feat(obs): improve telemetry stack, replication metrics, and Grafana alignment (#2672)

Co-authored-by: Filipe Monteiro <a22407332@alunos.ulht.pt>
Co-authored-by: cxymds <Cxymds@qq.com>
Co-authored-by: weisd <im@weisd.in>
Co-authored-by: loverustfs <hello@rustfs.com>
Co-authored-by: 安正超 <anzhengchao@gmail.com>

.docker/observability/README.md

@@ -13,6 +13,9 @@ The stack is composed of the following best-in-class open-source components:
 - **Jaeger** (v1.59.0): Distributed tracing system (configured as a secondary UI/storage).
 - **OpenTelemetry Collector** (v0.104.0): A vendor-agnostic implementation for receiving, processing, and exporting telemetry data.
 
+By default, this stack uses Tempo in single-binary mode and does not require Kafka/Redpanda.
+If you want the Kafka-backed HA Tempo path, use `docker-compose-example-for-rustfs.yml` together with `docker-compose-tempo-ha-override.yml`.
+
 ## Architecture
 
 1. **Telemetry Collection**: Applications send OTLP (OpenTelemetry Protocol) data (Metrics, Logs, Traces) to the **OpenTelemetry Collector**.
@@ -46,6 +49,15 @@ Run the following command to start the entire stack:
 docker compose up -d
 ```
 
+### High Availability Tempo
+
+The default `docker-compose.yml` is the single-node stack.
+If you need the Kafka-backed HA Tempo configuration, start it with:
+
+```bash
+docker compose -f docker-compose-example-for-rustfs.yml -f docker-compose-tempo-ha-override.yml up -d
+```
+
 ### Access Dashboards
 
 | Service        | URL                                              | Credentials       | Description                    |

.docker/observability/README_ZH.md

@@ -13,6 +13,9 @@
 - **Jaeger** (v1.59.0): 分布式追踪系统（配置为辅助 UI/存储）。
 - **OpenTelemetry Collector** (v0.104.0): 接收、处理和导出遥测数据的供应商无关实现。
 
+默认情况下，这套技术栈使用 Tempo 单二进制模式，不依赖 Kafka/Redpanda。
+如果需要基于 Kafka 的 HA Tempo 路径，请使用 `docker-compose-example-for-rustfs.yml` 配合 `docker-compose-tempo-ha-override.yml`。
+
 ## 架构
 
 1.  **遥测收集**: 应用程序将 OTLP (OpenTelemetry Protocol) 数据（指标、日志、追踪）发送到 **OpenTelemetry Collector**。
@@ -46,6 +49,15 @@
 docker compose up -d
 ```
 
+### Tempo 高可用模式
+
+默认的 `docker-compose.yml` 对应单机栈。
+如果需要基于 Kafka 的 HA Tempo 配置，请使用：
+
+```bash
+docker compose -f docker-compose-example-for-rustfs.yml -f docker-compose-tempo-ha-override.yml up -d
+```
+
 ### 访问仪表盘
 
 | 服务 | URL | 凭据 | 描述 |

.docker/observability/docker-compose-example-for-rustfs.yml

@@ -85,10 +85,8 @@ services:
     networks:
       - otel-network
     restart: unless-stopped
-    depends_on:
-      - redpanda
     healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3200/ready" ]
+      test: [ "CMD", "/tempo", "-version" ]
       interval: 10s
       timeout: 5s
       retries: 3
@@ -205,7 +203,7 @@ services:
       - prometheus
       - loki
     healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:13133" ]
+      test: [ "CMD", "/otelcol-contrib", "--version" ]
       interval: 10s
       timeout: 5s
       retries: 3

.docker/observability/docker-compose.yml

@@ -16,10 +16,8 @@ services:
 
   # --- Tracing ---
   tempo:
-    image: grafana/tempo:2.10.3
+    image: grafana/tempo:2.10.5
     container_name: tempo
-    depends_on:
-      - redpanda
     command: [ "-config.file=/etc/tempo.yaml" ]
     volumes:
       - ./tempo.yaml:/etc/tempo.yaml:ro
@@ -33,31 +31,11 @@ services:
       - otel-network
     restart: unless-stopped
     healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3200/ready" ]
+      test: [ "CMD", "/tempo", "-version" ]
       interval: 10s
       timeout: 5s
       retries: 3
       start_period: 15s
-  redpanda:
-    image: redpandadata/redpanda:latest
-    ports:
-      - "9092:9092" # Kafka API for clients
-    command: >
-      redpanda start --overprovisioned
-      --mode=dev-container
-      --kafka-addr=PLAINTEXT://0.0.0.0:9092
-      --advertise-kafka-addr=PLAINTEXT://redpanda:9092
-
-  redpanda-console:
-    image: docker.redpanda.com/redpandadata/console:latest
-    environment:
-      - CONFIG_FILEPATH=/etc/redpanda/redpanda-console-config.yaml
-    volumes:
-      - ./redpanda-console.yaml:/etc/redpanda/redpanda-console-config.yaml
-    ports:
-      - "8080:8080"
-    depends_on:
-      - redpanda
 
   vulture:
     image: grafana/tempo-vulture:latest
@@ -168,7 +146,7 @@ services:
       - prometheus
       - loki
     healthcheck:
-      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:13133" ]
+      test: [ "CMD", "/otelcol-contrib", "--version" ]
       interval: 10s
       timeout: 5s
       retries: 3

