diff --git a/group_vars/all/main.yml b/group_vars/all/main.yml index 051a8fac07e93153ea74dcec2972b512708597b7..6bb820db5ae7a6420d5fa8145cb6a8bb88a4bd2b 100644 --- a/group_vars/all/main.yml +++ b/group_vars/all/main.yml @@ -1,6 +1,6 @@ --- -dslproxy: "<CHANGE_ME:hostname>" +dslproxy: "dsoclab.gn4-3-wp8-soc.sunet.se" # TheHive Button plugin THEHIVE_URL: "https://hive.gn4-3-wp8-soc.sunet.se/" @@ -36,6 +36,21 @@ mysql_name: "dsoclab-mysql" mysql_img: "{{repo}}/mysql:{{version}}{{suffix}}" mysql_dbrootpass: "Pass006" +cassandra_name: "dsoclab-cassandra" +cassandra_img: "{{repo}}/cassandra:{{version}}{{suffix}}" + +thehive_name: "dsoclab-thehive" +thehive_img: "{{repo}}/thehive:{{version}}{{suffix}}" +# GENERATED WITH cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 64 | head -n 1 +thehive_secret_key: "LcnI9eKLo33711BmCnzf6UM1y05pdmj3dlADL81PxuffWqhobRoiiGFftjNPKpmM" + +cortex_name: "dsoclab-cortex" +cortex_img: "{{repo}}/cortex:{{version}}{{suffix}}" +cortex_elasticsearch_mem: "256m" +# GENERATED WITH cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 64 | head -n 1 +cortex_secret_key: "9CZ844IcAp5dHjsgU4iuaEssdopLcS6opzhVP3Ys4t4eRpNlHmwZdtfveLEXpM9D" +cortex_odfe_pass: "Pass009" + kspass: "Testing003" tspass: "Testing003" @@ -44,8 +59,8 @@ sysctlconfig: - { key: "net.core.wmem_max", val: "2097152" } - { key: "vm.max_map_count" , val: "524288" } -nifi_javamem: "4g" -odfe_javamem: "2g" +nifi_javamem: "1g" +odfe_javamem: "512m" nifi_version: 1.11.4 nifi_repo: "https://archive.apache.org/dist" @@ -53,13 +68,6 @@ nifi_repo: "https://archive.apache.org/dist" ca_cn: "SOCTOOLS-CA" soctools_users: - - firstname: "Arne" - lastname: "Oslebo" - username: "arne.oslebo" - email: "arne.oslebo@uninett.no" - DN: "CN=Arne Oslebo" - CN: "Arne Oslebo" - password: "Pass002" - firstname: "Bozidar" lastname: "Proevski" username: "bozidar.proevski" @@ -67,6 +75,13 @@ soctools_users: DN: "CN=Bozidar Proevski" CN: "Bozidar Proevski" password: "Pass001" + - firstname: "Arne" + lastname: "Oslebo" + username: "arne.oslebo" + email: "arne.oslebo@uninett.no" + DN: "CN=Arne Oslebo" + CN: "Arne Oslebo" + password: "Pass002" odfees_img: "{{repo}}/odfees:{{version}}{{suffix}}" odfekibana_img: "{{repo}}/odfekibana:{{version}}{{suffix}}" diff --git a/roles/build/tasks/cassandra.yml b/roles/build/tasks/cassandra.yml new file mode 100644 index 0000000000000000000000000000000000000000..1c0a2c6930135fe01a0e9e872e036f6c911eccd3 --- /dev/null +++ b/roles/build/tasks/cassandra.yml @@ -0,0 +1,11 @@ +--- + +- name: Configure the cassandra Dockerfile + template: + src: cassandra/Dockerfile.j2 + dest: "{{role_path}}/files/cassandraDockerfile" + +- name: Build cassandra image + command: docker build -t {{repo}}/cassandra:{{version}}{{suffix}} -f {{role_path}}/files/cassandraDockerfile {{role_path}}/files + + diff --git a/roles/build/tasks/centos.yml b/roles/build/tasks/centos.yml index c03dadf045266b9158f6a31a536cf18b5104ed35..c7be287621104cc8eb257bf0734a5c2641b58c33 100644 --- a/roles/build/tasks/centos.yml +++ b/roles/build/tasks/centos.yml @@ -5,86 +5,96 @@ name: "{{repo}}/centos:{{version}}{{suffix}}" register: centosimg -- name: Assert CentOS image - assert: - that: centosimg.images | length == 0 - fail_msg: "CentOS image already exists" +#- name: Skip if image exists +# meta: end_play +# when: centosimg.images | length != 0 -- name: Create etc tree in build directory - file: - path: '{{ temp_root}}/{{ item.path }}' - state: directory - mode: '{{ item.mode }}' - with_filetree: templates/etcroot/ - when: item.state == 'directory' +# tags: +# - start -- name: Populate etc tree in build directory - template: - src: '{{ item.src }}' - dest: '{{ temp_root}}/{{ item.path }}' - force: yes - with_filetree: templates/etcroot - when: item.state == 'file' - -- name: Create dev tree in build directory - command: mknod -m {{ item.mode }} {{ item.dev }} {{ item.type }} {{ item.major }} {{ item.minor }} - args: - creates: "{{ item.dev }}" - with_items: - - { mode: 600, dev: "{{temp_root}}/dev/console", type: c, major: 5, minor: 1 } - - { mode: 600, dev: "{{temp_root}}/dev/initctl", type: p, major: '', minor: '' } - - { mode: 666, dev: "{{temp_root}}/dev/full", type: c, major: 1, minor: 7 } - - { mode: 666, dev: "{{temp_root}}/dev/null", type: c, major: 1, minor: 3 } - - { mode: 666, dev: "{{temp_root}}/dev/ptmx", type: c, major: 5, minor: 2 } - - { mode: 666, dev: "{{temp_root}}/dev/random", type: c, major: 1, minor: 8 } - - { mode: 666, dev: "{{temp_root}}/dev/tty", type: c, major: 5, minor: 0 } - - { mode: 666, dev: "{{temp_root}}/dev/tty0", type: c, major: 4, minor: 0 } - - { mode: 666, dev: "{{temp_root}}/dev/urandom", type: c, major: 1, minor: 9 } - - { mode: 666, dev: "{{temp_root}}/dev/zero", type: c, major: 1, minor: 5 } - -- name: Install centos-release in build directory - yum: - installroot: "{{ temp_root}}" - name: centos-release - state: present - -- name: Install Core CentOS in build directory - yum: - installroot: "{{ temp_root}}" - name: - - "@Core" - - yum-plugin-ovl.noarch - - epel-release - state: present - -- name: Clean yum cache - command: 'yum --installroot="{{ temp_root}}" -y clean all' - -- name: Remove unneeded directories - file: - path: "{{temp_root}}/{{item}}" - state: absent - with_items: - - usr/share/cracklib - - var/cache/yum - - sbin/sln - - etc/ld.so.cache - - var/cache/ldconfig - - usr/share/backgrounds - -- name: Create needed directories - file: - path: "{{temp_root}}/{{item}}" - state: directory - with_items: - - var/cache/yum - - var/cache/ldconfig - -- name: Import image in docker - shell: tar --numeric-owner -c -C {{temp_root }} . | docker import - {{repo}}/centos:{{version}}{{suffix}} - -- name: Remove temp directory - file: - path: "{{temp_root}}" - state: absent +#- name: Assert CentOS image +# assert: +# that: centosimg.images | length == 0 +# fail_msg: "CentOS image already exists" +- name: Build CentOS image + when: centosimg.images | length == 0 + block: + - name: Create etc tree in build directory + file: + path: '{{ temp_root}}/{{ item.path }}' + state: directory + mode: '{{ item.mode }}' + with_filetree: templates/etcroot/ + when: item.state == 'directory' + + - name: Populate etc tree in build directory + template: + src: '{{ item.src }}' + dest: '{{ temp_root}}/{{ item.path }}' + force: yes + with_filetree: templates/etcroot + when: item.state == 'file' + + - name: Create dev tree in build directory + command: mknod -m {{ item.mode }} {{ item.dev }} {{ item.type }} {{ item.major }} {{ item.minor }} + args: + creates: "{{ item.dev }}" + with_items: + - { mode: 600, dev: "{{temp_root}}/dev/console", type: c, major: 5, minor: 1 } + - { mode: 600, dev: "{{temp_root}}/dev/initctl", type: p, major: '', minor: '' } + - { mode: 666, dev: "{{temp_root}}/dev/full", type: c, major: 1, minor: 7 } + - { mode: 666, dev: "{{temp_root}}/dev/null", type: c, major: 1, minor: 3 } + - { mode: 666, dev: "{{temp_root}}/dev/ptmx", type: c, major: 5, minor: 2 } + - { mode: 666, dev: "{{temp_root}}/dev/random", type: c, major: 1, minor: 8 } + - { mode: 666, dev: "{{temp_root}}/dev/tty", type: c, major: 5, minor: 0 } + - { mode: 666, dev: "{{temp_root}}/dev/tty0", type: c, major: 4, minor: 0 } + - { mode: 