Introduce calcite 2902

[Mukvin]

No description provided.

[Mukvin]

Calcite Upgrade Report

---

Benchmark

package org.apache.kylin.query.engine;

import org.apache.calcite.rel.RelRoot;
import org.apache.calcite.sql.parser.SqlParseException;
import org.apache.kylin.common.KylinConfig;
import org.apache.kylin.common.util.NLocalFileMetadataTestCase;
import org.openjdk.jmh.annotations.Benchmark;
import org.openjdk.jmh.annotations.BenchmarkMode;
import org.openjdk.jmh.annotations.Fork;
import org.openjdk.jmh.annotations.Measurement;
import org.openjdk.jmh.annotations.Mode;
import org.openjdk.jmh.annotations.OutputTimeUnit;
import org.openjdk.jmh.annotations.Scope;
import org.openjdk.jmh.annotations.Setup;
import org.openjdk.jmh.annotations.State;
import org.openjdk.jmh.annotations.Threads;
import org.openjdk.jmh.annotations.Warmup;
import org.openjdk.jmh.results.format.ResultFormatType;
import org.openjdk.jmh.runner.Runner;
import org.openjdk.jmh.runner.options.Options;
import org.openjdk.jmh.runner.options.OptionsBuilder;

import java.util.concurrent.TimeUnit;

@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.MILLISECONDS)
@Warmup(iterations = 1)
@Measurement(iterations = 30)
@Threads(8)
@Fork(value = 1, jvmArgs = {"-Xms4G", "-Xmx4G"})
@State(Scope.Benchmark)
public class QueryOptimizerBenchmark {

    private QueryExec qe;
    private String sql;

    private RelRoot node;

    @Setup
    public void setUp() throws Exception {
        NLocalFileMetadataTestCase case1 = new NLocalFileMetadataTestCase();
        case1.createTestMetadata();
        KylinConfig.getInstanceFromEnv().setProperty("kylin.query.dataframe-cache-enabled", "false");
    }

