassandra-env +# based on this formula: min(100 * num_cores, 1/4 * heap size) +# +# The main trade-off for the young generation is that the larger it +# is, the longer GC pause times will be. The shorter it is, the more +# expensive GC will be (usually). +# +# It is not recommended to set the young generation size if using the +# G1 GC, since that will override the target pause-time goal. +# More info: http://www.oracle.com/technetwork/articles/java/g1gc-1984535.html +# +# The example below assumes a modern 8-core+ machine for decent +# times. If in doubt, and if you do not particularly want to tweak, go +# 100 MB per physical CPU core. +#-Xmn800M + +################################### +# EXPIRATION DATE OVERFLOW POLICY # +################################### + +# Defines how to handle INSERT requests with TTL exceeding the maximum supported expiration date: +# * REJECT: this is the default policy and will reject any requests with expiration date timestamp after 2038-01-19T03:14:06+00:00. +# * CAP: any insert with TTL expiring after 2038-01-19T03:14:06+00:00 will expire on 2038-01-19T03:14:06+00:00 and the client will receive a warning. +# * CAP_NOWARN: same as previous, except that the client warning will not be emitted. +# +#-Dcassandra.expiration_date_overflow_policy=REJECT + +################# +# GC SETTINGS # +################# + +### CMS Settings + +-XX:+UseParNewGC +-XX:+UseConcMarkSweepGC +-XX:+CMSParallelRemarkEnabled +-XX:SurvivorRatio=8 +-XX:MaxTenuringThreshold=1 +-XX:CMSInitiatingOccupancyFraction=75 +-XX:+UseCMSInitiatingOccupancyOnly +-XX:CMSWaitDuration=10000 +-XX:+CMSParallelInitialMarkEnabled +-XX:+CMSEdenChunksRecordAlways +# some JVMs will fill up their heap when accessed via JMX, see CASSANDRA-6541 +-XX:+CMSClassUnloadingEnabled + +### G1 Settings (experimental, comment previous section and uncomment section below to enable) + +## Use the Hotspot garbage-first collector. +#-XX:+UseG1GC +# +## Have the JVM do less remembered set work during STW, instead +## preferring concurrent GC. Reduces p99.9 latency. +#-XX:G1RSetUpdatingPauseTimePercent=5 +# +## Main G1GC tunable: lowering the pause target will lower throughput and vise versa. +## 200ms is the JVM default and lowest viable setting +## 1000ms increases throughput. Keep it smaller than the timeouts in cassandra.yaml. +#-XX:MaxGCPauseMillis=500 + +## Optional G1 Settings + +# Save CPU time on large (>= 16GB) heaps by delaying region scanning +# until the heap is 70% full. The default in Hotspot 8u40 is 40%. +#-XX:InitiatingHeapOccupancyPercent=70 + +# For systems with > 8 cores, the default ParallelGCThreads is 5/8 the number of logical cores. +# Otherwise equal to the number of cores when 8 or less. +# Machines with > 10 cores should try setting these to <= full cores. +#-XX:ParallelGCThreads=16 +# By default, ConcGCThreads is 1/4 of ParallelGCThreads. +# Setting both to the same value can reduce STW durations. +#-XX:ConcGCThreads=16 + +### GC logging options -- uncomment to enable + +-XX:+PrintGCDetails +-XX:+PrintGCDateStamps +-XX:+PrintHeapAtGC +-XX:+PrintTenuringDistribution +-XX:+PrintGCApplicationStoppedTime +-XX:+PrintPromotionFailure +#-XX:PrintFLSStatistics=1 +#-Xloggc:/var/log/cassandra/gc.log +-XX:+UseGCLogFileRotation +-XX:NumberOfGCLogFiles=10 +-XX:GCLogFileSize=10M + diff --git a/playbooks/templates/replayer.yml b/playbooks/templates/replayer.yml new file mode 100644 index 0000000..15ebf8b --- /dev/null +++ b/playbooks/templates/replayer.yml @@ -0,0 +1,8 @@ +storage: + cls: remote + args: + url: http://localhost:{{rpc_port}}/ +journal: + #max_poll_interval_ms: 1000 + max_poll_records: 100 + session_timeout_ms: 60000 diff --git a/playbooks/templates/replayer@.service b/playbooks/templates/replayer@.service new file mode 100644 index 0000000..bdb12c0 --- /dev/null +++ b/playbooks/templates/replayer@.service @@ -0,0 +1,14 @@ +[Unit] +Description=swh-storage RPC server with Cassandra as backend +After=network.target +Requires=swh-storage-cassandra@%i.service + +[Service] +Type=simple +ExecStart=/bin/bash -c 'sleep $(( RANDOM % 60 )); exec /home/{{ansible_user}}/.local/bin/swh journal --config-file /home/{{ansible_user}}/replayer_%i.yml replay --broker esnode1.internal.softwareheritage.org --group-id vlorentz-cassandra-test-0' +Restart=on-failure +Environment=PYTHONUNBUFFERED=1 +SyslogIdentifier=replayer-%i + +[Install] +WantedBy=default.target diff --git a/playbooks/templates/storage_cassandra.yml b/playbooks/templates/storage_cassandra.yml new file mode 100644 index 0000000..5b351cd --- /dev/null +++ b/playbooks/templates/storage_cassandra.yml @@ -0,0 +1,8 @@ +storage: + cls: cassandra + args: + hosts: [{{listen_address}}] + keyspace: swh_test + objstorage: + cls: memory + args: {} diff --git a/playbooks/templates/swh-storage-cassandra@.service b/playbooks/templates/swh-storage-cassandra@.service new file mode 100644 index 0000000..4f0361b --- /dev/null +++ b/playbooks/templates/swh-storage-cassandra@.service @@ -0,0 +1,16 @@ +[Unit] +Description=swh-storage RPC server with Cassandra as backend +After=network.target + +[Service] +Type=simple +ExecStart=/home/{{ansible_user}}/.local/bin/swh storage rpc-serve /home/{{ansible_user}}/storage_cassandra.yml --port %i --host 127.0.0.1 +Restart=on-failure +Environment=PYTHONUNBUFFERED=1 +SyslogIdentifier=swh-storage-cassandra-%i + +Nice=10 + +[Install] +WantedBy=default.target +