666, dev: "{{temp_root}}/dev/urandom", type: c, major: 1, minor: 9 } + - { mode: 666, dev: "{{temp_root}}/dev/zero", type: c, major: 1, minor: 5 } + + - name: Install centos-release in build directory + yum: + installroot: "{{ temp_root}}" + name: centos-release + state: present + + - name: Install Core CentOS in build directory + yum: + installroot: "{{ temp_root}}" + name: + - "@Core" + - yum-plugin-ovl.noarch + - epel-release + state: present + + - name: Clean yum cache + command: 'yum --installroot="{{ temp_root}}" -y clean all' + + - name: Remove unneeded directories + file: + path: "{{temp_root}}/{{item}}" + state: absent + with_items: + - usr/share/cracklib + - var/cache/yum + - sbin/sln + - etc/ld.so.cache + - var/cache/ldconfig + - usr/share/backgrounds + + - name: Create needed directories + file: + path: "{{temp_root}}/{{item}}" + state: directory + with_items: + - var/cache/yum + - var/cache/ldconfig + + - name: Import image in docker + shell: tar --numeric-owner -c -C {{temp_root }} . | docker import - {{repo}}/centos:{{version}}{{suffix}} + + - name: Remove temp directory + file: + path: "{{temp_root}}" + state: absent + diff --git a/roles/build/tasks/cortex.yml b/roles/build/tasks/cortex.yml new file mode 100644 index 0000000000000000000000000000000000000000..9a5adbef67cf1fee1f7eb48f23e4d083a8c6631d --- /dev/null +++ b/roles/build/tasks/cortex.yml @@ -0,0 +1,11 @@ +--- + +- name: Configure the Cortex Dockerfile + template: + src: cortex/Dockerfile.j2 + dest: "{{role_path}}/files/cortexDockerfile" + +- name: Build the Cortex image + command: docker build -t {{repo}}/cortex:{{version}}{{suffix}} -f {{role_path}}/files/cortexDockerfile {{role_path}}/files + + diff --git a/roles/build/tasks/main.yml b/roles/build/tasks/main.yml index d9ff848876d5eda6d07deac0f43892a96dc972fe..223766f87e2d7d1ae88de3d70dd7810a0dbdf091 100644 --- a/roles/build/tasks/main.yml +++ b/roles/build/tasks/main.yml @@ -15,3 +15,6 @@ - include: odfekibana.yml - include: keycloak.yml - include: misp.yml +- include: cassandra.yml +- include: thehive.yml +- include: cortex.yml diff --git a/roles/build/tasks/thehive.yml b/roles/build/tasks/thehive.yml new file mode 100644 index 0000000000000000000000000000000000000000..35fe08ebf7d5da456a40f0a0de273d102d5eada2 --- /dev/null +++ b/roles/build/tasks/thehive.yml @@ -0,0 +1,11 @@ +--- + +- name: Configure theHive Dockerfile + template: + src: thehive/Dockerfile.j2 + dest: "{{role_path}}/files/thehiveDockerfile" + +- name: Build theHive image + command: docker build -t {{repo}}/thehive:{{version}}{{suffix}} -f {{role_path}}/files/thehiveDockerfile {{role_path}}/files + + diff --git a/roles/build/templates/cassandra/Dockerfile.j2 b/roles/build/templates/cassandra/Dockerfile.j2 new file mode 100644 index 0000000000000000000000000000000000000000..94b0ca08c01de7c4b225bdcb81c7a35c2ffb33ff --- /dev/null +++ b/roles/build/templates/cassandra/Dockerfile.j2 @@ -0,0 +1,35 @@ +FROM {{repo}}/openjdk:{{version}}{{suffix}} + +USER root +#COPY cassandra.repo /etc/yum.repos.d/cassandra.repo +#COPY supervisord.conf /etc/supervisord.conf +#COPY start.sh /start.sh +RUN echo "[cassandra]" > /etc/yum.repos.d/cassandra.repo && \ + echo "name=Apache Cassandra" >> /etc/yum.repos.d/cassandra.repo && \ + echo "baseurl=https://downloads.apache.org/cassandra/redhat/311x/" >> /etc/yum.repos.d/cassandra.repo && \ + echo "gpgcheck=1" >> /etc/yum.repos.d/cassandra.repo && \ + echo "repo_gpgcheck=1" >> /etc/yum.repos.d/cassandra.repo && \ + echo "gpgkey=https://downloads.apache.org/cassandra/KEYS" >> /etc/yum.repos.d/cassandra.repo && \ + echo '#!/bin/bash' > /start.sh && \ + echo 'export CASSANDRA_HOME=/usr/share/cassandra' >> /start.sh && \ + echo 'export CASSANDRA_CONF=$CASSANDRA_HOME/conf' >> /start.sh && \ + echo 'export CASSANDRA_INCLUDE=$CASSANDRA_HOME/cassandra.in.sh' >> /start.sh && \ + echo 'log_file=/var/log/cassandra/cassandra.log' >> /start.sh && \ + echo 'pid_file=/var/run/cassandra/cassandra.pid' >> /start.sh && \ + echo 'lock_file=/var/lock/subsys/cassandra' >> /start.sh && \ + echo 'CASSANDRA_PROG=/usr/sbin/cassandra' >> /start.sh && \ + echo '' >> /start.sh && \ + echo '$CASSANDRA_PROG -p $pid_file > $log_file 2>&1' >> /start.sh && \ + yum install -y epel-release && \ + yum install -y cassandra supervisor && \ + mkdir /usr/share/cassandra/conf && \ + cp -a /etc/cassandra/conf/* /usr/share/cassandra/conf && \ + chown -R cassandra:cassandra /usr/share/cassandra && \ + chown -R cassandra:cassandra /var/lib/cassandra && \ + sed -i -e 's,/etc/cassandra,/usr/share/cassandra,g' /usr/share/cassandra/cassandra.in.sh && \ + chmod a+x /start.sh && \ + yum -y clean all +EXPOSE 7000 9042 +#ENTRYPOINT ["/usr/bin/supervisord", "-c", "/etc/supervisord.conf"] +USER cassandra +# ENTRYPOINT ["/start.sh"] diff --git a/roles/build/templates/cassandra/cassandra.repo.j2 b/roles/build/templates/cassandra/cassandra.repo.j2 new file mode 100644 index 0000000000000000000000000000000000000000..8fdb78c9a4e3868ea6693110941914adc511877e --- /dev/null +++ b/roles/build/templates/cassandra/cassandra.repo.j2 @@ -0,0 +1,6 @@ +[cassandra] +name=Apache Cassandra +baseurl=https://downloads.apache.org/cassandra/redhat/311x/ +gpgcheck=1 +repo_gpgcheck=1 +gpgkey=https://downloads.apache.org/cassandra/KEYS diff --git a/roles/build/templates/cassandra/start.sh.j2 b/roles/build/templates/cassandra/start.sh.j2 new file mode 100644 index 0000000000000000000000000000000000000000..fa91e921956d5d2d6fa1be6812a9794071b20965 --- /dev/null +++ b/roles/build/templates/cassandra/start.sh.j2 @@ -0,0 +1,10 @@ +#!/bin/bash +export CASSANDRA_HOME=/usr/share/cassandra +export CASSANDRA_CONF=$CASSANDRA_HOME/conf +export CASSANDRA_INCLUDE=$CASSANDRA_HOME/cassandra.in.sh +log_file=/var/log/cassandra/cassandra.log +pid_file=/var/run/cassandra/cassandra.pid +lock_file=/var/lock/subsys/cassandra +CASSANDRA_PROG=/usr/sbin/cassandra + +$CASSANDRA_PROG -p $pid_file > $log_file 2>&1 diff --git a/roles/build/templates/cassandra/supervisord.conf.j2 b/roles/build/templates/cassandra/supervisord.conf.j2 new file mode 100644 index 0000000000000000000000000000000000000000..d1f405eb91d5bae99af653dae0d5c246ae723f08 --- /dev/null +++ b/roles/build/templates/cassandra/supervisord.conf.j2 @@ -0,0 +1,10 @@ +[supervisord] +loglevel=debug +nodaemon=true +[program:cassandra] +user=cassandra +directory=/usr/share/cassandra +stdout_logfile=/var/log/cassandra/cassandra.log +redirect_stderr=true +environment=CASSANDRA_HOME="/usr/share/cassandra",CASSANDRA_CONF="/usr/share/cassandra/conf",CASSANDRA_INCLUDE="$CASSANDRA_HOME/cassandra.in.sh" +command=/usr/sbin/cassandra -p /var/run/cassandra/cassandra.pid diff --git a/roles/build/templates/cortex/Dockerfile.j2 b/roles/build/templates/cortex/Dockerfile.j2 new file mode 100644 index 0000000000000000000000000000000000000000..d56dbf02c14be1e71860da43814eddc904aa7177 --- /dev/null +++ b/roles/build/templates/cortex/Dockerfile.j2 @@ -0,0 +1,32 @@ +FROM {{repo}}/openjdk:{{version}}{{suffix}} + +USER root +#COPY thehive.repo /etc/yum.repos.d/thehive.repo +#COPY supervisord.conf /etc/supervisord.conf +#COPY start.sh /start.sh +RUN echo "[thehive-project]" > /etc/yum.repos.d/thehive.repo && \ + echo "enabled=1" >> /etc/yum.repos.d/thehive.repo && \ + echo "priority=1" >> /etc/yum.repos.d/thehive.repo && \ + echo "name=TheHive-Project RPM repository" >> /etc/yum.repos.d/thehive.repo && \ + echo "baseurl=http://rpm.thehive-project.org/stable/noarch" >> /etc/yum.repos.d/thehive.repo && \ + echo "gpgcheck=1" >> /etc/yum.repos.d/thehive.repo && \ + yum install -y epel-release && \ + rpm --import https://raw.githubusercontent.com/TheHive-Project/TheHive/master/PGP-PUBLIC-KEY && \ + rpm --import https://artifacts.elastic.co/GPG-KEY-elasticsearch && \ + yum install -y cortex supervisor daemonize vim net-tools telnet htop python3-pip.noarch git gcc python3-devel.x86_64 ssdeep-devel.x86_64 python3-wheel.noarch libexif-devel.x86_64 libexif.x86_64 perl-Image-ExifTool.noarch gcc-c++ whois && \ + rpm -Uvh https://artifacts.elastic.co/downloads/elasticsearch/elasticsearch-oss-6.8.13.rpm && \ + chown -R elasticsearch:elasticsearch /etc/elasticsearch && \ + mkdir -p /home/cortex && \ + chown -R cortex:cortex /home/cortex && \ + chown -R cortex:cortex /etc/cortex && \ + cd /opt && \ + git clone https://github.com/TheHive-Project/Cortex-Analyzers && \ + chown -R cortex:cortex /opt/Cortex-Analyzers && \ + cd /opt/Cortex-Analyzers && \ + for I in analyzers/*/requirements.txt; do LC_ALL=en_US.UTF-8 pip3 install --no-cache-dir -U -r $I || true; done && \ + for I in responders/*/requirements.txt; do LC_ALL=en_US.UTF-8 pip3 install --no-cache-dir -U -r $I || true; done && \ + yum -y clean all +EXPOSE 9001 +#ENTRYPOINT ["/usr/bin/supervisord", "-c", "/etc/supervisord.conf"] +USER cortex +# ENTRYPOINT ["/start.sh"] diff --git a/roles/build/templates/cortex/application.conf b/roles/build/templates/cortex/application.conf new file mode 100644 index 0000000000000000000000000000000000000000..0e28b4d0d71643d558b0d014be354985a02d19c7 --- /dev/null +++ b/roles/build/templates/cortex/application.conf @@ -0,0 +1,158 @@ +# Sample Cortex application.conf file + +## SECRET KEY +# +# The secret key is used to secure cryptographic functions. +# +# IMPORTANT: If you deploy your application to several instances, make +# sure to use the same key. +# # # # # # +# GENERATED WITH cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 64 | head -n 1 +# # # # # # +play.http.secret.key="9CZ844IcAp5dHjsgU4iuaEssdopLcS6opzhVP3Ys4t4eRpNlHmwZdtfveLEXpM9D" + +## ElasticSearch +search { + # Name of the index + index = cortex3 + # ElasticSearch instance address. + # For cluster, join address:port with ',': "http://ip1:9200,ip2:9200,ip3:9200" + uri = "http://dsoclab-elastic:9200" + + ## Advanced configuration + # Scroll keepalive. + #keepalive = 1m + # Scroll page size. + #pagesize = 50 + # Number of shards + #nbshards = 5 + # Number of replicas + #nbreplicas = 1 + # Arbitrary settings + #settings { + # # Maximum number of nested fields + # mapping.nested_fields.limit = 100 + #} + + ## Authentication configuration + #search.username = "" + #search.password = "" + + ## SSL configuration + #search.keyStore { + # path = "/path/to/keystore" + # type = "JKS" # or PKCS12 + # password = "keystore-password" + #} + #search.trustStore { + # path = "/path/to/trustStore" + # type = "JKS" # or PKCS12 + # password = "trustStore-password" + #} +} + +## Cache +# +# If an analyzer is executed against the same observable, the previous report can be returned without re-executing the +# analyzer. The cache is used only if the second job occurs within cache.job (the default is 10 minutes). +cache.job = 10 minutes + +## Authentication +auth { + # "provider" parameter contains the authentication provider(s). It can be multi-valued, which is useful + # for migration. + # The available auth types are: + # - services.LocalAuthSrv : passwords are stored in the user entity within ElasticSearch). No + # configuration are required. + # - ad : use ActiveDirectory to authenticate users. The associated configuration shall be done in + # the "ad" section below. + # - ldap : use LDAP to authenticate users. The associated configuration shall be done in the + # "ldap" section below. + provider = [local] + + ad { + # The Windows domain name in DNS format. This parameter is required if you do not use + # 'serverNames' below. + #domainFQDN = "mydomain.local" + + # Optionally you can specify the host names of the domain controllers instead of using 'domainFQDN + # above. If this parameter is not set, TheHive uses 'domainFQDN'. + #serverNames = [ad1.mydomain.local, ad2.mydomain.local] + + # The Windows domain name using short format. This parameter is required. + #domainName = "MYDOMAIN" + + # If 'true', use SSL to connect to the domain controller. + #useSSL = true + } + + ldap { + # The LDAP server name or address. The port can be specified using the 'host:port' + # syntax. This parameter is required if you don't use 'serverNames' below. + #serverName = "ldap.mydomain.local:389" + + # If you have multiple LDAP servers, use the multi-valued setting 'serverNames' instead. + #serverNames = [ldap1.mydomain.local, ldap2.mydomain.local] + + # Account to use to bind to the LDAP server. This parameter is required. + #bindDN = "cn=thehive,ou=services,dc=mydomain,dc=local" + + # Password of the binding account. This parameter is required. + #bindPW = "***secret*password***" + + # Base DN to search users. This parameter is required. + #baseDN = "ou=users,dc=mydomain,dc=local" + + # Filter to search user in the directory server. Please note that {0} is replaced + # by the actual user name. This parameter is required. + #filter = "(cn={0})" + + # If 'true', use SSL to connect to the LDAP directory server. + #useSSL = true + } +} + +## ANALYZERS +# +analyzer { + # analyzer location + # url can be point to: + # - directory where analyzers are installed + # - json file containing the list of analyzer descriptions + urls = [ + #"https://dl.bintray.com/thehive-project/cortexneurons/analyzers.json" + "/opt/Cortex-Analyzers/analyzers" + ] + + # Sane defaults. Do not change unless you know what you are doing. + fork-join-executor { + # Min number of threads available for analysis. + parallelism-min = 2 + # Parallelism (threads) ... ceil(available processors * factor). + parallelism-factor = 2.0 + # Max number of threads available for analysis. + parallelism-max = 4 + } +} + +# RESPONDERS +# +responder { + # responder location (same format as analyzer.urls) + urls = [ + #"https://dl.bintray.com/thehive-project/cortexneurons/reponders.json" + "/opt/Cortex-Analyzers/responders" + ] + + # Sane defaults. Do not change unless you know what you are doing. + fork-join-executor { + # Min number of threads available for analysis. + parallelism-min = 2 + # Parallelism (threads) ... ceil(available processors * factor). + parallelism-factor = 2.0 + # Max number of threads available for analysis. + parallelism-max = 4 + } +} + +# It's the end my friend. Happy hunting! diff --git a/roles/build/templates/cortex/thehive.repo b/roles/build/templates/cortex/thehive.repo new file mode 100644 index 0000000000000000000000000000000000000000..ff3806454fc41de2193c94a2a4da095b763d95bf --- /dev/null +++ b/roles/build/templates/cortex/thehive.repo @@ -0,0 +1,7 @@ +[thehive-project] +enabled=1 +priority=1 +name=TheHive-Project RPM repository +baseurl=http://rpm.thehive-project.org/stable/noarch +gpgcheck=1 + diff --git a/roles/build/templates/haproxy/Dockerfile.j2 b/roles/build/templates/haproxy/Dockerfile.j2 index 17b595f365a4e4c17e4e17c9364c24855d55774f..d9f84c4c3ec60e5593ab4a3ccffee1660585260e 100644 --- a/roles/build/templates/haproxy/Dockerfile.j2 +++ b/roles/build/templates/haproxy/Dockerfile.j2 @@ -1,4 +1,4 @@ -FROM gn43-dsl/centos:{{version}}{{suffix}} +FROM {{repo}}/centos:{{version}}{{suffix}} ENV HAPROXY_VERSION 2.2.3 ENV HAPROXY_URL https://www.haproxy.org/download/2.2/src/haproxy-2.2.3.tar.gz diff --git a/roles/build/templates/thehive/Dockerfile.j2 b/roles/build/templates/thehive/Dockerfile.j2 new file mode 100644 index 0000000000000000000000000000000000000000..773c7c2c7846ade845264764c68e22f36a0cf957 --- /dev/null +++ b/roles/build/templates/thehive/Dockerfile.j2 @@ -0,0 +1,24 @@ +FROM {{repo}}/openjdk:{{version}}{{suffix}} + +USER root +#COPY thehive.repo /etc/yum.repos.d/thehive.repo +#COPY supervisord.conf /etc/supervisord.conf +#COPY start.sh /start.sh +RUN echo "[thehive-project]" > /etc/yum.repos.d/thehive.repo && \ + echo "enabled=1" >> /etc/yum.repos.d/thehive.repo && \ + echo "priority=1" >> /etc/yum.repos.d/thehive.repo && \ + echo "name=TheHive-Project RPM repository" >> /etc/yum.repos.d/thehive.repo && \ + echo "baseurl=http://rpm.thehive-project.org/stable/noarch" >> /etc/yum.repos.d/thehive.repo && \ + echo "gpgcheck=1" >> /etc/yum.repos.d/thehive.repo && \ + yum install -y epel-release && \ + rpm --import https://raw.githubusercontent.com/TheHive-Project/TheHive/master/PGP-PUBLIC-KEY && \ + yum install -y thehive4 supervisor daemonize vim net-tools telnet htop && \ + mkdir -p /opt/thp_data/files/thehive && \ + chown -R thehive:thehive /opt/thp_data/files/thehive && \ + mkdir -p /home/thehive && \ + chown -R thehive:thehive /home/thehive /etc/thehive && \ + yum -y clean all +EXPOSE 9000 +#ENTRYPOINT ["/usr/bin/supervisord", "-c", "/etc/supervisord.conf"] +USER thehive +# ENTRYPOINT ["/start.sh"] diff --git a/roles/build/templates/thehive/start.sh b/roles/build/templates/thehive/start.sh new file mode 100644 index 0000000000000000000000000000000000000000..fa91e921956d5d2d6fa1be6812a9794071b20965 --- /dev/null +++ b/roles/build/templates/thehive/start.sh @@ -0,0 +1,10 @@ +#!/bin/bash +export CASSANDRA_HOME=/usr/share/cassandra +export CASSANDRA_CONF=$CASSANDRA_HOME/conf +export CASSANDRA_INCLUDE=$CASSANDRA_HOME/cassandra.in.sh +log_file=/var/log/cassandra/cassandra.log +pid_file=/var/run/cassandra/cassandra.pid +lock_file=/var/lock/subsys/cassandra +CASSANDRA_PROG=/usr/sbin/cassandra + +$CASSANDRA_PROG -p $pid_file > $log_file 2>&1 diff --git a/roles/build/templates/thehive/supervisord.conf b/roles/build/templates/thehive/supervisord.conf new file mode 100644 index 0000000000000000000000000000000000000000..d1f405eb91d5bae99af653dae0d5c246ae723f08 --- /dev/null +++ b/roles/build/templates/thehive/supervisord.conf @@ -0,0 +1,10 @@ +[supervisord] +loglevel=debug +nodaemon=true +[program:cassandra] +user=cassandra +directory=/usr/share/cassandra +stdout_logfile=/var/log/cassandra/cassandra.log +redirect_stderr=true +environment=CASSANDRA_HOME="/usr/share/cassandra",CASSANDRA_CONF="/usr/share/cassandra/conf",CASSANDRA_INCLUDE="$CASSANDRA_HOME/cassandra.in.sh" +command=/usr/sbin/cassandra -p /var/run/cassandra/cassandra.pid diff --git a/roles/build/templates/thehive/thehive.repo b/roles/build/templates/thehive/thehive.repo new file mode 100644 index 0000000000000000000000000000000000000000..ff3806454fc41de2193c94a2a4da095b763d95bf --- /dev/null +++ b/roles/build/templates/thehive/thehive.repo @@ -0,0 +1,7 @@ +[thehive-project] +enabled=1 +priority=1 +name=TheHive-Project RPM repository +baseurl=http://rpm.thehive-project.org/stable/noarch +gpgcheck=1 + diff --git a/roles/ca/tasks/main.yml b/roles/ca/tasks/main.yml index 88e6d2a779156fc965fa11c83f77ccbcbf90a29b..ec25dad3fb6e42eb153c8e1b32dd54e5cb28f764 100644 --- a/roles/ca/tasks/main.yml +++ b/roles/ca/tasks/main.yml @@ -44,6 +44,8 @@ - "{{ groups['odfekibanacontainers'] }}" - "{{ groups['keycloakcontainers'] }}" - "{{ groups['mispcontainers'] }}" + - "{{ groups['thehive'] }}" + - "{{ groups['cortex'] }}" - "{{ groups['haproxy'] }}" environment: EASYRSA_BATCH: 1 @@ -62,6 +64,8 @@ - "{{ groups['odfekibanacontainers'] }}" - "{{ groups['keycloakcontainers'] }}" - "{{ groups['mispcontainers'] }}" + - "{{ groups['thehive'] }}" + - "{{ groups['cortex'] }}" - "{{ groups['haproxy'] }}" environment: EASYRSA_BATCH: 1 @@ -95,6 +99,8 @@ - "{{ groups['odfeescontainers'] }}" - "{{ groups['odfekibanacontainers'] }}" - "{{ groups['keycloakcontainers'] }}" + - "{{ groups['thehive'] }}" + - "{{ groups['cortex'] }}" - "{{ groups['mispcontainers'] }}" environment: EASYRSA_BATCH: 1 @@ -121,6 +127,13 @@ with_items: - "{{ groups['odfekibanacontainers'] }}" +- name: Copy cortex host p12 certs to cortex role + copy: + src: roles/ca/files/CA/private/{{item}}.p12 + dest: roles/cortex/files/{{item}}.p12 + with_items: + - "{{ groups['cortex'] }}" + - name: Copy odfekibana host certs to odfekibana role copy: src: roles/ca/files/CA/issued/{{item}}.crt @@ -177,6 +190,34 @@ with_items: - "{{ groups['mispcontainers'] }}" +- name: Copy thehive host cert to thehive role + copy: + src: roles/ca/files/CA/issued/{{item}}.crt + dest: roles/thehive/files/{{item}}.crt + with_items: + - "{{ groups['thehive'] }}" + +- name: Copy thehive host key to thehive role + copy: + src: roles/ca/files/CA/private/{{item}}.key + dest: roles/thehive/files/{{item}}.key + with_items: + - "{{ groups['thehive'] }}" + +- name: Copy cortex host cert to cortex role + copy: + src: roles/ca/files/CA/issued/{{item}}.crt + dest: roles/cortex/files/{{item}}.crt + with_items: + - "{{ groups['cortex'] }}" + +- name: Copy cortex host key to cortex role + copy: + src: roles/ca/files/CA/private/{{item}}.key + dest: roles/cortex/files/{{item}}.key + with_items: + - "{{ groups['cortex'] }}" + - name: Copy truststore to roles copy: src: roles/ca/files/truststore/cacerts.jks @@ -187,6 +228,7 @@ - odfekibana - keycloak - misp + - cortex - name: Copy ca cert to roles copy: @@ -198,6 +240,8 @@ - odfekibana - keycloak - misp + - thehive + - cortex - name: Check for existing user certificates command: roles/ca/files/easyrsa/easyrsa show-cert {{item.CN | regex_escape()}} diff --git a/roles/cassandra/defaults/main.yml b/roles/cassandra/defaults/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cassandra/files/.empty b/roles/cassandra/files/.empty new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cassandra/handlers/main.yml b/roles/cassandra/handlers/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cassandra/meta/main.yml b/roles/cassandra/meta/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cassandra/tasks/main.yml b/roles/cassandra/tasks/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..7912910a2ebcd07a79d6649b7529fae5bde3a0cf --- /dev/null +++ b/roles/cassandra/tasks/main.yml @@ -0,0 +1,28 @@ +--- + +- name: Configure Cassandra + template: + src: cassandra.yaml.j2 + dest: /usr/share/cassandra/conf/cassandra.yaml + tags: + - start + +- name: Start Cassandra + command: "/start.sh" + tags: + - start + +- name: Wait for