forked from pingcap/tidb
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtpch.result
1303 lines (1303 loc) · 70.3 KB
/
tpch.result
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
set tidb_cost_model_version=1;
CREATE DATABASE IF NOT EXISTS TPCH;
USE TPCH;
CREATE TABLE IF NOT EXISTS nation ( N_NATIONKEY INTEGER NOT NULL,
N_NAME CHAR(25) NOT NULL,
N_REGIONKEY INTEGER NOT NULL,
N_COMMENT VARCHAR(152),
PRIMARY KEY (N_NATIONKEY));
CREATE TABLE IF NOT EXISTS region ( R_REGIONKEY INTEGER NOT NULL,
R_NAME CHAR(25) NOT NULL,
R_COMMENT VARCHAR(152),
PRIMARY KEY (R_REGIONKEY));
CREATE TABLE IF NOT EXISTS part ( P_PARTKEY INTEGER NOT NULL,
P_NAME VARCHAR(55) NOT NULL,
P_MFGR CHAR(25) NOT NULL,
P_BRAND CHAR(10) NOT NULL,
P_TYPE VARCHAR(25) NOT NULL,
P_SIZE INTEGER NOT NULL,
P_CONTAINER CHAR(10) NOT NULL,
P_RETAILPRICE DECIMAL(15,2) NOT NULL,
P_COMMENT VARCHAR(23) NOT NULL,
PRIMARY KEY (P_PARTKEY));
CREATE TABLE IF NOT EXISTS supplier ( S_SUPPKEY INTEGER NOT NULL,
S_NAME CHAR(25) NOT NULL,
S_ADDRESS VARCHAR(40) NOT NULL,
S_NATIONKEY INTEGER NOT NULL,
S_PHONE CHAR(15) NOT NULL,
S_ACCTBAL DECIMAL(15,2) NOT NULL,
S_COMMENT VARCHAR(101) NOT NULL,
PRIMARY KEY (S_SUPPKEY));
CREATE TABLE IF NOT EXISTS partsupp ( PS_PARTKEY INTEGER NOT NULL,
PS_SUPPKEY INTEGER NOT NULL,
PS_AVAILQTY INTEGER NOT NULL,
PS_SUPPLYCOST DECIMAL(15,2) NOT NULL,
PS_COMMENT VARCHAR(199) NOT NULL,
PRIMARY KEY (PS_PARTKEY,PS_SUPPKEY));
CREATE TABLE IF NOT EXISTS customer ( C_CUSTKEY INTEGER NOT NULL,
C_NAME VARCHAR(25) NOT NULL,
C_ADDRESS VARCHAR(40) NOT NULL,
C_NATIONKEY INTEGER NOT NULL,
C_PHONE CHAR(15) NOT NULL,
C_ACCTBAL DECIMAL(15,2) NOT NULL,
C_MKTSEGMENT CHAR(10) NOT NULL,
C_COMMENT VARCHAR(117) NOT NULL,
PRIMARY KEY (C_CUSTKEY));
CREATE TABLE IF NOT EXISTS orders ( O_ORDERKEY INTEGER NOT NULL,
O_CUSTKEY INTEGER NOT NULL,
O_ORDERSTATUS CHAR(1) NOT NULL,
O_TOTALPRICE DECIMAL(15,2) NOT NULL,
O_ORDERDATE DATE NOT NULL,
O_ORDERPRIORITY CHAR(15) NOT NULL,
O_CLERK CHAR(15) NOT NULL,
O_SHIPPRIORITY INTEGER NOT NULL,
O_COMMENT VARCHAR(79) NOT NULL,
PRIMARY KEY (O_ORDERKEY));
CREATE TABLE IF NOT EXISTS lineitem ( L_ORDERKEY INTEGER NOT NULL,
L_PARTKEY INTEGER NOT NULL,
L_SUPPKEY INTEGER NOT NULL,
L_LINENUMBER INTEGER NOT NULL,
L_QUANTITY DECIMAL(15,2) NOT NULL,
L_EXTENDEDPRICE DECIMAL(15,2) NOT NULL,
L_DISCOUNT DECIMAL(15,2) NOT NULL,
L_TAX DECIMAL(15,2) NOT NULL,
L_RETURNFLAG CHAR(1) NOT NULL,
L_LINESTATUS CHAR(1) NOT NULL,
L_SHIPDATE DATE NOT NULL,
L_COMMITDATE DATE NOT NULL,
L_RECEIPTDATE DATE NOT NULL,
L_SHIPINSTRUCT CHAR(25) NOT NULL,
L_SHIPMODE CHAR(10) NOT NULL,
L_COMMENT VARCHAR(44) NOT NULL,
PRIMARY KEY (L_ORDERKEY,L_LINENUMBER));
load stats 's/tpch_stats/nation.json';
load stats 's/tpch_stats/region.json';
load stats 's/tpch_stats/part.json';
load stats 's/tpch_stats/supplier.json';
load stats 's/tpch_stats/partsupp.json';
load stats 's/tpch_stats/customer.json';
load stats 's/tpch_stats/orders.json';
load stats 's/tpch_stats/lineitem.json';
set @@session.tidb_opt_agg_push_down = 0;
/*
Q1 Pricing Summary Report
This query reports the amount of business that was billed, shipped, and returned.
The Pricing Summary Report Query provides a summary pricing report for all lineitems shipped as of a given date.
The date is within 60 - 120 days of the greatest ship date contained in the database. The query lists totals for
extended price, discounted extended price, discounted extended price plus tax, average quantity, average extended
price, and average discount. These aggregates are grouped by RETURNFLAG and LINESTATUS, and listed in
ascending order of RETURNFLAG and LINESTATUS. A count of the number of lineitems in each group is
included.
Planner enhancement: none.
*/
explain format = 'brief'
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
lineitem
where
l_shipdate <= date_sub('1998-12-01', interval 108 day)
group by
l_returnflag,
l_linestatus
order by
l_returnflag,
l_linestatus;
id estRows task access object operator info
Sort 2.94 root tpch.lineitem.l_returnflag, tpch.lineitem.l_linestatus
└─Projection 2.94 root tpch.lineitem.l_returnflag, tpch.lineitem.l_linestatus, Column#18, Column#19, Column#20, Column#21, Column#22, Column#23, Column#24, Column#25
└─HashAgg 2.94 root group by:tpch.lineitem.l_linestatus, tpch.lineitem.l_returnflag, funcs:sum(Column#26)->Column#18, funcs:sum(Column#27)->Column#19, funcs:sum(Column#28)->Column#20, funcs:sum(Column#29)->Column#21, funcs:avg(Column#30, Column#31)->Column#22, funcs:avg(Column#32, Column#33)->Column#23, funcs:avg(Column#34, Column#35)->Column#24, funcs:count(Column#36)->Column#25, funcs:firstrow(tpch.lineitem.l_returnflag)->tpch.lineitem.l_returnflag, funcs:firstrow(tpch.lineitem.l_linestatus)->tpch.lineitem.l_linestatus
└─TableReader 2.94 root data:HashAgg
└─HashAgg 2.94 cop[tikv] group by:tpch.lineitem.l_linestatus, tpch.lineitem.l_returnflag, funcs:sum(tpch.lineitem.l_quantity)->Column#26, funcs:sum(tpch.lineitem.l_extendedprice)->Column#27, funcs:sum(mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount)))->Column#28, funcs:sum(mul(mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount)), plus(1, tpch.lineitem.l_tax)))->Column#29, funcs:count(tpch.lineitem.l_quantity)->Column#30, funcs:sum(tpch.lineitem.l_quantity)->Column#31, funcs:count(tpch.lineitem.l_extendedprice)->Column#32, funcs:sum(tpch.lineitem.l_extendedprice)->Column#33, funcs:count(tpch.lineitem.l_discount)->Column#34, funcs:sum(tpch.lineitem.l_discount)->Column#35, funcs:count(1)->Column#36
└─Selection 293795345.00 cop[tikv] le(tpch.lineitem.l_shipdate, 1998-08-15 00:00:00.000000)
└─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
/*
Q2 Minimum Cost Supplier Query
This query finds which supplier should be selected to place an order for a given part in a given region.
