Skip to content

using streaming_bulk instead of bulk for more consistent indexing #35

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

Merged
alemsh merged 2 commits into from
Jun 25, 2026
Merged

using streaming_bulk instead of bulk for more consistent indexing #35

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
979fe63
using streaming_bulk instead of bulk for more consistent indexing
alemsh Jun 24, 2026
03edd43
add try except for BulkIndexErrors, fix run_interval field being appl…
alemsh Jun 25, 2026
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
20 changes: 15 additions & 5 deletions condor_history_to_es.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,13 +46,15 @@ def es_generator(entries):
if options.dailyindex:
data['_index'] += '-'+(data['date'].split('T')[0].replace('-','.'))
data['_id'] = data['GlobalJobId'].replace('#','-').replace('.','-')
data['run_interval'] = {'gte': data['JobCurrentStartDate'], 'lte': data['EnteredCurrentStatus']}
if data['JobStatus'] == 4:
data['run_interval'] = {'gte': data['JobCurrentStartDate'], 'lte': data['EnteredCurrentStatus']}
if not data['_id']:
continue
yield data

from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulk
from elasticsearch.helpers import BulkIndexError
from elasticsearch.helpers import streaming_bulk

prefix = 'http'
address = options.address
Expand All @@ -75,7 +77,7 @@ def es_generator(entries):
es = Elasticsearch(hosts=[url],
request_timeout=5000,
bearer_auth=token,
sniff_on_connection_fail=True)
sniff_on_node_failure=True)

def es_import(document_generator):
if options.dry_run:
Expand All @@ -85,8 +87,16 @@ def es_import(document_generator):
json.dump(hit, sys.stdout)
success = True
else:
success, _ = bulk(es, document_generator, max_retries=20, initial_backoff=10, max_backoff=360)
return success
successes = 0
try:
for success, _ in streaming_bulk(es, document_generator, max_retries=20, initial_backoff=10, max_backoff=360):
successes += success
except BulkIndexError as e:
for error in e.errors:
print(error)

print(f"Indexed {successes} documents")
return successes

failed = False
if options.access_points and options.collectors:
Expand Down
Loading