You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@impala.apache.org by "Balazs Hevele (Code Review)" <ge...@cloudera.org> on 2026/03/31 10:43:41 UTC
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Balazs Hevele has uploaded this change for review. ( http://gerrit.cloudera.org:8080/24154
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
TODO:
-add codegen for Tuple::TryDeepCopy
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
7 files changed, 116 insertions(+), 150 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/1
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newchange
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 1
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#5).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
TODO:
-add codegen for Tuple::TryDeepCopy
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
16 files changed, 403 insertions(+), 222 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/5
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 5
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#6).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
TODO:
-add codegen for Tuple::TryDeepCopy
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
16 files changed, 456 insertions(+), 222 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/6
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 6
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Yida Wu, Csaba Ringhofer, Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#12).
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
This patch does not do proper codegen for collection types, instead it
calls the interpreted code for them.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 31% improvement.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
20 files changed, 594 insertions(+), 241 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/12
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 12
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 1:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22053/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 1
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Tue, 31 Mar 2026 11:07:00 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Balazs Hevele has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 15:
(2 comments)
http://gerrit.cloudera.org:8080/#/c/24154/14//COMMIT_MSG
Commit Message:
http://gerrit.cloudera.org:8080/#/c/24154/14//COMMIT_MSG@29
PS14, Line 29:
> Can you add some codegen stats like in https://gerrit.cloudera.org/#/c/2408
Done
http://gerrit.cloudera.org:8080/#/c/24154/14/be/src/runtime/row-batch.h
File be/src/runtime/row-batch.h:
http://gerrit.cloudera.org:8080/#/c/24154/14/be/src/runtime/row-batch.h@361
PS14, Line 361: IR_NO_INLINE Ser
> Should be no inline, right?
Done
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 15
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 10:25:37 +0000
Gerrit-HasComments: Yes
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Yida Wu, Csaba Ringhofer, Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#14).
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
This patch does not do proper codegen for collection types, instead it
calls the interpreted code for them.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 31% improvement.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
20 files changed, 606 insertions(+), 247 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/14
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 14
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Yida Wu, Csaba Ringhofer, Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#11).
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 45% improvement.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
21 files changed, 596 insertions(+), 254 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/11
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 11
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Balazs Hevele has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 14:
Patch 14 is a reabase.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 14
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 07:40:16 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 14:
Build Failed
https://jenkins.impala.io/job/gerrit-code-review-checks/23408/ : Initial code review checks failed. See linked job for details on the failure.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 14
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 08:03:12 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 5:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22090/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 5
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Tue, 07 Apr 2026 12:41:51 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#7).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
19 files changed, 619 insertions(+), 253 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/7
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 7
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 15:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/23416/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 15
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 10:47:31 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 15:
Build started: https://jenkins.impala.io/job/gerrit-verify-dryrun/13803/ DRY_RUN=false
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 15
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 12:54:04 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 3:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22063/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 3
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Wed, 01 Apr 2026 13:15:41 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#2).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
TODO:
-add codegen for Tuple::TryDeepCopy
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
10 files changed, 192 insertions(+), 196 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/2
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 2
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#8).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
20 files changed, 605 insertions(+), 253 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/8
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 8
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 8:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22097/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 8
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Thu, 09 Apr 2026 11:32:38 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 9:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22102/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 9
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Fri, 10 Apr 2026 09:03:06 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Csaba Ringhofer (Code Review)" <ge...@cloudera.org>.
Csaba Ringhofer has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 11:
(12 comments)
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG
Commit Message:
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG@16
PS11, Line 16:
Can you mention that collections are still handled in an interpreted way?
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG@27
PS11, Line 27: SerializeBatchTime changed from 1s797ms to 1s239ms.
Can you check if there is change if codegen is turned off?
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG@28
PS11, Line 28: This is about 45% improvement.
shouldn't we calculate this compared to the larger value?