The Minimum Cost Supplier Query finds, in a given region, for each part of a certain type and size, the supplier who
can supply it at minimum cost. If several suppliers in that region offer the desired part type and size at the same
(minimum) cost, the query lists the parts from suppliers with the 100 highest account balances. For each supplier,
the query lists the supplier's account balance, name and nation; the part's number and manufacturer; the supplier's
address, phone number and comment information.
Planner enhancement: join reorder.
*/
explain format = 'brief'
select
s_acctbal,
s_name,
n_name,
p_partkey,
p_mfgr,
s_address,
s_phone,
s_comment
from
part,
supplier,
partsupp,
nation,
region
where
p_partkey = ps_partkey
and s_suppkey = ps_suppkey
and p_size = 30
and p_type like '%STEEL'
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'ASIA'
and ps_supplycost = (
select
min(ps_supplycost)
from
partsupp,
supplier,
nation,
region
where
p_partkey = ps_partkey
and s_suppkey = ps_suppkey
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'ASIA'
)
order by
s_acctbal desc,
n_name,
s_name,
p_partkey
limit 100;
id estRows task access object operator info
Projection 100.00 root tpch.supplier.s_acctbal, tpch.supplier.s_name, tpch.nation.n_name, tpch.part.p_partkey, tpch.part.p_mfgr, tpch.supplier.s_address, tpch.supplier.s_phone, tpch.supplier.s_comment
└─TopN 100.00 root tpch.supplier.s_acctbal:desc, tpch.nation.n_name, tpch.supplier.s_name, tpch.part.p_partkey, offset:0, count:100
└─Projection 155496.00 root tpch.part.p_partkey, tpch.part.p_mfgr, tpch.supplier.s_name, tpch.supplier.s_address, tpch.supplier.s_phone, tpch.supplier.s_acctbal, tpch.supplier.s_comment, tpch.nation.n_name
└─HashJoin 155496.00 root inner join, equal:[eq(tpch.part.p_partkey, tpch.partsupp.ps_partkey) eq(tpch.partsupp.ps_supplycost, Column#50)]
├─HashJoin(Build) 155496.00 root inner join, equal:[eq(tpch.partsupp.ps_partkey, tpch.part.p_partkey)]
│ ├─TableReader(Build) 155496.00 root data:Selection
│ │ └─Selection 155496.00 cop[tikv] eq(tpch.part.p_size, 30), like(tpch.part.p_type, "%STEEL", 92)
│ │ └─TableFullScan 10000000.00 cop[tikv] table:part keep order:false
│ └─HashJoin(Probe) 8155010.44 root inner join, equal:[eq(tpch.supplier.s_suppkey, tpch.partsupp.ps_suppkey)]
│ ├─HashJoin(Build) 100000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.supplier.s_nationkey)]
│ │ ├─HashJoin(Build) 5.00 root inner join, equal:[eq(tpch.region.r_regionkey, tpch.nation.n_regionkey)]
│ │ │ ├─TableReader(Build) 1.00 root data:Selection
│ │ │ │ └─Selection 1.00 cop[tikv] eq(tpch.region.r_name, "ASIA")
│ │ │ │ └─TableFullScan 5.00 cop[tikv] table:region keep order:false
│ │ │ └─TableReader(Probe) 25.00 root data:TableFullScan
│ │ │ └─TableFullScan 25.00 cop[tikv] table:nation keep order:false
│ │ └─TableReader(Probe) 500000.00 root data:TableFullScan
│ │ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
│ └─TableReader(Probe) 40000000.00 root data:TableFullScan
│ └─TableFullScan 40000000.00 cop[tikv] table:partsupp keep order:false
└─Selection(Probe) 6524008.35 root not(isnull(Column#50))
└─HashAgg 8155010.44 root group by:tpch.partsupp.ps_partkey, funcs:min(tpch.partsupp.ps_supplycost)->Column#50, funcs:firstrow(tpch.partsupp.ps_partkey)->tpch.partsupp.ps_partkey
└─HashJoin 8155010.44 root inner join, equal:[eq(tpch.supplier.s_suppkey, tpch.partsupp.ps_suppkey)]
├─HashJoin(Build) 100000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.supplier.s_nationkey)]
│ ├─HashJoin(Build) 5.00 root inner join, equal:[eq(tpch.region.r_regionkey, tpch.nation.n_regionkey)]
│ │ ├─TableReader(Build) 1.00 root data:Selection
│ │ │ └─Selection 1.00 cop[tikv] eq(tpch.region.r_name, "ASIA")
│ │ │ └─TableFullScan 5.00 cop[tikv] table:region keep order:false
│ │ └─TableReader(Probe) 25.00 root data:TableFullScan
│ │ └─TableFullScan 25.00 cop[tikv] table:nation keep order:false
│ └─TableReader(Probe) 500000.00 root data:TableFullScan
│ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
└─TableReader(Probe) 40000000.00 root data:TableFullScan
└─TableFullScan 40000000.00 cop[tikv] table:partsupp keep order:false
/*
Q3 Shipping Priority Query
This query retrieves the 10 unshipped orders with the highest value.
The Shipping Priority Query retrieves the shipping priority and potential revenue, defined as the sum of
l_extendedprice * (1-l_discount), of the orders having the largest revenue among those that had not been shipped as
of a given date. Orders are listed in decreasing order of revenue. If more than 10 unshipped orders exist, only the 10
orders with the largest revenue are listed.
planner enhancement: if group-by item have primary key, non-priamry key is useless.
