andygrove commented on code in PR #3649:
URL: https://github.com/apache/datafusion-comet/pull/3649#discussion_r2906589224
##
native/core/src/execution/jni_api.rs:
##
@@ -952,6 +952,7 @@ pub unsafe extern "system" fn
Java_org_apache_comet_Native_columnarToRowConvert(
) -> jni::
mbutrovich commented on code in PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#discussion_r2906925439
##
datafusion/physical-plan/src/joins/semi_anti_sort_merge_join/stream.rs:
##
@@ -0,0 +1,1160 @@
+// Licensed to the Apache Software Foundation (ASF) under one
alamb commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2906927341
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements
adriangb commented on code in PR #20749:
URL: https://github.com/apache/datafusion/pull/20749#discussion_r2898345002
##
datafusion/expr/src/logical_plan/plan.rs:
##
@@ -3490,7 +3490,9 @@ pub struct Aggregate {
pub input: Arc,
/// Grouping expressions
pub group_exp
kazantsev-maksim opened a new pull request, #20825:
URL: https://github.com/apache/datafusion/pull/20825
## Which issue does this PR close?
N/A
## Rationale for this change
Add new spark function:
https://spark.apache.org/docs/latest/api/sql/index.html#dayname
##
alamb commented on PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#issuecomment-4025539235
What I am planning to do next in this PR (after I finish up some other
things for work) is
1. Integrate in "morsels" into the Parquet opener flow (as a proof of
concept)
2. Sketc
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2907084995
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2907084995
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
adriangb commented on PR #20426:
URL: https://github.com/apache/datafusion/pull/20426#issuecomment-4026458043
> I'm not sure if i can give meaningful contribution in this case, ballista
is relaying on datafusion for this behaviour.
>
> would we need to capture change of behaviour some
jonathanc-n commented on code in PR #20768:
URL: https://github.com/apache/datafusion/pull/20768#discussion_r2907643585
##
datafusion/common/src/utils/aggregate.rs:
##
@@ -0,0 +1,117 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor licens
mbutrovich commented on code in PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#discussion_r2907668997
##
datafusion/physical-plan/src/joins/semi_anti_sort_merge_join/stream.rs:
##
@@ -0,0 +1,1218 @@
+// Licensed to the Apache Software Foundation (ASF) under one
milenkovicm commented on PR #20426:
URL: https://github.com/apache/datafusion/pull/20426#issuecomment-4026563388
Maybe sending an email to dev list for visibility would make sense, would it?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log
adriangb commented on code in PR #20830:
URL: https://github.com/apache/datafusion/pull/20830#discussion_r2907975070
##
datafusion/sql/src/expr/mod.rs:
##
@@ -612,16 +612,24 @@ impl SqlToRel<'_, S> {
planner_context,
),
_ =>
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4026969643
🤖 `./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 code in PR #20830:
URL: https://github.com/apache/datafusion/pull/20830#discussion_r2907975070
##
datafusion/sql/src/expr/mod.rs:
##
@@ -612,16 +612,24 @@ impl SqlToRel<'_, S> {
planner_context,
),
_ =>
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4026969381
🤖: Benchmark completed
Details
```
Comparing HEAD and parquet-morsel-driven-execution-237164415184908839
Benchmark clickbench_pa
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4026973928
🤖 `./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-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4026973719
🤖: Benchmark completed
Details
```
Comparing HEAD and parquet-morsel-driven-execution-237164415184908839
Benchmark tpch_sf1.json
andygrove opened a new pull request, #3652:
URL: https://github.com/apache/datafusion-comet/pull/3652
## Summary
- Enable `debug-assertions = true` in the CI cargo profile to catch
potential issues with unsafe code at test time
- Enable `RUST_BACKTRACE=1` in all CI workflows to get ful
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2908022899
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
SergioChan opened a new pull request, #20833:
URL: https://github.com/apache/datafusion/pull/20833
## Summary
- fix planning for set-operation operands (`UNION` / `EXCEPT` / `INTERSECT`)
when a non-left operand has repeated unnamed projection literals
- on duplicate projection-name pla
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2908022899
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
cetra3 commented on code in PR #20822:
URL: https://github.com/apache/datafusion/pull/20822#discussion_r2908036318
##
datafusion/datasource-parquet/src/row_filter.rs:
##
@@ -294,6 +308,42 @@ impl<'schema> PushdownChecker<'schema> {
}
}
+/// Checks whether a s
cetra3 commented on code in PR #20822:
URL: https://github.com/apache/datafusion/pull/20822#discussion_r2908034845
##
datafusion/datasource-parquet/src/row_filter.rs:
##
@@ -368,6 +418,47 @@ impl TreeNodeVisitor<'_> for PushdownChecker<'_> {
type Node = Arc;
fn f_dow
stuhood commented on PR #20832:
URL: https://github.com/apache/datafusion/pull/20832#issuecomment-4027029835
This did not fail because `sqllogictest-sqlite` did not run for some reason:
likely because `.github/workflows/labeler/labeler-config.yml` will not match
for the edits that have been
mbutrovich commented on PR #20832:
URL: https://github.com/apache/datafusion/pull/20832#issuecomment-4027020228
+1 from me, I just raised this issue with @andygrove on Comet today when we
are adding `debug_assert` around some code and I commented that "we don't run
that in CI anyway."
