erenavsarogullari opened a new pull request, #20372:
URL: https://github.com/apache/datafusion/pull/20372
## Which issue does this PR close?
- Closes #20371.
## Rationale for this change
Currently, `datafusion.runtime.max_temp_directory_size` is a disk based
config but when it i
Dandandan commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3905133276
I think you're not 100% following my point, but not sure:
* I believe TPCH / TPCDS (looking locally) it the tables are I think are
generated based on number of CPU cores
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905166961
🤖: Benchmark completed
Details
```
Comparing HEAD and filter-pushdown-dynamic-bytes
Benchmark tpch_sf1.json
-
adriangb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3905179031
But to be clear, I think a version that is at least able to switch the
approach mid scan is strictly better. But since that requires a API changes and
coordination across crate
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905692013
show benchmark queue
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific com
adriangb commented on PR #20362:
URL: https://github.com/apache/datafusion/pull/20362#issuecomment-3905689818
@zhuqi-lucas could you review this change please?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL ab
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905692963
🤖 Hi @adriangb, you asked to view the benchmark queue
(https://github.com/apache/datafusion/pull/20363#issuecomment-3905692013).
No pending jobs in `jobs/`.
--
This is a
lyne7-sc commented on code in PR #20364:
URL: https://github.com/apache/datafusion/pull/20364#discussion_r2810352004
##
datafusion/functions-nested/src/set_ops.rs:
##
@@ -527,42 +531,52 @@ fn general_array_distinct(
if array.is_empty() {
return Ok(Arc::new(array.cl
neilconway commented on issue #18181:
URL: https://github.com/apache/datafusion/issues/18181#issuecomment-3906058209
The repro actually uses `array_has_any`, not `array_has`. Can we rename the
title of this ticket for clarity?
--
This is an automated message from the Apache Git Service.
T
neilconway commented on issue #20377:
URL: https://github.com/apache/datafusion/issues/20377#issuecomment-3906062707
take
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To
neilconway opened a new issue, #20377:
URL: https://github.com/apache/datafusion/issues/20377
### Is your feature request related to a problem or challenge?
For the scalar needle case, array_has is reasonably fast but it could be
optimized by avoiding the per-row work that is currentl
neilconway commented on issue #20377:
URL: https://github.com/apache/datafusion/issues/20377#issuecomment-3906064528
See also #18181, although in that case the observed performance issue is
actually with `array_has_any`.
--
This is an automated message from the Apache Git Service.
To resp
Dandandan commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3905199459
Ah ok - yeah that makes sense 👍
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go t
erenavsarogullari opened a new pull request, #20375:
URL: https://github.com/apache/datafusion/pull/20375
## Which issue does this PR close?
- Closes 20373.
## Rationale for this change
Minor refactoring on error message by exposing required config name for the
end user. This is
kumarUjjawal commented on code in PR #20336:
URL: https://github.com/apache/datafusion/pull/20336#discussion_r2810983428
##
datafusion/functions/src/macros.rs:
##
@@ -393,37 +394,76 @@ macro_rules! make_math_binary_udf {
&self,
args: Sca
Dandandan opened a new pull request, #20378:
URL: https://github.com/apache/datafusion/pull/20378
## Which issue does this PR close?
## Rationale for this change
Keep up to date. I saw when looking at
https://github.com/apache/datafusion/issues/20325 we were still at 0.12.4
Dandandan commented on PR #20378:
URL: https://github.com/apache/datafusion/pull/20378#issuecomment-3906877330
run benchmark clickbench_partitioned
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to
Dandandan commented on PR #20378:
URL: https://github.com/apache/datafusion/pull/20378#issuecomment-3906878700
run benchmark clickbench_partitioned
DATAFUSION_EXECUTION_PARQUET_PUSHDOWN_FILTERS=true
DATAFUSION_EXECUTION_PARQUET_REORDER_FILTERS=true
--
This is an automated mes
adriangb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3905154744
I do get your point. TPCH / TPCDS will essentially not use late
materialization off/ `RowFilter` because like you say all files are opened at
once.
