Update Grafana dashboard

matter-labs · Sep 27, 2023 · 41a3f88 · 41a3f88
1 parent d69d96a
commit 41a3f88
Show file tree

Hide file tree

Showing 3 changed files with 29 additions and 29 deletions.
diff --git a/grafana_dashboard.json b/grafana_dashboard.json
@@ -341,7 +341,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "avg(rate(network_rpc_message_size_sum{test_id=\"$test_id\",type=~\"req_sent|resp_sent\"}[1m])) by (type,method,submethod)",
+          "expr": "avg(rate(network_rpc_message_size_bytes_sum{test_id=\"$test_id\",type=~\"req_sent|resp_sent\"}[1m])) by (type,method,submethod)",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
@@ -352,7 +352,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "quantile(0.1, rate(concurrency_net_tcp__bytes_sent{test_id=\"$test_id\"}[1m]))",
+          "expr": "quantile(0.1, rate(concurrency_net_tcp_sent_bytes{test_id=\"$test_id\"}[1m]))",
           "hide": false,
           "legendFormat": "total, 10th percentile",
           "range": true,
@@ -364,7 +364,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "quantile(0.5, rate(concurrency_net_tcp__bytes_sent{test_id=\"$test_id\"}[1m]))",
+          "expr": "quantile(0.5, rate(concurrency_net_tcp_sent_bytes{test_id=\"$test_id\"}[1m]))",
           "hide": false,
           "legendFormat": "total, 50th percentile",
           "range": true,
@@ -376,7 +376,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "quantile(0.9, rate(concurrency_net_tcp__bytes_sent{test_id=\"$test_id\"}[1m]))",
+          "expr": "quantile(0.9, rate(concurrency_net_tcp_sent_bytes{test_id=\"$test_id\"}[1m]))",
           "hide": false,
           "legendFormat": "total, 90th percentile",
           "range": true,
@@ -388,7 +388,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "quantile(1., rate(concurrency_net_tcp__bytes_sent{test_id=\"$test_id\"}[1m]))",
+          "expr": "quantile(1., rate(concurrency_net_tcp_sent_bytes{test_id=\"$test_id\"}[1m]))",
           "hide": false,
           "legendFormat": "total, max",
           "range": true,
@@ -482,7 +482,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "rate(avg(network_rpc_latency_count{test_id=\"$test_id\",type=\"client_send_recv\"}) by (method,submethod) [1m])",
+          "expr": "rate(avg(network_rpc_latency_seconds_count{test_id=\"$test_id\",type=\"client_send_recv\"}) by (method,submethod) [1m])",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
@@ -569,7 +569,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "sum by(le) (rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"consensus\",type=\"client_send_recv\",submethod=\"LeaderPrepare\"}[1m]))",
+          "expr": "sum by(le) (rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"consensus\",type=\"client_send_recv\",submethod=\"LeaderPrepare\"}[1m]))",
           "format": "heatmap",
           "instant": false,
           "interval": "",
@@ -659,7 +659,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "sum by(le) (rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))",
+          "expr": "sum by(le) (rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))",
           "format": "heatmap",
           "instant": false,
           "interval": "",
@@ -755,7 +755,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "rate(max(executor_lib_io__finalized_block_number{test_id=\"$test_id\"})[1m])",
+          "expr": "rate(max(executor_finalized_block_number{test_id=\"$test_id\"})[1m])",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
@@ -847,7 +847,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "max(executor_lib_io__finalized_block_number{test_id=\"$test_id\"})",
+          "expr": "max(executor_finalized_block_number{test_id=\"$test_id\"})",
           "legendFormat": "__auto",
           "range": true,
           "refId": "max"
@@ -858,7 +858,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "min(executor_lib_io__finalized_block_number{test_id=\"$test_id\"})",
+          "expr": "min(executor_finalized_block_number{test_id=\"$test_id\"})",
           "hide": false,
           "legendFormat": "__auto",
           "range": true,
@@ -953,7 +953,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "avg(consensus_replica__view_timeout{test_id=\"$test_id\"})",
+          "expr": "avg(consensus_replica_view_timeout_seconds{test_id=\"$test_id\"})",
           "legendFormat": "avg",
           "range": true,
           "refId": "A"
@@ -964,7 +964,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "max(consensus_replica__view_timeout{test_id=\"$test_id\"})",
+          "expr": "max(consensus_replica_view_timeout_seconds{test_id=\"$test_id\"})",
           "hide": false,
           "legendFormat": "max",
           "range": true,
@@ -1044,7 +1044,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "sum(rate(consensus_leader__commit_phase_latency_bucket{test_id=\"$test_id\"}[1m])) by (le)",
+          "expr": "sum(rate(consensus_leader_commit_phase_latency_seconds_bucket{test_id=\"$test_id\"}[1m])) by (le)",
           "format": "heatmap",
           "legendFormat": "__auto",
           "range": true,
