Hello Riza Suminto, Csaba Ringhofer, Impala Public Jenkins,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/18366
to look at the new patch set (#5).
Change subject: IMPALA-11204: Template implementation for
OrcStringColumnReader::ReadValue
......................................................................
IMPALA-11204: Template implementation for OrcStringColumnReader::ReadValue
There are some checks in OrcStringColumnReader::ReadValue() that we can
determine outside the scope of this method. They should be optimized
since this is a critical method that will be executed for each row (and
for each string column). With these checks, the method is too complex to
be inlined in OrcBatchedReader::ReadValueBatch() by the compiler.
This patch templates OrcStringColumnReader::ReadValue() with two
parameters, one for the target slot type (i.e. STRING/CHAR/VARCHAR),
ther other for whether the column is dictionary encoded. Also adds an
ALWAYS_INLINE marker to force inlining it.
OrcStringColumnReader::ReadValueBatch() will call a template version of
ReadValue() based on the slot type and the orc batch encoded state.
Ran a single node perf test on TPCH(30) on my dev box using 3 impalad
instances. There are some improvements and no significant regressions:
+----------+--------+-------------+------------+
| Query | Avg(s) | Base Avg(s) | Delta(Avg) |
+----------+--------+-------------+------------+
| TPCH-Q19 | 5.62 | 6.07 | I -7.41% |
| TPCH-Q6 | 2.56 | 2.78 | I -7.77% |
| TPCH-Q4 | 3.85 | 4.25 | I -9.42% |
| TPCH-Q12 | 4.25 | 4.99 | I -14.78% |
+----------+--------+-------------+------------+
Base commit: ff21728
File Format: orc/snap/block
Iterations: 30
Change-Id: I5e5f88c28059fb3d3ac1172e6d383d06ee3bedd5
---
M be/src/exec/orc-column-readers.cc
M be/src/exec/orc-column-readers.h
2 files changed, 77 insertions(+), 5 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/66/18366/5
--
To view, visit http://gerrit.cloudera.org:8080/18366
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: I5e5f88c28059fb3d3ac1172e6d383d06ee3bedd5
Gerrit-Change-Number: 18366
Gerrit-PatchSet: 5
Gerrit-Owner: Quanlong Huang <huangquanl...@gmail.com>
Gerrit-Reviewer: Csaba Ringhofer <csringho...@cloudera.com>
Gerrit-Reviewer: Impala Public Jenkins <impala-public-jenk...@cloudera.com>
Gerrit-Reviewer: Quanlong Huang <huangquanl...@gmail.com>
Gerrit-Reviewer: Riza Suminto <riza.sumi...@cloudera.com>
