feat: add otel-host-agent and archon stacks, update signoz

This commit is contained in:
Sun-ZhenXing
2026-05-31 11:28:15 +08:00
parent 53b841926e
commit b7d3248b37
14 changed files with 886 additions and 26 deletions
+8
View File
@@ -0,0 +1,8 @@
# OpenTelemetry Collector Contrib image version
OTEL_COLLECTOR_VERSION=0.153.0
# Deployment environment label (used in resource attributes)
DEPLOY_ENV=production
# OTLP HTTP exporter endpoint (your OTel backend, e.g. OpenObserve, Grafana Tempo, Jaeger)
OTEL_EXPORTER_ENDPOINT=http://localhost:4318
+121
View File
@@ -0,0 +1,121 @@
receivers:
otlp:
protocols:
grpc:
endpoint: 0.0.0.0:4317
http:
endpoint: 0.0.0.0:4318
hostmetrics:
root_path: /hostfs
collection_interval: 60s
scrapers:
cpu: {}
disk: {}
load: {}
filesystem:
exclude_fs_types:
match_type: strict
fs_types:
- autofs
- binfmt_misc
- cgroup
- configfs
- debugfs
- devpts
- devtmpfs
- fusectl
- hugetlbfs
- mqueue
- nsfs
- overlay
- proc
- procfs
- pstore
- rpc_pipefs
- securityfs
- squashfs
- sysfs
- tmpfs
- tracefs
exclude_mount_points:
match_type: regexp
mount_points:
- ^/dev/.*$
- ^/proc/.*$
- ^/sys/.*$
- ^/run/.*$
- ^/var/lib/docker/.*$
- ^/snap/.*$
memory: {}
network:
exclude:
match_type: regexp
interfaces:
- '^veth.*$'
- '^docker.*$'
- '^br-.*$'
- ^lo$
paging: {}
process:
mute_process_name_error: true
mute_process_exe_error: true
mute_process_io_error: true
mute_process_user_error: true
processes: {}
system: {}
docker_stats:
endpoint: unix:///var/run/docker.sock
collection_interval: 10s
timeout: 20s
processors:
batch:
send_batch_size: 1000
timeout: 10s
resourcedetection:
detectors: [env, system]
timeout: 2s
system:
hostname_sources: [os]
memory_limiter:
check_interval: 5s
limit_mib: 4000
spike_limit_mib: 800
exporters:
otlphttp:
endpoint: ${OTEL_EXPORTER_ENDPOINT}
tls:
insecure: true
compression: gzip
sending_queue:
enabled: true
num_consumers: 10
queue_size: 10000
retry_on_failure:
enabled: true
extensions:
health_check:
endpoint: 0.0.0.0:13133
pprof:
endpoint: 0.0.0.0:1777
zpages:
endpoint: 0.0.0.0:55679
service:
extensions: [health_check, pprof, zpages]
pipelines:
traces:
receivers: [otlp]
processors: [memory_limiter, resourcedetection, batch]
exporters: [otlphttp]
metrics:
receivers: [otlp, hostmetrics, docker_stats]
processors: [memory_limiter, resourcedetection, batch]
exporters: [otlphttp]
logs:
receivers: [otlp]
processors: [memory_limiter, resourcedetection, batch]
exporters: [otlphttp]
+23
View File
@@ -0,0 +1,23 @@
services:
collection-agent:
image: otel/opentelemetry-collector-contrib:${OTEL_COLLECTOR_VERSION:-0.153.0}
restart: unless-stopped
user: '0:0'
network_mode: host
environment:
- OTEL_RESOURCE_ATTRIBUTES=deployment.environment=${DEPLOY_ENV:-production}
- OTEL_EXPORTER_ENDPOINT=${OTEL_EXPORTER_ENDPOINT:-http://localhost:4318}
volumes:
- ./config.yaml:/etc/otelcol-contrib/config.yaml:ro
- /:/hostfs:ro
- /var/run/docker.sock:/var/run/docker.sock:ro
deploy:
resources:
limits:
cpus: '1.0'
memory: 2G
logging:
driver: json-file
options:
max-size: 10m
max-file: '3'
+6 -3
View File
@@ -9,11 +9,14 @@ TZ=UTC
# SigNoz Version Configuration
# ============================================
# SigNoz image repository/name
SIGNOZ_IMAGE_NAME=signoz/signoz