Cassandra + wait_for: + host: "{{groups['cassandra'][0]}}" + port: 9042 + state: started + delay: 5 + tags: + - start + +- name: Stop Cassandra + command: "pkill -SIGTERM -F /var/run/cassandra/cassandra.pid" + tags: + - stop + diff --git a/roles/cassandra/templates/cassandra.yaml.j2 b/roles/cassandra/templates/cassandra.yaml.j2 new file mode 100644 index 0000000000000000000000000000000000000000..1727f4f44f0b56876a0a16d9179e98ed7a82cc52 --- /dev/null +++ b/roles/cassandra/templates/cassandra.yaml.j2 @@ -0,0 +1,1279 @@ +# 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: 'thp' + +# 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 + +# 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 + +# 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 + +# 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 + +# 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 + +# 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<String, String> 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: "<ip1>,<ip2>,<ip3>" + - seeds: "{{ansible_default_ipv4.address}}" + +# 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 + +# Limits the maximum Merkle tree depth to avoid consuming too much +# memory during repairs. +# +# The default setting of 18 generates trees of maximum size around +# 50 MiB / tree. If you are running out of memory during repairs consider +# lowering this to 15 (~6 MiB / tree) or lower, but try not to lower it +# too much past that or you will lose too much resolution and stream +# too much redundant data during repair. Cannot be set lower than 10. +# +# For more details see https://issues.apache.org/jira/browse/CASSANDRA-14096. +# +# repair_session_max_tree_depth: 18 + +# 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: false +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: {{ansible_default_ipv4.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: {{ansible_default_ipv4.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: false + +# 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 + +# 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 + +# Filtering and secondary index queries at read consistency levels above ONE/LOCAL_ONE use a +# mechanism called replica filtering protection to ensure that results from stale replicas do +# not violate consistency. (See CASSANDRA-8272 and CASSANDRA-15907 for more details.) This +# mechanism materializes replica results by partition on-heap at the coordinator. The more possibly +# stale results returned by the replicas, the more rows materialized during the query. +replica_filtering_protection: + # These thresholds exist to limit the damage severely out-of-date replicas can cause during these + # queries. They limit the number of rows from all replicas individual index and filtering queries + # can materialize on-heap to return correct results at the desired read consistency level. + # + # "cached_replica_rows_warn_threshold" is the per-query threshold at which a warning will be logged. + # "cached_replica_rows_fail_threshold" is the per-query threshold at which the query will fail. + # + # These thresholds may also be adjusted at runtime using the StorageService mbean. + # + # If the failure threshold is breached, it is likely that either the current page/fetch size + # is too large or one or more replicas is severely out-of-sync and in need of repair. + cached_rows_warn_threshold: 2000 + cached_rows_fail_threshold: 32000 + +# 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<String, Object>. +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 + + +######################### +# EXPERIMENTAL FEATURES # +######################### + +# Enables materialized view creation on this node. +# Materialized views are considered experimental and are not recommended for production use. +enable_materialized_views: true + +# Enables SASI index creation on this node. +# SASI indexes are considered experimental and are not recommended for production use. +enable_sasi_indexes: true diff --git a/roles/cassandra/vars/main.yml b/roles/cassandra/vars/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cortex/defaults/main.yml b/roles/cortex/defaults/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cortex/files/.empty b/roles/cortex/files/.empty new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cortex/handlers/main.yml b/roles/cortex/handlers/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cortex/meta/main.yml b/roles/cortex/meta/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/cortex/tasks/main.yml b/roles/cortex/tasks/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..5d1eeb21e68d7a614760b36f4867b2aede6397f8 --- /dev/null +++ b/roles/cortex/tasks/main.yml @@ -0,0 +1,95 @@ +--- + +- name: Copy cacert to ca-trust dir + remote_user: root + copy: + src: "files/{{ca_cn}}.crt" + dest: /etc/pki/ca-trust/source/anchors/ca.crt + tags: + - start + - startcortex + +- name: Install cacert to root truststore + remote_user: root + command: "update-ca-trust" + tags: + - start + - startcortex + +- name: Copy certificates in cortex conf dir + copy: + src: "{{ item }}" + dest: "/etc/cortex/{{ item }}" + mode: 0600 + with_items: + - "{{ inventory_hostname }}.p12" + - "{{ inventory_hostname }}.crt" + - "{{ inventory_hostname }}.key" + - cacerts.jks + - "{{ca_cn}}.crt" + tags: + - start + - startcortex + +- name: Configure embedded Elasticsearch 6 + remote_user: root + template: + src: jvm.options.j2 + dest: /etc/elasticsearch/jvm.options + tags: + - start + - startcortex + +- name: Start embedded Elasticsearch 6 + remote_user: root + command: > + daemonize + -u elasticsearch + -c /usr/share/elasticsearch + -p /tmp/elasticsearch.pid + -o /tmp/elasticsearch-stdout.log + /usr/share/elasticsearch/bin/elasticsearch + tags: + - start + - startcortex + +- name: Configure Cortex + template: + src: application.conf.j2 + dest: /etc/cortex/application.conf + tags: + - start + - startcortex + +- name: Start Cortex + command: > + daemonize + -c /opt/cortex + -p /tmp/cortex.pid + -o /tmp/cortex-stdout.log + /opt/cortex/bin/cortex + -Dconfig.file=/etc/cortex/application.conf + -Dlogger.file=/etc/cortex/logback.xml + -J-Xms1g + -J-Xmx1g + -Dpidfile.path=/dev/null + tags: + - start + - startcortex + +- name: Wait for Cortex + wait_for: + host: "{{groups['cortex'][0]}}" + port: 9001 + state: started + delay: 5 + tags: + - start + - startcortex + +- name: Stop Cortex + command: "pkill -SIGTERM -F /tmp/cortex.pid" + tags: + - stop + - stopcortex + diff --git a/roles/cortex/templates/application.conf.j2 b/roles/cortex/templates/application.conf.j2 new file mode 100644 index 0000000000000000000000000000000000000000..35323e050bc2460ef223066103b41aa563dd95e6 --- /dev/null +++ b/roles/cortex/templates/application.conf.j2 @@ -0,0 +1,156 @@ +# Sample Cortex application.conf file + +## SECRET KEY +# +# The secret key is used to secure cryptographic functions. +# +# IMPORTANT: If you deploy your application to several instances, make +# sure to use the same key. +play.http.secret.key="{{cortex_secret_key}}" + +## ElasticSearch +search { + # Name of the index + index = cortex + # ElasticSearch instance address. + # For cluster, join address:port