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/krpc-data-stream-sender-ir.cc
File be/src/runtime/krpc-data-stream-sender-ir.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/krpc-data-stream-sender-ir.cc@74
PS11, Line 74: RETURN_IF_ERROR(
: src->Serialize(dest, compress ? compression_scratch_.get() : nullptr));
nit: I would prefer to have only an inner function in ir.cc instead of the whole things - IMO things like the timer and calling compression shouldn't be here
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch-ir.cc
File be/src/runtime/outbound-row-batch-ir.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch-ir.cc@80
PS11, Line 80: bool IR_ALWAYS_INLINE StatusOK(Status* status) {
: return status->ok();
: }
Is this used somewhere?
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.h
File be/src/runtime/outbound-row-batch.h:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.h@81
PS11, Line 81: assumetyps
typo
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.h@94
PS11, Line 94: class DedupMap : public FixedSizeHashTable<Tuple*, int> {
: public:
: static const char* LLVM_CLASS_NAME;
: };
:
: Status IR_ALWAYS_INLINE AppendTupleWithDedup(const TupleRow* row,
: const TupleRow* prev_row, int tuple_idx, DedupMap* distinct_tuples,
: TupleDescriptor* desc, int byte_size, int num_tuples);
:
: Status IR_NO_INLINE AppendRowWithDedup(
: const TupleRow* row, const TupleRow* prev_row, DedupMap* distinct_tuples,
: const RowDescriptor* row_desc) noexcept;
Adding some comments related to deduplication or pointing to another place that explains it would be nice.
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.cc
File be/src/runtime/outbound-row-batch.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.cc@146
PS11, Line 146: llvm::Value* tuple_desc
It looks unusual that we get tuple desc as value. This is needed to be able to deepcopy collections, right, as that part is not fully codegend? Can you add a comment about this?
Btw would it make sense to not pass this if there are no collections?
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.inline.h
File be/src/runtime/outbound-row-batch.inline.h:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.inline.h@25
PS11, Line 25: #include "util/fixed-size-hash-table.h"
Where is this used?
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc
File be/src/runtime/tuple.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc@594
PS11, Line 594: Value
here and at a few other other places using llvm::Constant* seems clearer to me
It may be even better to add constness somehow to the variable name to make compile vs runtime dataflow easier to follow.
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc@599
PS11, Line 599: succeed
nit: indicating that this means "data_end was reached" would be clearer
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc@641
PS11, Line 641: builder.CreateStore(data_start, data);
: builder.CreateStore(offset_start, offset);
Is resetting needing? The non-codegen code doesn't seem to do this.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 11
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Mon, 29 Jun 2026 17:13:28 +0000
Gerrit-HasComments: Yes
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Balazs Hevele has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 11:
In patch 11, rebase commit and resolved merge conflicts.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 11
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Mon, 29 Jun 2026 15:08:23 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 7:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22092/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 7
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Wed, 08 Apr 2026 13:22:52 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Balazs Hevele has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 12:
(12 comments)
Thanks for the review!
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG
Commit Message:
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG@16
PS11, Line 16:
> Can you mention that collections are still handled in an interpreted way?
Done
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG@27
PS11, Line 27: bin/load-data.py -s 30 -f --workloads tpch
> Can you check if there is change if codegen is turned off?
With codegen turned off, it is about the same as before the change, for this particular query.
http://gerrit.cloudera.org:8080/#/c/24154/11//COMMIT_MSG@28
PS11, Line 28: --table_formats text/none
> shouldn't we calculate this compared to the larger value?
Done
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/krpc-data-stream-sender-ir.cc
File be/src/runtime/krpc-data-stream-sender-ir.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/krpc-data-stream-sender-ir.cc@74
PS11, Line 74:
:
> nit: I would prefer to have only an inner function in ir.cc instead of the
Done
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch-ir.cc
File be/src/runtime/outbound-row-batch-ir.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch-ir.cc@80
PS11, Line 80: bool IR_ALWAYS_INLINE StatusOK(Status* status) {
: return status->ok();
: }
> Is this used somewhere?
