From 23b929ea10daded7447f806f8860447626e573a6 Mon Sep 17 00:00:00 2001
From: Shirshanka Das <shirshanka@apache.org>
Date: Mon, 5 Sep 2022 11:53:39 -0700
Subject: [PATCH] feat(cli): report memory usage during ingest (#5828)

---
 .../src/datahub/ingestion/run/pipeline.py              | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/metadata-ingestion/src/datahub/ingestion/run/pipeline.py b/metadata-ingestion/src/datahub/ingestion/run/pipeline.py
index 009eecc4de6f8a..3413ea215a6dbe 100644
--- a/metadata-ingestion/src/datahub/ingestion/run/pipeline.py
+++ b/metadata-ingestion/src/datahub/ingestion/run/pipeline.py
@@ -1,5 +1,6 @@
 import itertools
 import logging
+import os
 import platform
 import sys
 import time
@@ -7,6 +8,8 @@
 from typing import Any, Dict, Iterable, List, Optional, cast
 
 import click
+import humanfriendly
+import psutil
 
 import datahub
 from datahub.configuration.common import PipelineExecutionError
@@ -106,6 +109,13 @@ class CliReport(Report):
     py_exec_path: str = sys.executable
     os_details: str = platform.platform()
 
+    def compute_stats(self) -> None:
+
+        self.mem_info = humanfriendly.format_size(
+            psutil.Process(os.getpid()).memory_info().rss
+        )
+        return super().compute_stats()
+
 
 class Pipeline:
     config: PipelineConfig