with ',': "http://ip1:9200,ip2:9200,ip3:9200" + #uri = "https://{{groups['odfeescontainers'][0]}}:9200" + uri = "http://localhost:9200" + + ## Advanced configuration + # Scroll keepalive. + #keepalive = 1m + # Scroll page size. + #pagesize = 50 + # Number of shards + #nbshards = 5 + # Number of replicas + #nbreplicas = 1 + # Arbitrary settings + #settings { + # # Maximum number of nested fields + # mapping.nested_fields.limit = 100 + #} + +## ## Authentication configuration +## search.username = "cortex" +## search.password = "{{cortex_odfe_pass}}" +## +## ## SSL configuration +## search.keyStore { +## path = "/etc/cortex/dsoclab-cortex.p12" +## type = "PKCS12" # or PKCS12 +## password = "{{kspass}}" +## } +## search.trustStore { +## path = "/etc/cortex/cacerts.jks" +## type = "JKS" # or PKCS12 +## password = "{{tspass}}" +## } +} + +## Cache +# +# If an analyzer is executed against the same observable, the previous report can be returned without re-executing the +# analyzer. The cache is used only if the second job occurs within cache.job (the default is 10 minutes). +cache.job = 10 minutes + +## Authentication +auth { + # "provider" parameter contains the authentication provider(s). It can be multi-valued, which is useful + # for migration. + # The available auth types are: + # - services.LocalAuthSrv : passwords are stored in the user entity within ElasticSearch). No + # configuration are required. + # - ad : use ActiveDirectory to authenticate users. The associated configuration shall be done in + # the "ad" section below. + # - ldap : use LDAP to authenticate users. The associated configuration shall be done in the + # "ldap" section below. + provider = [local] + + ad { + # The Windows domain name in DNS format. This parameter is required if you do not use + # 'serverNames' below. + #domainFQDN = "mydomain.local" + + # Optionally you can specify the host names of the domain controllers instead of using 'domainFQDN + # above. If this parameter is not set, TheHive uses 'domainFQDN'. + #serverNames = [ad1.mydomain.local, ad2.mydomain.local] + + # The Windows domain name using short format. This parameter is required. + #domainName = "MYDOMAIN" + + # If 'true', use SSL to connect to the domain controller. + #useSSL = true + } + + ldap { + # The LDAP server name or address. The port can be specified using the 'host:port' + # syntax. This parameter is required if you don't use 'serverNames' below. + #serverName = "ldap.mydomain.local:389" + + # If you have multiple LDAP servers, use the multi-valued setting 'serverNames' instead. + #serverNames = [ldap1.mydomain.local, ldap2.mydomain.local] + + # Account to use to bind to the LDAP server. This parameter is required. + #bindDN = "cn=thehive,ou=services,dc=mydomain,dc=local" + + # Password of the binding account. This parameter is required. + #bindPW = "***secret*password***" + + # Base DN to search users. This parameter is required. + #baseDN = "ou=users,dc=mydomain,dc=local" + + # Filter to search user in the directory server. Please note that {0} is replaced + # by the actual user name. This parameter is required. + #filter = "(cn={0})" + + # If 'true', use SSL to connect to the LDAP directory server. + #useSSL = true + } +} + +## ANALYZERS +# +analyzer { + # analyzer location + # url can be point to: + # - directory where analyzers are installed + # - json file containing the list of analyzer descriptions + urls = [ + #"https://dl.bintray.com/thehive-project/cortexneurons/analyzers.json" + "/opt/Cortex-Analyzers/analyzers" + ] + + # Sane defaults. Do not change unless you know what you are doing. + fork-join-executor { + # Min number of threads available for analysis. + parallelism-min = 2 + # Parallelism (threads) ... ceil(available processors * factor). + parallelism-factor = 2.0 + # Max number of threads available for analysis. + parallelism-max = 4 + } +} + +# RESPONDERS +# +responder { + # responder location (same format as analyzer.urls) + urls = [ + #"https://dl.bintray.com/thehive-project/cortexneurons/reponders.json" + "/opt/Cortex-Analyzers/responders" + ] + + # Sane defaults. Do not change unless you know what you are doing. + fork-join-executor { + # Min number of threads available for analysis. + parallelism-min = 2 + # Parallelism (threads) ... ceil(available processors * factor). + parallelism-factor = 2.0 + # Max number of threads available for analysis. + parallelism-max = 4 + } +} + +# It's the end my friend. Happy hunting! diff --git a/roles/cortex/templates/jvm.options.j2 b/roles/cortex/templates/jvm.options.j2 new file mode 100644 index 0000000000000000000000000000000000000000..1dbf0a94bca81390ffb2e414ccd513b1e28fbbd4 --- /dev/null +++ b/roles/cortex/templates/jvm.options.j2 @@ -0,0 +1,128 @@ +## JVM configuration + +################################################################ +## IMPORTANT: JVM heap size +################################################################ +## +## You should always set the min and max JVM heap +## size to the same value. For example, to set +## the heap to 4 GB, set: +## +## -Xms4g +## -Xmx4g +## +## See https://www.elastic.co/guide/en/elasticsearch/reference/current/heap-size.html +## for more information +## +################################################################ + +# Xms represents the initial size of total heap space +# Xmx represents the maximum size of total heap space + +-Xms{{cortex_elasticsearch_mem}} +-Xmx{{cortex_elasticsearch_mem}} + +################################################################ +## Expert settings +################################################################ +## +## All settings below this section are considered +## expert settings. Don't tamper with them unless +## you understand what you are doing +## +################################################################ + +## GC configuration +8-13:-XX:+UseConcMarkSweepGC +8-13:-XX:CMSInitiatingOccupancyFraction=75 +8-13:-XX:+UseCMSInitiatingOccupancyOnly + +## G1GC Configuration +# NOTE: G1 GC is only supported on JDK version 10 or later +# to use G1GC, uncomment the next two lines and update the version on the +# following three lines to your version of the JDK +# 10-13:-XX:-UseConcMarkSweepGC +# 10-13:-XX:-UseCMSInitiatingOccupancyOnly +14-:-XX:+UseG1GC +14-:-XX:G1ReservePercent=25 +14-:-XX:InitiatingHeapOccupancyPercent=30 + +## DNS cache policy +# cache ttl in seconds for positive DNS lookups noting that this overrides the +# JDK security property networkaddress.cache.ttl; set to -1 to cache forever +-Des.networkaddress.cache.ttl=60 +# cache ttl in seconds for negative DNS lookups noting that this overrides the +# JDK security property networkaddress.cache.negative ttl; set to -1 to cache +# forever +-Des.networkaddress.cache.negative.ttl=10 + +## optimizations + +# pre-touch memory pages used by the JVM during initialization +-XX:+AlwaysPreTouch + +## basic + +# explicitly set the stack size +-Xss1m + +# set to headless, just in case +-Djava.awt.headless=true + +# ensure UTF-8 encoding by default (e.g. filenames) +-Dfile.encoding=UTF-8 + +# use our provided JNA always versus the system one +-Djna.nosys=true + +# turn off a JDK optimization that throws away stack traces