*/
explain format = 'brief'
select
l_orderkey,
sum(l_extendedprice * (1 - l_discount)) as revenue,
o_orderdate,
o_shippriority
from
customer,
orders,
lineitem
where
c_mktsegment = 'AUTOMOBILE'
and c_custkey = o_custkey
and l_orderkey = o_orderkey
and o_orderdate < '1995-03-13'
and l_shipdate > '1995-03-13'
group by
l_orderkey,
o_orderdate,
o_shippriority
order by
revenue desc,
o_orderdate
limit 10;
id estRows task access object operator info
Projection 10.00 root tpch.lineitem.l_orderkey, Column#35, tpch.orders.o_orderdate, tpch.orders.o_shippriority
└─TopN 10.00 root Column#35:desc, tpch.orders.o_orderdate, offset:0, count:10
└─HashAgg 40252367.98 root group by:Column#48, Column#49, Column#50, funcs:sum(Column#44)->Column#35, funcs:firstrow(Column#45)->tpch.orders.o_orderdate, funcs:firstrow(Column#46)->tpch.orders.o_shippriority, funcs:firstrow(Column#47)->tpch.lineitem.l_orderkey
└─Projection 91515927.49 root mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount))->Column#44, tpch.orders.o_orderdate->Column#45, tpch.orders.o_shippriority->Column#46, tpch.lineitem.l_orderkey->Column#47, tpch.lineitem.l_orderkey->Column#48, tpch.orders.o_orderdate->Column#49, tpch.orders.o_shippriority->Column#50
└─IndexHashJoin 91515927.49 root inner join, inner:IndexLookUp, outer key:tpch.orders.o_orderkey, inner key:tpch.lineitem.l_orderkey, equal cond:eq(tpch.orders.o_orderkey, tpch.lineitem.l_orderkey)
├─HashJoin(Build) 22592975.51 root inner join, equal:[eq(tpch.customer.c_custkey, tpch.orders.o_custkey)]
│ ├─TableReader(Build) 1498236.00 root data:Selection
│ │ └─Selection 1498236.00 cop[tikv] eq(tpch.customer.c_mktsegment, "AUTOMOBILE")
│ │ └─TableFullScan 7500000.00 cop[tikv] table:customer keep order:false
│ └─TableReader(Probe) 36870000.00 root data:Selection
│ └─Selection 36870000.00 cop[tikv] lt(tpch.orders.o_orderdate, 1995-03-13 00:00:00.000000)
│ └─TableFullScan 75000000.00 cop[tikv] table:orders keep order:false
└─IndexLookUp(Probe) 91515927.49 root
├─IndexRangeScan(Build) 168388203.74 cop[tikv] table:lineitem, index:PRIMARY(L_ORDERKEY, L_LINENUMBER) range: decided by [eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)], keep order:false
└─Selection(Probe) 91515927.49 cop[tikv] gt(tpch.lineitem.l_shipdate, 1995-03-13 00:00:00.000000)
└─TableRowIDScan 168388203.74 cop[tikv] table:lineitem keep order:false
/*
Q4 Order Priority Checking Query
This query determines how well the order priority system is working and gives an assessment of customer satisfaction.
The Order Priority Checking Query counts the number of orders ordered in a given quarter of a given year in which
at least one lineitem was received by the customer later than its committed date. The query lists the count of such
orders for each order priority sorted in ascending priority order.
*/
explain format = 'brief'
select
o_orderpriority,
count(*) as order_count
from
orders
where
o_orderdate >= '1995-01-01'
and o_orderdate < date_add('1995-01-01', interval '3' month)
and exists (
select
*
from
lineitem
where
l_orderkey = o_orderkey
and l_commitdate < l_receiptdate
)
group by
o_orderpriority
order by
o_orderpriority;
id estRows task access object operator info
Sort 1.00 root tpch.orders.o_orderpriority
└─Projection 1.00 root tpch.orders.o_orderpriority, Column#27
└─HashAgg 1.00 root group by:tpch.orders.o_orderpriority, funcs:count(1)->Column#27, funcs:firstrow(tpch.orders.o_orderpriority)->tpch.orders.o_orderpriority
└─IndexHashJoin 2340750.00 root semi join, inner:IndexLookUp, outer key:tpch.orders.o_orderkey, inner key:tpch.lineitem.l_orderkey, equal cond:eq(tpch.orders.o_orderkey, tpch.lineitem.l_orderkey)
├─TableReader(Build) 2925937.50 root data:Selection
│ └─Selection 2925937.50 cop[tikv] ge(tpch.orders.o_orderdate, 1995-01-01 00:00:00.000000), lt(tpch.orders.o_orderdate, 1995-04-01 00:00:00.000000)
│ └─TableFullScan 75000000.00 cop[tikv] table:orders keep order:false
└─IndexLookUp(Probe) 11851908.75 root
├─IndexRangeScan(Build) 14814885.94 cop[tikv] table:lineitem, index:PRIMARY(L_ORDERKEY, L_LINENUMBER) range: decided by [eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)], keep order:false
└─Selection(Probe) 11851908.75 cop[tikv] lt(tpch.lineitem.l_commitdate, tpch.lineitem.l_receiptdate)
└─TableRowIDScan 14814885.94 cop[tikv] table:lineitem keep order:false
/*
Q5 Local Supplier Volume Query
This query lists the revenue volume done through local suppliers.
The Local Supplier Volume Query lists for each nation in a region the revenue volume that resulted from lineitem
transactions in which the customer ordering parts and the supplier filling them were both within that nation. The
query is run in order to determine whether to institute local distribution centers in a given region. The query considers
only parts ordered in a given year. The query displays the nations and revenue volume in descending order by
revenue. Revenue volume for all qualifying lineitems in a particular nation is defined as sum(l_extendedprice * (1 -
l_discount)).
Planner enhancement: join reorder.