# SigNoz all-in-one backend + frontend + alertmanager version
SIGNOZ_VERSION=v0.118.0
SIGNOZ_VERSION=v0.125.1
# SigNoz OTel Collector version (also used for migration jobs)
SIGNOZ_OTEL_COLLECTOR_VERSION=v0.144.2
SIGNOZ_OTEL_COLLECTOR_VERSION=v0.144.4
# ClickHouse version
SIGNOZ_CLICKHOUSE_VERSION=25.5.6
@@ -113,4 +116,4 @@ SIGNOZ_ZOOKEEPER_MEMORY_LIMIT=512M
SIGNOZ_ZOOKEEPER_CPU_RESERVATION=0.1
# Memory reservation for ZooKeeper
SIGNOZ_ZOOKEEPER_MEMORY_RESERVATION=128M
SIGNOZ_ZOOKEEPER_MEMORY_RESERVATION=128M
+13 -10
View File
@@ -15,14 +15,14 @@ SigNoz is an open-source observability platform that provides monitoring and tro
## Services
| Service | Image | Description |
| -------------------------------- | ------------------------------------- | ------------------------------------------------------ |
| `signoz` | signoz/signoz:v0.118.0 | All-in-one backend, frontend UI, and alert manager |
| `otel-collector` | signoz/signoz-otel-collector:v0.144.2 | Receives, processes, and exports telemetry data |
| `clickhouse` | clickhouse/clickhouse-server:25.5.6 | Time-series database for traces, metrics, and logs |
| `zookeeper-1` | signoz/zookeeper:3.7.1 | ZooKeeper for ClickHouse replication metadata |
| `init-clickhouse` | clickhouse/clickhouse-server:25.5.6 | One-shot init that downloads the histogramQuantile UDF |
| `signoz-telemetrystore-migrator` | signoz/signoz-otel-collector:v0.144.2 | One-shot schema migration for ClickHouse |
| Service | Image | Description |
| -------------------------------- | ----------------------------------------------------------------- | ------------------------------------------------------ |
| `signoz` | `${SIGNOZ_IMAGE_NAME:-signoz/signoz}:${SIGNOZ_VERSION:-v0.125.1}` | All-in-one backend, frontend UI, and alert manager |
| `otel-collector` | signoz/signoz-otel-collector:v0.144.4 | Receives, processes, and exports telemetry data |
| `clickhouse` | clickhouse/clickhouse-server:25.5.6 | Time-series database for traces, metrics, and logs |
| `zookeeper-1` | signoz/zookeeper:3.7.1 | ZooKeeper for ClickHouse replication metadata |
| `init-clickhouse` | clickhouse/clickhouse-server:25.5.6 | One-shot init that downloads the histogramQuantile UDF |
| `signoz-telemetrystore-migrator` | signoz/signoz-otel-collector:v0.144.4 | One-shot schema migration for ClickHouse |
## Quick Start
@@ -61,13 +61,16 @@ SigNoz is an open-source observability platform that provides monitoring and tro
| `SIGNOZ_PORT_OVERRIDE` | `8080` | SigNoz UI host port |
| `SIGNOZ_OTEL_GRPC_PORT_OVERRIDE` | `4317` | OTLP gRPC receiver host port |
| `SIGNOZ_OTEL_HTTP_PORT_OVERRIDE` | `4318` | OTLP HTTP receiver host port |
| `SIGNOZ_VERSION` | `v0.118.0` | SigNoz image version |
| `SIGNOZ_OTEL_COLLECTOR_VERSION` | `v0.144.2` | OTel Collector image version |
| `SIGNOZ_IMAGE_NAME` | `signoz/signoz` | SigNoz image repository/name |
| `SIGNOZ_VERSION` | `v0.125.1` | SigNoz image version |
| `SIGNOZ_OTEL_COLLECTOR_VERSION` | `v0.144.4` | OTel Collector image version |
| `SIGNOZ_CLICKHOUSE_VERSION` | `25.5.6` | ClickHouse image version |
| `TZ` | `UTC` | Timezone |
See `.env.example` for the complete list including resource limits.
`SIGNOZ_IMAGE_NAME` lets you switch the SigNoz image repository while keeping the tag controlled by `SIGNOZ_VERSION`.