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2908038777
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2908038777
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4027038769
🤖: Benchmark completed
Details
```
Comparing HEAD and parquet-morsel-driven-execution-237164415184908839
Benchmark tpcds_sf1.jso
stuhood commented on PR #20832:
URL: https://github.com/apache/datafusion/pull/20832#issuecomment-4027048631
> It should already be enabled for `[profile.ci]` though, right? I don't
mind it being explicit, just curious.
Yea, it looks like you are right:
https://doc.rust-lang.org/carg
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2908022899
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
comphead commented on PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#issuecomment-4025063993
One thing to mention: to control the flag
`datafusion.optimizer.enable_semi_anti_sort_merge_join` or
`DATAFUSION_OPTIMIZER_ENABLE_SEMI_ANTI_SORT_MERGE_JOIN` in `bench.sh`, at least
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2906896138
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
adriangb commented on PR #20822:
URL: https://github.com/apache/datafusion/pull/20822#issuecomment-4025483431
Let's leave this open for a day to collect feedback 😃
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
U
milenkovicm commented on issue #19692:
URL: https://github.com/apache/datafusion/issues/19692#issuecomment-4025493986
@benbellick is investigating at the moment
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
mbutrovich commented on code in PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#discussion_r2907131246
##
datafusion/physical-plan/src/joins/semi_anti_sort_merge_join/stream.rs:
##
@@ -0,0 +1,1160 @@
+// Licensed to the Apache Software Foundation (ASF) under one
mbutrovich commented on code in PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#discussion_r2907131246
##
datafusion/physical-plan/src/joins/semi_anti_sort_merge_join/stream.rs:
##
@@ -0,0 +1,1160 @@
+// Licensed to the Apache Software Foundation (ASF) under one
milenkovicm opened a new pull request, #20827:
URL: https://github.com/apache/datafusion/pull/20827
## Which issue does this PR close?
Relates to #20785
## Rationale for this change
substrait has released patch release 0.62.3 which is backward incompatible,
which breaks
milenkovicm commented on issue #19692:
URL: https://github.com/apache/datafusion/issues/19692#issuecomment-4026230209
created #20827 with pinned version
--
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 t
Dandandan commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4026228743
run benchmark clickbench_partitioned tpch tpcds
DATAFUSION_EXECUTION_PARQUET_PUSHDOWN_FILTERS=true
DATAFUSION_EXECUTION_PARQUET_REORDER_FILTERS=true
--
This is a
buraksenn commented on issue #2548:
URL: https://github.com/apache/datafusion/issues/2548#issuecomment-4026245610
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
friendlymatthew opened a new pull request, #20829:
URL: https://github.com/apache/datafusion/pull/20829
## Which issue does this PR close?
- Closes https://github.com/apache/datafusion/issues/20828
## Rationale for this change
This PR adds a series of benchmarks that comp
milenkovicm commented on PR #20785:
URL: https://github.com/apache/datafusion/pull/20785#issuecomment-4026243931
I have pinned version of substrait for df.53 in #20827 if no better
suggestion
--
This is an automated message from the Apache Git Service.
