mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-06 13:27:43 +00:00
improve logger entry for Observability
This commit is contained in:
houseme
@@ -0,0 +1,65 @@
|
||||
services:
|
||||
otel-collector:
|
||||
image: otel/opentelemetry-collector-contrib:0.120.0
|
||||
environment:
|
||||
- TZ=Asia/Shanghai
|
||||
volumes:
|
||||
- ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml
|
||||
ports:
|
||||
- 1888:1888
|
||||
- 8888:8888
|
||||
- 8889:8889
|
||||
- 13133:13133
|
||||
- 4317:4317
|
||||
- 4318:4318
|
||||
- 55679:55679
|
||||
networks:
|
||||
- otel-network
|
||||
jaeger:
|
||||
image: jaegertracing/jaeger:2.3.0
|
||||
environment:
|
||||
- TZ=Asia/Shanghai
|
||||
ports:
|
||||
- "16686:16686"
|
||||
- "14317:4317"
|
||||
- "14318:4318"
|
||||
networks:
|
||||
- otel-network
|
||||
prometheus:
|
||||
image: prom/prometheus:v3.2.0
|
||||
environment:
|
||||
- TZ=Asia/Shanghai
|
||||
volumes:
|
||||
- ./prometheus.yml:/etc/prometheus/prometheus.yml
|
||||
ports:
|
||||
- "9090:9090"
|
||||
networks:
|
||||
- otel-network
|
||||
loki:
|
||||
image: grafana/loki:3.4.2
|
||||
environment:
|
||||
- TZ=Asia/Shanghai
|
||||
volumes:
|
||||
- ./loki-config.yaml:/etc/loki/local-config.yaml
|
||||
ports:
|
||||
- "3100:3100"
|
||||
command: -config.file=/etc/loki/local-config.yaml
|
||||
networks:
|
||||
- otel-network
|
||||
grafana:
|
||||
image: grafana/grafana:11.5.2
|
||||
ports:
|
||||
- "3000:3000" # Web UI
|
||||
environment:
|
||||
- GF_SECURITY_ADMIN_PASSWORD=admin
|
||||
- TZ=Asia/Shanghai
|
||||
networks:
|
||||
- otel-network
|
||||
|
||||
|
||||
networks:
|
||||
otel-network:
|
||||
driver: bridge
|
||||
name: "network_otel_config"
|
||||
driver_opts:
|
||||
com.docker.network.enable_ipv6: "true"
|
||||
@@ -0,0 +1,88 @@
|
||||
|
||||
service:
|
||||
extensions: [jaeger_storage, jaeger_query, remote_sampling, healthcheckv2]
|
||||
pipelines:
|
||||
traces:
|
||||
receivers: [otlp, jaeger, zipkin]
|
||||
processors: [batch, adaptive_sampling]
|
||||
exporters: [jaeger_storage_exporter]
|
||||
telemetry:
|
||||
resource:
|
||||
service.name: jaeger
|
||||
metrics:
|
||||
level: detailed
|
||||
readers:
|
||||
- pull:
|
||||
exporter:
|
||||
prometheus:
|
||||
host: 0.0.0.0
|
||||
port: 8888
|
||||
logs:
|
||||
level: debug
|
||||
# TODO Initialize telemetry tracer once OTEL released new feature.
|
||||
# https://github.com/open-telemetry/opentelemetry-collector/issues/10663
|
||||
|
||||
extensions:
|
||||
healthcheckv2:
|
||||
use_v2: true
|
||||
http:
|
||||
|
||||
# pprof:
|
||||
# endpoint: 0.0.0.0:1777
|
||||
# zpages:
|
||||
# endpoint: 0.0.0.0:55679
|
||||
|
||||
jaeger_query:
|
||||
storage:
|
||||
traces: some_store
|
||||
traces_archive: another_store
|
||||
ui:
|
||||
config_file: ./cmd/jaeger/config-ui.json
|
||||
# The maximum duration that is considered for clock skew adjustments.
|
||||
# Defaults to 0 seconds, which means it's disabled.
|
||||
max_clock_skew_adjust: 0s
|
||||
|
||||
jaeger_storage:
|
||||
backends:
|
||||
some_store:
|
||||
memory:
|
||||
max_traces: 100000
|
||||
another_store:
|
||||
memory:
|
||||
max_traces: 100000
|
||||
|
||||
remote_sampling:
|
||||
# You can either use file or adaptive sampling strategy in remote_sampling
|
||||
# file:
|
||||
# path: ./cmd/jaeger/sampling-strategies.json
|
||||
adaptive:
|
||||
sampling_store: some_store
|
||||
initial_sampling_probability: 0.1
|
||||
http:
|
||||
grpc:
|
||||
|
||||
receivers:
|
||||
otlp:
|
||||
protocols:
|
||||
grpc:
|
||||
http:
|
||||
|
||||
jaeger:
|
||||
protocols:
|
||||
grpc:
|
||||
thrift_binary:
|
||||
thrift_compact:
|
||||
thrift_http:
|
||||
|
||||
zipkin:
|
||||
|
||||
processors:
|
||||
batch:
