Skip to content

Retry data URLs a couple of times upon failure #2321

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
badboy wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Retry data URLs a couple of times upon failure #2321

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 16 additions & 3 deletions etl/glean_etl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
import requests
import stringcase
import yaml
from requests.adapters import HTTPAdapter, Retry

from .bigquery import get_bigquery_column_name, get_bigquery_ping_table_name
from .expiry import get_expiry_text, get_mapped_expiry
Expand Down Expand Up @@ -230,16 +231,28 @@ def _is_metric_in_ping(metric, ping_data):
return True


def fetch_json(url, tries=5):
"""
Fetch JSON from the given URL
and try a total of `tries` times upon failure.
"""

s = requests.Session()
retries = Retry(total=tries, backoff_factor=0.1, status_forcelist=[500, 502, 503, 504])
s.mount("https://", HTTPAdapter(max_retries=retries))
return s.get(url).json()


def write_glean_metadata(output_dir, functions_dir, app_names=None):
"""
Writes out the metadata for use by the dictionary
"""
# first, get the basic metadata from various sources
annotations_index = requests.get(ANNOTATIONS_URL).json()
annotations_index = fetch_json(ANNOTATIONS_URL)
looker_namespaces = yaml.safe_load(requests.get(NAMESPACES_URL).text)
product_details = requests.get(FIREFOX_PRODUCT_DETAIL_URL).json()
product_details = fetch_json(FIREFOX_PRODUCT_DETAIL_URL)
latest_fx_release_version = list(product_details)[-1]
metrics_sampling_info = _get_metric_sample_data(requests.get(EXPERIMENT_DATA_URL).json())
metrics_sampling_info = _get_metric_sample_data(fetch_json(EXPERIMENT_DATA_URL))

mps_repo_path = _clone_mps()

Expand Down