To respond to the message, please l
buraksenn commented on issue #2547:
URL: https://github.com/apache/datafusion/issues/2547#issuecomment-4026245096
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
friendlymatthew opened a new issue, #20828:
URL: https://github.com/apache/datafusion/issues/20828
https://github.com/apache/datafusion/pull/20822 allows us to push struct
field filters down to the parquet source. It would be good to have a series of
benchmarks so we can measure the impact
alamb commented on PR #20749:
URL: https://github.com/apache/datafusion/pull/20749#issuecomment-4026309324
> I'm concerned that we start to have multiple optimizers that have to
coordinate (namely CSE, the expression pushdown for get_field and this) but I
don't have any suggestions for a be
milenkovicm commented on PR #20426:
URL: https://github.com/apache/datafusion/pull/20426#issuecomment-4026321284
I'm not sure if i can give meaningful contribution in this case, ballista is
relaying on datafusion for this behaviour.
would we need to capture change of behaviour somewh
alamb commented on code in PR #20749:
URL: https://github.com/apache/datafusion/pull/20749#discussion_r2907571484
##
datafusion/expr/src/logical_plan/plan.rs:
##
@@ -3490,7 +3490,9 @@ pub struct Aggregate {
pub input: Arc,
/// Grouping expressions
pub group_expr:
rluvaton commented on code in PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#discussion_r2907574950
##
datafusion/physical-plan/src/joins/semi_anti_sort_merge_join/stream.rs:
##
@@ -0,0 +1,1218 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+/
alamb commented on PR #15532:
URL: https://github.com/apache/datafusion/pull/15532#issuecomment-4026332826
Here is a new proposal:
- https://github.com/apache/datafusion/pull/20749
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to G
coderfender commented on code in PR #20555:
URL: https://github.com/apache/datafusion/pull/20555#discussion_r2907577014
##
datafusion/spark/src/function/conversion/cast.rs:
##
@@ -0,0 +1,633 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributo
buraksenn opened a new pull request, #20830:
URL: https://github.com/apache/datafusion/pull/20830
## Which issue does this PR close?
- Closes #2548.
## Rationale for this change
ANY operator only supports equality check
## What changes are included in this PR?
Adds supp
romanoff commented on PR #2266:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/2266#issuecomment-4027676269
@iffyio Updated. Thank you
--
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
mbutrovich closed pull request #3648: test: DataFusion PR #20806 (specialized
SemiAntiSortMergeJoin operator)
URL: https://github.com/apache/datafusion-comet/pull/3648
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
U
romanoff commented on PR #2265:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/2265#issuecomment-4027686256
@iffyio Updated. Thank you
--
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
comphead commented on code in PR #3649:
URL: https://github.com/apache/datafusion-comet/pull/3649#discussion_r2908545294
##
native/Cargo.toml:
##
@@ -71,4 +71,5 @@ strip = "debuginfo"
inherits = "release"
lto = false # Skip LTO for faster linking
codegen-units = 16
adriangb commented on code in PR #13103:
URL: https://github.com/apache/datafusion/pull/13103#discussion_r2908543586
##
datafusion/core/benches/sql_planner.rs:
##
@@ -258,20 +303,25 @@ fn criterion_benchmark(c: &mut Criterion) {
})
});
-c.bench_function("logi
andygrove commented on PR #3649:
URL:
https://github.com/apache/datafusion-comet/pull/3649#issuecomment-4027713651
test failure is an existing issue in main branch and is fixed in
https://github.com/apache/datafusion-comet/pull/3652.
I will rebase this PR once that is merged
--
Th
andygrove commented on PR #3652:
URL:
https://github.com/apache/datafusion-comet/pull/3652#issuecomment-4027715211
@mbutrovich I think this explains the bus error you saw recently
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitH
romanoff commented on PR #2264:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/2264#issuecomment-4027720508
@iffyio Updated. Thank you
--
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
comphead commented on PR #3649:
URL:
https://github.com/apache/datafusion-comet/pull/3649#issuecomment-4027725410
> test failure is an existing issue in main branch and is fixed in #3652.
>
> I will rebase this PR once that is merged
The tests passed on CI, it says `sbt.ForkMai
andygrove commented on PR #3649:
URL:
https://github.com/apache/datafusion-comet/pull/3649#issuecomment-4027728445
> > test failure is an existing issue in main branch and is fixed in #3652.