*/
explain format = 'brief'
select
n_name,
sum(l_extendedprice * (1 - l_discount)) as revenue
from
customer,
orders,
lineitem,
supplier,
nation,
region
where
c_custkey = o_custkey
and l_orderkey = o_orderkey
and l_suppkey = s_suppkey
and c_nationkey = s_nationkey
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'MIDDLE EAST'
and o_orderdate >= '1994-01-01'
and o_orderdate < date_add('1994-01-01', interval '1' year)
group by
n_name
order by
revenue desc;
id estRows task access object operator info
Sort 5.00 root Column#49:desc
└─Projection 5.00 root tpch.nation.n_name, Column#49
└─HashAgg 5.00 root group by:Column#52, funcs:sum(Column#50)->Column#49, funcs:firstrow(Column#51)->tpch.nation.n_name
└─Projection 11822812.50 root mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount))->Column#50, tpch.nation.n_name->Column#51, tpch.nation.n_name->Column#52
└─Projection 11822812.50 root tpch.lineitem.l_extendedprice, tpch.lineitem.l_discount, tpch.nation.n_name
└─HashJoin 11822812.50 root inner join, equal:[eq(tpch.orders.o_custkey, tpch.customer.c_custkey) eq(tpch.supplier.s_nationkey, tpch.customer.c_nationkey)]
├─TableReader(Build) 7500000.00 root data:TableFullScan
│ └─TableFullScan 7500000.00 cop[tikv] table:customer keep order:false
└─HashJoin(Probe) 11822812.50 root inner join, equal:[eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)]
├─TableReader(Build) 11822812.50 root data:Selection
│ └─Selection 11822812.50 cop[tikv] ge(tpch.orders.o_orderdate, 1994-01-01 00:00:00.000000), lt(tpch.orders.o_orderdate, 1995-01-01 00:00:00.000000)
│ └─TableFullScan 75000000.00 cop[tikv] table:orders keep order:false
└─HashJoin(Probe) 61163763.01 root inner join, equal:[eq(tpch.supplier.s_suppkey, tpch.lineitem.l_suppkey)]
├─HashJoin(Build) 100000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.supplier.s_nationkey)]
│ ├─HashJoin(Build) 5.00 root inner join, equal:[eq(tpch.region.r_regionkey, tpch.nation.n_regionkey)]
│ │ ├─TableReader(Build) 1.00 root data:Selection
│ │ │ └─Selection 1.00 cop[tikv] eq(tpch.region.r_name, "MIDDLE EAST")
│ │ │ └─TableFullScan 5.00 cop[tikv] table:region keep order:false
│ │ └─TableReader(Probe) 25.00 root data:TableFullScan
│ │ └─TableFullScan 25.00 cop[tikv] table:nation keep order:false
│ └─TableReader(Probe) 500000.00 root data:TableFullScan
│ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
└─TableReader(Probe) 300005811.00 root data:TableFullScan
└─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
/*
Q6 Forecasting Revenue Change Query
This query quantifies the amount of revenue increase that would have resulted from eliminating certain companywide
discounts in a given percentage range in a given year. Asking this type of "what if" query can be used to look
for ways to increase revenues.
The Forecasting Revenue Change Query considers all the lineitems shipped in a given year with discounts between
DISCOUNT-0.01 and DISCOUNT+0.01. The query lists the amount by which the total revenue would have
increased if these discounts had been eliminated for lineitems with l_quantity less than quantity. Note that the
potential revenue increase is equal to the sum of [l_extendedprice * l_discount] for all lineitems with discounts and
quantities in the qualifying range.
*/
explain format = 'brief'
select
sum(l_extendedprice * l_discount) as revenue
from
lineitem
where
l_shipdate >= '1994-01-01'
and l_shipdate < date_add('1994-01-01', interval '1' year)
and l_discount between 0.06 - 0.01 and 0.06 + 0.01
and l_quantity < 24;
id estRows task access object operator info
StreamAgg 1.00 root funcs:sum(Column#20)->Column#18
└─TableReader 1.00 root data:StreamAgg
└─StreamAgg 1.00 cop[tikv] funcs:sum(mul(tpch.lineitem.l_extendedprice, tpch.lineitem.l_discount))->Column#20
└─Selection 3713858.13 cop[tikv] ge(tpch.lineitem.l_discount, 0.05), ge(tpch.lineitem.l_shipdate, 1994-01-01 00:00:00.000000), le(tpch.lineitem.l_discount, 0.07), lt(tpch.lineitem.l_quantity, 24), lt(tpch.lineitem.l_shipdate, 1995-01-01 00:00:00.000000)
└─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
/*
Q7 Volume Shipping Query
This query determines the value of goods shipped between certain nations to help in the re-negotiation of shipping
contracts.
The Volume Shipping Query finds, for two given nations, the gross discounted revenues derived from lineitems in
which parts were shipped from a supplier in either nation to a customer in the other nation during 1995 and 1996.
The query lists the supplier nation, the customer nation, the year, and the revenue from shipments that took place in
that year. The query orders the answer by Supplier nation, Customer nation, and year (all ascending).
Planner enahancement: join reorder.
*/
explain format = 'brief'
select
supp_nation,
cust_nation,
l_year,
sum(volume) as revenue
from
(
select
n1.n_name as supp_nation,
n2.n_name as cust_nation,
extract(year from l_shipdate) as l_year,
l_extendedprice * (1 - l_discount) as volume
from
supplier,
lineitem,
orders,
customer,
nation n1,
nation n2
where
s_suppkey = l_suppkey
and o_orderkey = l_orderkey
and c_custkey = o_custkey
and s_nationkey = n1.n_nationkey
and c_nationkey = n2.n_nationkey
and (
(n1.n_name = 'JAPAN' and n2.n_name = 'INDIA')
or (n1.n_name = 'INDIA' and n2.n_name = 'JAPAN')
)
and l_shipdate between '1995-01-01' and '1996-12-31'
) as shipping
group by
supp_nation,
cust_nation,
l_year
order by
supp_nation,
cust_nation,
l_year;
id estRows task access object operator info
Sort 769.96 root tpch.nation.n_name, tpch.nation.n_name, Column#50
└─Projection 769.96 root tpch.nation.n_name, tpch.nation.n_name, Column#50, Column#52
└─HashAgg 769.96 root group by:Column#59, Column#60, Column#61, funcs:sum(Column#55)->Column#52, funcs:firstrow(Column#56)->tpch.nation.n_name, funcs:firstrow(Column#57)->tpch.nation.n_name, funcs:firstrow(Column#58)->Column#50
└─Projection 1957240.42 root mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount))->Column#55, tpch.nation.n_name->Column#56, tpch.nation.n_name->Column#57, extract(YEAR, tpch.lineitem.l_shipdate)->Column#58, tpch.nation.n_name->Column#59, tpch.nation.n_name->Column#60, extract(YEAR, tpch.lineitem.l_shipdate)->Column#61
└─Projection 1957240.42 root tpch.lineitem.l_extendedprice, tpch.lineitem.l_discount, tpch.lineitem.l_shipdate, tpch.nation.n_name, tpch.nation.n_name
└─HashJoin 1957240.42 root inner join, equal:[eq(tpch.customer.c_nationkey, tpch.nation.n_nationkey)], other cond:or(and(eq(tpch.nation.n_name, "JAPAN"), eq(tpch.nation.n_name, "INDIA")), and(eq(tpch.nation.n_name, "INDIA"), eq(tpch.nation.n_name, "JAPAN")))
├─TableReader(Build) 2.00 root data:Selection
│ └─Selection 2.00 cop[tikv] or(eq(tpch.nation.n_name, "INDIA"), eq(tpch.nation.n_name, "JAPAN"))
│ └─TableFullScan 25.00 cop[tikv] table:n2 keep order:false
└─HashJoin(Probe) 24465505.20 root inner join, equal:[eq(tpch.orders.o_custkey, tpch.customer.c_custkey)]
├─TableReader(Build) 7500000.00 root data:TableFullScan
│ └─TableFullScan 7500000.00 cop[tikv] table:customer keep order:false
└─IndexJoin(Probe) 24465505.20 root inner join, inner:TableReader, outer key:tpch.lineitem.l_orderkey, inner key:tpch.orders.o_orderkey, equal cond:eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)
├─HashJoin(Build) 24465505.20 root inner join, equal:[eq(tpch.supplier.s_suppkey, tpch.lineitem.l_suppkey)]
│ ├─HashJoin(Build) 40000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.supplier.s_nationkey)]
│ │ ├─TableReader(Build) 2.00 root data:Selection
│ │ │ └─Selection 2.00 cop[tikv] or(eq(tpch.nation.n_name, "JAPAN"), eq(tpch.nation.n_name, "INDIA"))
│ │ │ └─TableFullScan 25.00 cop[tikv] table:n1 keep order:false
│ │ └─TableReader(Probe) 500000.00 root data:TableFullScan
│ │ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
│ └─TableReader(Probe) 91446230.29 root data:Selection
│ └─Selection 91446230.29 cop[tikv] ge(tpch.lineitem.l_shipdate, 1995-01-01 00:00:00.000000), le(tpch.lineitem.l_shipdate, 1996-12-31 00:00:00.000000)
│ └─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
└─TableReader(Probe) 24465505.20 root data:TableRangeScan
└─TableRangeScan 24465505.20 cop[tikv] table:orders range: decided by [tpch.lineitem.l_orderkey], keep order:false
/*
Q8 National Market Share Query
This query determines how the market share of a given nation within a given region has changed over two years for
a given part type.
