impr(ci): retry container image pushing and send slack messages for failures (#11416)

## Problem
We've seen quite a few CI failures related to pushes to docker hub
failing with weird error messages that indicate maybe docker hub is just
not reliable.

## Summary of changes
Retry container image pushing up to 10 times, and send a slack message
if we had to retry, regardless of the job succeeding or not.

.github/scripts/push_with_image_map.py

@@ -11,12 +11,27 @@ try:
 except json.JSONDecodeError as e:
     raise ValueError("Failed to parse IMAGE_MAP as JSON") from e
 
-for source, targets in parsed_image_map.items():
-    for target in targets:
-        cmd = ["docker", "buildx", "imagetools", "create", "-t", target, source]
-        print(f"Running: {' '.join(cmd)}")
-        result = subprocess.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+failures = []
 
-        if result.returncode != 0:
-            print(f"Error: {result.stdout}")
-            raise RuntimeError(f"Command failed: {' '.join(cmd)}")
+pending = [(source, target) for source, targets in parsed_image_map.items() for target in targets]
+
+while len(pending) > 0:
+    if len(failures) > 10:
+        print("Error: more than 10 failures!")
+        for failure in failures:
+            print(f'"{failure[0]}" failed with the following output:')
+            print(failure[1])
+        raise RuntimeError("Retry limit reached.")
+
+    source, target = pending.pop(0)
+    cmd = ["docker", "buildx", "imagetools", "create", "-t", target, source]
+    print(f"Running: {' '.join(cmd)}")
+    result = subprocess.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+
+    if result.returncode != 0:
+        failures.append((" ".join(cmd), result.stdout))
+        pending.append((source, target))
+
+if len(failures) > 0 and (github_output := os.getenv("GITHUB_OUTPUT")):
+    with open(github_output, "a") as f:
+        f.write("slack_notify=true\n")