Conversation
This was referenced Sep 17, 2026
Contributor
|
ACTION NEEDED The PR title and description are used as the merge commit message. Please update your PR title and description to match the specification. For details on the error please inspect the "PR Title Check" action. |
This was referenced Sep 17, 2026
BubbleCal
force-pushed
the
yang/oss-2269-6-row-lineage-bench
branch
from
September 17, 2026 08:39
f65221b to
3bb5b86
Compare
BubbleCal
changed the title
BubbleCal
force-pushed
the
yang/oss-2269-6-row-lineage-bench
branch
from
September 17, 2026 08:47
3bb5b86 to
3fe94b4
Compare
BubbleCal
added this pull request to stack #9343
September 17, 2026 08:56
… data file Compaction computes the output fragments' row lineage before writing: the row ids and versions carry over from the inputs and the output file sizes are fixed in advance. When the table's policy spills a sequence type, its values ride along as hidden uint64 columns of the batches being written, under the reserved field ids, and each output fragment's metadata marks them as spilled into its own data file. A compacted fragment on a table that opts in has one file instead of two, and a scan that projects _rowid reads it from the file it already has open. The write path lets the columns through: write_fragments sets the three hidden fields aside before the schema is checked against the dataset's and puts them back on the written schema under their reserved ids, and Schema::validate admits exactly those ids under those names. The field id constants move to lance-core for that. Binary-copy compaction cannot add columns to the files it copies, so it keeps writing a separate lineage file, as does the update path. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Two workloads bracket what the run encoding can do with a sequence: 30% of rows deleted then compacted, where the row ids still encode as a range plus a bitmap, and every row rewritten in random order then compacted, where no run structure survives. Within each, the two arms differ only in the table's lance.row_lineage.spill setting, and the benchmark reports manifest and transaction-file bytes, cold open, small-append commit latency, sequence load, row id index build, a take by row id, compaction wall time and bytes on disk. Co-authored-by: Will Jones <willjones127@gmail.com> Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
BubbleCal
force-pushed
the
yang/oss-2269-6-row-lineage-bench
branch
from
September 17, 2026 10:52
3fe94b4 to
b700ea9
Compare
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.
Last of the §5.3 stack (#8931, #9250), on top of #9347. The benchmark behind the numbers in #9337, from #8953 and extended to the table-config switch and the shuffled workload.
Stack
What it measures
LANCE_ENABLE_UNSTABLE_SPILLED_ROW_LINEAGE=1 cargo bench --bench rowid_spill, withBENCH_FRAGMENTS,BENCH_ROWS_PER_FRAGMENT,BENCH_DELETE_PERCENT,BENCH_APPENDSandBENCH_SCENARIOSto size it. Two workloads:deleted(30% of rows deleted, then compacted; the sequences still run-encode) andshuffled(every row rewritten in random order, then compacted; no run structure survives). Within each, the inline arm never opts in and the spilled arm setslance.row_lineage.spill=true. Per arm it reports manifest and transaction-file bytes split by sequence, cold open, small-append commit latency, one sequence load, the row id index build, a take by row id once the index exists, compaction wall time and bytes on disk. The take is checked against the value the row should hold, so a spilled sequence that resolved to the wrong row fails the benchmark rather than looking fast.Results and their reading are in #9337.
Refs #8931, #9250
🤖 Generated with Claude Code