> Because a disabled
xanderbailey commented on PR #20358:
URL: https://github.com/apache/datafusion/pull/20358#issuecomment-3905215154
Warning that spark has `spark.sql.mapKeyDedupPolicy`
```
spark.sql.mapKeyDedupPolicy | EXCEPTION | The policy to deduplicate map keys
in builtin function: CreateMap, M
github-actions[bot] commented on PR #2221:
URL:
https://github.com/apache/datafusion-comet/pull/2221#issuecomment-3906107507
Thank you for your contribution. Unfortunately, this pull request is stale
because it has been open 60 days with no activity. Please remove the stale
label or commen
github-actions[bot] commented on PR #1992:
URL:
https://github.com/apache/datafusion-comet/pull/1992#issuecomment-3906107575
Thank you for your contribution. Unfortunately, this pull request is stale
because it has been open 60 days with no activity. Please remove the stale
label or commen
github-actions[bot] commented on PR #2312:
URL:
https://github.com/apache/datafusion-comet/pull/2312#issuecomment-3906107436
Thank you for your contribution. Unfortunately, this pull request is stale
because it has been open 60 days with no activity. Please remove the stale
label or commen
evangelisilva commented on PR #20138:
URL: https://github.com/apache/datafusion/pull/20138#issuecomment-3905070967
@berkaysynnada I have updated the PR based on your feedback:
* **Fixed Formatting**: Ran `cargo fmt` to ensure everything aligns with
the project's style.
* **Clea
Dandandan commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3905071439
See https://github.com/apache/datafusion/pull/20160#issuecomment-3905053370
I think approaches to adaptiveness/selectivity tracking also need to work
_during_ file scan
AlyAbdelmoneim commented on PR #20253:
URL: https://github.com/apache/datafusion/pull/20253#issuecomment-3906679565
Hi @Jefffrey, the test failure I’m seeing doesn’t seem related to my
changes, it still occurs on the `main` branch. You can reproduce it by running:
```bash
cargo
Dandandan commented on code in PR #20364:
URL: https://github.com/apache/datafusion/pull/20364#discussion_r2809091594
##
datafusion/functions-nested/src/set_ops.rs:
##
@@ -527,42 +531,52 @@ fn general_array_distinct(
if array.is_empty() {
return Ok(Arc::new(array.c
mkleen commented on PR #20047:
URL: https://github.com/apache/datafusion/pull/20047#issuecomment-3904420250
@nuno-faria I really appreciate the thorough feedback — it’s very helpful.
I’ll dig into this.
--
This is an automated message from the Apache Git Service.
To respond to the message
alamb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3904422160
> Maybe I'm just being biased here but I personally think the expensive to
evaluate but not helpful join dynamic filters are just a pathological case of
"expensive low selectivity
alamb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3904425520
Thinking more about this, I wonder if we could model the choice of where to
evaluate a filter as a dynamic filter 🤔
Aka make two filters for each predicate
* The one in
adriangb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3904432303
> Thinking more about this, I wonder if we could model the choice of where
to evaluate a filter as a dynamic filter 🤔
>
> Aka make two filters for each predicate
>
adriangb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3904434055
> > Maybe I'm just being biased here but I personally think the expensive to
evaluate but not helpful join dynamic filters are just a pathological case of
"expensive low select
AlonSpivack commented on issue #15161:
URL: https://github.com/apache/datafusion/issues/15161#issuecomment-3904440723
I'm hitting this bug in production on
DataFusion v52, and it's causing silently incorrect
query results across multiple scenarios.
I want to add important context beyond
suibianwanwank commented on issue #8777:
URL: https://github.com/apache/datafusion/issues/8777#issuecomment-3904440991
> Yes. Just restating the deadlock concern from the issue description. I
generated this diagram to show the problem - if the probe side buffer is full,
the "FanoutExec" is
theirix commented on issue #20367:
URL: https://github.com/apache/datafusion/issues/20367#issuecomment-390713
take
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To un
Dandandan commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904523263
> Wonder if I'm infinite looping it or something :(
Yes I think previously it got stuck during infinite loops / extremely long
running tasks.
--
This is an automated messa
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904526739
> > Wonder if I'm infinite looping it or something :(
>
> Yes I think previously it got stuck during infinite loops / extremely long
running tasks.