The market share for a given nation within a given region is defined as the fraction of the revenue, the sum of
[l_extendedprice * (1-l_discount)], from the products of a specified type in that region that was supplied by suppliers
from the given nation. The query determines this for the years 1995 and 1996 presented in this order.
Planner enhancement: join reorder.
*/
explain format = 'brief'
select
o_year,
sum(case
when nation = 'INDIA' then volume
else 0
end) / sum(volume) as mkt_share
from
(
select
extract(year from o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) as volume,
n2.n_name as nation
from
part,
supplier,
lineitem,
orders,
customer,
nation n1,
nation n2,
region
where
p_partkey = l_partkey
and s_suppkey = l_suppkey
and l_orderkey = o_orderkey
and o_custkey = c_custkey
and c_nationkey = n1.n_nationkey
and n1.n_regionkey = r_regionkey
and r_name = 'ASIA'
and s_nationkey = n2.n_nationkey
and o_orderdate between '1995-01-01' and '1996-12-31'
and p_type = 'SMALL PLATED COPPER'
) as all_nations
group by
o_year
order by
o_year;
id estRows task access object operator info
Sort 719.02 root Column#62
└─Projection 719.02 root Column#62, div(Column#64, Column#65)->Column#66
└─HashAgg 719.02 root group by:Column#78, funcs:sum(Column#75)->Column#64, funcs:sum(Column#76)->Column#65, funcs:firstrow(Column#77)->Column#62
└─Projection 563136.02 root case(eq(tpch.nation.n_name, INDIA), mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount)), 0)->Column#75, mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount))->Column#76, extract(YEAR, tpch.orders.o_orderdate)->Column#77, extract(YEAR, tpch.orders.o_orderdate)->Column#78
└─Projection 563136.02 root tpch.lineitem.l_extendedprice, tpch.lineitem.l_discount, tpch.orders.o_orderdate, tpch.nation.n_name
└─HashJoin 563136.02 root inner join, equal:[eq(tpch.supplier.s_nationkey, tpch.nation.n_nationkey)]
├─TableReader(Build) 25.00 root data:TableFullScan
│ └─TableFullScan 25.00 cop[tikv] table:n2 keep order:false
└─HashJoin(Probe) 563136.02 root inner join, equal:[eq(tpch.lineitem.l_suppkey, tpch.supplier.s_suppkey)]
├─TableReader(Build) 500000.00 root data:TableFullScan
│ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
└─HashJoin(Probe) 563136.02 root inner join, equal:[eq(tpch.lineitem.l_partkey, tpch.part.p_partkey)]
├─TableReader(Build) 61674.00 root data:Selection
│ └─Selection 61674.00 cop[tikv] eq(tpch.part.p_type, "SMALL PLATED COPPER")
│ └─TableFullScan 10000000.00 cop[tikv] table:part keep order:false
└─IndexHashJoin(Probe) 90788402.51 root inner join, inner:IndexLookUp, outer key:tpch.orders.o_orderkey, inner key:tpch.lineitem.l_orderkey, equal cond:eq(tpch.orders.o_orderkey, tpch.lineitem.l_orderkey)
├─HashJoin(Build) 22413367.93 root inner join, equal:[eq(tpch.customer.c_custkey, tpch.orders.o_custkey)]
│ ├─HashJoin(Build) 1500000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.customer.c_nationkey)]
│ │ ├─HashJoin(Build) 5.00 root inner join, equal:[eq(tpch.region.r_regionkey, tpch.nation.n_regionkey)]
│ │ │ ├─TableReader(Build) 1.00 root data:Selection
│ │ │ │ └─Selection 1.00 cop[tikv] eq(tpch.region.r_name, "ASIA")
│ │ │ │ └─TableFullScan 5.00 cop[tikv] table:region keep order:false
│ │ │ └─TableReader(Probe) 25.00 root data:TableFullScan
│ │ │ └─TableFullScan 25.00 cop[tikv] table:n1 keep order:false
│ │ └─TableReader(Probe) 7500000.00 root data:TableFullScan
│ │ └─TableFullScan 7500000.00 cop[tikv] table:customer keep order:false
│ └─TableReader(Probe) 22413367.93 root data:Selection
│ └─Selection 22413367.93 cop[tikv] ge(tpch.orders.o_orderdate, 1995-01-01 00:00:00.000000), le(tpch.orders.o_orderdate, 1996-12-31 00:00:00.000000)
│ └─TableFullScan 75000000.00 cop[tikv] table:orders keep order:false
└─IndexLookUp(Probe) 90788402.51 root
├─IndexRangeScan(Build) 90788402.51 cop[tikv] table:lineitem, index:PRIMARY(L_ORDERKEY, L_LINENUMBER) range: decided by [eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)], keep order:false
└─TableRowIDScan(Probe) 90788402.51 cop[tikv] table:lineitem keep order:false
/*
Q9 Product Type Profit Measure Query
This query determines how much profit is made on a given line of parts, broken out by supplier nation and year.
The Product Type Profit Measure Query finds, for each nation and each year, the profit for all parts ordered in that
year that contain a specified substring in their names and that were filled by a supplier in that nation. The profit is
defined as the sum of [(l_extendedprice*(1-l_discount)) - (ps_supplycost * l_quantity)] for all lineitems describing
parts in the specified line. The query lists the nations in ascending alphabetical order and, for each nation, the year
and profit in descending order by year (most recent first).
Planner enhancement: join reorder.
