& so it begins

This commit is contained in:
user
2026-02-28 14:50:04 +02:00
commit f00381f2b6
536 changed files with 26294 additions and 0 deletions

42
dev/README.md Normal file
View File

@@ -0,0 +1,42 @@
# Dev
Self-contained local development stack. Spin up all shared infrastructure on a per-project basis.
## Services
| Service | Description | Port(s) |
| ------------------ | ---------------------------------------- | -------------- |
| **PostgreSQL** | Primary relational database | `5432` |
| **Valkey** | Redis-compatible cache / message broker | `6379` |
| **SigNoz** | Observability UI (traces, metrics, logs) | `8080` |
| **OTel Collector** | OpenTelemetry ingest (gRPC / HTTP) | `4317`, `4318` |
| **ClickHouse** | Telemetry storage backend for SigNoz | — |
## Run
```sh
cd dev
docker compose -f docker-compose.dev.yaml up -d
```
## Stop
```sh
docker compose -f docker-compose.dev.yaml down
```
To also remove all persisted data volumes:
```sh
docker compose -f docker-compose.dev.yaml down -v
```
## Connection strings
| Resource | Default value |
| ---------- | --------------------------------------------------------- |
| PostgreSQL | `postgresql://postgres:postgres@localhost:5432/primarydb` |
| Valkey | `redis://localhost:6379` |
| SigNoz UI | `http://localhost:8080` |
| OTLP gRPC | `localhost:4317` |
| OTLP HTTP | `localhost:4318` |

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>

1142
dev/clickhouse-config.xml Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,21 @@
<functions>
<function>
<type>executable</type>
<name>histogramQuantile</name>
<return_type>Float64</return_type>
<argument>
<type>Array(Float64)</type>
<name>buckets</name>
</argument>
<argument>
<type>Array(Float64)</type>
<name>counts</name>
</argument>
<argument>
<type>Float64</type>
<name>quantile</name>
</argument>
<format>CSV</format>
<command>./histogramQuantile</command>
</function>
</functions>

123
dev/clickhouse-users.xml Normal file
View File

@@ -0,0 +1,123 @@
<?xml version="1.0"?>
<clickhouse>
<!-- See also the files in users.d directory where the settings can be overridden. -->
<!-- Profiles of settings. -->
<profiles>
<!-- Default settings. -->
<default>
<!-- Maximum memory usage for processing single query, in bytes. -->
<max_memory_usage>10000000000</max_memory_usage>
<!-- How to choose between replicas during distributed query processing.
random - choose random replica from set of replicas with minimum number of errors
nearest_hostname - from set of replicas with minimum number of errors, choose replica
with minimum number of different symbols between replica's hostname and local hostname
(Hamming distance).
in_order - first live replica is chosen in specified order.
first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
-->
<load_balancing>random</load_balancing>
</default>
<!-- Profile that allows only read queries. -->
<readonly>
<readonly>1</readonly>
</readonly>
</profiles>
<!-- Users and ACL. -->
<users>
<!-- If user name was not specified, 'default' user is used. -->
<default>
<!-- See also the files in users.d directory where the password can be overridden.
Password could be specified in plaintext or in SHA256 (in hex format).
If you want to specify password in plaintext (not recommended), place it in 'password' element.
Example: <password>qwerty</password>.
Password could be empty.
If you want to specify SHA256, place it in 'password_sha256_hex' element.
Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>
If you want to specify a previously defined LDAP server (see 'ldap_servers' in the main config) for authentication,
place its name in 'server' element inside 'ldap' element.
Example: <ldap><server>my_ldap_server</server></ldap>
If you want to authenticate the user via Kerberos (assuming Kerberos is enabled, see 'kerberos' in the main config),
place 'kerberos' element instead of 'password' (and similar) elements.
The name part of the canonical principal name of the initiator must match the user name for authentication to succeed.
You can also place 'realm' element inside 'kerberos' element to further restrict authentication to only those requests
whose initiator's realm matches it.
Example: <kerberos />
Example: <kerberos><realm>EXAMPLE.COM</realm></kerberos>
How to generate decent password:
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
In first line will be password and in second - corresponding SHA256.
How to generate double SHA1:
Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha1sum | tr -d '-' | xxd -r -p | sha1sum | tr -d '-'
In first line will be password and in second - corresponding double SHA1.
-->
<password></password>
<!-- List of networks with open access.
To open access from everywhere, specify:
<ip>::/0</ip>
To open access only from localhost, specify:
<ip>::1</ip>
<ip>127.0.0.1</ip>
Each element of list has one of the following forms:
<ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
<host> Hostname. Example: server01.clickhouse.com.
To check access, DNS query is performed, and all received addresses compared to peer address.
<host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.clickhouse\.com$
To check access, DNS PTR query is performed for peer address and then regexp is applied.
Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
Strongly recommended that regexp is ends with $
All results of DNS requests are cached till server restart.
-->
<networks>
<ip>::/0</ip>
</networks>
<!-- Settings profile for user. -->
<profile>default</profile>
<!-- Quota for user. -->
<quota>default</quota>
<!-- User can create other users and grant rights to them. -->
<!-- <access_management>1</access_management> -->
</default>
</users>
<!-- Quotas. -->
<quotas>
<!-- Name of quota. -->
<default>
<!-- Limits for time interval. You could specify many intervals with different limits. -->
<interval>
<!-- Length of interval. -->
<duration>3600</duration>
<!-- No limits. Just calculate resource usage for time interval. -->
<queries>0</queries>
<errors>0</errors>
<result_rows>0</result_rows>
<read_rows>0</read_rows>
<execution_time>0</execution_time>
</interval>
</default>
</quotas>
</clickhouse>

