feat: add prometheus custom configuration for participants (#354)

README.md

@@ -199,6 +199,15 @@ participants:
   # network parameter num_validator_keys_per_node
   validator_count: null
 
+  # Prometheus additional configuration for a given participant prometheus target.
+  # Execution, beacon and validator client targets on prometheus will include this
+  # configuration.
+  prometheus_config:
+    # Scrape interval to be used. Default to 15 seconds
+    scrape_interval: 15s
+    # Additional labels to be added. Default to empty
+    labels: {}
+
 # Default configuration parameters for the Eth network
 network_params:
   # The network ID of the network.
@@ -315,6 +324,13 @@ mev_params:
   mev_relay_website_extra_args: []
   # Extra parameters to send to the builder
   mev_builder_extra_args: []
+  # Prometheus additional configuration for the mev builder participant.
+  # Execution, beacon and validator client targets on prometheus will include this configuration.
+  mev_builder_prometheus_config:
+    # Scrape interval to be used. Default to 15 seconds
+    scrape_interval: 15s
+    # Additional labels to be added. Default to empty
+    labels: {}
   # Image to use for mev-flood
   mev_flood_image: flashbots/mev-flood
   # Extra parameters to send to mev-flood
@@ -428,9 +444,11 @@ snooper_enabled: true
 </details>
 
 ## Custom labels for Docker and Kubernetes
+
 There are 4 custom labels that can be used to identify the nodes in the network. These labels are used to identify the nodes in the network and can be used to run chaos tests on specific nodes. An example for these labels are as follows:
 
 Execution Layer (EL) nodes:
+
 ```sh
   "com.kurtosistech.custom.ethereum-package-client": "geth",
   "com.kurtosistech.custom.ethereum-package-client-image": "ethereum-client-go-latest",
@@ -439,6 +457,7 @@ Execution Layer (EL) nodes:
 ```
 
 Consensus Layer (CL) nodes - Beacon:
+
 ```sh
   "com.kurtosistech.custom.ethereum-package-client": "lighthouse",
   "com.kurtosistech.custom.ethereum-package-client-image": "sigp-lighthouse-latest",
@@ -447,6 +466,7 @@ Consensus Layer (CL) nodes - Beacon:
 ```
 