*/
explain format = 'brief'
select
nation,
o_year,
sum(amount) as sum_profit
from
(
select
n_name as nation,
extract(year from o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) - ps_supplycost * l_quantity as amount
from
part,
supplier,
lineitem,
partsupp,
orders,
nation
where
s_suppkey = l_suppkey
and ps_suppkey = l_suppkey
and ps_partkey = l_partkey
and p_partkey = l_partkey
and o_orderkey = l_orderkey
and s_nationkey = n_nationkey
and p_name like '%dim%'
) as profit
group by
nation,
o_year
order by
nation,
o_year desc;
id estRows task access object operator info
Sort 2406.00 root tpch.nation.n_name, Column#53:desc
└─Projection 2406.00 root tpch.nation.n_name, Column#53, Column#55
└─HashAgg 2406.00 root group by:Column#67, Column#68, funcs:sum(Column#64)->Column#55, funcs:firstrow(Column#65)->tpch.nation.n_name, funcs:firstrow(Column#66)->Column#53
└─Projection 241379546.70 root minus(mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount)), mul(tpch.partsupp.ps_supplycost, tpch.lineitem.l_quantity))->Column#64, tpch.nation.n_name->Column#65, extract(YEAR, tpch.orders.o_orderdate)->Column#66, tpch.nation.n_name->Column#67, extract(YEAR, tpch.orders.o_orderdate)->Column#68
└─Projection 241379546.70 root tpch.lineitem.l_quantity, tpch.lineitem.l_extendedprice, tpch.lineitem.l_discount, tpch.partsupp.ps_supplycost, tpch.orders.o_orderdate, tpch.nation.n_name
└─IndexJoin 241379546.70 root inner join, inner:TableReader, outer key:tpch.lineitem.l_orderkey, inner key:tpch.orders.o_orderkey, equal cond:eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)
├─IndexJoin(Build) 241379546.70 root inner join, inner:IndexLookUp, outer key:tpch.lineitem.l_suppkey, tpch.lineitem.l_partkey, inner key:tpch.partsupp.ps_suppkey, tpch.partsupp.ps_partkey, equal cond:eq(tpch.lineitem.l_partkey, tpch.partsupp.ps_partkey), eq(tpch.lineitem.l_suppkey, tpch.partsupp.ps_suppkey)
│ ├─HashJoin(Build) 241379546.70 root inner join, equal:[eq(tpch.lineitem.l_partkey, tpch.part.p_partkey)]
│ │ ├─TableReader(Build) 8000000.00 root data:Selection
│ │ │ └─Selection 8000000.00 cop[tikv] like(tpch.part.p_name, "%dim%", 92)
│ │ │ └─TableFullScan 10000000.00 cop[tikv] table:part keep order:false
│ │ └─HashJoin(Probe) 300005811.00 root inner join, equal:[eq(tpch.supplier.s_suppkey, tpch.lineitem.l_suppkey)]
│ │ ├─HashJoin(Build) 500000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.supplier.s_nationkey)]
│ │ │ ├─TableReader(Build) 25.00 root data:TableFullScan
│ │ │ │ └─TableFullScan 25.00 cop[tikv] table:nation keep order:false
│ │ │ └─TableReader(Probe) 500000.00 root data:TableFullScan
│ │ │ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
│ │ └─TableReader(Probe) 300005811.00 root data:TableFullScan
│ │ └─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
│ └─IndexLookUp(Probe) 241379546.70 root
│ ├─IndexRangeScan(Build) 241379546.70 cop[tikv] table:partsupp, index:PRIMARY(PS_PARTKEY, PS_SUPPKEY) range: decided by [eq(tpch.partsupp.ps_partkey, tpch.lineitem.l_partkey) eq(tpch.partsupp.ps_suppkey, tpch.lineitem.l_suppkey)], keep order:false
│ └─TableRowIDScan(Probe) 241379546.70 cop[tikv] table:partsupp keep order:false
└─TableReader(Probe) 241379546.70 root data:TableRangeScan
└─TableRangeScan 241379546.70 cop[tikv] table:orders range: decided by [tpch.lineitem.l_orderkey], keep order:false
/*
Q10 Returned Item Reporting Query
The query identifies customers who might be having problems with the parts that are shipped to them.
The Returned Item Reporting Query finds the top 20 customers, in terms of their effect on lost revenue for a given
quarter, who have returned parts. The query considers only parts that were ordered in the specified quarter. The
query lists the customer's name, address, nation, phone number, account balance, comment information and revenue
lost. The customers are listed in descending order of lost revenue. Revenue lost is defined as
sum(l_extendedprice*(1-l_discount)) for all qualifying lineitems.
Planner enhancement: join reorder, if group-by item have primary key, non-priamry key is useless.
*/
explain format = 'brief'
select
c_custkey,
c_name,
sum(l_extendedprice * (1 - l_discount)) as revenue,
c_acctbal,
n_name,
c_address,
c_phone,
c_comment
from
customer,
orders,
lineitem,
nation
where
c_custkey = o_custkey
and l_orderkey = o_orderkey
and o_orderdate >= '1993-08-01'
and o_orderdate < date_add('1993-08-01', interval '3' month)
and l_returnflag = 'R'
and c_nationkey = n_nationkey
group by
c_custkey,
c_name,
c_acctbal,
c_phone,
n_name,
c_address,
c_comment
order by
revenue desc
limit 20;
id estRows task access object operator info
Projection 20.00 root tpch.customer.c_custkey, tpch.customer.c_name, Column#39, tpch.customer.c_acctbal, tpch.nation.n_name, tpch.customer.c_address, tpch.customer.c_phone, tpch.customer.c_comment
└─TopN 20.00 root Column#39:desc, offset:0, count:20
└─HashAgg 3017307.69 root group by:Column#53, Column#54, Column#55, Column#56, Column#57, Column#58, Column#59, funcs:sum(Column#45)->Column#39, funcs:firstrow(Column#46)->tpch.customer.c_custkey, funcs:firstrow(Column#47)->tpch.customer.c_name, funcs:firstrow(Column#48)->tpch.customer.c_address, funcs:firstrow(Column#49)->tpch.customer.c_phone, funcs:firstrow(Column#50)->tpch.customer.c_acctbal, funcs:firstrow(Column#51)->tpch.customer.c_comment, funcs:firstrow(Column#52)->tpch.nation.n_name
└─Projection 12222016.17 root mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount))->Column#45, tpch.customer.c_custkey->Column#46, tpch.customer.c_name->Column#47, tpch.customer.c_address->Column#48, tpch.customer.c_phone->Column#49, tpch.customer.c_acctbal->Column#50, tpch.customer.c_comment->Column#51, tpch.nation.n_name->Column#52, tpch.customer.c_custkey->Column#53, tpch.customer.c_name->Column#54, tpch.customer.c_acctbal->Column#55, tpch.customer.c_phone->Column#56, tpch.nation.n_name->Column#57, tpch.customer.c_address->Column#58, tpch.customer.c_comment->Column#59
└─Projection 12222016.17 root tpch.customer.c_custkey, tpch.customer.c_name, tpch.customer.c_address, tpch.customer.c_phone, tpch.customer.c_acctbal, tpch.customer.c_comment, tpch.lineitem.l_extendedprice, tpch.lineitem.l_discount, tpch.nation.n_name
└─IndexHashJoin 12222016.17 root inner join, inner:IndexLookUp, outer key:tpch.orders.o_orderkey, inner key:tpch.lineitem.l_orderkey, equal cond:eq(tpch.orders.o_orderkey, tpch.lineitem.l_orderkey)
├─HashJoin(Build) 3017307.69 root inner join, equal:[eq(tpch.customer.c_custkey, tpch.orders.o_custkey)]
│ ├─TableReader(Build) 3017307.69 root data:Selection
│ │ └─Selection 3017307.69 cop[tikv] ge(tpch.orders.o_orderdate, 1993-08-01 00:00:00.000000), lt(tpch.orders.o_orderdate, 1993-11-01 00:00:00.000000)
│ │ └─TableFullScan 75000000.00 cop[tikv] table:orders keep order:false
│ └─HashJoin(Probe) 7500000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.customer.c_nationkey)]
│ ├─TableReader(Build) 25.00 root data:TableFullScan
│ │ └─TableFullScan 25.00 cop[tikv] table:nation keep order:false
│ └─TableReader(Probe) 7500000.00 root data:TableFullScan
│ └─TableFullScan 7500000.00 cop[tikv] table:customer keep order:false
└─IndexLookUp(Probe) 12222016.17 root
├─IndexRangeScan(Build) 49605980.10 cop[tikv] table:lineitem, index:PRIMARY(L_ORDERKEY, L_LINENUMBER) range: decided by [eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)], keep order:false
└─Selection(Probe) 12222016.17 cop[tikv] eq(tpch.lineitem.l_returnflag, "R")
└─TableRowIDScan 49605980.10 cop[tikv] table:lineitem keep order:false
/*
Q11 Important Stock Identification Query
This query finds the most important subset of suppliers' stock in a given nation.
