Hello Tim Armstrong, Csaba Ringhofer,
I'd like you to reexamine a change. Please visit
http://gerrit.cloudera.org:8080/9943
to look at the new patch set (#6).
Change subject: IMPALA-5706: Parallelise read I/O in sorter
......................................................................
IMPALA-5706: Parallelise read I/O in sorter
This patch covers multiple changes with the purpose of optimizing
spilling sort mechanism:
- Use double-buffering when merging the sorted runs. As a result
while a run's page is being processed the next one can be loaded
from disk in the background.
- Remove the hard-coded maximum limit of buffers that can be used
for merging the sorted runs. Instead this number is calculated
based on the available memory through buffer pool.
- The already sorted runs are distributed evenly between the last
intermediate merge and the final merge to avoid that a heavy
intermediate merge is followed by a light final merge.
- Right before starting the merging phase Sorter tries to allocate
additional memory through the buffer pool.
- An output run is not allocated anymore for the final merge.
Performance measurements were made during manual testing to verify
that this is in fact an optimization:
- In case doing a sort on top of a join when working with a
restricted amount of memory then the Sort node successfully
allocates additional memory right before the merging phase. This
is feasible because once Join finishes sending new input data and
calls InputDone() then it releases memory that can be picked up
by the Sorter. This results in shallower merging trees (more runs
grabbed for a merge).
- Manual tests showed that when a single final merge is performed
this change slightly decreases the execution time for sorting.
Further testing should be done to cover double-buffering scenarios as
my manual testing so far didn't show any performance gain when
intermediate merges were performed. Most probably because due to
double-buffering the number of runs in a single merge decreases and I
have to hit an I/O heavy scenario to overcome this.
Change-Id: I74857c1694802e81f1cfc765d2b4e8bc644387f9
---
M be/src/runtime/sorter.cc
M be/src/runtime/sorter.h
M fe/src/main/java/org/apache/impala/planner/SortNode.java
M
testdata/workloads/functional-planner/queries/PlannerTest/constant-folding.test
M testdata/workloads/functional-planner/queries/PlannerTest/max-row-size.test
M
testdata/workloads/functional-planner/queries/PlannerTest/mt-dop-validation.test
M
testdata/workloads/functional-planner/queries/PlannerTest/resource-requirements.test
M
testdata/workloads/functional-planner/queries/PlannerTest/sort-expr-materialization.test
M testdata/workloads/functional-query/queries/QueryTest/analytic-fns.test
M
testdata/workloads/functional-query/queries/QueryTest/spilling-naaj-no-deny-reservation.test
M
testdata/workloads/functional-query/queries/QueryTest/spilling-sorts-exhaustive.test
M testdata/workloads/tpch/queries/sort-reservation-usage.test
M tests/custom_cluster/test_mem_reservations.py
M tests/query_test/test_sort.py
14 files changed, 357 insertions(+), 246 deletions(-)
git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/43/9943/6
--
To view, visit http://gerrit.cloudera.org:8080/9943
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: newpatchset
Gerrit-Change-Id: I74857c1694802e81f1cfc765d2b4e8bc644387f9
Gerrit-Change-Number: 9943
Gerrit-PatchSet: 6
Gerrit-Owner: Gabor Kaszab <[email protected]>
Gerrit-Reviewer: Csaba Ringhofer <[email protected]>
Gerrit-Reviewer: Gabor Kaszab <[email protected]>
Gerrit-Reviewer: Tim Armstrong <[email protected]>