|
||||
# Adaptive Sampling Processor is required to support adaptive sampling.
|
||||
# It expects remote_sampling extension with `adaptive:` config to be enabled.
|
||||
adaptive_sampling:
|
||||
|
||||
exporters:
|
||||
jaeger_storage_exporter:
|
||||
trace_storage: some_store
|
||||
|
||||
@@ -0,0 +1,63 @@
|
||||
auth_enabled: false
|
||||
|
||||
server:
|
||||
http_listen_port: 3100
|
||||
grpc_listen_port: 9096
|
||||
log_level: debug
|
||||
grpc_server_max_concurrent_streams: 1000
|
||||
|
||||
common:
|
||||
instance_addr: 127.0.0.1
|
||||
path_prefix: /tmp/loki
|
||||
storage:
|
||||
filesystem:
|
||||
chunks_directory: /tmp/loki/chunks
|
||||
rules_directory: /tmp/loki/rules
|
||||
replication_factor: 1
|
||||
ring:
|
||||
kvstore:
|
||||
store: inmemory
|
||||
|
||||
query_range:
|
||||
results_cache:
|
||||
cache:
|
||||
embedded_cache:
|
||||
enabled: true
|
||||
max_size_mb: 100
|
||||
|
||||
limits_config:
|
||||
metric_aggregation_enabled: true
|
||||
|
||||
schema_config:
|
||||
configs:
|
||||
- from: 2020-10-24
|
||||
store: tsdb
|
||||
object_store: filesystem
|
||||
schema: v13
|
||||
index:
|
||||
prefix: index_
|
||||
period: 24h
|
||||
|
||||
pattern_ingester:
|
||||
enabled: true
|
||||
metric_aggregation:
|
||||
loki_address: localhost:3100
|
||||
|
||||
ruler:
|
||||
alertmanager_url: http://localhost:9093
|
||||
|
||||
frontend:
|
||||
encoding: protobuf
|
||||
|
||||
# By default, Loki will send anonymous, but uniquely-identifiable usage and configuration
|
||||
# analytics to Grafana Labs. These statistics are sent to https://stats.grafana.org/
|
||||
#
|
||||
# Statistics help us better understand how Loki is used, and they show us performance
|
||||
# levels for most users. This helps us prioritize features and documentation.
|
||||
# For more information on what's sent, look at
|
||||
# https://github.com/grafana/loki/blob/main/pkg/analytics/stats.go
|
||||
# Refer to the buildReport method to see what goes into a report.
|
||||
#
|
||||
# If you would like to disable reporting, uncomment the following lines:
|
||||
#analytics:
|
||||
# reporting_enabled: false
|
||||
@@ -0,0 +1,57 @@
|
||||
receivers:
|
||||
otlp:
|
||||
protocols:
|
||||
grpc: # OTLP gRPC 接收器
|
||||
endpoint: 0.0.0.0:4317
|
||||
http: # OTLP HTTP 接收器
|
||||
endpoint: 0.0.0.0:4318
|
||||
|
||||
processors:
|
||||
batch: # 批处理处理器，提升吞吐量
|
||||
timeout: 5s
|
||||
send_batch_size: 1000
|
||||
memory_limiter:
|
||||
check_interval: 1s
|
||||
limit_mib: 512
|
||||
|
||||
exporters:
|
||||
otlp/traces: # OTLP 导出器，用于跟踪数据
|
||||
endpoint: "jaeger:4317" # Jaeger 的 OTLP gRPC 端点
|
||||
tls:
|
||||
insecure: true # 开发环境禁用 TLS，生产环境需配置证书
|
||||
prometheus: # Prometheus 导出器，用于指标数据
|
||||
endpoint: "0.0.0.0:8889" # Prometheus 刮取端点
|
||||
namespace: "otel" # 指标前缀
|
||||
send_timestamps: true # 发送时间戳
|
||||
# enable_open_metrics: true
|
||||
loki: # Loki 导出器，用于日志数据
|
||||
# endpoint: "http://loki:3100/otlp/v1/logs"
|
||||
endpoint: "http://loki:3100/loki/api/v1/push"
|
||||
tls:
|
||||
insecure: true
|
||||
extensions:
|
||||
health_check:
|
||||
pprof:
|
||||
zpages:
|
||||
service:
|
||||
extensions: [health_check, pprof, zpages] # 启用扩展
|
||||
pipelines:
|
||||
traces:
|
||||
receivers: [otlp]
|
||||
processors: [memory_limiter,batch]
|
||||
exporters: [otlp/traces]
|
||||
metrics:
|
||||
receivers: [otlp]
|
||||
processors: [batch]
|
||||
exporters: [prometheus]
|
||||
logs:
|
||||
receivers: [otlp]
|
||||
processors: [batch]
|
||||
exporters: [loki]
|
||||
telemetry:
|
||||
logs:
|
||||
level: "info" # Collector 日志级别
|
||||
metrics:
|
||||
address: "0.0.0.0:8888" # Collector 自身指标暴露
|
||||
|
||||
|
||||
@@ -0,0 +1,11 @@
|
||||
global:
|
||||
scrape_interval: 5s # 刮取间隔
|
||||
|
||||
scrape_configs:
|
||||
- job_name: 'otel-collector'
|
||||
static_configs:
|
||||
- targets: ['otel-collector:8888'] # 从 Collector 刮取指标
|
||||
- job_name: 'otel-metrics'
|
||||
static_configs:
|
||||
- targets: ['otel-collector:8889'] # 应用指标
|
||||
|
||||
Reference in New Issue
Block a user