218
dev/docker-compose.dev.yaml Normal file
View File

@@ -0,0 +1,218 @@
x-common: &common
networks:
- signoz-net
restart: unless-stopped
logging:
options:
max-size: 50m
max-file: "3"
x-clickhouse-defaults: &clickhouse-defaults
!!merge <<: *common
image: clickhouse/clickhouse-server:25.5.6
tty: true
labels:
signoz.io/scrape: "true"
signoz.io/port: "9363"
signoz.io/path: "/metrics"
depends_on:
init-clickhouse:
condition: service_completed_successfully
zookeeper-1:
condition: service_healthy
healthcheck:
test:
- CMD
- wget
- --spider
- -q
- 0.0.0.0:8123/ping
interval: 30s
timeout: 5s
retries: 3
ulimits:
nproc: 65535
nofile:
soft: 262144
hard: 262144
environment:
- CLICKHOUSE_SKIP_USER_SETUP=1
x-zookeeper-defaults: &zookeeper-defaults
!!merge <<: *common
image: signoz/zookeeper:3.7.1
user: root
labels:
signoz.io/scrape: "true"
signoz.io/port: "9141"
signoz.io/path: "/metrics"
healthcheck:
test:
- CMD-SHELL
- curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null
interval: 30s
timeout: 5s
retries: 3
x-db-depend: &db-depend
!!merge <<: *common
depends_on:
clickhouse:
condition: service_healthy
# ======
# Main
# ======
services:
valkey:
restart: always
image: valkey/valkey:9.0.3
networks:
- signoz-net
ports:
- 6379:6379
volumes:
- dev_valkey_data:/data
postgresql:
restart: always
image: postgres:18.3
networks:
- signoz-net
ports:
- 5432:5432
environment:
POSTGRES_DB: primarydb
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
volumes:
- dev_postgresql_data:/var/lib/postgresql
init-clickhouse:
!!merge <<: *common
image: clickhouse/clickhouse-server:25.5.6
container_name: signoz-init-clickhouse
command:
- bash
- -c
- |
version="v0.0.1"
node_os=$$(uname -s | tr '[:upper:]' '[:lower:]')
node_arch=$$(uname -m | sed s/aarch64/arm64/ | sed s/x86_64/amd64/)
echo "Fetching histogram-binary for $${node_os}/$${node_arch}"
cd /tmp
wget -O histogram-quantile.tar.gz "https://github.com/SigNoz/signoz/releases/download/histogram-quantile%2F$${version}/histogram-quantile_$${node_os}_$${node_arch}.tar.gz"
tar -xvzf histogram-quantile.tar.gz
mv histogram-quantile /var/lib/clickhouse/user_scripts/histogramQuantile
restart: on-failure
volumes:
- clickhouse-user-scripts:/var/lib/clickhouse/user_scripts/
zookeeper-1:
!!merge <<: *zookeeper-defaults
container_name: signoz-zookeeper-1
# ports:
# - "2181:2181"
# - "2888:2888"
# - "3888:3888"
volumes:
- zookeeper-1:/bitnami/zookeeper
environment:
- ZOO_SERVER_ID=1
- ALLOW_ANONYMOUS_LOGIN=yes
- ZOO_AUTOPURGE_INTERVAL=1
- ZOO_ENABLE_PROMETHEUS_METRICS=yes
- ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
clickhouse:
!!merge <<: *clickhouse-defaults
container_name: signoz-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-custom-function.xml:/etc/clickhouse-server/custom-function.xml
- clickhouse-user-scripts:/var/lib/clickhouse/user_scripts/
- ./clickhouse-cluster.xml:/etc/clickhouse-server/config.d/cluster.xml
- clickhouse:/var/lib/clickhouse/
# - ./clickhouse-storage.xml:/etc/clickhouse-server/config.d/storage.xml
signoz:
!!merge <<: *db-depend
image: signoz/signoz:${VERSION:-v0.113.0}
container_name: signoz
ports:
- "8080:8080" # signoz port
volumes:
- sqlite:/var/lib/signoz/
environment:
- SIGNOZ_ALERTMANAGER_PROVIDER=signoz
- SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN=tcp://clickhouse:9000
- SIGNOZ_SQLSTORE_SQLITE_PATH=/var/lib/signoz/signoz.db
- SIGNOZ_TOKENIZER_JWT_SECRET=secret
healthcheck:
test:
- CMD
- wget
- --spider
- -q
- localhost:8080/api/v1/health
interval: 30s
timeout: 5s
retries: 3
otel-collector:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.1}
container_name: signoz-otel-collector
entrypoint:
- /bin/sh
command:
- -c
- |
/signoz-otel-collector migrate sync check &&
/signoz-otel-collector --config=/etc/otel-collector-config.yaml --manager-config=/etc/manager-config.yaml --copy-path=/var/tmp/collector-config.yaml
volumes:
- ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
- ./otel-collector-opamp-config.yaml:/etc/manager-config.yaml
environment:
- OTEL_RESOURCE_ATTRIBUTES=host.name=signoz-host,os.type=linux
- LOW_CARDINAL_EXCEPTION_GROUPING=false
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
- SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
ports:
# - "1777:1777" # pprof extension
- "4317:4317" # OTLP gRPC receiver
- "4318:4318" # OTLP HTTP receiver
signoz-telemetrystore-migrator:
!!merge <<: *db-depend
image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.1}
container_name: signoz-telemetrystore-migrator
environment:
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
- SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
entrypoint:
- /bin/sh
command:
- -c
- |
/signoz-otel-collector migrate bootstrap &&
/signoz-otel-collector migrate sync up &&
/signoz-otel-collector migrate async up
restart: on-failure
# Peripherals
networks:
signoz-net:
name: signoz-net
volumes:
dev_valkey_data:
name: dev-valkey-data
dev_postgresql_data:
name: dev-postgresql-data
clickhouse:
name: signoz-clickhouse
clickhouse-user-scripts:
name: signoz-clickhouse-user-scripts
sqlite:
name: signoz-sqlite
zookeeper-1:
name: signoz-zookeeper-1

