Qualify improvements#39
Open
Vedin wants to merge 10 commits into
Open
Conversation
Adds snowplow_dedup_topk_bench: runs the canonical Snowplow event deduplication query (QUALIFY ROW_NUMBER() OVER (PARTITION BY event_id ORDER BY collector_tstamp, dvce_created_tstamp) <= 1) over a synthetic snowplow-shaped table, asserts the grouped top-K rewrite fires and the row count is exact, and emits OPTIMIZED_MS (best-of-N) for benchmarking. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
…ial timing Cross-run machine noise (~20%, correlated within a single process) made raw best-of-N milliseconds unusable for keep/discard decisions. Replace the OPTIMIZED_MS metric with OPTIMIZED_RATIO: time the native DataFusion window path (a fixed reference that never touches in-scope code) and the GroupedTopKExec fast path back-to-back each iteration, and report the median optimized/reference ratio. The ratio cancels machine noise. Lower is better. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
…verter (no per-row ScalarValue)
…encode_rows, drop ScalarValue helpers
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This changes fix problem performance. It at least -60% of current state. There is a big problem with it because it adds more memory pressure. We still can merge it like this but current datafusion state a little bit more durable due to GreedyMemoryPool and DiskManager. Meanwhile I try to introduce somme guard of spill integration here as well.