GitHub-Proxy/signoz
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/SigNoz/signoz synced 2025-08-12 03:39:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(clickhouse): 🔧 include cluster.xml for distributed set up (#1810)

Browse Source 
* chore(clickhouse): 🔧 include cluster.xml for distributed set up

Signed-off-by: Prashant Shahi <prashant@signoz.io>
This commit is contained in:
Prashant Shahi 2022-12-05 17:26:13 +05:30 committed by GitHub
parent a46f074e22
commit 8bb3eefeb5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 225 additions and 250 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
deploy/docker-swarm/clickhouse-setup/clickhouse-cluster.xml Normal file
View File

@ -0,0 +1,75 @@
<?xml version="1.0"?>
<clickhouse>
<!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
Optional. If you don't use replicated tables, you could omit that.
See https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/replication/
-->
<zookeeper>
<node index="1">
<host>zookeeper-1</host>
<port>2181</port>
</node>
<!-- <node index="2">
<host>zookeeper-2</host>
<port>2181</port>
</node>
<node index="3">
<host>zookeeper-3</host>
<port>2181</port>
</node> -->
</zookeeper>
<!-- Configuration of clusters that could be used in Distributed tables.
https://clickhouse.com/docs/en/operations/table_engines/distributed/
-->
<remote_servers>
<cluster>
<!-- Inter-server per-cluster secret for Distributed queries
default: no secret (no authentication will be performed)
If set, then Distributed queries will be validated on shards, so at least:
- such cluster should exist on the shard,
- such cluster should have the same secret.
And also (and which is more important), the initial_user will
be used as current user for the query.
Right now the protocol is pretty simple and it only takes into account:
- cluster name
- query
Also it will be nice if the following will be implemented:
- source hostname (see interserver_http_host), but then it will depends from DNS,
it can use IP address instead, but then the you need to get correct on the initiator node.
- target hostname / ip address (same notes as for source hostname)
- time-based security tokens
-->
<!-- <secret></secret> -->
<shard>
<!-- Optional. Whether to write data to just one of the replicas. Default: false (write data to all replicas). -->
<!-- <internal_replication>false</internal_replication> -->
<!-- Optional. Shard weight when writing data. Default: 1. -->
<!-- <weight>1</weight> -->
<replica>
<host>clickhouse</host>
<port>9000</port>
<!-- Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority). -->
<!-- <priority>1</priority> -->
</replica>
</shard>
<!-- <shard>
<replica>
<host>clickhouse-2</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>clickhouse-3</host>
<port>9000</port>
</replica>
</shard> -->
</cluster>
</remote_servers>
</clickhouse>

75
deploy/docker/clickhouse-setup/clickhouse-cluster.xml Normal file
View File

@ -0,0 +1,75 @@
<?xml version="1.0"?>
<clickhouse>
<!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
Optional. If you don't use replicated tables, you could omit that.
See https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/replication/
-->
<zookeeper>
<node index="1">
<host>zookeeper-1</host>
<port>2181</port>
</node>
<!-- <node index="2">
<host>zookeeper-2</host>
<port>2181</port>
</node>
<node index="3">
<host>zookeeper-3</host>
<port>2181</port>
</node> -->
</zookeeper>
<!-- Configuration of clusters that could be used in Distributed tables.
https://clickhouse.com/docs/en/operations/table_engines/distributed/
-->
<remote_servers>
<cluster>
<!-- Inter-server per-cluster secret for Distributed queries
default: no secret (no authentication will be performed)
If set, then Distributed queries will be validated on shards, so at least:
- such cluster should exist on the shard,
- such cluster should have the same secret.
And also (and which is more important), the initial_user will
be used as current user for the query.
Right now the protocol is pretty simple and it only takes into account:
- cluster name
- query
Also it will be nice if the following will be implemented:
- source hostname (see interserver_http_host), but then it will depends from DNS,
it can use IP address instead, but then the you need to get correct on the initiator node.
- target hostname / ip address (same notes as for source hostname)
- time-based security tokens
-->
<!-- <secret></secret> -->
<shard>
<!-- Optional. Whether to write data to just one of the replicas. Default: false (write data to all replicas). -->
<!-- <internal_replication>false</internal_replication> -->
<!-- Optional. Shard weight when writing data. Default: 1. -->
<!-- <weight>1</weight> -->
<replica>
<host>clickhouse</host>
<port>9000</port>
<!-- Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority). -->
<!-- <priority>1</priority> -->
</replica>
</shard>
<!-- <shard>
<replica>
<host>clickhouse-2</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>clickhouse-3</host>
<port>9000</port>
</replica>
</shard> -->
</cluster>
</remote_servers>
</clickhouse>