My bad I’ll try to a
theirix opened a new pull request, #20368:
URL: https://github.com/apache/datafusion/pull/20368
## Which issue does this PR close?
- Closes #20367.
## Rationale for this change
It's more ergonomic to have colored diffs in sqllogictest's output.
The upstream librar
theirix opened a new issue, #20367:
URL: https://github.com/apache/datafusion/issues/20367
### Is your feature request related to a problem or challenge?
It would be nice to have colored diffs in sqllogictest's output - easier to
see differences.
### Describe the solution you'd
neilconway commented on code in PR #20361:
URL: https://github.com/apache/datafusion/pull/20361#discussion_r2809204758
##
datafusion/functions/src/string/concat_ws.rs:
##
@@ -546,4 +564,41 @@ mod tests {
Ok(())
}
+
+#[test]
+fn concat_ws_utf8view_scalar_s
Dandandan commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904317167
FYI @alamb
> Hm it seems stuck again
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
UR
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904383525
@Dandandan this is mostly vibe coded, I'm only 50% confident it even makes
sense without reviewing the code fwiw
--
This is an automated message from the Apache Git Service.
To re
adriangb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3904395716
> Make dynamic filters pruning-only for the moment (behind a flag) and only
push down static filters to the parquet reader (i.e. await results here
https://github.com/apache/da
nuno-faria commented on code in PR #20047:
URL: https://github.com/apache/datafusion/pull/20047#discussion_r2809240718
##
datafusion-cli/src/main.rs:
##
@@ -647,9 +644,9 @@ mod tests {
+---+-+-+--+
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904489674
show benchmark queue
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific com
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904490794
Wonder if I'm infinite looping it or something :(
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL ab
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904489818
🤖 Hi @adriangb, you asked to view the benchmark queue
(https://github.com/apache/datafusion/pull/20363#issuecomment-3904489674).
| Job | User | Benchmarks | Comment |
|
Dandandan commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3904610347
> Thinking more about this, I wonder if we could model the choice of where
to evaluate a filter as a dynamic filter 🤔
>
> Aka make two filters for each predicate
>
Dandandan commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3903918629
show benchmark queue
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific co
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3903918963
🤖 Hi @Dandandan, you asked to view the benchmark queue
(https://github.com/apache/datafusion/pull/20363#issuecomment-3903918629).
| Job | User | Benchmarks | Comment |
|
Dandandan commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3903920732
Hm it seems stuck again
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific
cj-zhukov opened a new pull request, #20366:
URL: https://github.com/apache/datafusion/pull/20366
## Which issue does this PR close?
- Closes #https://github.com/apache/datafusion/issues/18279.
## Rationale for this change
## What changes are included in t
cj-zhukov commented on PR #20366:
URL: https://github.com/apache/datafusion/pull/20366#issuecomment-3903865617
### High-Level Overview
This PR refactors the three percentile functions:
- `percentile_cont`
- `approx_percentile_cont`
- `approx_percentile_cont_with_weight`
Ch
xanderbailey commented on code in PR #20361:
URL: https://github.com/apache/datafusion/pull/20361#discussion_r2809008987
##
datafusion/sqllogictest/test_files/expr.slt:
##
@@ -504,6 +504,19 @@ abc
statement ok
drop table foo
+# concat_ws with a Utf8View column as separator
+
neilconway commented on PR #20317:
URL: https://github.com/apache/datafusion/pull/20317#issuecomment-3904688713
@Jefffrey Is this okay to land in `main`, do you think? Lmk if you have
other feedback or concerns.
--
This is an automated message from the Apache Git Service.
To respond to th
neilconway commented on PR #20278:
URL: https://github.com/apache/datafusion/pull/20278#issuecomment-3904687970
@martin-g Is this okay to land in `main`, do you think? Lmk if you have
other feedback or concerns.
--
This is an automated message from the Apache Git Service.
