Merge pull request #279 from NethermindEth/feat/metrics

added metrics, migrated to Grafana Agent flow

.github/workflows/api-deploy.yml

@@ -94,7 +94,6 @@ jobs:
     runs-on: ubuntu-latest
     needs: Build
     steps:
-
       - name: Configure AWS credentials
         uses: aws-actions/configure-aws-credentials@v1
         with:
@@ -117,9 +116,14 @@ jobs:
           environment-variables: |
             RUST_LOG=INFO
             LOG_LEVEL=normal
+            ENVIRONMENT=dev
+            METRICS_PORT=8001
             VITE_URL=https://cairo-remix-dev.nethermind.io
+            SERVICE_VERSION=v${{ needs.Build.outputs.image-version }}
             PROMTAIL_USERNAME=${{secrets.PROMTAIL_USERNAME}}
             PROMTAIL_PASSWORD=${{secrets.PROMTAIL_PASSWORD}}
+            PROMETHEUS_USERNAME=${{secrets.PROMETHEUS_USERNAME}}
+            PROMETHEUS_PASSWORD=${{secrets.PROMETHEUS_PASSWORD}}
 
       - name: Deploy Amazon ECS task definition
         uses: aws-actions/amazon-ecs-deploy-task-definition@v1
@@ -133,7 +137,6 @@ jobs:
     runs-on: ubuntu-latest
     needs: Build
     steps:
-
       - name: Configure AWS credentials
         uses: aws-actions/configure-aws-credentials@v1
         with:
@@ -156,9 +159,14 @@ jobs:
           environment-variables: |
             RUST_LOG=INFO
             LOG_LEVEL=normal
+            ENVIRONMENT=prod
+            METRICS_PORT=8001
             VITE_URL=https://cairo-remix-dev.nethermind.io
+            SERVICE_VERSION=v${{ needs.Build.outputs.image-version }}
             PROMTAIL_USERNAME=${{secrets.PROMTAIL_USERNAME}}
             PROMTAIL_PASSWORD=${{secrets.PROMTAIL_PASSWORD}}
+            PROMETHEUS_USERNAME=${{secrets.PROMETHEUS_USERNAME}}
+            PROMETHEUS_PASSWORD=${{secrets.PROMETHEUS_PASSWORD}}
 
       - name: Deploy Amazon ECS task definition
         uses: aws-actions/amazon-ecs-deploy-task-definition@v1

.github/workflows/prod-build-and-deploy.yml

@@ -132,9 +132,14 @@ jobs:
           # inject the expected React package URL for CORS logic
           environment-variables: |
             RUST_LOG=INFO
+            ENVIRONMENT=dev
+            METRICS_PORT=8001
             VITE_URL=https://cairo-remix.nethermind.io
+            SERVICE_VERSION=v${{ needs.Build.outputs.image-version }}
             PROMTAIL_USERNAME=${{secrets.PROMTAIL_USERNAME}}
             PROMTAIL_PASSWORD=${{secrets.PROMTAIL_PASSWORD}}
+            PROMETHEUS_USERNAME=${{secrets.PROMETHEUS_USERNAME}}
+            PROMETHEUS_PASSWORD=${{secrets.PROMETHEUS_PASSWORD}}
 
       - name: Deploy Amazon ECS task definition
         uses: aws-actions/amazon-ecs-deploy-task-definition@v1

DockerfileRocket

@@ -5,7 +5,6 @@ ARG SCARB_VERSION
 ENV DEBIAN_FRONTEND=noninteractive
 ENV DEBCONF_NONINTERACTIVE_SEEN=true
 ENV SCARB_VERSION=${SCARB_VERSION}
-
 RUN apt-get clean
 
 RUN apt-get update
@@ -24,8 +23,7 @@ RUN wget -q -O - https://apt.grafana.com/gpg.key | gpg --dearmor | tee /etc/apt/
 RUN echo "deb [signed-by=/etc/apt/keyrings/grafana.gpg] https://apt.grafana.com stable main" | tee -a /etc/apt/sources.list.d/grafana.list
 