### Sending Telemetry Data
Configure your application's OpenTelemetry SDK to export to:
+13 -10
View File
@@ -15,14 +15,14 @@ SigNoz 是一个开源的可观测性平台,为分布式应用程序提供监
## 服务列表
| 服务 | 镜像 | 描述 |
| -------------------------------- | ------------------------------------- | ---------------------------------------- |
| `signoz` | signoz/signoz:v0.118.0 | 后端、前端 UI 和告警管理器的合体镜像 |
| `otel-collector` | signoz/signoz-otel-collector:v0.144.2 | 接收、处理和导出遥测数据 |
| `clickhouse` | clickhouse/clickhouse-server:25.5.6 | 存储追踪、指标和日志的时序数据库 |
| `zookeeper-1` | signoz/zookeeper:3.7.1 | ZooKeeper,用于 ClickHouse 副本元数据 |
| `init-clickhouse` | clickhouse/clickhouse-server:25.5.6 | 一次性初始化,下载 histogramQuantile UDF |
| `signoz-telemetrystore-migrator` | signoz/signoz-otel-collector:v0.144.2 | 一次性 ClickHouse Schema 迁移 |
| 服务 | 镜像 | 描述 |
| -------------------------------- | ----------------------------------------------------------------- | ---------------------------------------- |
| `signoz` | `${SIGNOZ_IMAGE_NAME:-signoz/signoz}:${SIGNOZ_VERSION:-v0.125.1}` | 后端、前端 UI 和告警管理器的合体镜像 |
| `otel-collector` | signoz/signoz-otel-collector:v0.144.4 | 接收、处理和导出遥测数据 |
| `clickhouse` | clickhouse/clickhouse-server:25.5.6 | 存储追踪、指标和日志的时序数据库 |
| `zookeeper-1` | signoz/zookeeper:3.7.1 | ZooKeeper,用于 ClickHouse 副本元数据 |
| `init-clickhouse` | clickhouse/clickhouse-server:25.5.6 | 一次性初始化,下载 histogramQuantile UDF |
| `signoz-telemetrystore-migrator` | signoz/signoz-otel-collector:v0.144.4 | 一次性 ClickHouse Schema 迁移 |
## 快速开始
@@ -61,13 +61,16 @@ SigNoz 是一个开源的可观测性平台,为分布式应用程序提供监
| `SIGNOZ_PORT_OVERRIDE` | `8080` | SigNoz UI 宿主机端口 |
| `SIGNOZ_OTEL_GRPC_PORT_OVERRIDE` | `4317` | OTLP gRPC 接收器宿主机端口 |
| `SIGNOZ_OTEL_HTTP_PORT_OVERRIDE` | `4318` | OTLP HTTP 接收器宿主机端口 |
| `SIGNOZ_VERSION` | `v0.118.0` | SigNoz 镜像版本 |
| `SIGNOZ_OTEL_COLLECTOR_VERSION` | `v0.144.2` | OTel Collector 镜像版本 |
| `SIGNOZ_IMAGE_NAME` | `signoz/signoz` | SigNoz 镜像仓库名或镜像名 |
| `SIGNOZ_VERSION` | `v0.125.1` | SigNoz 镜像版本 |
| `SIGNOZ_OTEL_COLLECTOR_VERSION` | `v0.144.4` | OTel Collector 镜像版本 |
| `SIGNOZ_CLICKHOUSE_VERSION` | `25.5.6` | ClickHouse 镜像版本 |
| `TZ` | `UTC` | 时区 |
完整变量列表(含资源限制)请查看 `.env.example`。
`SIGNOZ_IMAGE_NAME` 用于切换 SigNoz 镜像仓库,同时继续由 `SIGNOZ_VERSION` 控制标签版本。
### 发送遥测数据
将应用程序的 OpenTelemetry SDK 配置为向以下端点导出数据:
+3 -3
View File
@@ -116,7 +116,7 @@ services:
# One-shot migration: bootstraps and runs schema migrations
signoz-telemetrystore-migrator:
<<: *db-depend
image: ${GLOBAL_REGISTRY:-}signoz/signoz-otel-collector:${SIGNOZ_OTEL_COLLECTOR_VERSION:-v0.144.2}
image: ${GLOBAL_REGISTRY:-}signoz/signoz-otel-collector:${SIGNOZ_OTEL_COLLECTOR_VERSION:-v0.144.4}
restart: on-failure
environment:
- TZ=${TZ:-UTC}
@@ -140,7 +140,7 @@ services:
# SigNoz all-in-one backend + frontend + alertmanager
signoz:
<<: *db-depend
image: ${GLOBAL_REGISTRY:-}signoz/signoz:${SIGNOZ_VERSION:-v0.118.0}
image: ${GLOBAL_REGISTRY:-}${SIGNOZ_IMAGE_NAME:-signoz/signoz}:${SIGNOZ_VERSION:-v0.125.1}
ports:
- '${SIGNOZ_PORT_OVERRIDE:-8080}:8080'
volumes:
@@ -169,7 +169,7 @@ services:
# OTel Collector for receiving telemetry data
otel-collector:
<<: *db-depend
image: ${GLOBAL_REGISTRY:-}signoz/signoz-otel-collector:${SIGNOZ_OTEL_COLLECTOR_VERSION:-v0.144.2}
image: ${GLOBAL_REGISTRY:-}signoz/signoz-otel-collector:${SIGNOZ_OTEL_COLLECTOR_VERSION:-v0.144.4}
entrypoint: [/bin/sh]
command:
- -c