Yes, this is used in OutboundRowBatch::CodegenAppendRowWithDedup to early return if AppendTuple failed for a tuple in the row.
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.h
File be/src/runtime/outbound-row-batch.h:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.h@81
PS11, Line 81: assumes th
> typo
Done
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.h@94
PS11, Line 94: class DedupMap : public FixedSizeHashTable<Tuple*, int> {
: public:
: static const char* LLVM_CLASS_NAME;
: };
:
: // Append tuple/row with deduplication:
: // -nullptr tuples will be encoded as -1 in tuple_offsets_
: // -as a fast deduplication for adjacent rows, if the tuple points to the same memory
: // as the previous row's corresponding tuple, its offset will be duplicated in
: // tuple_offsets_, and the call to AppendTuple will be spared
: // -optionally, if a DedupMap is provided in distinct_tuples, the tuple's hash will be
: // compared against all previous tuples, an
> Adding some comments related to deduplication or pointing to another place
Done
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.cc
File be/src/runtime/outbound-row-batch.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.cc@146
PS11, Line 146: // This is passed throu
> It looks unusual that we get tuple desc as value. This is needed to be able
I added a comment clarifying this.
Currently, there is no easy way to have a separate function signature without a TupleDesc* argument as long as collection types are not codegen'd. Added a todo for that.
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.inline.h
File be/src/runtime/outbound-row-batch.inline.h:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/outbound-row-batch.inline.h@25
PS11, Line 25:
> Where is this used?
Removed it.
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc
File be/src/runtime/tuple.cc:
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc@594
PS11, Line 594: Const
> here and at a few other other places using llvm::Constant* seems clearer to
Done
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc@599
PS11, Line 599: succeed
> nit: indicating that this means "data_end was reached" would be clearer
Done
http://gerrit.cloudera.org:8080/#/c/24154/11/be/src/runtime/tuple.cc@641
PS11, Line 641: builder.CreateStore(data_start, data);
: builder.CreateStore(offset_start, offset);
> Is resetting needing? The non-codegen code doesn't seem to do this.
The interpreted code does it the other way:
-creates a copy of the pointer
-it advances the value of the copy
-only updates the passed in pointer if the deepcopy succeeded
The comment in tuple.h also explicitly says "If it fails, 'data' will be the same as before the call", though I didn't check if any uses rely on that.
It was easier to reset the passed in argument upon failure in codegen code, but it should be possible to do it the other way as well.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 12
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Mon, 20 Jul 2026 08:48:02 +0000
Gerrit-HasComments: Yes
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 11:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/23050/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 11
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Mon, 29 Jun 2026 15:30:08 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Csaba Ringhofer (Code Review)" <ge...@cloudera.org>.
Csaba Ringhofer has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 12: Code-Review+1
(1 comment)
http://gerrit.cloudera.org:8080/#/c/24154/12/be/src/runtime/row-batch-ir.cc
File be/src/runtime/row-batch-ir.cc:
http://gerrit.cloudera.org:8080/#/c/24154/12/be/src/runtime/row-batch-ir.cc@27
PS12, Line 27: UseFullDedup
optional: This could be calculated at codegen time, as it actually only depends on the the row descriptor, not the actually row batch.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 12
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Mon, 27 Jul 2026 07:11:25 +0000
Gerrit-HasComments: Yes
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Balazs Hevele has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 13:
(1 comment)
http://gerrit.cloudera.org:8080/#/c/24154/12/be/src/runtime/row-batch-ir.cc
File be/src/runtime/row-batch-ir.cc:
http://gerrit.cloudera.org:8080/#/c/24154/12/be/src/runtime/row-batch-ir.cc@27
PS12, Line 27: UseFullDedup
> optional: This could be calculated at codegen time, as it actually only dep
Done
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 13
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 04:02:20 +0000
Gerrit-HasComments: Yes
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has submitted this change and it was merged. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
This patch does not do proper codegen for collection types, instead it
calls the interpreted code for them.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 31% improvement.