@@ -1139,7 +1139,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "rate(sum (consensus_leader__processing_latency_sum{test_id=\"$test_id\"}) by (type)[1m])/rate(sum (consensus_leader__processing_latency_count{test_id=\"$test_id\"}) by (type)[1m])",
+          "expr": "rate(sum (consensus_leader_processing_latency_seconds_sum{test_id=\"$test_id\"}) by (type)[1m])/rate(sum (consensus_leader_processing_latency_seconds_count{test_id=\"$test_id\"}) by (type)[1m])",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
@@ -1150,7 +1150,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "rate(sum (consensus_replica__processing_latency_sum{test_id=\"$test_id\"}) by (type)[1m])/rate(sum (consensus_replica__processing_latency_count{test_id=\"$test_id\"}) by (type)[1m])",
+          "expr": "rate(sum (consensus_replica_processing_latency_seconds_sum{test_id=\"$test_id\"}) by (type)[1m])/rate(sum (consensus_replica_processing_latency_seconds_count{test_id=\"$test_id\"}) by (type)[1m])",
           "hide": false,
           "legendFormat": "__auto",
           "range": true,
@@ -1527,7 +1527,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "sum(rate(concurrency_net_tcp__established{test_id=\"$test_id\",direction=\"inbound\"}[1m]))",
+          "expr": "sum(rate(concurrency_net_tcp_established{test_id=\"$test_id\",direction=\"inbound\"}[1m]))",
           "legendFormat": "new inbound",
           "range": true,
           "refId": "A"
@@ -1646,7 +1646,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "avg((min(histogram_quantile(0.8,rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))) by (instance))/(min(rate(consensus_leader__commit_phase_latency_sum{test_id=\"$test_id\"}[1m])/rate(consensus_leader__commit_phase_latency_count{test_id=\"$test_id\"}[1m])) by (instance)))",
+          "expr": "avg((min(histogram_quantile(0.8,rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))) by (instance))/(min(rate(consensus_leader_commit_phase_latency_seconds_sum{test_id=\"$test_id\"}[1m])/rate(consensus_leader_commit_phase_latency_seconds_count{test_id=\"$test_id\"}[1m])) by (instance)))",
           "hide": false,
           "legendFormat": "actual commit phase rate",
           "range": true,
@@ -1658,7 +1658,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "2*avg(histogram_quantile(0.8,rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m])))*rate(max(executor_lib_io__finalized_block_number{test_id=\"$test_id\"})[1m])",
+          "expr": "2*avg(histogram_quantile(0.8,rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m])))*rate(max(executor_finalized_block_number{test_id=\"$test_id\"})[1m])",
           "hide": false,
           "legendFormat": "actual block rate",
           "range": true,
@@ -1670,7 +1670,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "avg(2*histogram_quantile(0.8,rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))/(3*histogram_quantile(0.66,rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))))",
+          "expr": "avg(2*histogram_quantile(0.8,rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))/(3*histogram_quantile(0.66,rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))))",
           "hide": false,
           "legendFormat": "theoretical optimum for 2/3 signatures 3 roundtrips",
           "range": true,
@@ -1694,7 +1694,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "1/(\n    1/(avg(histogram_quantile(0.8,rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m])))*rate(max(executor_lib_io__finalized_block_number{test_id=\"$test_id\"})[1m]))\n-\n    1/avg((min(histogram_quantile(0.8,rate(network_rpc_latency_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))) by (instance))/(min(rate(consensus_leader__commit_phase_latency_sum{test_id=\"$test_id\"}[1m])/rate(consensus_leader__commit_phase_latency_count{test_id=\"$test_id\"}[1m])) by (instance)))\n)",
+          "expr": "1/(\n    1/(avg(histogram_quantile(0.8,rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m])))*rate(max(executor_finalized_block_number{test_id=\"$test_id\"})[1m]))\n-\n    1/avg((min(histogram_quantile(0.8,rate(network_rpc_latency_seconds_bucket{test_id=\"$test_id\",method=\"ping\",type=\"client_send_recv\"}[1m]))) by (instance))/(min(rate(consensus_leader_commit_phase_latency_seconds_sum{test_id=\"$test_id\"}[1m])/rate(consensus_leader_commit_phase_latency_seconds_count{test_id=\"$test_id\"}[1m])) by (instance)))\n)",
           "hide": false,
           "legendFormat": "actual prepare phase rate (approx)",
           "range": true,
@@ -1789,7 +1789,7 @@
             "uid": "ebcc7fad-20b5-44f0-a8ab-7ba2195ef2c0"
           },
           "editorMode": "code",
-          "expr": "(avg(rate(network_rpc_latency_sum{test_id=\"$test_id\",type=~\"client_send_recv\"}[30s])/rate(network_rpc_latency_count{test_id=\"$test_id\",type=~\"client_send_recv\",method!=\"sync_validator_addrs\"}[30s])) by (method,submethod,type))",
+          "expr": "(avg(rate(network_rpc_latency_seconds_sum{test_id=\"$test_id\",type=~\"client_send_recv\"}[30s])/rate(network_rpc_latency_seconds_count{test_id=\"$test_id\",type=~\"client_send_recv\",method!=\"sync_validator_addrs\"}[30s])) by (method,submethod,type))",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"