> > I will rebase this PR once that is merged
>
> The tests passed on CI, it says `sbt.Fork
coderfender commented on PR #20555:
URL: https://github.com/apache/datafusion/pull/20555#issuecomment-4027732114
@martin-g , requesting review to port ceil function from comet to spark
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on t
coderfender commented on PR #20703:
URL: https://github.com/apache/datafusion/pull/20703#issuecomment-4027732995
@martin-g , requesting review to port ceil function from comet to spark
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on t
romanoff commented on PR #2266:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/2266#issuecomment-4027737863
Had to add
https://github.com/apache/datafusion-sqlparser-rs/pull/2266/changes#diff-80f1d10500bf0503869a8a33086830849ab5455192c0269291eefb70d11911e3L3211-R3214
due to fa
andygrove commented on PR #3649:
URL:
https://github.com/apache/datafusion-comet/pull/3649#issuecomment-4027742337
> > > > test failure is an existing issue in main branch and is fixed in
#3652.
> > > > I will rebase this PR once that is merged
> > >
> > >
> > > The tests pass
andygrove commented on PR #3649:
URL:
https://github.com/apache/datafusion-comet/pull/3649#issuecomment-4027740564
> > > test failure is an existing issue in main branch and is fixed in #3652.
> > > I will rebase this PR once that is merged
> >
> >
> > The tests passed on CI, i
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4025092875
🤖 `./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 code in PR #20426:
URL: https://github.com/apache/datafusion/pull/20426#discussion_r2906316372
##
datafusion/core/src/physical_planner.rs:
##
@@ -3436,16 +3436,16 @@ mod tests {
#[tokio::test]
async fn in_list_types() -> Result<()> {
-//
comphead commented on issue #19692:
URL: https://github.com/apache/datafusion/issues/19692#issuecomment-4025076907
> maybe we should backport
[#20785](https://github.com/apache/datafusion/pull/20785) to 53 release. at the
moment build with 52.2 will break with:
> wdyt [@comphead](https:/
CuteChuanChuan commented on PR #20498:
URL: https://github.com/apache/datafusion/pull/20498#issuecomment-4025127060
Addressed review comments:
- Added all-null mask fast path
- Replaced ArrayDataBuilder with safe constructors (PrimitiveArray,
BooleanArray, FixedSizeBinaryArray) and add
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4025330608
🤖 `./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
comphead commented on issue #19692:
URL: https://github.com/apache/datafusion/issues/19692#issuecomment-4025630574
> i would suggest to pin substrait version to previous for 53 release,
instead of merging any of them at this point if you agree
Ic, feel free to create a PR to `branch-5
benbellick commented on issue #20756:
URL: https://github.com/apache/datafusion/issues/20756#issuecomment-4025657071
[Copying my comment from
here](https://github.com/apache/datafusion/pull/20785#issuecomment-4025653255):
> This release of substrait-rs breaks semvar compatibility. This wa
benbellick commented on PR #20785:
URL: https://github.com/apache/datafusion/pull/20785#issuecomment-4025653255
This release of `substrait-rs` breaks semvar compatibility. This was an
oversight on my end due to the fact that `release-plz` didn't detect a
submodule bump as a breaking change.
Dandandan commented on code in PR #20820:
URL: https://github.com/apache/datafusion/pull/20820#discussion_r2907199070
##
datafusion/datasource/src/morsel.rs:
##
@@ -0,0 +1,57 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreem
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4025876117
🤖 `./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
Dandandan commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4025875574
run benchmark tpcds tpch clickbench_partitioned clickbench_extended
--
This is an automated message from the Apache Git Service.
To respond to the message, please log
martin-g commented on code in PR #20426:
URL: https://github.com/apache/datafusion/pull/20426#discussion_r2908005743
##
datafusion/expr-common/src/signature.rs:
##
@@ -158,7 +158,7 @@ pub enum Arity {
pub enum TypeSignature {
/// One or more arguments of a common type out
coderfender commented on code in PR #20555:
URL: https://github.com/apache/datafusion/pull/20555#discussion_r2908195575
##
datafusion/spark/src/function/conversion/cast.rs:
##
@@ -0,0 +1,633 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributo
LiaCastaneda commented on code in PR #18921:
URL: https://github.com/apache/datafusion/pull/18921#discussion_r2908204189
##
DOC.md:
##
@@ -0,0 +1,1166 @@
+This PR adds support for lambdas with column capture and the `array_transform`
function used to test the lambda implementat
neilconway commented on code in PR #20426:
URL: https://github.com/apache/datafusion/pull/20426#discussion_r2908222551
##
datafusion/expr-common/src/type_coercion/binary.rs:
##
@@ -843,102 +842,100 @@ pub fn try_type_union_resolution_with_struct(
Ok(final_struct_types)
}
Dandandan commented on PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#issuecomment-4027275844
run benchmark tpch DATAFUSION_OPTIMIZER_PREFER_HASH_JOIN=false
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
alamb-ghbot commented on PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#issuecomment-4027276009
🤖 Hi @Dandandan, thanks for the request
(https://github.com/apache/datafusion/pull/20806#issuecomment-4027275844).