The Important Stock Identification Query finds, from scanning the available stock of suppliers in a given nation, all
the parts that represent a significant percentage of the total value of all available parts. The query displays the part
number and the value of those parts in descending order of value.
*/
explain format = 'brief'
select
ps_partkey,
sum(ps_supplycost * ps_availqty) as value
from
partsupp,
supplier,
nation
where
ps_suppkey = s_suppkey
and s_nationkey = n_nationkey
and n_name = 'MOZAMBIQUE'
group by
ps_partkey having
sum(ps_supplycost * ps_availqty) > (
select
sum(ps_supplycost * ps_availqty) * 0.0001000000
from
partsupp,
supplier,
nation
where
ps_suppkey = s_suppkey
and s_nationkey = n_nationkey
and n_name = 'MOZAMBIQUE'
)
order by
value desc;
id estRows task access object operator info
Projection 1304801.67 root tpch.partsupp.ps_partkey, Column#35->Column#58
└─Sort 1304801.67 root Column#35:desc
└─Selection 1304801.67 root gt(Column#35, NULL)
└─HashAgg 1631002.09 root group by:Column#61, funcs:sum(Column#59)->Column#35, funcs:firstrow(Column#60)->tpch.partsupp.ps_partkey
└─Projection 1631002.09 root mul(tpch.partsupp.ps_supplycost, cast(tpch.partsupp.ps_availqty, decimal(10,0) BINARY))->Column#59, tpch.partsupp.ps_partkey->Column#60, tpch.partsupp.ps_partkey->Column#61
└─HashJoin 1631002.09 root inner join, equal:[eq(tpch.supplier.s_suppkey, tpch.partsupp.ps_suppkey)]
├─HashJoin(Build) 20000.00 root inner join, equal:[eq(tpch.nation.n_nationkey, tpch.supplier.s_nationkey)]
│ ├─TableReader(Build) 1.00 root data:Selection
│ │ └─Selection 1.00 cop[tikv] eq(tpch.nation.n_name, "MOZAMBIQUE")
│ │ └─TableFullScan 25.00 cop[tikv] table:nation keep order:false
│ └─TableReader(Probe) 500000.00 root data:TableFullScan
│ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
└─TableReader(Probe) 40000000.00 root data:TableFullScan
└─TableFullScan 40000000.00 cop[tikv] table:partsupp keep order:false
/*
Q12 Shipping Modes and Order Priority Query
This query determines whether selecting less expensive modes of shipping is negatively affecting the critical-priority
orders by causing more parts to be received by customers after the committed date.
The Shipping Modes and Order Priority Query counts, by ship mode, for lineitems actually received by customers in
a given year, the number of lineitems belonging to orders for which the l_receiptdate exceeds the l_commitdate for
two different specified ship modes. Only lineitems that were actually shipped before the l_commitdate are considered.
The late lineitems are partitioned into two groups, those with priority URGENT or HIGH, and those with a
priority other than URGENT or HIGH.
*/
explain format = 'brief'
select
l_shipmode,
sum(case
when o_orderpriority = '1-URGENT'
or o_orderpriority = '2-HIGH'
then 1
else 0
end) as high_line_count,
sum(case
when o_orderpriority <> '1-URGENT'
and o_orderpriority <> '2-HIGH'
then 1
else 0
end) as low_line_count
from
orders,
lineitem
where
o_orderkey = l_orderkey
and l_shipmode in ('RAIL', 'FOB')
and l_commitdate < l_receiptdate
and l_shipdate < l_commitdate
and l_receiptdate >= '1997-01-01'
and l_receiptdate < date_add('1997-01-01', interval '1' year)
group by
l_shipmode
order by
l_shipmode;
id estRows task access object operator info
Sort 1.00 root tpch.lineitem.l_shipmode
└─Projection 1.00 root tpch.lineitem.l_shipmode, Column#27, Column#28
└─HashAgg 1.00 root group by:Column#40, funcs:sum(Column#37)->Column#27, funcs:sum(Column#38)->Column#28, funcs:firstrow(Column#39)->tpch.lineitem.l_shipmode
└─Projection 10023369.01 root cast(case(or(eq(tpch.orders.o_orderpriority, 1-URGENT), eq(tpch.orders.o_orderpriority, 2-HIGH)), 1, 0), decimal(20,0) BINARY)->Column#37, cast(case(and(ne(tpch.orders.o_orderpriority, 1-URGENT), ne(tpch.orders.o_orderpriority, 2-HIGH)), 1, 0), decimal(20,0) BINARY)->Column#38, tpch.lineitem.l_shipmode->Column#39, tpch.lineitem.l_shipmode->Column#40
└─Projection 10023369.01 root tpch.orders.o_orderpriority, tpch.lineitem.l_shipmode
└─IndexJoin 10023369.01 root inner join, inner:TableReader, outer key:tpch.lineitem.l_orderkey, inner key:tpch.orders.o_orderkey, equal cond:eq(tpch.lineitem.l_orderkey, tpch.orders.o_orderkey)
├─TableReader(Build) 10023369.01 root data:Selection
│ └─Selection 10023369.01 cop[tikv] ge(tpch.lineitem.l_receiptdate, 1997-01-01 00:00:00.000000), in(tpch.lineitem.l_shipmode, "RAIL", "FOB"), lt(tpch.lineitem.l_commitdate, tpch.lineitem.l_receiptdate), lt(tpch.lineitem.l_receiptdate, 1998-01-01 00:00:00.000000), lt(tpch.lineitem.l_shipdate, tpch.lineitem.l_commitdate)
│ └─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
└─TableReader(Probe) 10023369.01 root data:TableRangeScan
└─TableRangeScan 10023369.01 cop[tikv] table:orders range: decided by [tpch.lineitem.l_orderkey], keep order:false
/*
Q13 Customer Distribution Query
This query seeks relationships between customers and the size of their orders.