    @Benchmark
    public void optimizeRel() throws SqlParseException {
        String sql = "SELECT \n" +
                "P_LINEORDER.LO_SHIPMODE as P_LINEORDER_LO_SHIPMODE,\n" +
                "P_LINEORDER.LO_LINENUMBER as P_LINEORDER_LO_LINENUMBER,\n" +
                "P_LINEORDER.LO_ORDTOTALPRICE as P_LINEORDER_LO_ORDTOTALPRICE,\n" +
                "P_LINEORDER.LO_SUPPLYCOST as P_LINEORDER_LO_SUPPLYCOST,\n" +
                "P_LINEORDER.LO_SUPPKEY as P_LINEORDER_LO_SUPPKEY,\n" +
                "P_LINEORDER.LO_QUANTITY as P_LINEORDER_LO_QUANTITY,\n" +
                "P_LINEORDER.LO_PARTKEY as P_LINEORDER_LO_PARTKEY,\n" +
                "P_LINEORDER.LO_ORDERKEY as P_LINEORDER_LO_ORDERKEY,\n" +
                "P_LINEORDER.LO_CUSTKEY as P_LINEORDER_LO_CUSTKEY,\n" +
                "P_LINEORDER.LO_SHIPPRIOTITY as P_LINEORDER_LO_SHIPPRIOTITY,\n" +
                "P_LINEORDER.LO_DISCOUNT as P_LINEORDER_LO_DISCOUNT,\n" +
                "P_LINEORDER.LO_ORDERPRIOTITY as P_LINEORDER_LO_ORDERPRIOTITY,\n" +
                "P_LINEORDER.LO_ORDERDATE as P_LINEORDER_LO_ORDERDATE,\n" +
                "P_LINEORDER.LO_REVENUE as P_LINEORDER_LO_REVENUE,\n" +
                "P_LINEORDER.V_REVENUE as P_LINEORDER_V_REVENUE,\n" +
                "P_LINEORDER.LO_COMMITDATE as P_LINEORDER_LO_COMMITDATE,\n" +
                "P_LINEORDER.LO_EXTENDEDPRICE as P_LINEORDER_LO_EXTENDEDPRICE,\n" +
                "P_LINEORDER.LO_TAX as P_LINEORDER_LO_TAX,\n" +
                "DATES.D_WEEKNUMINYEAR as DATES_D_WEEKNUMINYEAR,\n" +
                "DATES.D_LASTDAYINWEEKFL as DATES_D_LASTDAYINWEEKFL,\n" +
                "DATES.D_LASTDAYINMONTHFL as DATES_D_LASTDAYINMONTHFL,\n" +
                "DATES.D_DAYOFWEEK as DATES_D_DAYOFWEEK,\n" +
                "DATES.D_MONTHNUMINYEAR as DATES_D_MONTHNUMINYEAR,\n" +
                "DATES.D_YEARMONTHNUM as DATES_D_YEARMONTHNUM,\n" +
                "DATES.D_YEARMONTH as DATES_D_YEARMONTH,\n" +
                "DATES.D_DAYNUMINMONTH as DATES_D_DAYNUMINMONTH,\n" +
                "DATES.D_SELLINGSEASON as DATES_D_SELLINGSEASON,\n" +
                "DATES.D_WEEKDAYFL as DATES_D_WEEKDAYFL,\n" +
                "DATES.D_YEAR as DATES_D_YEAR,\n" +
                "DATES.D_HOLIDAYFL as DATES_D_HOLIDAYFL,\n" +
                "DATES.D_DAYNUMINWEEK as DATES_D_DAYNUMINWEEK,\n" +
                "DATES.D_DAYNUMINYEAR as DATES_D_DAYNUMINYEAR,\n" +
                "DATES.D_DATE as DATES_D_DATE,\n" +
                "DATES.D_MONTH as DATES_D_MONTH,\n" +
                "DATES.D_DATEKEY as DATES_D_DATEKEY,\n" +
                "CUSTOMER.C_ADDRESS as CUSTOMER_C_ADDRESS,\n" +
                "CUSTOMER.C_NATION as CUSTOMER_C_NATION,\n" +
                "CUSTOMER.C_CITY as CUSTOMER_C_CITY,\n" +
                "CUSTOMER.C_PHONE as CUSTOMER_C_PHONE,\n" +
                "CUSTOMER.C_REGION as CUSTOMER_C_REGION,\n" +
                "CUSTOMER.C_NAME as CUSTOMER_C_NAME,\n" +
                "CUSTOMER.C_MKTSEGMENT as CUSTOMER_C_MKTSEGMENT,\n" +
                "CUSTOMER.C_CUSTKEY as CUSTOMER_C_CUSTKEY,\n" +
                "PART.P_PARTKEY as PART_P_PARTKEY,\n" +
                "PART.P_CONTAINER as PART_P_CONTAINER,\n" +
                "PART.P_SIZE as PART_P_SIZE,\n" +
                "PART.P_NAME as PART_P_NAME,\n" +
                "PART.P_CATEGORY as PART_P_CATEGORY,\n" +
                "PART.P_TYPE as PART_P_TYPE,\n" +
                "PART.P_MFGR as PART_P_MFGR,\n" +
                "PART.P_BRAND as PART_P_BRAND,\n" +
                "PART.P_COLOR as PART_P_COLOR,\n" +
                "SUPPLIER.S_ADDRESS as SUPPLIER_S_ADDRESS,\n" +
                "SUPPLIER.S_NAME as SUPPLIER_S_NAME,\n" +
                "SUPPLIER.S_NATION as SUPPLIER_S_NATION,\n" +
                "SUPPLIER.S_SUPPKEY as SUPPLIER_S_SUPPKEY,\n" +
                "SUPPLIER.S_REGION as SUPPLIER_S_REGION,\n" +
                "SUPPLIER.S_PHONE as SUPPLIER_S_PHONE,\n" +
                "SUPPLIER.S_CITY as SUPPLIER_S_CITY\n" +
                "FROM \n" +
                "SSB.P_LINEORDER as P_LINEORDER \n" +
                "LEFT JOIN SSB.DATES as DATES\n" +
                "ON P_LINEORDER.LO_ORDERDATE=DATES.D_DATEKEY\n" +
                "LEFT JOIN SSB.CUSTOMER as CUSTOMER\n" +
                "ON P_LINEORDER.LO_CUSTKEY=CUSTOMER.C_CUSTKEY\n" +
                "LEFT JOIN SSB.PART as PART\n" +
                "ON P_LINEORDER.LO_PARTKEY=PART.P_PARTKEY\n" +
                "LEFT JOIN SSB.SUPPLIER as SUPPLIER\n" +
                "ON P_LINEORDER.LO_SUPPKEY=SUPPLIER.S_SUPPKEY";
        QueryExec qe = new QueryExec("demo", KylinConfig.getInstanceFromEnv());
        RelRoot node = qe.sqlConverter.convertSqlToRelNode(sql);
        for(int i = 0; i <= 3000; i++){
            qe.optimize(node);
        }
    }