 RUN apt-get update
-
-RUN apt-get install grafana-agent
+RUN apt-get install grafana-agent-flow
 
 WORKDIR /opt/app
 
@@ -35,15 +33,13 @@ SHELL ["/bin/bash", "-lc"]
 RUN curl --proto '=https' --tlsv1.2 -sSf https://docs.swmansion.com/scarb/install.sh | bash -s -- -v $SCARB_VERSION
 ENV PATH="/root/.local/bin:${PATH}"
 
-# copy Remix plugin source and install Rust
-COPY . /opt/app
-
+# Install Rust
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- --default-toolchain stable -y
-
 RUN whoami
-
 ENV PATH="/root/.cargo/bin:${PATH}"
 
+# copy Remix plugin source
+COPY . /opt/app
 RUN git submodule update --init
 
 # Build the API service

api/Cargo.toml

@@ -6,6 +6,7 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+anyhow = "1.0.91"
 rocket = { version = "0.5.1", features = ["json"] }
 serde = { version = "1.0.189", features = ["derive"] }
 tracing = "^0.1"
@@ -17,4 +18,5 @@ crossbeam-queue = "0.3.8"
 crossbeam-skiplist = "0.1.1"
 fmt = "0.1.0"
 thiserror = "1.0.50"
-chrono = "0.4.31"
+chrono = "0.4.31"
+prometheus = "0.13.4"

api/configs/grafana-logs.config.river

@@ -0,0 +1,52 @@
+local.file_match "logs" {
+	path_targets = [{
+		__address__ = "localhost",
+        __path__    = env("PROMTAIL_BASE_DIR") + "/logs/*",
+		host        = "localhost",
+		job         = "starknet-remix-docker-logs",
+	}]
+}
+
+loki.source.file "logs" {
+    targets = local.file_match.logs.targets
+    forward_to = [loki.write.logs.receiver]
+}
+
+loki.write "logs" {
+    external_labels = {
+        environment = env("ENVIRONMENT"),
+        service_version = env("SERVICE_VERSION"),
+    }
+    endpoint {
+        url = "https://logs-prod-us-central1.grafana.net/loki/api/v1/push"
+        basic_auth {
+          username = env("PROMTAIL_USERNAME")
+          password = env("PROMTAIL_PASSWORD")
+        }
+    }
+}
+
+prometheus.remote_write "metrics" {
+    endpoint {
+        name = "starknet-remix-metrics"
+        url = "https://prometheus-us-central1.grafana.net/api/prom/push"
+
+        basic_auth {
+            username = env("PROMETHEUS_USERNAME")
+            password = env("PROMETHEUS_PASSWORD")
+        }
+    }
+}
+
+prometheus.scrape "metrics" {
+    targets = [{
+        __address__ = "localhost:" + env("METRICS_PORT"),
+        __metrics_path__ = "/metrics",
+        environment = env("ENVIRONMENT"),
+        service_version = env("SERVICE_VERSION"),
+    }]
+    forward_to = [prometheus.remote_write.metrics.receiver]
+
+    job_name = "starknet-remix-metrics-job"
+    scrape_interval = "30s"
+}

api/docker_run.sh

@@ -2,8 +2,18 @@
 
 # Note: This script needs to run from inside /api dir
 export PROMTAIL_BASE_DIR=$(pwd)  
+export METRICS_PORT=${METRICS_PORT-8001}
 
+if [ -z ${ENVIRONMENT} ]; then
+  echo "ENVIRONMENT env var undefined"
+  exit 1
+fi
 