for common +# exceptions because stack traces are important for debugging +-XX:-OmitStackTraceInFastThrow + +# enable helpful NullPointerExceptions (https://openjdk.java.net/jeps/358), if +# they are supported +14-:-XX:+ShowCodeDetailsInExceptionMessages + +# flags to configure Netty +-Dio.netty.noUnsafe=true +-Dio.netty.noKeySetOptimization=true +-Dio.netty.recycler.maxCapacityPerThread=0 + +# log4j 2 +-Dlog4j.shutdownHookEnabled=false +-Dlog4j2.disable.jmx=true + +-Djava.io.tmpdir=${ES_TMPDIR} + +## heap dumps + +# generate a heap dump when an allocation from the Java heap fails +# heap dumps are created in the working directory of the JVM +-XX:+HeapDumpOnOutOfMemoryError + +# specify an alternative path for heap dumps; ensure the directory exists and +# has sufficient space +-XX:HeapDumpPath=/var/lib/elasticsearch + +# specify an alternative path for JVM fatal error logs +-XX:ErrorFile=/var/log/elasticsearch/hs_err_pid%p.log + +## JDK 8 GC logging + +8:-XX:+PrintGCDetails +8:-XX:+PrintGCDateStamps +8:-XX:+PrintTenuringDistribution +8:-XX:+PrintGCApplicationStoppedTime +8:-Xloggc:/var/log/elasticsearch/gc.log +8:-XX:+UseGCLogFileRotation +8:-XX:NumberOfGCLogFiles=32 +8:-XX:GCLogFileSize=64m + +# JDK 9+ GC logging +9-:-Xlog:gc*,gc+age=trace,safepoint:file=/var/log/elasticsearch/gc.log:utctime,pid,tags:filecount=32,filesize=64m +# due to internationalization enhancements in JDK 9 Elasticsearch need to set the provider to COMPAT otherwise +# time/date parsing will break in an incompatible way for some date patterns and locals +9-:-Djava.locale.providers=COMPAT + +# temporary workaround for C2 bug with JDK 10 on hardware with AVX-512 +10-:-XX:UseAVX=2 diff --git a/roles/cortex/vars/main.yml b/roles/cortex/vars/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/docker/tasks/cassandra.yml b/roles/docker/tasks/cassandra.yml new file mode 100644 index 0000000000000000000000000000000000000000..a26bd28c104bc70cc17916496a1da8b68d978cd9 --- /dev/null +++ b/roles/docker/tasks/cassandra.yml @@ -0,0 +1,26 @@ +--- + +- name: Create cassandra containers and connect to network + docker_container: + name: "{{ item }}" + hostname: "{{ item }}" + image: "{{ cassandra_img }}" + networks: + - name: "{{ soctools_netname }}" + networks_cli_compatible: yes + volumes: + - "{{cassandra_name}}:/var/lib/cassandra" + entrypoint: "/bin/bash" + interactive: "yes" + with_items: "{{ groups['cassandra'] }}" + tags: + - start + +- name: Disconnect cassandra containers from network and remove + docker_container: + name: "{{ item }}" + state: absent + with_items: "{{ groups['cassandra'] }}" + tags: + - stop + diff --git a/roles/docker/tasks/cortex.yml b/roles/docker/tasks/cortex.yml new file mode 100644 index 0000000000000000000000000000000000000000..c8d7b1ea2fd7564d5e4829620e994773168d11c7 --- /dev/null +++ b/roles/docker/tasks/cortex.yml @@ -0,0 +1,29 @@ +--- + +- name: Create cortex containers and connect to network + docker_container: + name: "{{ item }}" + hostname: "{{ item }}" + image: "{{ cortex_img }}" + networks: + - name: "{{ soctools_netname }}" + networks_cli_compatible: yes +# published_ports: +# - "9001:9001" + volumes: + - "{{item}}:/var/lib/elasticsearch/" + entrypoint: "/bin/bash" + interactive: "yes" + with_items: "{{ groups['cortex'] }}" + tags: + - start + - startcortex + +- name: Disconnect cortex containers from network and remove + docker_container: + name: "{{ item }}" + state: absent + with_items: "{{ groups['cortex'] }}" + tags: + - stop + - stopcortex diff --git a/roles/docker/tasks/haproxy.yml b/roles/docker/tasks/haproxy.yml index 687ee07fc651ba81a7ad269491dec034b2dbc669..10dc08e09d929ab86254e4bb37b962da8880338c 100644 --- a/roles/docker/tasks/haproxy.yml +++ b/roles/docker/tasks/haproxy.yml @@ -15,6 +15,8 @@ - "9443:9443" - "9200:9200" - "7750:7750" + - "9000:9000" + - "9001:9001" entrypoint: "/bin/bash" interactive: "yes" tags: diff --git a/roles/docker/tasks/main.yml b/roles/docker/tasks/main.yml index f9ee4d3343a497c3fe135c3f4cf915543d574c99..d09016fa8b7912a3659bf0629cbae142c57a2037 100644 --- a/roles/docker/tasks/main.yml +++ b/roles/docker/tasks/main.yml @@ -10,6 +10,9 @@ - include: odfekibana.yml - include: misp.yml - include: keycloak.yml +- include: cassandra.yml +- include: thehive.yml +- include: cortex.yml - include: haproxy.yml - include: networkremove.yml diff --git a/roles/docker/tasks/networkcreate.yml b/roles/docker/tasks/networkcreate.yml index 15dd085b67010e748051df77b69b0933cb3b2a0a..3e1cdf67676f71c9e9efcd8b7419d2d4d25a096a 100644 --- a/roles/docker/tasks/networkcreate.yml +++ b/roles/docker/tasks/networkcreate.yml @@ -8,4 +8,5 @@ - subnet: "{{ soctools_network }}" tags: - start + - startcortex diff --git a/roles/docker/tasks/thehive.yml b/roles/docker/tasks/thehive.yml new file mode 100644 index 0000000000000000000000000000000000000000..f8effea72c1f2dd0a5d938e89012ffe5b3f1269b --- /dev/null +++ b/roles/docker/tasks/thehive.yml @@ -0,0 +1,26 @@ +--- + +- name: Create thehive containers and connect to network + docker_container: + name: "{{ item }}" + hostname: "{{ item }}" + image: "{{ thehive_img }}" + networks: + - name: "{{ soctools_netname }}" + networks_cli_compatible: yes +# published_ports: +# - "9000:9000" + entrypoint: "/bin/bash" + interactive: "yes" + with_items: "{{ groups['thehive'] }}" + tags: + - start + +- name: Disconnect thehive containers from network and remove + docker_container: + name: "{{ item }}" + state: absent + with_items: "{{ groups['thehive'] }}" + tags: + - stop + diff --git a/roles/docker/tasks/volumecreate.yml b/roles/docker/tasks/volumecreate.yml index 656d1e96b9ae80b5a572a3806fab77c29e7a40b5..706652a162e79b0c5defbc6a731fcde9d3decebe 100644 --- a/roles/docker/tasks/volumecreate.yml +++ b/roles/docker/tasks/volumecreate.yml @@ -8,6 +8,22 @@ tags: - start +- name: Create cassandra volumes + docker_volume: + name: "{{item}}" + with_items: + - "{{ groups['cassandra'] }}" + tags: + - start + +- name: Create cortex volumes + docker_volume: + name: "{{item}}" + with_items: + - "{{ groups['cortex'] }}" + tags: + - start + - name: Create NiFi volumes docker_volume: name: "{{item}}" diff --git a/roles/haproxy/templates/haproxy.cfg.j2 b/roles/haproxy/templates/haproxy.cfg.j2 index ad7771013a8df7e0232be23466d34ea74f70f0ce..e62740e78b24395594aeef2789b464eed20ecc7b 100644 --- a/roles/haproxy/templates/haproxy.cfg.j2 +++ b/roles/haproxy/templates/haproxy.cfg.j2 @@ -57,6 +57,30 @@ listen keycloakserv server {{keycloakhost}} {{keycloakhost}}:8443 ssl check verify none {% endfor %} +listen thehiveserv + bind *:9000 ssl crt /etc/ssl/haproxy alpn h2,http/1.1 + mode http + maxconn 5000 + fullconn 5000 + balance source + option tcpka + option forwardfor +{% for thehivehost in groups['thehive'] %} + server {{thehivehost}} {{thehivehost}}:9000 check verify none +{% endfor %} + +listen cortexserv + bind *:9001 ssl crt /etc/ssl/haproxy alpn h2,http/1.1 + mode http + maxconn 5000 + fullconn 5000 + balance source + option tcpka + option forwardfor +{% for cortexhost in groups['cortex'] %} + server {{cortexhost}} {{cortexhost}}:9001 check verify none +{% endfor %} + {% for port in range(50, 60) %} listen nifiservtcp77{{port}} bind *:77{{port}} diff --git