Handle errors in Runtime #489
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Member
justheuristic
commented
Jun 23, 2022
•
justheuristic
commented
- fix edge case where expert requests with 3.99-4MB payload would fail due to max message size (due to serialization overhead)
- recover from errors in the Runtime, propagate them to the corresponding tasks
- previously, a failing function would terminate the entire server - which was a major pain for me personally :)
- failure to process a request will now trigger P2PHandlerError instead of P2PDaemonError (cuz it does not kill the daemon)
- allow optional metadata in ExpertRequest / ExpertResponse for extendability [todo: validate it vs. @mryab ]
3 tasks
Codecov Report
@@ Coverage Diff @@
## master #489 +/- ##
==========================================
- Coverage 85.75% 85.62% -0.14%
==========================================
Files 80 80
Lines 7794 7812 +18
==========================================
+ Hits 6684 6689 +5
- Misses 1110 1123 +13
|
GreenFatGuy
reviewed
Jun 23, 2022
mryab
reviewed
Jun 23, 2022
hivemind/moe/server/runtime.py
Outdated
| except KeyboardInterrupt: | ||
| raise | ||
| except BaseException as exception: | ||
| logger.exception(f"Caught {exception}, attempting to recover", exc_info=True) |
There was a problem hiding this comment.
exc_info is most likely not necessary
Co-authored-by: Max Ryabinin <mryabinin0@gmail.com>
mryab
approved these changes
Jun 24, 2022
mryab
pushed a commit
that referenced
this pull request
Sep 13, 2022
- fix edge case where expert requests with 3.99-4MB payload would fail due to max message size (due to serialization overhead) - recover from errors in the Runtime, propagate them to the corresponding tasks - previously, a failing function would terminate the entire server - which was a major pain for me personally :) - failure to process a request will now trigger P2PHandlerError instead of P2PDaemonError (cuz it does not kill the daemon) - allow optional metadata in ExpertRequest / ExpertResponse for extendability [todo: validate it vs. @mryab ] Co-authored-by: Max Ryabinin <mryabinin0@gmail.com> Co-authored-by: Pavel Samygin <samygin@phystech.edu> (cherry picked from commit ef0b842)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.