deser array tree from a vortex array#8063
Open
onursatici wants to merge 5 commits into
Open
Conversation
Merging this PR will not alter performance
|
onursatici
force-pushed
the
os/array-serialise-columnar
branch
from
93e517d to
3257531
Compare
onursatici
force-pushed
the
os/layout-overrides
branch
from
906945c to
34bf8aa
Compare
onursatici
force-pushed
the
os/array-serialise-columnar
branch
from
3257531 to
3c34669
Compare
onursatici
force-pushed
the
os/array-serialise-columnar
branch
from
3c34669 to
c33a177
Compare
Signed-off-by: Onur Satici <onur@spiraldb.com>
Signed-off-by: Onur Satici <onur@spiraldb.com>
Signed-off-by: Onur Satici <onur@spiraldb.com>
onursatici
force-pushed
the
os/array-serialise-columnar
branch
from
c33a177 to
e40b94f
Compare
joseph-isaacs
added
the
action/benchmark
github-actions
Bot
removed
the
action/benchmark
| /// `fba::ArrayStats`. Binary columns hold `ScalarValue::to_proto_bytes` blobs (decoded | ||
| /// using the array's dtype at read time); the `*_exact` bools tag whether `min`/`max` | ||
| /// were exact. `sum` is exact-only by construction so there is no `sum_exact` column. | ||
| pub static STATS_COLUMNS_DTYPE: LazyLock<DType> = LazyLock::new(|| { |
Contributor
There was a problem hiding this comment.
this is soon doing to be a extensible scalar (that is from the agg partial).
joseph-isaacs
left a comment
joseph-isaacs
left a comment
Contributor
There was a problem hiding this comment.
My main question is about the hard coded stat serde
Contributor
Polar Signals Profiling ResultsLatest Run
Powered by Polar Signals Cloud |
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.018x ➖, 0↑ 1↓)
datafusion / vortex-compact (0.992x ➖, 0↑ 0↓)
datafusion / parquet (0.993x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.033x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.014x ➖, 0↑ 0↓)
duckdb / parquet (1.005x ➖, 0↑ 0↓)
File Size Changes (1 files changed, +0.0% overall, 1↑ 0↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.058x ➖, 0↑ 5↓)
datafusion / vortex-compact (1.039x ➖, 0↑ 1↓)
datafusion / parquet (0.983x ➖, 2↑ 0↓)
datafusion / arrow (1.005x ➖, 0↑ 1↓)
duckdb / vortex-file-compressed (1.014x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.014x ➖, 0↑ 0↓)
duckdb / parquet (1.009x ➖, 1↑ 3↓)
duckdb / duckdb (1.000x ➖, 0↑ 0↓)
File Size Changes (9 files changed, -0.1% overall, 4↑ 5↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 1.217x ❌ How to read Verdict and Engines
datafusion / vortex-file-compressed (1.217x ❌, 0↑ 8↓)
No file size changes detected. |
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.018x ➖, 0↑ 10↓)
datafusion / vortex-compact (1.000x ➖, 1↑ 0↓)
datafusion / parquet (0.993x ➖, 2↑ 0↓)
duckdb / vortex-file-compressed (1.016x ➖, 1↑ 3↓)
duckdb / vortex-compact (1.004x ➖, 1↑ 2↓)
duckdb / parquet (0.999x ➖, 0↑ 0↓)
duckdb / duckdb (1.000x ➖, 3↑ 1↓)
File Size Changes (6 files changed, -0.0% overall, 1↑ 5↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.368x ❌, 0↑ 3↓)
datafusion / vortex-compact (1.113x ➖, 0↑ 2↓)
datafusion / parquet (1.316x ❌, 0↑ 5↓)
duckdb / vortex-file-compressed (1.115x ➖, 0↑ 2↓)
duckdb / vortex-compact (1.140x ➖, 0↑ 2↓)
duckdb / parquet (1.143x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) How to read Verdict and Engines
duckdb / vortex-file-compressed (1.037x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.014x ➖, 0↑ 0↓)
duckdb / parquet (1.026x ➖, 0↑ 0↓)
File Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: Random AccessVortex (geomean): 0.907x ➖ How to read Verdict and Engines
unknown / unknown (0.980x ➖, 13↑ 2↓)
|
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.027x ➖, 0↑ 1↓)
datafusion / vortex-compact (1.010x ➖, 0↑ 0↓)
datafusion / parquet (0.996x ➖, 0↑ 0↓)
datafusion / arrow (1.000x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.005x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.996x ➖, 0↑ 0↓)
duckdb / parquet (0.991x ➖, 1↑ 0↓)
duckdb / duckdb (0.995x ➖, 0↑ 0↓)
File Size Changes (26 files changed, +0.0% overall, 13↑ 13↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.028x ➖, 0↑ 4↓)
datafusion / parquet (1.003x ➖, 0↑ 1↓)
duckdb / vortex-file-compressed (1.028x ➖, 2↑ 6↓)
duckdb / parquet (0.999x ➖, 0↑ 0↓)
duckdb / duckdb (1.009x ➖, 0↑ 0↓)
File Size Changes (104 files changed, -0.0% overall, 50↑ 54↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: Appian on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.014x ➖, 0↑ 0↓)
datafusion / parquet (1.010x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.016x ➖, 0↑ 0↓)
duckdb / parquet (1.006x ➖, 0↑ 0↓)
duckdb / duckdb (0.998x ➖, 0↑ 0↓)
File Size Changes (4 files changed, -0.0% overall, 1↑ 3↓)
Totals:
Full attributed analysis
|
Contributor
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.237x ➖, 0↑ 8↓)
datafusion / vortex-compact (1.365x ❌, 0↑ 12↓)
datafusion / parquet (1.057x ➖, 1↑ 3↓)
duckdb / vortex-file-compressed (1.166x ➖, 0↑ 5↓)
duckdb / vortex-compact (1.176x ➖, 0↑ 5↓)
duckdb / parquet (1.179x ➖, 0↑ 1↓)
Full attributed analysis
|
Contributor
Benchmarks: CompressionVortex (geomean): 1.007x ➖ How to read Verdict and Engines
unknown / unknown (1.012x ➖, 0↑ 7↓)
|
Contributor
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.203x ➖, 0↑ 4↓)
datafusion / vortex-compact (1.231x ➖, 0↑ 6↓)
datafusion / parquet (1.160x ➖, 0↑ 5↓)
duckdb / vortex-file-compressed (1.098x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.133x ➖, 0↑ 2↓)
duckdb / parquet (1.139x ➖, 0↑ 0↓)
Full attributed analysis
|
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
2 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.
Summary
Add support for serialising a
ArrayNodetree into a vortex array, with array stats. Before we always serialised these into flatbuffers that were appended to the tail of the serialised array buffers. This PR adds the scaffolding to get a vortex array that can later at read time used to deserialise the buffers into ArrayRef's.Main user of this would be the array tree layout, which will land in a followup PR