use a single bucket rather than one per conversion

This commit is contained in:
2026-06-17 11:09:52 -07:00
parent 08a28f6924
commit 42b9ae85a8
10 changed files with 77 additions and 51 deletions
@@ -122,23 +122,13 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
ksuid = Ksuid()
conversion_id = str(ksuid)
bucket_name = f"oc-{bytes(ksuid).hex()}"
upload_key = "input/source.pptx"
object_prefix = f"{conversion_id}/"
upload_key = f"{object_prefix}input/source.pptx"
expires_at = utc_now() + timedelta(seconds=self._config.s3_session_ttl_seconds)
try:
self._store.ensure_bucket(bucket_name)
except S3Error as exc:
log_s3_error(
"ensure_bucket",
endpoint=self._config.s3_endpoint,
secure=self._config.s3_secure,
exc=exc,
)
raise
try:
upload_url = self._store.presigned_put_url(
bucket_name,
self._config.s3_bucket,
upload_key,
ttl_seconds=self._config.s3_session_ttl_seconds,
)
@@ -159,7 +149,7 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
full_jpeg_quality=full_jpeg_quality,
thumbnail_jpeg_quality=thumbnail_jpeg_quality,
notes=request.notes if request.HasField("notes") else None,
bucket_name=bucket_name,
object_prefix=object_prefix,
upload_object_key=upload_key,
status=conversion_pb2.CONVERSION_STATUS_PENDING,
)
@@ -168,7 +158,7 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
return conversion_pb2.CreateConversionResponse(
conversion_id=conversion_id,
upload_bucket=bucket_name,
upload_bucket=self._config.s3_bucket,
upload_object_key=upload_key,
upload_url=upload_url,
expires_at=_to_timestamp(expires_at),
@@ -265,7 +255,11 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
if session.conversion_task is not None and not session.conversion_task.done():
session.conversion_task.cancel()
await self._cleanup_local_artifacts(session)
await asyncio.to_thread(self._store.remove_bucket_tree, session.bucket_name)
await asyncio.to_thread(
self._store.remove_prefix,
self._config.s3_bucket,
session.object_prefix,
)
return conversion_pb2.DeleteConversionResponse(
conversion_id=session.conversion_id,
deleted=True,
@@ -295,7 +289,7 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
try:
await asyncio.to_thread(
self._store.fget_object,
session.bucket_name,
self._config.s3_bucket,
session.upload_object_key,
source_path,
)
@@ -436,10 +430,12 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
upload_total = slide_total * 2
upload_index = 0
for slide in slides:
object_key = f"output/slide-{slide.index:04d}{slide.image_path.suffix}"
self._store.fput_object(session.bucket_name, object_key, slide.image_path)
object_key = (
f"{session.object_prefix}output/slide-{slide.index:04d}{slide.image_path.suffix}"
)
self._store.fput_object(self._config.s3_bucket, object_key, slide.image_path)
image_url = self._store.presigned_get_url(
session.bucket_name,
self._config.s3_bucket,
object_key,
ttl_seconds=self._config.s3_session_ttl_seconds,
)
@@ -447,15 +443,16 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
if progress_callback is not None:
progress_callback(upload_index, upload_total)
thumbnail_object_key = (
f"output/thumb/slide-{slide.index:04d}{slide.thumbnail_path.suffix}"
f"{session.object_prefix}output/thumb/slide-{slide.index:04d}"
f"{slide.thumbnail_path.suffix}"
)
self._store.fput_object(
session.bucket_name,
self._config.s3_bucket,
thumbnail_object_key,
slide.thumbnail_path,
)
thumbnail_image_url = self._store.presigned_get_url(
session.bucket_name,
self._config.s3_bucket,
thumbnail_object_key,
ttl_seconds=self._config.s3_session_ttl_seconds,
)
@@ -515,7 +512,11 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
"""Delete storage resources after the configured session retention period."""
try:
await asyncio.sleep(self._config.conversion_cleanup_delay_seconds)
await asyncio.to_thread(self._store.remove_bucket_tree, session.bucket_name)
await asyncio.to_thread(
self._store.remove_prefix,
self._config.s3_bucket,
session.object_prefix,
)
except asyncio.CancelledError:
return
finally: