Ciaran/minor download bugs (#1674)
## Motivation Two minor bugs in the download coordinator: cancelling a download didn't reset its status to pending, and a single error in _emit_existing_download_progress would kill the loop permanently. ## Changes - Cancel emits pending status: When a download is cancelled, emit a DownloadPending event so the UI/cluster state reflects that the model is no longer actively downloading. - Resilient progress emission loop: Move the try/except inside the while loop so transient errors are logged but the periodic emission continues. ## Why It Works - The cancel fix ensures the download status is consistent — without it, a cancelled download would still appear as in-progress. - The loop fix prevents a single exception from permanently stopping the 60-second periodic progress broadcast.
This commit is contained in:
@@ -133,6 +133,16 @@ class DownloadCoordinator:
|
||||
if model_id in self.active_downloads and model_id in self.download_status:
|
||||
logger.info(f"Cancelling download for {model_id}")
|
||||
self.active_downloads.pop(model_id).cancel()
|
||||
current_status = self.download_status[model_id]
|
||||
pending = DownloadPending(
|
||||
shard_metadata=current_status.shard_metadata,
|
||||
node_id=self.node_id,
|
||||
model_directory=self._model_dir(model_id),
|
||||
)
|
||||
self.download_status[model_id] = pending
|
||||
await self.event_sender.send(
|
||||
NodeDownloadProgress(download_progress=pending)
|
||||
)
|
||||
|
||||
async def _start_download(self, shard: ShardMetadata) -> None:
|
||||
model_id = shard.model_card.model_id
|
||||
@@ -287,8 +297,8 @@ class DownloadCoordinator:
|
||||
del self.download_status[model_id]
|
||||
|
||||
async def _emit_existing_download_progress(self) -> None:
|
||||
try:
|
||||
while True:
|
||||
while True:
|
||||
try:
|
||||
logger.debug(
|
||||
"DownloadCoordinator: Fetching and emitting existing download progress..."
|
||||
)
|
||||
@@ -376,8 +386,8 @@ class DownloadCoordinator:
|
||||
logger.debug(
|
||||
"DownloadCoordinator: Done emitting existing download progress."
|
||||
)
|
||||
await anyio.sleep(60)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"DownloadCoordinator: Error emitting existing download progress: {e}"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"DownloadCoordinator: Error emitting existing download progress: {e}"
|
||||
)
|
||||
await anyio.sleep(60)
|
||||
|
||||
Reference in New Issue
Block a user