[CORE][VL] Add naitve plan string and plan with stats

[ulysses-you]

What changes were proposed in this pull request?

This pr adds two things:

1. Support inject native plan string to Spark explain, e.g.,

--conf spark.gluten.sql.injectNativePlanStringToExplain=true

(9) WholeStageCodegenTransformer (2)
Input [6]: [c1#0L, c2#1L, c3#2L, c1#3L, c2#4L, c3#5L]
Arguments: false
Native Plan:
-- Project[expressions: (n3_6:BIGINT, "n0_0"), (n3_7:BIGINT, "n0_1"), (n3_8:BIGINT, "n0_2"), (n3_9:BIGINT, "n1_0"), (n3_10:BIGINT, "n1_1"), (n3_11:BIGINT, "n1_2")] -> n3_6:BIGINT, n3_7:BIGINT, n3_8:BIGINT, n3_9:BIGINT, n3_10:BIGINT, n3_11:BIGINT
  -- HashJoin[INNER n1_1=n0_1] -> n1_0:BIGINT, n1_1:BIGINT, n1_2:BIGINT, n0_0:BIGINT, n0_1:BIGINT, n0_2:BIGINT
    -- TableScan[table: hive_table, range filters: [(c2, Filter(IsNotNull, deterministic, null not allowed))]] -> n1_0:BIGINT, n1_1:BIGINT, n1_2:BIGINT
    -- ValueStream[] -> n0_0:BIGINT, n0_1:BIGINT, n0_2:BIGINT

2. Support print plan with stats to executor system output stream. Note, it's task level so it will print plan with stats for each task, e.g,

--conf spark.gluten.sql.debug=true

I20231121 10:35:50.516695 90119467 WholeStageResultIterator.cc:220] Native Plan with stats for: [Stage: 0 TID: 7]
-- Project[expressions: (n1_1:BIGINT, add("n0_0",1))] -> n1_1:BIGINT
   Output: 10 rows (96B, 1 batches), Cpu time: 44.50us, Blocked wall time: 0ns, Peak memory: 192B, Memory allocations: 1, Threads: 1
      queuedWallNanos              sum: 2.00us, count: 1, min: 2.00us, max: 2.00us
      runningAddInputWallNanos     sum: 1.21us, count: 1, min: 1.21us, max: 1.21us
      runningFinishWallNanos       sum: 0ns, count: 1, min: 0ns, max: 0ns
      runningGetOutputWallNanos    sum: 63.87us, count: 1, min: 63.87us, max: 63.87us
  -- TableScan[table: hive_table] -> n0_0:BIGINT
     Input: 10 rows (160B, 1 batches), Output: 10 rows (160B, 1 batches), Cpu time: 482.29us, Blocked wall time: 0ns, Peak memory: 960B, Memory allocations: 10, Threads: 1, Splits: 1
        dataSourceWallNanos              sum: 1.73ms, count: 1, min: 1.73ms, max: 1.73ms
        flattenStringDictionaryValues    sum: 0, count: 1, min: 0, max: 0
        ioWaitNanos                      sum: 650.00us, count: 1, min: 650.00us, max: 650.00us
        localReadBytes                   sum: 0B, count: 1, min: 0B, max: 0B
        numLocalRead                     sum: 0, count: 1, min: 0, max: 0
        numPrefetch                      sum: 0, count: 1, min: 0, max: 0
        numRamRead                       sum: 0, count: 1, min: 0, max: 0
        numStorageRead                   sum: 2, count: 1, min: 2, max: 2
        overreadBytes                    sum: 0B, count: 1, min: 0B, max: 0B
        prefetchBytes                    sum: 0B, count: 1, min: 0B, max: 0B
        queryThreadIoLatency             sum: 2, count: 1, min: 2, max: 2
        ramReadBytes                     sum: 0B, count: 1, min: 0B, max: 0B
        runningAddInputWallNanos         sum: 0ns, count: 1, min: 0ns, max: 0ns
        runningFinishWallNanos           sum: 42ns, count: 1, min: 42ns, max: 42ns
        runningGetOutputWallNanos        sum: 2.49ms, count: 1, min: 2.49ms, max: 2.49ms
        skippedSplitBytes                sum: 0B, count: 1, min: 0B, max: 0B
        skippedSplits                    sum: 0, count: 1, min: 0, max: 0
        skippedStrides                   sum: 0, count: 1, min: 0, max: 0
        storageReadBytes                 sum: 1.16KB, count: 1, min: 1.16KB, max: 1.16KB
        totalScanTime                    sum: 0ns, count: 1, min: 0ns, max: 0ns

How was this patch tested?

manually test, see the added docs

[github-actions]

Thanks for opening a pull request!

