Skip to content
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.

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

Dynamically set AlephWorker stages through env vars #3748

Merged
merged 1 commit into from
May 30, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
40 changes: 28 additions & 12 deletions aleph/settings.py
Original file line number Diff line number Diff line change
Expand Up @@ -252,18 +252,34 @@ def __init__(self) -> None:
self.STAGE_UPDATE_ENTITY = "updateentity"
self.STAGE_PRUNE_ENTITY = "pruneentity"

self.ALEPH_STAGES = [
self.STAGE_INDEX,
self.STAGE_XREF,
self.STAGE_REINGEST,
self.STAGE_REINDEX,
self.STAGE_LOAD_MAPPING,
self.STAGE_FLUSH_MAPPING,
self.STAGE_EXPORT_SEARCH,
self.STAGE_EXPORT_XREF,
self.STAGE_UPDATE_ENTITY,
self.STAGE_PRUNE_ENTITY,
]
self.ALEPH_STAGES = env.to_list(
"ALEPH_WORKER_STAGES",
[
self.STAGE_INDEX,
self.STAGE_XREF,
self.STAGE_REINGEST,
self.STAGE_REINDEX,
self.STAGE_LOAD_MAPPING,
self.STAGE_FLUSH_MAPPING,
self.STAGE_EXPORT_SEARCH,
self.STAGE_EXPORT_XREF,
self.STAGE_UPDATE_ENTITY,
self.STAGE_PRUNE_ENTITY,
],
)

self.QOS_MAPPING = {
self.STAGE_INDEX: self.RABBITMQ_QOS_INDEX_QUEUE,
self.STAGE_XREF: self.RABBITMQ_QOS_XREF_QUEUE,
self.STAGE_REINGEST: self.RABBITMQ_QOS_REINGEST_QUEUE,
self.STAGE_REINDEX: self.RABBITMQ_QOS_REINDEX_QUEUE,
self.STAGE_LOAD_MAPPING: self.RABBITMQ_QOS_LOAD_MAPPING_QUEUE,
self.STAGE_FLUSH_MAPPING: self.RABBITMQ_QOS_FLUSH_MAPPING_QUEUE,
self.STAGE_EXPORT_SEARCH: self.RABBITMQ_QOS_EXPORT_SEARCH_QUEUE,
self.STAGE_EXPORT_XREF: self.RABBITMQ_QOS_EXPORT_XREF_QUEUE,
self.STAGE_UPDATE_ENTITY: self.RABBITMQ_QOS_UPDATE_ENTITY_QUEUE,
self.STAGE_PRUNE_ENTITY: self.RABBITMQ_QOS_PRUNE_ENTITY_QUEUE,
}

# Document processing pipeline
self.INGEST_PIPELINE = env.to_list(
Expand Down
30 changes: 13 additions & 17 deletions aleph/worker.py
Original file line number Diff line number Diff line change
Expand Up @@ -229,25 +229,21 @@ def run_indexing_batches(self):


def get_worker(num_threads=1):
qos_mapping: Dict[str, int] = {
SETTINGS.STAGE_INDEX: SETTINGS.RABBITMQ_QOS_INDEX_QUEUE,
SETTINGS.STAGE_XREF: SETTINGS.RABBITMQ_QOS_XREF_QUEUE,
SETTINGS.STAGE_REINGEST: SETTINGS.RABBITMQ_QOS_REINGEST_QUEUE,
SETTINGS.STAGE_REINDEX: SETTINGS.RABBITMQ_QOS_REINDEX_QUEUE,
SETTINGS.STAGE_LOAD_MAPPING: SETTINGS.RABBITMQ_QOS_LOAD_MAPPING_QUEUE,
SETTINGS.STAGE_FLUSH_MAPPING: SETTINGS.RABBITMQ_QOS_FLUSH_MAPPING_QUEUE,
SETTINGS.STAGE_EXPORT_SEARCH: SETTINGS.RABBITMQ_QOS_EXPORT_SEARCH_QUEUE,
SETTINGS.STAGE_EXPORT_XREF: SETTINGS.RABBITMQ_QOS_EXPORT_XREF_QUEUE,
SETTINGS.STAGE_UPDATE_ENTITY: SETTINGS.RABBITMQ_QOS_UPDATE_ENTITY_QUEUE,
SETTINGS.STAGE_PRUNE_ENTITY: SETTINGS.RABBITMQ_QOS_PRUNE_ENTITY_QUEUE,
}

aleph_worker_queues = list(qos_mapping.keys())

log.info(f"Worker active, stages: {aleph_worker_queues}")
# The stages performed by AlephWorker correspond to
# RabbitMQ queues. Both use the same string as a name,
# By default, AlephWorker implements all stages
# (and reads from all queues) except "index" and "analyze".
aleph_worker_stages = list(SETTINGS.ALEPH_STAGES)

log.info(f"Worker active, stages: {aleph_worker_stages}")

qos_mapping = {}
for stage in aleph_worker_stages:
if stage not in qos_mapping:
qos_mapping[stage] = SETTINGS.QOS_MAPPING.get(stage, 1)

return AlephWorker(
queues=aleph_worker_queues,
queues=aleph_worker_stages,
conn=kv,
num_threads=num_threads or 1,
version=__version__,
Expand Down
Loading