diff --git a/node/libs/concurrency/src/metrics.rs b/node/libs/concurrency/src/metrics.rs
@@ -32,7 +32,7 @@ pub(crate) enum Direction {
 
 /// Metrics reported for TCP connections.
 #[derive(Debug, Metrics)]
-#[metrics(prefix = "concurrency_tcp")]
+#[metrics(prefix = "concurrency_net_tcp")]
 pub(crate) struct TcpMetrics {
     /// Total bytes sent over all TCP connections.
     #[metrics(unit = Unit::Bytes)]
@@ -41,9 +41,9 @@ pub(crate) struct TcpMetrics {
     #[metrics(unit = Unit::Bytes)]
     pub(crate) received: Counter,
     /// TCP connections established since the process started.
-    pub(crate) established_connections: Family<Direction, Counter>,
+    pub(crate) established: Family<Direction, Counter>,
     /// Number of currently active TCP connections.
-    pub(crate) active_connections: Family<Direction, Gauge>,
+    pub(crate) active: Family<Direction, Gauge>,
 }
 
 /// TCP metrics instance.

diff --git a/node/libs/concurrency/src/net/tcp/mod.rs b/node/libs/concurrency/src/net/tcp/mod.rs
@@ -31,15 +31,15 @@ pub type Listener = tokio::net::TcpListener;
 /// Accepts an INBOUND listener connection.
 pub async fn accept(ctx: &ctx::Ctx, this: &mut Listener) -> ctx::OrCanceled<io::Result<Stream>> {
     Ok(ctx.wait(this.accept()).await?.map(|stream| {
-        metrics::TCP_METRICS.established_connections[&Direction::Inbound].inc();
+        metrics::TCP_METRICS.established[&Direction::Inbound].inc();
 
         // We are the only owner of the correctly opened
         // socket at this point so `set_nodelay` should
         // always succeed.
         stream.0.set_nodelay(true).unwrap();
         Stream {
             stream: stream.0,
-            _active: metrics::TCP_METRICS.active_connections[&Direction::Inbound]
+            _active: metrics::TCP_METRICS.active[&Direction::Inbound]
                 .clone()
                 .into(),
         }
@@ -55,14 +55,14 @@ pub async fn connect(
         .wait(tokio::net::TcpStream::connect(addr))
         .await?
         .map(|stream| {
-            metrics::TCP_METRICS.established_connections[&Direction::Outbound].inc();
+            metrics::TCP_METRICS.established[&Direction::Outbound].inc();
             // We are the only owner of the correctly opened
             // socket at this point so `set_nodelay` should
             // always succeed.
             stream.set_nodelay(true).unwrap();
             Stream {
                 stream,
-                _active: metrics::TCP_METRICS.active_connections[&Direction::Outbound]
+                _active: metrics::TCP_METRICS.active[&Direction::Outbound]
                     .clone()
                     .into(),
             }