Could you open an issue for this pull request on Github Issues?

https://github.com/oap-project/gluten/issues

Then could you also rename commit message and pull request title in the following format?

[GLUTEN-${ISSUES_ID}][COMPONENT]feat/fix: ${detailed message}

See also:

• Other pull requests

[github-actions]

Run Gluten Clickhouse CI

[Yohahaha]

#1 is great, but I think #2 could be added in #3748 with debug config, thus we can avoid add more and more config, how do you think about that?

[ulysses-you]

@Yohahaha I'm fine to reuse an existed config spark.gluten.sql.debug

[github-actions]

Run Gluten Clickhouse CI

[github-actions]

Run Gluten Clickhouse CI

[ulysses-you]

cc @Yohahaha @philo-he @zhouyuan @JkSelf thank you

[zhouyuan]

👍

[Yohahaha]

LGTM!

[zhouyuan]

thank you @ulysses-you and @Yohahaha !

[GlutenPerfBot]

===== Performance report for TPCH SF2000 with Velox backend, for reference only ====

query	log/native_3787_time.csv	log/native_master_11_20_2023_60fc2a02e_time.csv	difference	percentage
q1	34.15	34.37	0.222	100.65%
q2	24.60	24.70	0.106	100.43%
q3	37.04	35.40	-1.642	95.57%
q4	36.78	36.40	-0.380	98.97%
q5	71.18	68.86	-2.319	96.74%
q6	7.44	7.01	-0.424	94.30%
q7	85.24	85.39	0.147	100.17%
q8	85.85	87.44	1.589	101.85%
q9	119.42	124.93	5.508	104.61%
q10	45.59	46.83	1.242	102.72%
q11	19.67	19.99	0.325	101.65%
q12	24.93	24.57	-0.358	98.57%
q13	45.78	44.85	-0.927	97.98%
q14	15.56	18.77	3.215	120.67%
q15	27.56	27.13	-0.425	98.46%
q16	15.39	15.41	0.024	100.15%
q17	100.11	102.21	2.095	102.09%
q18	147.84	149.83	1.988	101.34%
q19	15.32	13.48	-1.847	87.94%
q20	27.95	28.10	0.150	100.54%
q21	221.87	220.09	-1.771	99.20%
q22	12.93	12.89	-0.042	99.68%
total	1222.18	1228.65	6.475	100.53%

[GlutenPerfBot]

===== Performance report for TPCH SF2000 with Velox backend, for reference only ====

query	log/native_master_11_21_2023_time.csv	log/native_master_11_20_2023_60fc2a02e_time.csv	difference	percentage
q1	33.71	34.37	0.657	101.95%
q2	24.92	24.70	-0.220	99.12%
q3	37.63	35.40	-2.231	94.07%
q4	35.99	36.40	0.405	101.13%
q5	70.48	68.86	-1.618	97.70%
q6	7.11	7.01	-0.094	98.68%
q7	84.08	85.39	1.312	101.56%
q8	87.02	87.44	0.416	100.48%
q9	124.24	124.93	0.691	100.56%
q10	46.06	46.83	0.766	101.66%
q11	19.24	19.99	0.750	103.90%
q12	25.38	24.57	-0.812	96.80%
q13	45.84	44.85	-0.989	97.84%
q14	18.33	18.77	0.444	102.42%
q15	28.80	27.13	-1.668	94.21%
q16	15.37	15.41	0.046	100.30%
q17	100.95	102.21	1.260	101.25%
q18	146.37	149.83	3.462	102.37%
q19	12.89	13.48	0.589	104.57%
q20	28.27	28.10	-0.168	99.41%
q21	222.09	220.09	-1.999	99.10%
q22	12.99	12.89	-0.104	99.20%
total	1227.75	1228.65	0.898	100.07%