250
deploy/docker/clickhouse-setup/docker-compose-distributed.yaml
View File

@ -1,250 +0,0 @@
version: "2.4"
x-clickhouse-defaults: &clickhouse-defaults
restart: on-failure
image: clickhouse/clickhouse-server:22.8.8-alpine
tty: true
depends_on:
- zookeeper-1
- zookeeper-2
- zookeeper-3
logging:
options:
max-size: 50m
max-file: "3"
healthcheck:
# "clickhouse", "client", "-u ${CLICKHOUSE_USER}", "--password ${CLICKHOUSE_PASSWORD}", "-q 'SELECT 1'"
test: ["CMD", "wget", "--spider", "-q", "localhost:8123/ping"]
interval: 30s
timeout: 5s
retries: 3
ulimits:
nproc: 65535
nofile:
soft: 262144
hard: 262144
x-clickhouse-depend: &clickhouse-depend
depends_on:
clickhouse:
condition: service_healthy
clickhouse-2:
condition: service_healthy
clickhouse-3:
condition: service_healthy
services:
zookeeper-1:
image: bitnami/zookeeper:3.7.0
container_name: zookeeper-1
hostname: zookeeper-1
user: root
ports:
- "2181:2181"
- "2888:2888"
- "3888:3888"
volumes:
- ./data/zookeeper-1:/bitnami/zookeeper
environment:
- ZOO_SERVER_ID=1
- ZOO_SERVERS=0.0.0.0:2888:3888,zookeeper-2:2888:3888,zookeeper-3:2888:3888
- ALLOW_ANONYMOUS_LOGIN=yes
- ZOO_AUTOPURGE_INTERVAL=1
zookeeper-2:
image: bitnami/zookeeper:3.7.0
container_name: zookeeper-2
hostname: zookeeper-2
user: root
ports:
- "2182:2181"
- "2889:2888"
- "3889:3888"
volumes:
- ./data/zookeeper-2:/bitnami/zookeeper
environment:
- ZOO_SERVER_ID=2
- ZOO_SERVERS=zookeeper-1:2888:3888,0.0.0.0:2888:3888,zookeeper-3:2888:3888
- ALLOW_ANONYMOUS_LOGIN=yes
- ZOO_AUTOPURGE_INTERVAL=1
zookeeper-3:
image: bitnami/zookeeper:3.7.0
container_name: zookeeper-3
hostname: zookeeper-3
user: root
ports:
- "2183:2181"
- "2890:2888"
- "3890:3888"
volumes:
- ./data/zookeeper-3:/bitnami/zookeeper
environment:
- ZOO_SERVER_ID=3
- ZOO_SERVERS=zookeeper-1:2888:3888,zookeeper-2:2888:3888,0.0.0.0:2888:3888
- ALLOW_ANONYMOUS_LOGIN=yes
- ZOO_AUTOPURGE_INTERVAL=1
clickhouse:
<<: *clickhouse-defaults
container_name: clickhouse
hostname: clickhouse
ports:
- "9000:9000"
- "8123:8123"
- "9181:9181"
volumes:
- ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
- ./clickhouse-users.xml:/etc/clickhouse-server/users.xml
- ./clickhouse-distributed.xml:/etc/clickhouse-server/config.d/distributed.xml
# - ./clickhouse-storage.xml:/etc/clickhouse-server/config.d/storage.xml
- ./data/clickhouse/:/var/lib/clickhouse/
clickhouse-2:
<<: *clickhouse-defaults
container_name: clickhouse-2
hostname: clickhouse-2
ports:
- "9001:9000"
- "8124:8123"
- "9182:9181"
volumes:
- ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
- ./clickhouse-users.xml:/etc/clickhouse-server/users.xml
- ./clickhouse-distributed.xml:/etc/clickhouse-server/config.d/distributed.xml
# - ./clickhouse-storage.xml:/etc/clickhouse-server/config.d/storage.xml
- ./data/clickhouse-2/:/var/lib/clickhouse/
clickhouse-3:
<<: *clickhouse-defaults
container_name: clickhouse-3
hostname: clickhouse-3
ports:
- "9002:9000"
- "8125:8123"
- "9183:9181"
volumes:
- ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
- ./clickhouse-users.xml:/etc/clickhouse-server/users.xml
- ./clickhouse-distributed.xml:/etc/clickhouse-server/config.d/distributed.xml
# - ./clickhouse-storage.xml:/etc/clickhouse-server/config.d/storage.xml
- ./data/clickhouse-3/:/var/lib/clickhouse/
alertmanager:
image: signoz/alertmanager:0.23.0-0.2
volumes:
- ./data/alertmanager:/data
depends_on:
query-service:
condition: service_healthy
restart: on-failure
command:
- --queryService.url=http://query-service:8085
- --storage.path=/data
# Notes for Maintainers/Contributors who will change Line Numbers of Frontend & Query-Section. Please Update Line Numbers in `./scripts/commentLinesForSetup.sh` & `./CONTRIBUTING.md`
query-service:
image: signoz/query-service:distributed-test-1
container_name: query-service
command: ["-config=/root/config/prometheus.yml"]
# ports:
# - "6060:6060" # pprof port
# - "8080:8080" # query-service port
volumes:
- ./prometheus.yml:/root/config/prometheus.yml
- ../dashboards:/root/config/dashboards
- ./data/signoz/:/var/lib/signoz/
environment:
- ClickHouseUrl=tcp://clickhouse:9000/?database=signoz_traces
- ALERTMANAGER_API_PREFIX=http://alertmanager:9093/api/
- SIGNOZ_LOCAL_DB_PATH=/var/lib/signoz/signoz.db
- DASHBOARDS_PATH=/root/config/dashboards
- STORAGE=clickhouse
- GODEBUG=netdns=go
- TELEMETRY_ENABLED=true
- DEPLOYMENT_TYPE=docker-standalone-amd
restart: on-failure
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "localhost:8080/api/v1/version"]
interval: 30s
timeout: 5s
retries: 3
<<: *clickhouse-depend
frontend:
image: signoz/frontend:distributed-test-1
container_name: frontend
restart: on-failure
depends_on:
- alertmanager
- query-service
ports:
- "3301:3301"
volumes:
- ../common/nginx-config.conf:/etc/nginx/conf.d/default.conf
otel-collector:
image: signoz/signoz-otel-collector:distributed-test-1
command: ["--config=/etc/otel-collector-config.yaml"]
# required for reading docker container logs
volumes:
- ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
- /var/lib/docker/containers:/var/lib/docker/containers:ro
environment:
- OTEL_RESOURCE_ATTRIBUTES=host.name=signoz-host,os.type=linux
ports:
# - "1777:1777" # pprof extension
- "4317:4317" # OTLP gRPC receiver
- "4318:4318" # OTLP HTTP receiver
# - "8888:8888" # OtelCollector internal metrics
# - "8889:8889" # signoz spanmetrics exposed by the agent
# - "9411:9411" # Zipkin port
# - "13133:13133" # health check extension
# - "14250:14250" # Jaeger gRPC
# - "14268:14268" # Jaeger thrift HTTP
# - "55678:55678" # OpenCensus receiver
# - "55679:55679" # zPages extension
restart: on-failure
<<: *clickhouse-depend
otel-collector-metrics:
image: signoz/signoz-otel-collector:distributed-test-1
command: ["--config=/etc/otel-collector-metrics-config.yaml"]
volumes:
- ./otel-collector-metrics-config.yaml:/etc/otel-collector-metrics-config.yaml
# ports:
# - "1777:1777" # pprof extension
# - "8888:8888" # OtelCollector internal metrics
# - "13133:13133" # Health check extension
# - "55679:55679" # zPages extension
restart: on-failure
<<: *clickhouse-depend
hotrod:
image: jaegertracing/example-hotrod:1.30
container_name: hotrod
logging:
options:
max-size: 50m
max-file: "3"
command: ["all"]
environment:
- JAEGER_ENDPOINT=http://otel-collector:14268/api/traces
load-hotrod:
image: "grubykarol/locust:1.2.3-python3.9-alpine3.12"
container_name: load-hotrod
hostname: load-hotrod
environment:
ATTACKED_HOST: http://hotrod:8080
LOCUST_MODE: standalone
NO_PROXY: standalone
TASK_DELAY_FROM: 5
TASK_DELAY_TO: 30
QUIET_MODE: "${QUIET_MODE:-false}"
LOCUST_OPTS: "--headless -u 10 -r 1"
volumes:
- ../common/locust-scripts:/locust

75
pkg/query-service/tests/test-deploy/clickhouse-cluster.xml Normal file
View File

@ -0,0 +1,75 @@
<?xml version="1.0"?>
<clickhouse>
<!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
Optional. If you don't use replicated tables, you could omit that.
See https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/replication/
-->
<zookeeper>
<node index="1">
<host>zookeeper-1</host>
<port>2181</port>
</node>
<!-- <node index="2">
<host>zookeeper-2</host>
<port>2181</port>
</node>
<node index="3">
<host>zookeeper-3</host>
<port>2181</port>
</node> -->
</zookeeper>
<!-- Configuration of clusters that could be used in Distributed tables.
https://clickhouse.com/docs/en/operations/table_engines/distributed/
-->
<remote_servers>
<cluster>
<!-- Inter-server per-cluster secret for Distributed queries
default: no secret (no authentication will be performed)
If set, then Distributed queries will be validated on shards, so at least:
- such cluster should exist on the shard,
- such cluster should have the same secret.
And also (and which is more important), the initial_user will
be used as current user for the query.
Right now the protocol is pretty simple and it only takes into account:
- cluster name
- query
Also it will be nice if the following will be implemented:
- source hostname (see interserver_http_host), but then it will depends from DNS,
it can use IP address instead, but then the you need to get correct on the initiator node.
- target hostname / ip address (same notes as for source hostname)
- time-based security tokens
-->
<!-- <secret></secret> -->
<shard>
<!-- Optional. Whether to write data to just one of the replicas. Default: false (write data to all replicas). -->
<!-- <internal_replication>false</internal_replication> -->
<!-- Optional. Shard weight when writing data. Default: 1. -->
<!-- <weight>1</weight> -->
<replica>
<host>clickhouse</host>
<port>9000</port>
<!-- Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority). -->
<!-- <priority>1</priority> -->
</replica>
</shard>
<!-- <shard>
<replica>
<host>clickhouse-2</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>clickhouse-3</host>
<port>9000</port>
</replica>
</shard> -->
</cluster>
</remote_servers>
</clickhouse>