docs: add covered metrics in docs

jina-ai · Nov 10, 2022 · 82c048d · 82c048d
1 parent d910673
commit 82c048d
Show file tree

Hide file tree

Showing 2 changed files with 46 additions and 22 deletions.
diff --git a/docs/fundamentals/flow/instrumenting-flow.md b/docs/fundamentals/flow/instrumenting-flow.md
@@ -166,9 +166,13 @@ You can find more information on the different type of metrics in Prometheus [he
 |-----------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------|
 | `jina_receiving_request_seconds`        | [Histogram](https://opentelemetry.io/docs/reference/specification/metrics/api/#histogram)    | Measures the time elapsed between receiving a request from the Gateway and sending back the response.         |
 | `jina_sending_request_seconds`          | [Histogram](https://opentelemetry.io/docs/reference/specification/metrics/api/#histogram)    | Measures the time elapsed between sending a downstream request to an Executor and receiving the response back. |
-| `jina_sent_request_bytes`            | [Histogram](https://opentelemetry.io/docs/reference/specification/metrics/api/#histogram)    | Measures the size in bytes of the request sent by the Head to the Executor.                     |
+| `jina_number_of_pending_requests`   | [UpDownCounter](https://opentelemetry.io/docs/reference/specification/metrics/api/#updowncounter)| Counts the number of pending requests.                                                                          |
+| `jina_successful_requests`    | [Counter](https://opentelemetry.io/docs/reference/specification/metrics/api/#counter)                  | Counts the number of successful requests returned by the Head.                                               |
+| `jina_failed_requests`        | [Counter](https://opentelemetry.io/docs/reference/specification/metrics/api/#counter)   | Counts the number of failed requests returned by the Head.                                                   |
 | `jina_sent_request_bytes`               | [Histogram](https://opentelemetry.io/docs/reference/specification/metrics/api/#histogram)    | Measures the size in bytes of the request sent by the Head to the Executor.                                   |
 | `jina_received_response_bytes`          | [Histogram](https://opentelemetry.io/docs/reference/specification/metrics/api/#histogram)    | Measures the size in bytes of the response returned by the Executor.                                          |
+| `jina_received_request_bytes`           | [Histogram](https://opentelemetry.io/docs/reference/specification/metrics/api/#histogram)   | Measures the size of the request in bytes received at the Head level.                                        |
+| `jina_sent_response_bytes`              | [Histogram](https://opentelemetry.io/docs/reference/specification/metrics/api/#histogram)   | Measures the size in bytes of the response returned from the Head to the Gateway.                             |
 
 #### Executor Pods
 

diff --git a/jina/serve/runtimes/head/request_handling.py b/jina/serve/runtimes/head/request_handling.py
@@ -1,15 +1,14 @@
 import asyncio
-from typing import TYPE_CHECKING, Dict, List, Optional, Tuple
+from typing import TYPE_CHECKING, Dict, Optional, Tuple
 
 from jina.serve.runtimes.monitoring import MonitoringRequestMixin
 from jina.serve.runtimes.worker.request_handling import WorkerRequestHandler
 
 if TYPE_CHECKING:  # pragma: no cover
-    from jina.logging.logger import JinaLogger
-
     from opentelemetry.metrics import Meter
     from prometheus_client import CollectorRegistry
 
+    from jina.logging.logger import JinaLogger
     from jina.types.request.data import DataRequest
 
 
@@ -22,19 +21,27 @@ class HeaderRequestHandler(MonitoringRequestMixin):
     """
 
     def __init__(
-            self,
-            logger: 'JinaLogger',
-            metrics_registry: Optional['CollectorRegistry'] = None,
-            meter: Optional['Meter'] = None,
-            runtime_name: Optional[str] = None
+        self,
+        logger: 'JinaLogger',
+        metrics_registry: Optional['CollectorRegistry'] = None,
+        meter: Optional['Meter'] = None,
+        runtime_name: Optional[str] = None,
     ):
         super().__init__(metrics_registry, meter, runtime_name)
         self.logger = logger
         self._executor_endpoint_mapping = None
         self._gathering_endpoints = False
         self.runtime_name = runtime_name
 
-    async def _gather_worker_tasks(self, requests, connection_pool, deployment_name, polling_type, timeout_send, retries):
+    async def _gather_worker_tasks(
+        self,
+        requests,
+        connection_pool,
+        deployment_name,
+        polling_type,
+        timeout_send,
+        retries,
+    ):
         worker_send_tasks = connection_pool.send_requests(
             requests=requests,
             deployment=deployment_name,
@@ -62,11 +69,11 @@ async def _gather_worker_tasks(self, requests, connection_pool, deployment_name,
 
     @staticmethod
     def _merge_metadata(
-            metadata,
-            uses_after_metadata,
-            uses_before_metadata,
-            total_shards,
-            failed_shards,
+        metadata,
+        uses_after_metadata,
+        uses_before_metadata,
+        total_shards,
+        failed_shards,
     ):
         merged_metadata = {}
         if uses_before_metadata:
@@ -84,9 +91,17 @@ def _merge_metadata(
         return merged_metadata
 
     async def _handle_data_request(
-            self, requests: List[DataRequest], connection_pool, uses_before_address, uses_after_address,
-            timeout_send, retries, reduce, polling_type, deployment_name
-    ) -> Tuple[DataRequest, Dict]:
+        self,
+        requests,
+        connection_pool,
+        uses_before_address,
+        uses_after_address,
+        timeout_send,
+        retries,
+        reduce,
+        polling_type,
+        deployment_name,
+    ) -> Tuple['DataRequest', Dict]:
         for req in requests:
             self._update_start_request_metrics(req)
         WorkerRequestHandler.merge_routes(requests)
@@ -110,9 +125,14 @@ async def _handle_data_request(
             exceptions,
             total_shards,
             failed_shards,
-        ) = await self._gather_worker_tasks(requests=requests, deployment_name=deployment_name,
-                                            timeout_send=timeout_send, connection_pool=connection_pool,
-                                            polling_type=polling_type, retries=retries)
+        ) = await self._gather_worker_tasks(
+            requests=requests,
+            deployment_name=deployment_name,
+            timeout_send=timeout_send,
+            connection_pool=connection_pool,
+            polling_type=polling_type,
+            retries=retries,
+        )
 
         if len(worker_results) == 0:
             if exceptions:
@@ -157,4 +177,4 @@ async def _handle_data_request(
 
         self._update_end_request_metrics(response_request)
 
-        return response_request, merged_metadata
+        return response_request, merged_metadata