    public static void main(String[] args) throws Exception {
        Options opts = new OptionsBuilder()
                .include(QueryOptimizerBenchmark.class.getSimpleName())
                .resultFormat(ResultFormatType.JSON)
                .build();
        new Runner(opts).run();
    }
}

Before(1.116.0-kylin-4.x-r021)

4804.941 ±(99.9%) 1623.696 ms/op
Iteration   1: 5926.838 ±(99.9%) 83.002 ms/op
Iteration   2: 6669.888 ±(99.9%) 302.045 ms/op
Iteration   3: 4533.345 ±(99.9%) 37.553 ms/op
Iteration   4: 4154.668 ±(99.9%) 53.689 ms/op
Iteration   5: 3836.025 ±(99.9%) 78.322 ms/op
Iteration   6: 3827.318 ±(99.9%) 47.342 ms/op
Iteration   7: 3966.734 ±(99.9%) 110.246 ms/op
Iteration   8: 3528.319 ±(99.9%) 36.724 ms/op
Iteration   9: 4548.459 ±(99.9%) 236.878 ms/op
Iteration  10: 3564.822 ±(99.9%) 130.477 ms/op
Iteration  11: 3532.063 ±(99.9%) 51.543 ms/op
Iteration  12: 3641.469 ±(99.9%) 69.136 ms/op
Iteration  13: 4020.822 ±(99.9%) 56.725 ms/op
Iteration  14: 3670.644 ±(99.9%) 53.022 ms/op
Iteration  15: 3644.789 ±(99.9%) 76.941 ms/op
Iteration  16: 3654.671 ±(99.9%) 87.807 ms/op
Iteration  17: 3909.223 ±(99.9%) 81.267 ms/op
Iteration  18: 3473.783 ±(99.9%) 51.718 ms/op
Iteration  19: 5288.901 ±(99.9%) 345.911 ms/op
Iteration  20: 3721.911 ±(99.9%) 33.372 ms/op
Iteration  21: 3661.732 ±(99.9%) 111.323 ms/op
Iteration  22: 3655.741 ±(99.9%) 39.567 ms/op
Iteration  23: 4405.195 ±(99.9%) 168.399 ms/op
Iteration  24: 3867.189 ±(99.9%) 45.348 ms/op
Iteration  25: 3907.763 ±(99.9%) 60.003 ms/op
Iteration  26: 4019.724 ±(99.9%) 97.995 ms/op
Iteration  27: 4609.844 ±(99.9%) 104.770 ms/op
Iteration  28: 4496.068 ±(99.9%) 148.081 ms/op
Iteration  29: 3811.977 ±(99.9%) 134.557 ms/op
Iteration  30: 3948.184 ±(99.9%) 96.599 ms/op


Result "org.apache.kylin.query.engine.QueryOptimizerBenchmark.optimizeRel":
  4116.604 ±(99.9%) 485.558 ms/op [Average]
  (min, avg, max) = (3473.783, 4116.604, 6669.888), stdev = 726.761
  CI (99.9%): [3631.045, 4602.162] (assumes normal distribution)


# Run complete. Total time: 00:08:01

REMEMBER: The numbers below are just data. To gain reusable insights, you need to follow up on
why the numbers are the way they are. Use profilers (see -prof, -lprof), design factorial
experiments, perform baseline and negative tests that provide experimental control, make sure
the benchmarking environment is safe on JVM/OS/HW level, ask for reviews from the domain experts.
Do not assume the numbers tell you what you want them to tell.