Codegen:
Before:
NumInstructions: 4.01K (4015)
NumOptimizedInstructions: 3.87K (3874)
ModuleBitcodeSize: 3.68 MB (3860700)
After:
NumInstructions: 5.26K (5259)
NumOptimizedInstructions: 5.15K (5151)
ModuleBitcodeSize: 3.71 MB (3892344)
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Reviewed-on: http://gerrit.cloudera.org:8080/24154
Reviewed-by: Csaba Ringhofer <cs...@cloudera.com>
Tested-by: Impala Public Jenkins <im...@cloudera.com>
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
20 files changed, 606 insertions(+), 247 deletions(-)
Approvals:
Csaba Ringhofer: Looks good to me, approved
Impala Public Jenkins: Verified
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: merged
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 16
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 15: Verified+1
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 15
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 17:46:32 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 2:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22062/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 2
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Wed, 01 Apr 2026 09:56:37 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#3).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
TODO:
-add codegen for Tuple::TryDeepCopy
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
14 files changed, 343 insertions(+), 221 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/3
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 3
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 4:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22086/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 4
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Tue, 07 Apr 2026 03:23:46 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#10).
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 45% improvement.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
21 files changed, 606 insertions(+), 254 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/10
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 10
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 13:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/23407/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 13
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 04:24:09 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 12:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/23315/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 12
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Mon, 20 Jul 2026 09:11:52 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Yida Wu, Csaba Ringhofer, Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#13).
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
This patch does not do proper codegen for collection types, instead it
calls the interpreted code for them.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 31% improvement.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
20 files changed, 606 insertions(+), 247 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/13
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 13
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Csaba Ringhofer (Code Review)" <ge...@cloudera.org>.
Csaba Ringhofer has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 14:
(2 comments)
http://gerrit.cloudera.org:8080/#/c/24154/14//COMMIT_MSG
Commit Message:
http://gerrit.cloudera.org:8080/#/c/24154/14//COMMIT_MSG@29
PS14, Line 29:
Can you add some codegen stats like in https://gerrit.cloudera.org/#/c/24089/ ?
http://gerrit.cloudera.org:8080/#/c/24154/14/be/src/runtime/row-batch.h
File be/src/runtime/row-batch.h:
http://gerrit.cloudera.org:8080/#/c/24154/14/be/src/runtime/row-batch.h@361
PS14, Line 361: IR_ALWAYS_INLINE
Should be no inline, right?
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 14
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 08:56:16 +0000
Gerrit-HasComments: Yes
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Csaba Ringhofer (Code Review)" <ge...@cloudera.org>.
Csaba Ringhofer has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
Patch Set 15: Code-Review+2
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 15
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>
Gerrit-Comment-Date: Tue, 28 Jul 2026 12:53:24 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 9: Verified+1
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 9
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Fri, 10 Apr 2026 13:53:02 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 8:
Build started: https://jenkins.impala.io/job/gerrit-verify-dryrun/13307/ DRY_RUN=true
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 8
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Thu, 09 Apr 2026 11:45:01 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 6:
Build Successful
https://jenkins.impala.io/job/gerrit-code-review-checks/22091/ : Initial code review checks passed. Use gerrit-verify-dryrun-external or gerrit-verify-dryrun to run full precommit tests.
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 6
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Wed, 08 Apr 2026 08:21:00 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#9).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 45% improvement.
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
21 files changed, 606 insertions(+), 254 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/9
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 9
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#4).
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
TODO:
-add codegen for Tuple::TryDeepCopy
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
M be/src/runtime/krpc-data-stream-sender-ir.cc
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
14 files changed, 353 insertions(+), 221 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/4
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 4
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 9:
Build started: https://jenkins.impala.io/job/gerrit-verify-dryrun/13310/ DRY_RUN=true
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 9
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Fri, 10 Apr 2026 09:24:57 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
Posted by "Impala Public Jenkins (Code Review)" <ge...@cloudera.org>.
