Merge branch 'develop' into develop

Author: FriendlyCM

.gitignore

@@ -25,6 +25,7 @@ go
 gopath
 go1.*
 *FullNode_output-directory*
+*.pub
 
 /single_node/output-directory/
 /metric_monitor/logs/
@@ -38,5 +39,4 @@ go1.*
 /metric_monitor/helm-charts/thanos-receive/charts/
 /metric_monitor/helm-charts/thanos-receive/Chart.lock
 /metric_monitor/store-data/
-
-*.pub
+/metric_monitor/grafana_data/

README.md

@@ -26,6 +26,7 @@ We also provide tools to facilitate the CI and testing process:
   - `root`: compute merkle root for tiny db. NOTE: large db may GC overhead
   limit exceeded.
   - `fork`: Modify the database of java-tron for shadow fork testing.
+  - `query`: Query the latest vote and reward information from the database.
 - **Stress Test**: Execute the stress test and evaluate the performance of the `java-tron` fullnode.
 
 

conf/private_net_layout.toml

@@ -1,10 +1,8 @@
-# [database]
-# database_tar = "/path/to/database"
-
 # [[nodes]]
 # node_ip = "192.168.1.1" # Remote node's IP
-# node_direcotry = "/path/to/direcotry" # Remote node's working direcotry for node
+# node_directory = "/path/to/direcotry" # Remote node's working direcotry for node
 # config_file = "/path/to/config" # Config file for remote node
+# docker_compose_file =”/path/to/config“ # Config  docker-compose  file for remote node
 # node_type = "fullnode/sr" # Fullnode or SR node
 # ssh_port = 22
 # ssh_user = "user1"
@@ -13,22 +11,21 @@
 
 # [[nodes]]
 # node_ip = "192.168.1.2"  # Changed IP to demonstrate different nodes
-# node_direcotry = "/path/to/direcotry"
+# node_directory = "/path/to/directory"
 # config_file = "/path/to/config"
+# docker_compose_file =”/path/to/config“ # Config  docker-compose  file for remote node
 # node_type = "fullnode/sr"
 # ssh_port = 2222  # Custom SCP port for this node
 # ssh_user = "user2"
 # # No password or key; assumes SSH agent or pre-configured key
 
-[database]
-database_tar = "/Users/barbatos/Downloads/hello.tgz"
 
 [[nodes]]
 node_ip = "ec2-3-25-116-244.ap-southeast-2.compute.amazonaws.com"
-node_direcotry = "/home/ubuntu/mytest"
-config_file = "/Users/barbatos/Documents/code/md/mydev/tron-docker/conf/private_net_config_others.conf"
-node_type = "fullnode"
+node_directory = "/home/ubuntu/mytest"
+config_file = "/Users/ubuntu/conf/private_net_config_others.conf"
+docker_compose_file = "/Users/ubuntu/docker-compose.yml"
 ssh_port = 22
 ssh_user = "ubuntu"
 # ssh_password = "password1"
-ssh_key = "/Users/barbatos/Downloads/test-ci.pem"  # Optional; uncomment if using key auth
+ssh_key = "/Users/ubuntu/Downloads/test-ci.pem"  # Optional; uncomment if using key auth

metric_monitor/REMOTE_WRITE_WITH_THANOS.md

@@ -45,7 +45,11 @@ As shown in the new architecture, the monitoring system consists of the followin
 ### Step 1: Set up TRON and Prometheus services
 Run the below command to start a java-tron FullNode, node exporter and Prometheus services:
 ```sh
-docker-compose -f ./docker-compose/docker-compose-target-node.yml up -d
+docker-compose -f ./docker-compose/docker-compose-target-node.yml up -d # Start all
+
+docker-compose -f ./docker-compose/docker-compose-target-node.yml up -d tron-node # Start tron-node only
+docker-compose -f ./docker-compose/docker-compose-target-node.yml up -d node-exporter # Start node-exporter only
+docker-compose -f ./docker-compose/docker-compose-target-node.yml up -d prometheus # Start prometheus only
 ```
 