 Consensus Layer (CL) nodes - Validator:
+
 ```sh
   "com.kurtosistech.custom.ethereum-package-client": "lighthouse",
   "com.kurtosistech.custom.ethereum-package-client-image": "sigp-lighthouse-latest",
@@ -521,7 +541,6 @@ Here's a table of where the keys are used
 | 5             | eip4788_deployment  | ✅                |                 | As contract deployer       |
 | 6             | mev_custom_flood    | ✅                |                 | As the sender of balance   |
 
-
 ## Developing On This Package
 
 First, install prerequisites:

network_params.yaml

@@ -1,11 +1,11 @@
 participants:
   - el_client_type: geth
     el_client_image: ethereum/client-go:latest
-    el_client_log_level: ''
+    el_client_log_level: ""
     el_extra_params: []
     cl_client_type: lighthouse
     cl_client_image: sigp/lighthouse:latest
-    cl_client_log_level: ''
+    cl_client_log_level: ""
     beacon_extra_params: []
     validator_extra_params: []
     builder_network_params: null
@@ -25,14 +25,18 @@ participants:
     v_min_mem: 0
     v_max_mem: 0
     count: 2
+    prometheus_config:
+      scrape_interval: 15s
+      labels: {}
 network_params:
-  network_id: '3151908'
-  deposit_contract_address: '0x4242424242424242424242424242424242424242'
+  network_id: "3151908"
+  deposit_contract_address: "0x4242424242424242424242424242424242424242"
   seconds_per_slot: 12
   num_validator_keys_per_node: 64
-  preregistered_validator_keys_mnemonic: 'giant issue aisle success illegal bike spike
+  preregistered_validator_keys_mnemonic:
+    "giant issue aisle success illegal bike spike
     question tent bar rely arctic volcano long crawl hungry vocal artwork sniff fantasy
-    very lucky have athlete'
+    very lucky have athlete"
   genesis_delay: 120
   max_churn: 8
   ejection_balance: 16000000000
@@ -58,6 +62,9 @@ mev_params:
   mev_relay_housekeeper_extra_args: []
   mev_relay_website_extra_args: []
   mev_builder_extra_args: []
+  mev_builder_prometheus_config:
+    scrape_interval: 15s
+    labels: {}
   mev_flood_image: flashbots/mev-flood
   mev_flood_extra_args: []
   mev_flood_seconds_per_bundle: 15

src/node_metrics_info.star

@@ -1,3 +1,13 @@
 # this is a dictionary as this will get serialzed to JSON
-def new_node_metrics_info(name, path, url):
-    return {"name": name, "path": path, "url": url}
+def new_node_metrics_info(
+    name,
+    path,
+    url,
+    config=None,
+):
+    return {
+        "name": name,
+        "path": path,
+        "url": url,
+        "config": config,
+    }

src/package_io/input_parser.star

@@ -145,6 +145,10 @@ def input_parser(plan, input_args):
                 ethereum_metrics_exporter_enabled=participant[
                     "ethereum_metrics_exporter_enabled"
                 ],
+                prometheus_config=struct(
+                    scrape_interval=participant["prometheus_config"]["scrape_interval"],
+                    labels=participant["prometheus_config"]["labels"],
+                ),
             )
             for participant in result["participants"]
         ],
@@ -425,6 +429,10 @@ def default_participant():
         "snooper_enabled": False,
         "ethereum_metrics_exporter_enabled": False,
         "count": 1,
+        "prometheus_config": {
+            "scrape_interval": "15s",
+            "labels": None,
+        },
     }
 
 
@@ -441,6 +449,10 @@ def get_default_mev_params():
         "mev_flood_image": "flashbots/mev-flood",
         "mev_flood_extra_args": [],
         "mev_flood_seconds_per_bundle": 15,
+        "mev_builder_prometheus_config": {
+            "scrape_interval": "15s",
+            "labels": None,
+        },
     }
 
 
@@ -546,6 +558,9 @@ def enrich_mev_extra_params(parsed_arguments_dict, mev_prefix, mev_port, mev_typ
                     + genesis_constants.PRE_FUNDED_ACCOUNTS[0].private_key
                 },
                 "validator_count": 0,
+                "prometheus_config": parsed_arguments_dict["mev_params"][
+                    "mev_builder_prometheus_config"
+                ],
             }
         )
 

src/participant_network.star

@@ -207,6 +207,11 @@ def launch_participant_network(
             participant.el_extra_env_vars,
         )
 
+        # Add participant el additional prometheus metrics
+        for metrics_info in el_client_context.el_metrics_info:
+            if metrics_info != None:
+                metrics_info["config"] = participant.prometheus_config
+
         all_el_client_contexts.append(el_client_context)
 
     plan.print("Successfully added {0} EL participants".format(num_participants))
@@ -343,6 +348,11 @@ def launch_participant_network(
                 participant.validator_extra_params,
             )
 
+        # Add participant cl additional prometheus labels
+        for metrics_info in cl_client_context.cl_nodes_metrics_info:
+            if metrics_info != None:
+                metrics_info["config"] = participant.prometheus_config
+
         all_cl_client_contexts.append(cl_client_context)
 
         ethereum_metrics_exporter_context = None

src/prometheus/prometheus_launcher.star

@@ -2,13 +2,16 @@ shared_utils = import_module("../shared_utils/shared_utils.star")
 
 SERVICE_NAME = "prometheus"
 
+PROMETHEUS_DEFAULT_SCRAPE_INTERVAL = "15s"
+
 EXECUTION_CLIENT_TYPE = "execution"
 BEACON_CLIENT_TYPE = "beacon"
 VALIDATOR_CLIENT_TYPE = "validator"
 
 METRICS_INFO_NAME_KEY = "name"
