Use sharded shuffle in Hybrid #1517
Merged
+46
−25
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Outdated suggestions cannot be applied.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.
It turns out, we've never used sharded shuffle in Hybrid, running local shuffles (per shard) instead. This change fixes that.
Also, drop
Shuffle
implementation for sharded contexts to prevent this from happening again.Using sharded shuffle costs about 20% in terms of latency, according to the latest benchmarks.
with sharded shuffle - 64 min for 1B rows
without sharded shuffle - 53 min for 1B rows
This change also contains a small fix for PRF - to use a resharding step that we forgot to use as well.