 You can verify the Prometheus service status and monitor targets by accessing `http://[host_IP]:9090/` in your browser. Alternatively, use `docker logs -f prometheus` to view the Prometheus service logs.
@@ -108,7 +112,7 @@ remote_write:
     <img src="../images/metric_push_external_label.png" alt="Alt Text" width="680" >
 
 - For `scrape_configs`:
-  - The `scrape_interval` defines the frequency at which Prometheus collects metrics. While configured for 1-second intervals to enable real-time monitoring, this setting can be customized according to your specific monitoring needs. Keep in mind that decreasing the interval will increase the service load, as metrics are collected each time the HTTP request triggered.
+  - The `scrape_interval` defines the frequency at which Prometheus collects metrics. While configured for 3-second intervals to enable real-time monitoring, this setting can be customized according to your specific monitoring needs. Keep in mind that decreasing the interval will increase the service load, as metrics are collected each time the HTTP request triggered.
   - The `targets` field specifies the java-tron services or other monitoring targets via their IP addresses and ports. Prometheus actively scrapes metrics from these defined endpoints.
   - The `labels` section contains key-value pairs that uniquely identify each target within Prometheus. These labels enable powerful filtering capabilities in Grafana dashboards - for example, you can filter metrics using expressions like `{group="group-tron"}`.
 
@@ -119,7 +123,7 @@ remote_write:
 ##### 2. Storage configurations
 - The volumes command `../prometheus_data:/prometheus` mounts a local directory used by Prometheus to store metrics data.
   - Even when using Prometheus with remote-write, metrics data is still temporarily stored locally.
-- The `--storage.tsdb.retention.time=7d` flag defines how long metrics data is retained. In this case, Prometheus automatically purges data older than 7 days. For a java-tron(v4.7.6+) FullNode, each metric request returns approximately 9KB of raw data. With a `scrape_interval` of 1 second and TSDB compression, **a single java-tron FullNode service requires about 2GB of Prometheus storage with 7 days of retention**.
+- The `--storage.tsdb.retention.time=7d` flag defines how long metrics data is retained. In this case, Prometheus automatically purges data older than 7 days. For a java-tron(v4.7.6+) FullNode, each metric request returns approximately 9KB of raw data. With a `scrape_interval` of 3 second and TSDB compression, **a single java-tron FullNode service requires about 700MB of Prometheus storage with 7 days of retention**.
 - The `--storage.tsdb.max-block-duration=30m` flag defines the maximum duration for generating TSDB blocks locally. With this setting, Prometheus will create new TSDB blocks at intervals no longer than 30 minutes, ensuring regular data persistence and efficient storage management.
 - Other storage flags can be found in the [official documentation](https://prometheus.io/docs/prometheus/latest/storage/#operational-aspects). For a quick start, you could use the default values.
 
@@ -146,7 +150,7 @@ docker-compose -f ./docker-compose/thanos-receive.yml up -d
 As Promethus has already been configured to send metric metadata to Thanos Receive, check the logs to ensure the Thanos Receive is running properly.
 
 ```sh
-docker logs -f thanos-receive-0
+docker logs -f thanos-receive
 
 ...
 ts=2025-04-03T03:13:49.395927626Z caller=intrumentation.go:56 level=info component=receive msg="changing probe status" status=ready
@@ -176,16 +180,16 @@ Core configuration for Thanos Receive in [thanos-receive.yml](./docker-compose/t
       - "--remote-write.address=0.0.0.0:10908"
       - "--label=receive_replica=\"0\""
       - "--label=receive_cluster=\"java-tron-mainnet\""
-      - "--objstore.config-file=/receive/bucket_storage_bucket.yml"
+      - "--objstore.config-file=/receive/bucket_storage.yml"
 ```
 #### Key configuration elements:
 ##### 1. Storage configuration
 - Local Storage:
   `../receive-data:/receive/data` maps the host directory for metric TSDB storage.
-  - Retention Policy: `--tsdb.retention=30d` auto-purges data older than 30 days. As tested, it takes about **6GB of disk space per month for one java-tron(v4.7.6+) FullNode**.
+  - Retention Policy: The `--tsdb.retention=30d` flag automatically purges data older than 30 days. Based on testing with a java-tron(v4.7.6+) FullNode using a 3-second metric scrape interval, storage consumption averages approximately **3GB of disk space per month**.
 