View File

@@ -0,0 +1,124 @@
connectors:
signozmeter:
metrics_flush_interval: 1h
dimensions:
- name: service.name
- name: deployment.environment
- name: host.name
receivers:
otlp:
protocols:
grpc:
endpoint: 0.0.0.0:4317
http:
endpoint: 0.0.0.0:4318
processors:
batch:
send_batch_size: 10000
send_batch_max_size: 11000
timeout: 10s
batch/meter:
send_batch_max_size: 25000
send_batch_size: 20000
timeout: 1s
resourcedetection:
# Using OTEL_RESOURCE_ATTRIBUTES envvar, env detector adds custom labels.
detectors: [env, system]
timeout: 2s
signozspanmetrics/delta:
metrics_exporter: signozclickhousemetrics
metrics_flush_interval: 60s
latency_histogram_buckets:
[
100us,
1ms,
2ms,
6ms,
10ms,
50ms,
100ms,
250ms,
500ms,
1000ms,
1400ms,
2000ms,
5s,
10s,
20s,
40s,
60s,
]
dimensions_cache_size: 100000
aggregation_temporality: AGGREGATION_TEMPORALITY_DELTA
enable_exp_histogram: true
dimensions:
- name: service.namespace
default: default
- name: deployment.environment
default: default
# This is added to ensure the uniqueness of the timeseries
# Otherwise, identical timeseries produced by multiple replicas of
# collectors result in incorrect APM metrics
- name: signoz.collector.id
- name: service.version
- name: browser.platform
- name: browser.mobile
- name: k8s.cluster.name
- name: k8s.node.name
- name: k8s.namespace.name
- name: host.name
- name: host.type
- name: container.name
extensions:
health_check:
endpoint: 0.0.0.0:13133
pprof:
endpoint: 0.0.0.0:1777
exporters:
clickhousetraces:
datasource: tcp://clickhouse:9000/signoz_traces
low_cardinal_exception_grouping: ${env:LOW_CARDINAL_EXCEPTION_GROUPING}
use_new_schema: true
signozclickhousemetrics:
dsn: tcp://clickhouse:9000/signoz_metrics
clickhouselogsexporter:
dsn: tcp://clickhouse:9000/signoz_logs
timeout: 10s
use_new_schema: true
signozclickhousemeter:
dsn: tcp://clickhouse:9000/signoz_meter
timeout: 45s
sending_queue:
enabled: false
metadataexporter:
cache:
provider: in_memory
dsn: tcp://clickhouse:9000/signoz_metadata
enabled: true
timeout: 45s
service:
telemetry:
logs:
encoding: json
extensions:
- health_check
- pprof
pipelines:
traces:
receivers: [otlp]
processors: [signozspanmetrics/delta, batch]
exporters: [clickhousetraces, metadataexporter, signozmeter]
metrics:
receivers: [otlp]
processors: [batch]
exporters: [signozclickhousemetrics, metadataexporter, signozmeter]
logs:
receivers: [otlp]
processors: [batch]
exporters: [clickhouselogsexporter, metadataexporter, signozmeter]
metrics/meter:
receivers: [signozmeter]
processors: [batch/meter]
exporters: [signozclickhousemeter]

View File

@@ -0,0 +1 @@
server_endpoint: ws://signoz:4320/v1/opamp