To respond to th
xitep commented on issue #2218:
URL:
https://github.com/apache/datafusion-sqlparser-rs/issues/2218#issuecomment-3904733068
i believe your suggestion could lead to reducing the size of the `Statement`
(it's about 2kb right now :/)
--
This is an automated message from the Apache Git Servic
SubhamSinghal opened a new pull request, #20370:
URL: https://github.com/apache/datafusion/pull/20370
## Which issue does this PR close?
- Closes https://github.com/apache/datafusion-comet/issues/3434
## Rationale for this change
Adding support for reading parquet field_i
guan404ming commented on PR #2212:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/2212#issuecomment-3904671284
Thanks!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific c
ethan-tyler opened a new pull request, #20369:
URL: https://github.com/apache/datafusion/pull/20369
## Which issue does this PR close?
- Closes #13614
## Rationale for this change
`LazyMemoryExec` currently uses generator closures (`LazyBatchGenerator`) as
its partition
neilconway commented on PR #20306:
URL: https://github.com/apache/datafusion/pull/20306#issuecomment-3904739530
Proposal:
1. Remove the early return from `coerce_arguments_for_signature()`, because
that seems wrong in any case. (I'm happy to send a PR for this or you can,
@Acfboy --
theirix commented on issue #8795:
URL: https://github.com/apache/datafusion/issues/8795#issuecomment-3904855285
The floor and ceil udfs now support decimal return type via #18979.
Non-trivial functions like pow, log, etc. are also supported (linked in the
parent EPIC).
So I thi
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904954170
show benchmark queue
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific com
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3904954291
🤖 Hi @adriangb, you asked to view the benchmark queue
(https://github.com/apache/datafusion/pull/20363#issuecomment-3904954170).
| Job | User | Benchmarks | Comment |
|
Dandandan commented on code in PR #19639:
URL: https://github.com/apache/datafusion/pull/19639#discussion_r2809847688
##
datafusion/datasource-parquet/src/row_filter.rs:
##
@@ -654,6 +711,211 @@ pub fn build_row_filter(
.map(|filters| Some(RowFilter::new(filters)))
}
Dandandan commented on PR #20160:
URL: https://github.com/apache/datafusion/pull/20160#issuecomment-3905053370
> [#20160
(comment)](https://github.com/apache/datafusion/pull/20160#issuecomment-3902329306)
>
> This is the main improvement.
Ok - yes I see some improvements here a
dependabot[bot] opened a new pull request, #1454:
URL: https://github.com/apache/datafusion-ballista/pull/1454
Bumps [tonic-prost](https://github.com/hyperium/tonic) from 0.14.3 to 0.14.4.
Release notes
Sourced from https://github.com/hyperium/tonic/releases";>tonic-prost's
release
dependabot[bot] opened a new pull request, #1456:
URL: https://github.com/apache/datafusion-ballista/pull/1456
Bumps [libc](https://github.com/rust-lang/libc) from 0.2.181 to 0.2.182.
Release notes
Sourced from https://github.com/rust-lang/libc/releases";>libc's releases.
0.2
dependabot[bot] opened a new pull request, #1457:
URL: https://github.com/apache/datafusion-ballista/pull/1457
Bumps [tonic-build](https://github.com/hyperium/tonic) from 0.14.3 to 0.14.4.
Release notes
Sourced from https://github.com/hyperium/tonic/releases";>tonic-build's
release
dependabot[bot] opened a new pull request, #1455:
URL: https://github.com/apache/datafusion-ballista/pull/1455
Bumps [tonic](https://github.com/hyperium/tonic) from 0.14.3 to 0.14.4.
Release notes
Sourced from https://github.com/hyperium/tonic/releases";>tonic's releases.
v0.
dependabot[bot] opened a new pull request, #1458:
URL: https://github.com/apache/datafusion-ballista/pull/1458
Bumps [uuid](https://github.com/uuid-rs/uuid) from 1.20.0 to 1.21.0.
Release notes
Sourced from https://github.com/uuid-rs/uuid/releases";>uuid's releases.
v1.21.0
dependabot[bot] opened a new pull request, #1459:
URL: https://github.com/apache/datafusion-ballista/pull/1459
Bumps [tonic-prost-build](https://github.com/hyperium/tonic) from 0.14.3 to
0.14.4.