[`scrape_comments.py`](https://github.com/alamb/datafusi
andygrove commented on PR #3649:
URL:
https://github.com/apache/datafusion-comet/pull/3649#issuecomment-4024881013
moving to draft while I run new benchmarks to confirm the benefit
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to Git
milenkovicm commented on PR #1494:
URL:
https://github.com/apache/datafusion-ballista/pull/1494#issuecomment-4024885809
please merge if you dont want to add anything else
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and u
andygrove commented on code in PR #3649:
URL: https://github.com/apache/datafusion-comet/pull/3649#discussion_r2906413832
##
native/Cargo.toml:
##
@@ -71,4 +71,5 @@ strip = "debuginfo"
inherits = "release"
lto = false # Skip LTO for faster linking
codegen-units = 16
avantgardnerio closed pull request #20824: Cherry pick fixes from 46
URL: https://github.com/apache/datafusion/pull/20824
--
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 uns
alamb-ghbot commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4024949804
🤖 `./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
avantgardnerio commented on PR #20824:
URL: https://github.com/apache/datafusion/pull/20824#issuecomment-4024953460
Wrong repo again, sorry.
--
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 sp
avantgardnerio opened a new pull request, #20824:
URL: https://github.com/apache/datafusion/pull/20824
(no comment)
--
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 unsub
Dandandan commented on PR #20481:
URL: https://github.com/apache/datafusion/pull/20481#issuecomment-4024948431
run benchmark tpcds tpch clickbench_partitioned clickbench_extended
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub
adriangb commented on code in PR #20822:
URL: https://github.com/apache/datafusion/pull/20822#discussion_r2906480912
##
datafusion/datasource-parquet/src/row_filter.rs:
##
@@ -368,6 +399,31 @@ impl TreeNodeVisitor<'_> for PushdownChecker<'_> {
type Node = Arc;
fn f_d
comphead commented on PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#issuecomment-4025013189
Thanks @mbutrovich, IMO it is great to start replacing current SMJ
implementation with more performant and easier to maintain structure. Even by
pieces. Good sign fuzz tests passed.
mbutrovich commented on code in PR #20806:
URL: https://github.com/apache/datafusion/pull/20806#discussion_r2906537029
##
benchmarks/src/smj.rs:
##
@@ -277,6 +277,7 @@ const SMJ_QUERIES: &[&str] = &[
WHERE EXISTS (
SELECT 1 FROM t2_sorted
WHERE
alamb commented on PR #20749:
URL: https://github.com/apache/datafusion/pull/20749#issuecomment-4026851535
FWIW this PR doesn't add a new optimizer rule, it extends an existing one
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitH
alamb commented on PR #20350:
URL: https://github.com/apache/datafusion/pull/20350#issuecomment-4026842812
Thanks again @sdf-jkl
--
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 commented on code in PR #20749:
URL: https://github.com/apache/datafusion/pull/20749#discussion_r2907885397
##
datafusion/expr/src/udaf.rs:
##
@@ -691,6 +707,74 @@ pub trait AggregateUDFImpl: Debug + DynEq + DynHash + Send
+ Sync {
None
}
+/// Rewrite
alamb commented on PR #20749:
URL: https://github.com/apache/datafusion/pull/20749#issuecomment-4026897337
> > I'm concerned that we start to have multiple optimizers that have to
coordinate (namely CSE, the expression pushdown for get_field and this) but I
don't have any suggestions for a
martin-g commented on code in PR #20433:
URL: https://github.com/apache/datafusion/pull/20433#discussion_r2907911166
##
datafusion/functions/src/math/log.rs:
##
Review Comment:
```suggestion
```
remove some debug leftover
--
This is an automated message from the A
1 - 100 of 371 matches
Mail list logo