Benchmark                            Mode  Cnt     Score     Error  Units
QueryOptimizerBenchmark.optimizeRel  avgt   30  4116.604 ± 485.558  ms/op

After(1.116.0-kylin-4.x-r024)

3512.040 ±(99.9%) 1539.879 ms/op
Iteration   1: 3209.740 ±(99.9%) 41.534 ms/op
Iteration   2: 2883.053 ±(99.9%) 65.956 ms/op
Iteration   3: 2889.543 ±(99.9%) 43.021 ms/op
Iteration   4: 2687.193 ±(99.9%) 65.863 ms/op
Iteration   5: 2775.590 ±(99.9%) 47.606 ms/op
Iteration   6: 2722.390 ±(99.9%) 63.297 ms/op
Iteration   7: 2715.576 ±(99.9%) 72.264 ms/op
Iteration   8: 2714.370 ±(99.9%) 64.343 ms/op
Iteration   9: 2778.215 ±(99.9%) 61.565 ms/op
Iteration  10: 2774.280 ±(99.9%) 53.732 ms/op
Iteration  11: 2814.291 ±(99.9%) 51.687 ms/op
Iteration  12: 2820.700 ±(99.9%) 32.117 ms/op
Iteration  13: 2808.322 ±(99.9%) 43.454 ms/op
Iteration  14: 2770.112 ±(99.9%) 25.359 ms/op
Iteration  15: 2816.414 ±(99.9%) 36.400 ms/op
Iteration  16: 2743.821 ±(99.9%) 31.754 ms/op
Iteration  17: 2765.046 ±(99.9%) 67.956 ms/op
Iteration  18: 2762.065 ±(99.9%) 41.252 ms/op
Iteration  19: 2792.257 ±(99.9%) 49.531 ms/op
Iteration  20: 2751.313 ±(99.9%) 35.463 ms/op
Iteration  21: 2737.771 ±(99.9%) 51.313 ms/op
Iteration  22: 2924.571 ±(99.9%) 37.405 ms/op
Iteration  23: 2834.411 ±(99.9%) 41.520 ms/op
Iteration  24: 2740.439 ±(99.9%) 31.275 ms/op
Iteration  25: 2728.094 ±(99.9%) 48.697 ms/op
Iteration  26: 2733.819 ±(99.9%) 35.052 ms/op
Iteration  27: 2748.317 ±(99.9%) 74.314 ms/op
Iteration  28: 2722.741 ±(99.9%) 41.552 ms/op
Iteration  29: 2896.345 ±(99.9%) 53.009 ms/op
Iteration  30: 3115.371 ±(99.9%) 55.581 ms/op


Result "org.apache.kylin.query.engine.QueryOptimizerBenchmark.optimizeRel":
  2805.872 ±(99.9%) 76.265 ms/op [Average]
  (min, avg, max) = (2687.193, 2805.872, 3209.740), stdev = 114.150
  CI (99.9%): [2729.607, 2882.137] (assumes normal distribution)


# Run complete. Total time: 00:07:09

REMEMBER: The numbers below are just data. To gain reusable insights, you need to follow up on
why the numbers are the way they are. Use profilers (see -prof, -lprof), design factorial
experiments, perform baseline and negative tests that provide experimental control, make sure
the benchmarking environment is safe on JVM/OS/HW level, ask for reviews from the domain experts.
Do not assume the numbers tell you what you want them to tell.

Benchmark                            Mode  Cnt     Score    Error  Units
QueryOptimizerBenchmark.optimizeRel  avgt   30  2805.872 ± 76.265  ms/op

Conclusion

>>> before=4116.604
>>> after=2805.872
>>> improve=(before - after)/before
>>> improve
0.3184012841652975

Improve 32.84%

[yahoNanJing]

Can we use a property to indicate the version and manage the related dependency to the dependencyManagement?

[Mukvin]

Good idea, but now the main pom.xml will update the version with every change. So the related dependencies are clear to be managed.

[github-actions]

This pull request has been marked as stale due to 30 days of inactivity. It will be closed in 90 days if no further activity occurs. If you think that’s incorrect or this pull request requires a review, please simply write any comment. If closed, you can revive the PR at any time and @mention a reviewer or discuss it on the dev@calcite.apache.org list. Thank you for your contributions.