Release notes
Sourced from https://github.com/hyperium/tonic/releases";>tonic-prost-bui
Acfboy commented on PR #20306:
URL: https://github.com/apache/datafusion/pull/20306#issuecomment-3906408699
Thanks @neilconway ! You are right. I have changed the pr and re-request
reivews.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log
adriangb commented on issue #20324:
URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3905097162
> See [#20160
(comment)](https://github.com/apache/datafusion/pull/20160#issuecomment-3905053370)
>
> I think approaches to adaptiveness/selectivity tracking also need to
erenavsarogullari commented on issue #20371:
URL: https://github.com/apache/datafusion/issues/20371#issuecomment-3905109121
take
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comme
erenavsarogullari opened a new issue, #20371:
URL: https://github.com/apache/datafusion/issues/20371
### Is your feature request related to a problem or challenge?
Currently, `datafusion.runtime.max_temp_directory_size` is a disk based
config but when it is set as `invalid limit` or `
evangelisilva opened a new pull request, #20376:
URL: https://github.com/apache/datafusion/pull/20376
# UDTF Argument Coercion Suppression
## Which issue does this PR close?
Closes #20293.
## Rationale for this change
Currently, User-Defined Table Functions (UDTFs)
CuteChuanChuan commented on issue #3165:
URL:
https://github.com/apache/datafusion-comet/issues/3165#issuecomment-3906750613
I have a question about implementing map_filter.
Spark's `map_filter` requires lambda syntax:
```sql
SELECT map_filter(map(1, 0, 2, 2), (k, v) -> k > v)
alamb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905143729
run benchmark tpch
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comm
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905144070
🤖 `./gh_compare_branch.sh`
[gh_compare_branch.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_branch.sh)
Running
Linux aal-dev 6.14.0-1018-gc
alamb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905144081
I restarted the job runner.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specifi
alamb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905145488
It might be time to invest in a more legit benchmark runner strategy -- my
bash script nest is not super reliable.
--
This is an automated message from the Apache Git Service.
T
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905798773
🤖 Hi @adriangb, thanks for the request
(https://github.com/apache/datafusion/pull/20363#issuecomment-3905798461).
[`scrape_comments.py`](https://github.com/alamb/datafusio
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905800999
run benchmarks
DATAFUSION_EXECUTION_PARQUET_PUSHDOWN_FILTERS=true
DATAFUSION_EXECUTION_PARQUET_REORDER_FILTERS=true
--
This is an automated message from the Apache Git Servic
alamb-ghbot commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905800566
🤖 `./gh_compare_branch.sh`
[gh_compare_branch.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_branch.sh)
Running
Linux aal-dev 6.14.0-1018-gc
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905798461
run benchmark tpds
DATAFUSION_EXECUTION_PARQUET_PUSHDOWN_FILTERS=true
DATAFUSION_EXECUTION_PARQUET_REORDER_FILTERS=true
--
This is an automated message from the Apache Git Se
adriangb commented on PR #20363:
URL: https://github.com/apache/datafusion/pull/20363#issuecomment-3905800281
run benchmark tpcds
DATAFUSION_EXECUTION_PARQUET_PUSHDOWN_FILTERS=true
DATAFUSION_EXECUTION_PARQUET_REORDER_FILTERS=true
--
This is an automated message from the Apache Git S
erenavsarogullari opened a new issue, #20373:
URL: https://github.com/apache/datafusion/issues/20373
### Is your feature request related to a problem or challenge?
Minor refactoring on error message by exposing required config name for the
end user. This is follow-up PR to both PR: #2
neilconway opened a new pull request, #20374:
URL: https://github.com/apache/datafusion/pull/20374
## Which issue does this PR close?
- Partially addresses #18181.
## Rationale for this change
Previous observations in #18181 suggested that `array_has` is relativel
erenavsarogullari commented on issue #20373:
URL: https://github.com/apache/datafusion/issues/20373#issuecomment-3905193811
take
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comme
Dandandan commented on issue #20325:
URL: https://github.com/apache/datafusion/issues/20325#issuecomment-3905282899
In addition to some of the overhead you already mentioned (CachedArrayReader
/ skips / filter + concat) that could be reduced, I think a lot is actually the
IO pattern.
neilconway commented on PR #20374:
URL: https://github.com/apache/datafusion/pull/20374#issuecomment-3905768726
Benchmarks:
```
group vanilla
opt
-
92 matches
Mail list logo