 METRICS_INFO_URL_KEY = "url"
 METRICS_INFO_PATH_KEY = "path"
+METRICS_INFO_ADDITIONAL_CONFIG_KEY = "config"
 
 # TODO(old) I'm not sure if we should use latest version or ping an specific version instead
 IMAGE_NAME = "prom/prometheus:latest"
@@ -95,16 +98,30 @@ def new_config_template_data(
     for context in el_client_contexts:
         if len(context.el_metrics_info) >= 1 and context.el_metrics_info[0] != None:
             execution_metrics_info = context.el_metrics_info[0]
+            scrape_interval = PROMETHEUS_DEFAULT_SCRAPE_INTERVAL
+            labels = {
+                "service": context.service_name,
+                "client_type": EXECUTION_CLIENT_TYPE,
+                "client_name": context.client_name,
+            }
+            additional_config = execution_metrics_info[
+                METRICS_INFO_ADDITIONAL_CONFIG_KEY
+            ]
+            if additional_config != None:
+                if additional_config.labels != None:
+                    labels.update(additional_config.labels)
+                if (
+                    additional_config.scrape_interval != None
+                    and additional_config.scrape_interval != ""
+                ):
+                    scrape_interval = additional_config.scrape_interval
             metrics_jobs.append(
                 new_metrics_job(
                     job_name=execution_metrics_info[METRICS_INFO_NAME_KEY],
                     endpoint=execution_metrics_info[METRICS_INFO_URL_KEY],
                     metrics_path=execution_metrics_info[METRICS_INFO_PATH_KEY],
-                    labels={
-                        "service": context.service_name,
-                        "client_type": EXECUTION_CLIENT_TYPE,
-                        "client_name": context.client_name,
-                    },
+                    labels=labels,
+                    scrape_interval=scrape_interval,
                 )
             )
     # Adding consensus clients metrics jobs
@@ -115,16 +132,28 @@ def new_config_template_data(
         ):
             # Adding beacon node metrics
             beacon_metrics_info = context.cl_nodes_metrics_info[0]
+            scrape_interval = PROMETHEUS_DEFAULT_SCRAPE_INTERVAL
+            labels = {
+                "service": context.beacon_service_name,
+                "client_type": BEACON_CLIENT_TYPE,
+                "client_name": context.client_name,
+            }
+            additional_config = beacon_metrics_info[METRICS_INFO_ADDITIONAL_CONFIG_KEY]
+            if additional_config != None:
+                if additional_config.labels != None:
+                    labels.update(additional_config.labels)
+                if (
+                    additional_config.scrape_interval != None
+                    and additional_config.scrape_interval != ""
+                ):
+                    scrape_interval = additional_config.scrape_interval
             metrics_jobs.append(
                 new_metrics_job(
                     job_name=beacon_metrics_info[METRICS_INFO_NAME_KEY],
                     endpoint=beacon_metrics_info[METRICS_INFO_URL_KEY],
                     metrics_path=beacon_metrics_info[METRICS_INFO_PATH_KEY],
-                    labels={
-                        "service": context.beacon_service_name,
-                        "client_type": BEACON_CLIENT_TYPE,
-                        "client_name": context.client_name,
-                    },
+                    labels=labels,
+                    scrape_interval=scrape_interval,
                 )
             )
         if (
@@ -133,16 +162,30 @@ def new_config_template_data(
         ):
             # Adding validator node metrics
             validator_metrics_info = context.cl_nodes_metrics_info[1]
+            scrape_interval = PROMETHEUS_DEFAULT_SCRAPE_INTERVAL
+            labels = {
+                "service": context.validator_service_name,
+                "client_type": VALIDATOR_CLIENT_TYPE,
+                "client_name": context.client_name,
+            }
+            additional_config = validator_metrics_info[
+                METRICS_INFO_ADDITIONAL_CONFIG_KEY
+            ]
+            if additional_config != None:
+                if additional_config.labels != None:
+                    labels.update(additional_config.labels)
+                if (
+                    additional_config.scrape_interval != None
+                    and additional_config.scrape_interval != ""
+                ):
+                    scrape_interval = additional_config.scrape_interval
             metrics_jobs.append(
                 new_metrics_job(
                     job_name=validator_metrics_info[METRICS_INFO_NAME_KEY],
                     endpoint=validator_metrics_info[METRICS_INFO_URL_KEY],
                     metrics_path=validator_metrics_info[METRICS_INFO_PATH_KEY],
-                    labels={
-                        "service": context.validator_service_name,
-                        "client_type": VALIDATOR_CLIENT_TYPE,
-                        "client_name": context.client_name,
-                    },
+                    labels=labels,
+                    scrape_interval=scrape_interval,
                 )
             )
 
@@ -179,7 +222,7 @@ def new_metrics_job(
     endpoint,
     metrics_path,
     labels,
-    scrape_interval="15s",
+    scrape_interval=PROMETHEUS_DEFAULT_SCRAPE_INTERVAL,
 ):
     return {
         "Name": job_name,