.docker/observability/grafana/provisioning/datasources.yaml

@@ -1,97 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-apiVersion: 1
-
-datasources:
-  - name: Prometheus
-    type: prometheus
-    uid: prometheus
-    access: proxy
-    orgId: 1
-    url: http://prometheus:9090
-    isDefault: true
-    version: 1
-    editable: false
-    jsonData:
-      httpMethod: GET
-      exemplarTraceIdDestinations:
-        - name: trace_id
-          datasourceUid: tempo
-
-  - name: Tempo
-    type: tempo
-    uid: tempo
-    access: proxy
-    orgId: 1
-    url: http://tempo:3200
-    isDefault: false
-    version: 1
-    editable: false
-    jsonData:
-      httpMethod: GET
-      serviceMap:
-        datasourceUid: prometheus
-      tracesToLogs:
-        datasourceUid: loki
-        tags: [ 'job', 'instance', 'pod', 'namespace', 'service.name' ]
-        mappedTags: [ { key: 'service.name', value: 'app' } ]
-        spanStartTimeShift: '1s'
-        spanEndTimeShift: '-1s'
-        filterByTraceID: true
-        filterBySpanID: false
-      tracesToMetrics:
-        datasourceUid: prometheus
-        tags: [ { key: 'service.name' }, { key: 'job' } ]
-        queries:
-          - name: 'Service-Level Latency'
-            query: 'sum(rate(traces_spanmetrics_latency_bucket{$$__tags}[5m])) by (le)'
-          - name: 'Service-Level Calls'
-            query: 'sum(rate(traces_spanmetrics_calls_total{$$__tags}[5m]))'
-          - name: 'Service-Level Errors'
-            query: 'sum(rate(traces_spanmetrics_calls_total{status_code="ERROR", $$__tags}[5m]))'
-      nodeGraph:
-        enabled: true
-
-  - name: Loki
-    type: loki
-    uid: loki
-    orgId: 1
-    url: http://loki:3100
-    isDefault: false
-    version: 1
-    editable: false
-    jsonData:
-      derivedFields:
-        - datasourceUid: tempo
-          matcherRegex: 'trace_id=(\w+)'
-          name: 'TraceID'
-          url: '$${__value.raw}'
-
-  - name: Jaeger
-    type: jaeger
-    uid: jaeger
-    url: http://jaeger:16686
-    access: proxy
-    isDefault: false
-    editable: false
-    jsonData:
-      tracesToLogs:
-        datasourceUid: loki
-        tags: [ 'job', 'instance', 'pod', 'namespace', 'service.name' ]
-        mappedTags: [ { key: 'service.name', value: 'app' } ]
-        spanStartTimeShift: '1s'
-        spanEndTimeShift: '-1s'
-        filterByTraceID: true
-        filterBySpanID: false

.docker/observability/tempo.yaml

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-partition_ring_live_store: true
 stream_over_http_enabled: true
 
 server:
@@ -33,33 +32,17 @@ distributor:
           endpoint: "0.0.0.0:4317"
         http:
           endpoint: "0.0.0.0:4318"
-  #log_received_spans:
-  #    enabled: true
-  #  log_discarded_spans:
-  #    enabled: true
 
-backend_scheduler:
-  provider:
-    compaction:
-      compaction:
-        block_retention: 1h
-
-backend_worker:
-  backend_scheduler_addr: localhost:3200
-  compaction:
-    block_retention: 1h
-  ring:
-    kvstore:
-      store: memberlist
-
-querier:
-  query_live_store: true
+ingester:
+  max_block_duration: 5m
 
 metrics_generator:
   registry:
     external_labels:
       source: tempo
       cluster: docker-compose
+  traces_storage:
+    path: /var/tempo/generator/traces
   storage:
     path: /var/tempo/generator/wal
     remote_write:
@@ -85,15 +68,5 @@ overrides:
       processors: [ "span-metrics", "service-graphs", "local-blocks" ]
       generate_native_histograms: both
 
-ingest:
-  enabled: true
-  kafka:
-    address: redpanda:9092
-    topic: tempo-ingest
-
-block_builder:
-  consume_cycle_duration: 30s
-
 usage_report:
   reporting_enabled: false
-