 - External Storage:
-  `../conf:/receive` mounts configuration files. The `--objstore.config-file` flag enables long-term storage in MinIO/S3-compatible buckets. In this case, it is [bucket_storage_bucket.yml](conf/bucket_storage_bucket.yml).
+  `../conf:/receive` mounts configuration files. The `--objstore.config-file` flag enables long-term storage in MinIO/S3-compatible buckets. In this case, it is [bucket_storage.yml](conf/bucket_storage.yml).
   - Thanos Receive uploads TSDB blocks to an object storage bucket every 2 hours by default.
   - Fallback Behavior: Omitting this flag keeps data local-only.
 
@@ -229,12 +233,12 @@ Core configuration in [thanos-store.yml](./docker-compose/thanos-store.yml):
   thanos_store:
     command:
       - "store"
-      - "--objstore.config-file=/etc/thanos/bucket_storage_bucket.yml"
+      - "--objstore.config-file=/etc/thanos/bucket_storage.yml"
       - "--grpc-address=0.0.0.0:10912"
 ```
 The Store gateway:
 
-- Connects to our Minio bucket via `bucket_storage_bucket.yml`, the same configuration file as Thanos Receive.
+- Connects to our Minio bucket via `bucket_storage.yml`, the same configuration file as Thanos Receive.
 - Exposes gRPC endpoint for Thanos Query to access historical data
 - Indexes object storage blocks for fast lookups
 
@@ -259,7 +263,7 @@ ts=2025-04-03T05:37:53.676072548Z caller=intrumentation.go:56 level=info msg="ch
 ts=2025-04-03T05:37:53.676288048Z caller=tls_config.go:274 level=info service=http/server component=query msg="Listening on" address=[::]:9091
 ts=2025-04-03T05:37:53.676313173Z caller=tls_config.go:277 level=info service=http/server component=query msg="TLS is disabled." http2=false address=[::]:9091
 ts=2025-04-03T05:37:53.676380298Z caller=grpc.go:131 level=info service=gRPC/server component=query msg="listening for serving gRPC" address=0.0.0.0:10901
-ts=2025-04-03T05:37:58.685901342Z caller=endpointset.go:425 level=info component=endpointset msg="adding new receive with [storeEndpoints exemplarsAPI]" address=thanos-receive-0:10907 extLset="{receive_cluster=\"java-tron-mainnet\", receive_replica=\"0\", tenant_id=\"default-tenant\"}"
+ts=2025-04-03T05:37:58.685901342Z caller=endpointset.go:425 level=info component=endpointset msg="adding new receive with [storeEndpoints exemplarsAPI]" address=thanos-receive:10907 extLset="{receive_cluster=\"java-tron-mainnet\", receive_replica=\"0\", tenant_id=\"default-tenant\"}"
 ts=2025-04-03T05:37:58.685969217Z caller=endpointset.go:425 level=info component=endpointset msg="adding new store with [storeEndpoints]" address=thanos-store:10912 extLset="{receive_cluster=\"java-tron-mainnet\", receive_replica=\"0\", tenant_id=\"default-tenant\"}"
 ...
 ```
@@ -275,7 +279,7 @@ Below are the core configurations for the Thanos Query service:
       - --endpoint.info-timeout=30s
       - --http-address=0.0.0.0:9091
       - --query.replica-label=receive_replica # Deduplication turned on for metric with the same replica_label
-      - --endpoint=thanos-receive-0:10907 # The grpc-address of the Thanos Receive service，if Receive run remotely replace container name "thanos-receive" with the real ip, could add multiple receive services
+      - --endpoint=thanos-receive:10907 # The grpc-address of the Thanos Receive service，if Receive run remotely replace container name "thanos-receive" with the real ip, could add multiple receive services
       - --store=thanos-store:10907 # for historical data query
 ```
 It will set up the Thanos Query service

…c_monitor/conf/bucket_storage_bucket.yml metric_monitor/conf/bucket_storage.ymlmetric_monitor/conf/bucket_storage_bucket.yml renamed to metric_monitor/conf/bucket_storage.yml metric_monitor/conf/bucket_storage_bucket.yml renamed to metric_monitor/conf/bucket_storage.yml