a/roles/odfees/tasks/main.yml b/roles/odfees/tasks/main.yml index d0f40ce3de42100ba1fc9185c0e36ea02ab608b0..ae6ae65701c4bebcf8cbd04bc4d4ddb9e246acfd 100644 --- a/roles/odfees/tasks/main.yml +++ b/roles/odfees/tasks/main.yml @@ -62,6 +62,19 @@ tags: - start +- name: Change password for cortex + command: "bash plugins/opendistro_security/tools/hash.sh -p {{cortex_odfe_pass}}" + register: cortexhash + # when: "'{{groups['odfeescontainers'][0]}}' in inventory_hostname" + tags: + - start + +- set_fact: + cortexhashpwd: "{{ cortexhash.stdout }}" + #adminhashpwd: "{{ hostvars[groups['odfeescontainers'][0]]['adminhash.stdout'] }}" + tags: + - start + - name: Configure opendistro_security properties template: src: "securityconfig/{{item}}.j2" diff --git a/roles/odfees/templates/securityconfig/internal_users.yml.j2 b/roles/odfees/templates/securityconfig/internal_users.yml.j2 index 4d57f37b9690d9a51d8722484827a5d689a6a71a..8b16954ae73b49503bbf0f03e6c7b53f2bfa9675 100644 --- a/roles/odfees/templates/securityconfig/internal_users.yml.j2 +++ b/roles/odfees/templates/securityconfig/internal_users.yml.j2 @@ -17,6 +17,15 @@ admin: - "admin" description: "Demo admin user" +cortex: + hash: "{{cortexhashpwd}}" + reserved: true + backend_roles: + - "admin" +# - "own_index" +# - "readall" + description: "Cortex user" + kibanaserver: hash: "$2a$12$4AcgAt3xwOWadA5s5blL6ev39OXDNhmOesEoo33eZtrq2N0YrU3H." reserved: true diff --git a/roles/thehive/defaults/main.yml b/roles/thehive/defaults/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/thehive/files/.empty b/roles/thehive/files/.empty new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/thehive/handlers/main.yml b/roles/thehive/handlers/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/thehive/meta/main.yml b/roles/thehive/meta/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/roles/thehive/tasks/main.yml b/roles/thehive/tasks/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..7d8f8599b4993245b64d48f8064d78d99d1fc174 --- /dev/null +++ b/roles/thehive/tasks/main.yml @@ -0,0 +1,38 @@ +--- + +- name: Configure TheHive + template: + src: application.conf.j2 + dest: /etc/thehive/application.conf + tags: + - start + +- name: Start TheHive + command: > + daemonize + -c /opt/thehive + -p /tmp/thehive.pid + -o /tmp/thehive-stdout.log + /opt/thehive/bin/thehive + -Dconfig.file=/etc/thehive/application.conf + -Dlogger.file=/etc/thehive/logback.xml + -J-Xms1g + -J-Xmx1g + -Dpidfile.path=/dev/null + tags: + - start + +- name: Wait for TheHive + wait_for: + host: "{{groups['thehive'][0]}}" + port: 9000 + state: started + delay: 5 + tags: + - start + +- name: Stop TheHive + command: "pkill -SIGTERM -F /tmp/thehive.pid" + tags: + - stop + diff --git a/roles/thehive/templates/application.conf.j2 b/roles/thehive/templates/application.conf.j2 new file mode 100644 index 0000000000000000000000000000000000000000..6fa36eb370673fc95111327904af57738cabda58 --- /dev/null +++ b/roles/thehive/templates/application.conf.j2 @@ -0,0 +1,100 @@ +### +## Documentation is available at https://github.com/TheHive-Project/TheHiveDocs/TheHive4 +### + +## Include Play secret key +# More information on secret key at https://www.playframework.com/documentation/2.8.x/ApplicationSecret +#include "/etc/thehive/secret.conf" +play.http.secret.key="{{thehive_secret_key}}" + +## Database configuration +db.janusgraph { + storage { + ## Cassandra configuration + # More information at https://docs.janusgraph.org/basics/configuration-reference/#storagecql + backend: cql + hostname: ["{{groups['cassandra'][0]}}.{{soctools_netname}}"] + # Cassandra authentication (if configured) + // username: "thehive" + // password: "password" + cql { + cluster-name: thp + keyspace: thehive + } + } + + ## For test only ! + # Comment Cassandra settings before enable Berkeley database + // storage.backend: berkeleyje + // storage.directory: /path/to/berkeleydb + // berkeleyje.freeDisk: 200 # disk usage threshold +} + +## Attachment storage configuration +storage { + ## Local filesystem + provider: localfs + localfs.directory: /opt/thp_data/files/thehive + + ## Hadoop filesystem (HDFS) + // provider: hdfs + // hdfs { + // root: "hdfs://localhost:10000" # namenode server hostname + // location: "/thehive" # location inside HDFS + // username: thehive # file owner + // } +} + +## Authentication configuration +# More information at https://github.com/TheHive-Project/TheHiveDocs/TheHive4/Administration/Authentication.md +//auth { +// providers: [ +// {name: session} # required ! +// {name: basic, realm: thehive} +// {name: local} +// {name: key} +// ] +# The format of logins must be valid email address format. If the provided login doesn't contain `@` the following +# domain is automatically appended +// defaultUserDomain: "thehive.local" +//} + +## CORTEX configuration +# More information at https://github.com/TheHive-Project/TheHiveDocs/TheHive4/Administration/Connectors.md +# Enable Cortex connector +// play.modules.enabled += org.thp.thehive.connector.cortex.CortexModule +// cortex { +// servers: [ +// { +// name: "local" # Cortex name +// url: "http://localhost:9001" # URL of Cortex instance +// auth { +// type: "bearer" +// key: "***" # Cortex API key +// } +// ws {} # HTTP client configuration (SSL and proxy) +// } +// ] +// } + +## MISP configuration +# More information at https://github.com/TheHive-Project/TheHiveDocs/TheHive4/Administration/Connectors.md +# Enable MISP connector +// play.modules.enabled += org.thp.thehive.connector.mips.MispModule +// misp { +// interval: 1 hour +// servers: [ +// { +// name = "local" # MISP name +// url = "http://localhost/" # URL or MISP +// auth { +// type = key +// key = "***" # MISP API key +// } +// ws {} # HTTP client configuration (SSL and proxy) +// } +// ] +//} + +# Define maximum size of attachments (default 10MB) +//play.http.parser.maxDiskBuffer: 1GB diff --git a/roles/thehive/vars/main.yml b/roles/thehive/vars/main.yml new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/soctools-inventory b/soctools-inventory index 98d5ca68712d5151acdda998bd5246581a340e20..cff0d648d769176bf1292cfcd88493c12ac03120 100644 --- a/soctools-inventory +++ b/soctools-inventory @@ -22,5 +22,14 @@ dsoclab-mysql ansible_connection=docker [mispcontainers] dsoclab-misp ansible_connection=docker +[cassandra] +dsoclab-cassandra ansible_connection=docker + +[thehive] +dsoclab-thehive ansible_connection=docker + +[cortex] +dsoclab-cortex ansible_connection=docker + [haproxy] dsoclab-haproxy ansible_connection=docker diff --git a/startsoctools.yml b/startsoctools.yml index af914f57d48d1afb289d0dc55497bbb7baa95f7c..f1154c340f91f5604fd36c1abd38f9cc718c58f0 100644 --- a/startsoctools.yml +++ b/startsoctools.yml @@ -15,6 +15,11 @@ roles: - mysql +- name: Reconfigure and start Cassandra + hosts: cassandra + roles: + - cassandra + - name: Reconfigure and start Keycloak hosts: keycloakcontainers roles: @@ -35,8 +40,18 @@ roles: - odfekibana -- name: Reconfigure and start misp +- name: Reconfigure and start MISP hosts: mispcontainers roles: - misp +- name: Reconfigure and start TheHive + hosts: thehive + roles: + - thehive + +- name: Reconfigure and start Cortex + hosts: cortex + roles: + - cortex +