-grafana-agent --config.expand-env=true --config.file ./configs/grafana-logs.config.yaml &
+if [ -z ${SERVICE_VERSION} ]; then
+  echo "SERVICE_VERSION env var undefined"
+  exit 1
+fi
+
+grafana-agent-flow run ./configs/grafana-logs.config.river &
 
 cargo run --release

api/example.env

@@ -1,2 +1,6 @@
+VITE_URL=http://localhost:3000
+METRICS_PORT=8001
 PROMTAIL_USERNAME=LOKI_Grafana_Username
-PROMTAIL_PASSWORD=LOKI_Grafana_password_API_Key
+PROMTAIL_PASSWORD=LOKI_Grafana_password_API_Key
+PROMETHEUS_USERNAME=PROMETHEUS_Grafana_Username
+PROMETHEUS_PASSWORD=PROMETHEUS_Grafana_password_API_Key

api/src/types.rs → api/src/errors.rs

@@ -1,7 +1,5 @@
 use std::io::Error as IoError;
 
-pub type Result<T> = std::result::Result<T, ApiError>;
-
 #[derive(Debug, thiserror::Error)]
 pub enum ApiError {
     #[error("Failed to execute command: {0}")]
@@ -35,3 +33,5 @@ pub enum ApiError {
     #[error("Error while trying to unlock mutex")]
     MutexUnlockError,
 }
+
+pub type Result<T, E = ApiError> = std::result::Result<T, E>;

api/src/handlers/cairo_version.rs

@@ -1,23 +1,26 @@
+use rocket::tokio::fs::read_dir;
+use rocket::State;
+use std::path::Path;
+use std::process::{Command, Stdio};
+use tracing::{error, info, instrument};
+
+use crate::errors::{ApiError, Result};
 use crate::handlers::process::{do_process_command, fetch_process_result};
 use crate::handlers::types::{ApiCommand, ApiCommandResult};
 use crate::rate_limiter::RateLimited;
-use crate::types::{ApiError, Result};
-use crate::utils::lib::DEFAULT_CAIRO_DIR;
+use crate::utils::lib::{CAIRO_COMPILERS_DIR, DEFAULT_CAIRO_DIR};
 use crate::worker::WorkerEngine;
-use rocket::State;
-use std::process::{Command, Stdio};
-use tracing::{error, info, instrument};
 
 // Read the version from the cairo Cargo.toml file.
-#[instrument]
+#[instrument(skip(_rate_limited))]
 #[get("/cairo_version")]
 pub async fn cairo_version(_rate_limited: RateLimited) -> String {
     info!("/cairo_version");
     do_cairo_version().unwrap_or_else(|e| format!("Failed to get cairo version: {:?}", e))
 }
 
 // Read the version from the cairo Cargo.toml file.
-#[instrument]
+#[instrument(skip(engine, _rate_limited))]
 #[get("/cairo_version_async")]
 pub async fn cairo_version_async(
     engine: &State<WorkerEngine>,
@@ -27,7 +30,7 @@ pub async fn cairo_version_async(
     do_process_command(ApiCommand::CairoVersion, engine)
 }
 
-#[instrument]
+#[instrument(skip(engine))]
 #[get("/cairo_version_result/<process_id>")]
 pub async fn get_cairo_version_result(process_id: String, engine: &State<WorkerEngine>) -> String {
     fetch_process_result(process_id, engine, |result| match result {
@@ -66,3 +69,29 @@ pub fn do_cairo_version() -> Result<String> {
         }
     }
 }
+
+#[instrument]
+#[get("/cairo_versions")]
+pub async fn cairo_versions() -> String {
+    do_cairo_versions()
+        .await
+        .unwrap_or_else(|e| format!("Failed to get cairo versions: {:?}", e))
+}
+
+/// Get cairo versions
+pub async fn do_cairo_versions() -> crate::errors::Result<String> {
+    let path = Path::new(CAIRO_COMPILERS_DIR);
+
+    let mut dir = read_dir(path).await.map_err(ApiError::FailedToReadDir)?;
+    let mut result = vec![];
+
+    while let Ok(Some(entry)) = dir.next_entry().await {
+        let entry = entry;
+        let path = entry.path();
+        if path.is_dir() {
+            result.push(entry.file_name().to_string_lossy().to_string());
+        }
+    }
+
+    Ok(format!("{:?}", result))
+}