@@ -9,8 +9,8 @@ global:
 scrape_configs:
   - job_name: java-tron
     honor_timestamps: true
-    scrape_interval: 1s
-    scrape_timeout: 1s
+    scrape_interval: 3s
+    scrape_timeout: 3s
     metrics_path: /metrics
     scheme: http
     follow_redirects: true
@@ -29,20 +29,19 @@ scrape_configs:
 # The remote_write configuration tells Prometheus to continuously write metrics to the Thanos Receive service.
 # Refer https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write
 remote_write:
-  - url: http://thanos-receive-0:10908/api/v1/receive # if Thanos Receive service run on the same host with Prometheus
+  - url: http://thanos-receive:10908/api/v1/receive # if Thanos Receive service run on the same host with Prometheus
     headers:
-      X-Auth-Token: "token"
       X-Service-Group: "tron-fullnode-group1"
-    remote_timeout: 10s
+    remote_timeout: 15s
     queue_config:
-      capacity: 2500
+      capacity: 50000
       max_shards: 200 # the maximum number of shards, or parallelism, Prometheus will use for each remote-write queue
       min_shards: 1
-      max_samples_per_send: 500
-      batch_send_deadline: 5s
-      min_backoff: 30ms
+      max_samples_per_send: 10000
+      batch_send_deadline: 3s
+      min_backoff: 200ms
       max_backoff: 5s
     metadata_config:
       send: true
-      send_interval: 1s # How frequently metric metadata is sent to remote storage.
-      max_samples_per_send: 500
+      send_interval: 3s # How frequently metric metadata is sent to remote storage.
+      max_samples_per_send: 50000

metric_monitor/conf/prometheus-remote-write.yml

@@ -10,6 +10,9 @@ services:
           memory: 1g
     environment:
       - GF_METRICS_ENABLED=true  # Enable Grafana metrics exposure
+      - GF_SERVER_HTTP_PORT=3000  # Set Grafana's internal port to 3000
+    volumes:
+      - ../grafana_data:/var/lib/grafana  # Grafana database and dashboards
     ports:
       - "3000:3000"
     restart: unless-stopped

metric_monitor/docker-compose/grafana.yml

@@ -11,7 +11,7 @@ services:
       - --endpoint.info-timeout=10s
       - --http-address=0.0.0.0:9091
       - --query.replica-label=receive_replica # Deduplication turned on for identical series except the replica label.
-      - --endpoint=thanos-receive-0:10907
+      - --endpoint=thanos-receive:10907
       #- --endpoint=thanos-receive-1:10907 # could add multiple receive services
       - --store=thanos-store:10912 # for historical data query
     restart: unless-stopped

metric_monitor/docker-compose/thanos-querier.yml

@@ -3,7 +3,7 @@ services:
   thanos-receive:
     image: quay.io/thanos/thanos:v0.33.0
     user: root
-    container_name: thanos-receive-0
+    container_name: thanos-receive
     volumes:
       - ../receive-data-0:/receive/data
       - ../conf:/receive
@@ -20,5 +20,5 @@ services:
       - "--remote-write.address=0.0.0.0:10908"
       - "--label=receive_replica=\"0\""
       - "--label=receive_cluster=\"java-tron-mainnet\""
-      - "--objstore.config-file=/receive/bucket_storage_bucket.yml"
+      - "--objstore.config-file=/receive/bucket_storage.yml"
     restart: unless-stopped

metric_monitor/docker-compose/thanos-receive.yml

@@ -13,7 +13,7 @@ services:
     command:
       - "store"
       - "--data-dir=/var/thanos/store"
-      - "--objstore.config-file=/etc/thanos/bucket_storage_bucket.yml"
+      - "--objstore.config-file=/etc/thanos/bucket_storage.yml"
       - "--http-address=0.0.0.0:10911"
       - "--grpc-address=0.0.0.0:10912"
     restart: unless-stopped