hyper-parquet: Fix caching of Parquet files and add single-file variant#971
Merged
thevar1able merged 2 commits intoJul 17, 2026
Conversation
Contributor
Author
|
@rschu1ze Would appreciate if you can take a look at this one. Thanks! |
Member
|
Sorry, I'm rather busy this week, expect some delay. In the meantime, maybe you could resolve the merge conflicts? |
The hyper-parquet harness created a TEMP external table per ./query connection. With the persistent-server model (issue ClickHouse#936) the driver opens a fresh connection per try. This caused our plan cache to be wiped, requiring re-sampling the data on every hot run as well. To properly test a cached scenario, this commit changes our harness to create persistent external tables and maintain an attached database throughout the server's lifetime. The query iterations themselves still open a fresh connection each time. We also introduce the `single` variant for the parquet lane, now reporting both `hyper-parquet-single` and `hyper-parquet-partitioned`. As a drive-by change, we also drop ::bigint casts from ClickBench Q29, since those are not needed anymore, matching the queries used by other systems as well. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
caetanosauer
force-pushed
the
hyper-parquet-persistent-external-plancache
branch
from
July 13, 2026 10:54
f5e8c1e to
c44a0dc
Compare
Contributor
Author
|
@rschu1ze No worries, thanks for the quick reply. Conflicts resolved now |
Member
|
Shouldn't the files under |
The hyper-parquet -> hyper-parquet-partitioned rename left the latest 20260630 result batch behind. Move it over and update the system name to "Salesforce Hyper (Parquet, partitioned)" to match the rest of the lane, removing the now-empty hyper-parquet folder entirely. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Contributor
Author
|
@thevar1able Thanks for catching this! The original commit was prepared just before the June 30 results came in. I fixed the issue now. |
thevar1able
approved these changes
Jul 17, 2026
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
3 participants
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.
The hyper-parquet harness created a TEMP external table per ./query
connection. With the persistent-server model (issue #936) the driver
opens a fresh connection per try. This caused our plan cache to be wiped,
requiring re-sampling the data on every hot run as well. To properly
test a cached scenario, this commit changes our harness to create
persistent external tables and maintain an attached database throughout
the server's lifetime. The query iterations themselves still open a
fresh connection each time.
We also introduce the
singlevariant for the parquet lane, nowreporting both
hyper-parquet-singleandhyper-parquet-partitioned.As a drive-by change, we also drop ::bigint casts from ClickBench Q29,
since those are not needed anymore, matching the queries used by other
systems as well.
Co-Authored-By: Claude Opus 4.8 (1M context) noreply@anthropic.com