Impala Public Jenkins has posted comments on this change. ( http://gerrit.cloudera.org:8080/24154 )
Change subject: WIP IMPALA-14852 Codegen tuple copy for Broadcast Exchange
......................................................................
Patch Set 8: Verified-1
Build failed: https://jenkins.impala.io/job/gerrit-verify-dryrun/13307/
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 8
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Comment-Date: Thu, 09 Apr 2026 16:03:46 +0000
Gerrit-HasComments: No
[Impala-ASF-CR] IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Posted by "Balazs Hevele (Code Review)" <ge...@cloudera.org>.
Hello Yida Wu, Csaba Ringhofer, Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/24154
to look at the new patch set (#15).
Change subject: IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
......................................................................
IMPALA-14852 Codegen tuple TryDeepCopy for Broadcast Exchange
Use Tuple::TryDeepCopy in RowBatch/OutboundRowBatch instead of DeepCopy.
For most tuples, this should save an extra size calculation, because the
size of the whole row is not calculated anymore before the copying, only
if a tuple doesn't fit, is its size calculated.
A codegen'd version of Tuple::TryDeepCopy is used for each tuple in the
row, which is generated based on the Tuple's Descriptor.
This patch does not do proper codegen for collection types, instead it
calls the interpreted code for them.
Measurements:
Measured with query:
SELECT l1.* FROM tpch30.lineitem l1
INNER JOIN tpch30.lineitem l2
ON l1.l_shipmode = l2.l_shipmode LIMIT 1;
Where tpch30 is generated by:
bin/load-data.py -s 30 -f --workloads tpch
--table_formats text/none,parquet/snap
SerializeBatchTime changed from 1s797ms to 1s239ms.
This is about 31% improvement.
Codegen:
Before:
NumInstructions: 4.01K (4015)
NumOptimizedInstructions: 3.87K (3874)
ModuleBitcodeSize: 3.68 MB (3860700)
After:
NumInstructions: 5.26K (5259)
NumOptimizedInstructions: 5.15K (5151)
ModuleBitcodeSize: 3.71 MB (3892344)
Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
---
M be/src/benchmarks/row-batch-serialize-benchmark.cc
M be/src/codegen/gen_ir_descriptions.py
M be/src/codegen/impala-ir.cc
M be/src/runtime/CMakeLists.txt
A be/src/runtime/descriptors-ir.cc
M be/src/runtime/descriptors.cc
M be/src/runtime/descriptors.h
M be/src/runtime/krpc-data-stream-sender.cc
M be/src/runtime/krpc-data-stream-sender.h
A be/src/runtime/outbound-row-batch-ir.cc
M be/src/runtime/outbound-row-batch.cc
M be/src/runtime/outbound-row-batch.h
M be/src/runtime/outbound-row-batch.inline.h
A be/src/runtime/row-batch-ir.cc
M be/src/runtime/row-batch.cc
M be/src/runtime/row-batch.h
M be/src/runtime/tuple-ir.cc
M be/src/runtime/tuple.cc
M be/src/runtime/tuple.h
M testdata/workloads/functional-query/queries/QueryTest/datastream-sender-codegen.test
20 files changed, 606 insertions(+), 247 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/54/24154/15
--
To view, visit http://gerrit.cloudera.org:8080/24154
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: Iaa43e949c63db047717104dbbe42d47f94ebf2d0
Gerrit-Change-Number: 24154
Gerrit-PatchSet: 15
Gerrit-Owner: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Balazs Hevele <bh...@cloudera.com>
Gerrit-Reviewer: Csaba Ringhofer <cs...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <im...@cloudera.com>
Gerrit-Reviewer: Yida Wu <wy...@gmail.com>