Files
impala/testdata/workloads/functional-query/queries/QueryTest/dedicated-coord-mem-estimates.test
TheOmid e327a28757 IMPALA-6684: Fix untracked memory in KRPC
During serialization of a row batch header, a tuple_data_ is created
which will hold the compressed tuple data for an outbound row batch.
We would like this tuple data to be trackable as it is responsible for
a significant portion of untrackable memory from the krpc data stream
sender. By using MemTrackerAllocator, we can allocate tuple data and
compression scratch and account for it in the memory tracker of the
KrpcDataStreamSender. This solution replaces the type for tuple data
and compression scratch from std::string to TrackedString, an
std:basic_string with MemTrackerAllocator as the custom allocator.

This patch adds memory estimation in DataStreamSink.java to account
for OutboundRowBatch memory allocation. This patch also removes the
thrift-based serialization because the thrift RPC has been removed
in the prior commit.

Testing:
 - Passed core tests.
 - Ran a single node benchmark which shows no regression.
 - Updated row-batch-serialize-test and row-batch-serialize-benchmark
   to test the row-batch serialization used by KRPC.
 - Manually collected query-profile, heap growth, and memory usage log
   showing untracked memory decreased by 1/2.
 - Add test_datastream_sender.py to verify the peak memory of EXCHANGE
   SENDER node.
 - Raise mem_limit in two of test_spilling_large_rows test case.
 - Print test line number in PlannerTestBase.java

New row-batch serialization benchmark:

Machine Info: Intel(R) Xeon(R) Platinum 8375C CPU @ 2.90GHz
serialize:            10%   50%   90%     10%     50%     90%
                                        (rel)   (rel)   (rel)
-------------------------------------------------------------
   ser_no_dups_base  18.6  18.8  18.9      1X      1X      1X
        ser_no_dups  18.5  18.5  18.8  0.998X  0.988X  0.991X
   ser_no_dups_full  14.7  14.8  14.8  0.793X   0.79X  0.783X

  ser_adj_dups_base  28.2  28.4  28.8      1X      1X      1X
       ser_adj_dups  68.9  69.1  69.8   2.44X   2.43X   2.43X
  ser_adj_dups_full  56.2  56.7  57.1   1.99X      2X   1.99X

      ser_dups_base  20.7  20.9  20.9      1X      1X      1X
           ser_dups  20.6  20.8  20.9  0.994X  0.995X      1X
      ser_dups_full  39.8    40  40.5   1.93X   1.92X   1.94X

deserialize:          10%   50%   90%     10%     50%     90%
                                        (rel)   (rel)   (rel)
-------------------------------------------------------------
 deser_no_dups_base  75.9  76.6    77      1X      1X      1X
      deser_no_dups  74.9  75.6    76  0.987X  0.987X  0.987X

deser_adj_dups_base   127   128   129      1X      1X      1X
     deser_adj_dups   179   193   195   1.41X   1.51X   1.51X

    deser_dups_base   128   128   129      1X      1X      1X
         deser_dups   165   190   193   1.29X   1.48X   1.49X

Change-Id: I2ba2b907ce4f275a7a1fb8cf75453c7003eb4b82
Reviewed-on: http://gerrit.cloudera.org:8080/18798
Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
2022-10-17 21:59:57 +00:00

97 lines
3.2 KiB
Plaintext

====
---- QUERY
# CTAS
create table test as select id from functional.alltypes where id > 1
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=16MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=100MB.*
row_regex: .*Cluster Memory Admitted: 132.00 MB.*
====
---- QUERY
# Truncate table to run the following inserts.
truncate table test
====
---- QUERY
# Small insert(i.e. values list, runs on coordinator only).
insert into test values (1), (2), (3)
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=10MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=100MB.*
row_regex: .*Cluster Memory Admitted: 10.00 MB.*
====
---- QUERY
# Large insert where it doesn't run on the coordinator.
insert into test select id from functional.alltypes where id > 3
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=16MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=100MB.*
row_regex: .*Cluster Memory Admitted: 132.00 MB.*
====
---- QUERY
# SELECT with merging exchange (i.e. order by).
select * from functional.alltypes order by int_col;
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=32MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=104MB.*
row_regex: .*Cluster Memory Admitted: 169.47 MB.*
====
---- QUERY
# SELECT with non-merging exchange.
select * from functional.alltypes;
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=21MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=104MB.*
row_regex: .*Cluster Memory Admitted: 146.20 MB.*
====
---- QUERY
# SELECT with a non-grouping aggregate in the coordinator fragment.
select avg(int_col) from functional.alltypes;
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=16MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=100MB.*
row_regex: .*Cluster Memory Admitted: 132.12 MB.*
====
---- QUERY
# SELECT with num_nodes=1 and a complex plan in the coordinator.
set num_nodes=1;
select
l_returnflag,
l_linestatus,
sum(l_quantity) as sum_qty,
sum(l_extendedprice) as sum_base_price,
sum(l_extendedprice * (1 - l_discount)) as sum_disc_price,
sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) as sum_charge,
avg(l_quantity) as avg_qty,
avg(l_extendedprice) as avg_price,
avg(l_discount) as avg_disc,
count(*) as count_order
from
tpch.lineitem
where
l_shipdate <= '1998-09-02'
group by
l_returnflag,
l_linestatus
order by
l_returnflag,
l_linestatus
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=98MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=198MB.*
row_regex: .*Cluster Memory Admitted: 198.00 MB.*
====
---- QUERY
# SELECT with multiple unpartitioned analytic functions to force the sort and analytics
# into the coordinator fragment.
select id,
min(int_col) over (order by year),
min(int_col) over (order by bigint_col),
avg(smallint_col) over (order by int_col),
max(int_col) over (order by smallint_col rows between unbounded preceding and 1 following)
from functional.alltypes;
---- RUNTIME_PROFILE
row_regex: .*Per-Host Resource Estimates: Memory=46MB.*
row_regex: .*Dedicated Coordinator Resource Estimate: Memory=124MB.*
row_regex: .*Cluster Memory Admitted: 216.00 MB.*
====