This query determines the distribution of customers by the number of orders they have made, including customers
who have no record of orders, past or present. It counts and reports how many customers have no orders, how many
have 1, 2, 3, etc. A check is made to ensure that the orders counted do not fall into one of several special categories
of orders. Special categories are identified in the order comment column by looking for a particular pattern.
*/
explain format = 'brief'
select
c_count,
count(*) as custdist
from
(
select
c_custkey,
count(o_orderkey) as c_count
from
customer left outer join orders on
c_custkey = o_custkey
and o_comment not like '%pending%deposits%'
group by
c_custkey
) c_orders
group by
c_count
order by
custdist desc,
c_count desc;
id estRows task access object operator info
Sort 7500000.00 root Column#19:desc, Column#18:desc
└─Projection 7500000.00 root Column#18, Column#19
└─HashAgg 7500000.00 root group by:Column#18, funcs:count(1)->Column#19, funcs:firstrow(Column#18)->Column#18
└─HashAgg 7500000.00 root group by:tpch.customer.c_custkey, funcs:count(tpch.orders.o_orderkey)->Column#18
└─HashJoin 60000000.00 root left outer join, equal:[eq(tpch.customer.c_custkey, tpch.orders.o_custkey)]
├─TableReader(Build) 7500000.00 root data:TableFullScan
│ └─TableFullScan 7500000.00 cop[tikv] table:customer keep order:false
└─TableReader(Probe) 60000000.00 root data:Selection
└─Selection 60000000.00 cop[tikv] not(like(tpch.orders.o_comment, "%pending%deposits%", 92))
└─TableFullScan 75000000.00 cop[tikv] table:orders keep order:false
/*
Q14 Promotion Effect Query
This query monitors the market response to a promotion such as TV advertisements or a special campaign.
The Promotion Effect Query determines what percentage of the revenue in a given year and month was derived from
promotional parts. The query considers only parts actually shipped in that month and gives the percentage. Revenue
is defined as (l_extendedprice * (1-l_discount)).
*/
explain format = 'brief'
select
100.00 * sum(case
when p_type like 'PROMO%'
then l_extendedprice * (1 - l_discount)
else 0
end) / sum(l_extendedprice * (1 - l_discount)) as promo_revenue
from
lineitem,
part
where
l_partkey = p_partkey
and l_shipdate >= '1996-12-01'
and l_shipdate < date_add('1996-12-01', interval '1' month);
id estRows task access object operator info
Projection 1.00 root div(mul(100.00, Column#27), Column#28)->Column#29
└─HashAgg 1.00 root funcs:sum(Column#31)->Column#27, funcs:sum(Column#32)->Column#28
└─Projection 4121984.49 root case(like(tpch.part.p_type, PROMO%, 92), mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount)), 0)->Column#31, mul(tpch.lineitem.l_extendedprice, minus(1, tpch.lineitem.l_discount))->Column#32
└─IndexJoin 4121984.49 root inner join, inner:TableReader, outer key:tpch.lineitem.l_partkey, inner key:tpch.part.p_partkey, equal cond:eq(tpch.lineitem.l_partkey, tpch.part.p_partkey)
├─TableReader(Build) 4121984.49 root data:Selection
│ └─Selection 4121984.49 cop[tikv] ge(tpch.lineitem.l_shipdate, 1996-12-01 00:00:00.000000), lt(tpch.lineitem.l_shipdate, 1997-01-01 00:00:00.000000)
│ └─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
└─TableReader(Probe) 4121984.49 root data:TableRangeScan
└─TableRangeScan 4121984.49 cop[tikv] table:part range: decided by [tpch.lineitem.l_partkey], keep order:false
/*
Q15 Top Supplier Query
This query determines the top supplier so it can be rewarded, given more business, or identified for special recognition.
The Top Supplier Query finds the supplier who contributed the most to the overall revenue for parts shipped during
a given quarter of a given year. In case of a tie, the query lists all suppliers whose contribution was equal to the
maximum, presented in supplier number order.
Planner enhancement: support view.
create view revenue0 (supplier_no, total_revenue) as
select
l_suppkey,
sum(l_extendedprice * (1 - l_discount))
from
lineitem
where
l_shipdate >= '1997-07-01'
and l_shipdate < date_add('1997-07-01', interval '3' month)
group by
l_suppkey
select
s_suppkey,
s_name,
s_address,
s_phone,
total_revenue
from
supplier,
revenue0
where
s_suppkey = supplier_no
and total_revenue = (
select
max(total_revenue)
from
revenue0
)
order by
s_suppkey
drop view revenue0
*/
/*
Q16 Parts/Supplier Relationship Query
This query finds out how many suppliers can supply parts with given attributes. It might be used, for example, to
determine whether there is a sufficient number of suppliers for heavily ordered parts.
The Parts/Supplier Relationship Query counts the number of suppliers who can supply parts that satisfy a particular
customer's requirements. The customer is interested in parts of eight different sizes as long as they are not of a given
type, not of a given brand, and not from a supplier who has had complaints registered at the Better Business Bureau.
Results must be presented in descending count and ascending brand, type, and size.
*/
explain format = 'brief'
select
p_brand,
p_type,
p_size,
count(distinct ps_suppkey) as supplier_cnt
from
partsupp,
part
where
p_partkey = ps_partkey
and p_brand <> 'Brand#34'
and p_type not like 'LARGE BRUSHED%'
and p_size in (48, 19, 12, 4, 41, 7, 21, 39)
and ps_suppkey not in (
select
s_suppkey
from
supplier
where
s_comment like '%Customer%Complaints%'
)
group by
p_brand,
p_type,
p_size
order by
supplier_cnt desc,
p_brand,
p_type,
p_size;
id estRows task access object operator info
Sort 14.41 root Column#23:desc, tpch.part.p_brand, tpch.part.p_type, tpch.part.p_size
└─Projection 14.41 root tpch.part.p_brand, tpch.part.p_type, tpch.part.p_size, Column#23
└─HashAgg 14.41 root group by:tpch.part.p_brand, tpch.part.p_size, tpch.part.p_type, funcs:count(distinct tpch.partsupp.ps_suppkey)->Column#23, funcs:firstrow(tpch.part.p_brand)->tpch.part.p_brand, funcs:firstrow(tpch.part.p_type)->tpch.part.p_type, funcs:firstrow(tpch.part.p_size)->tpch.part.p_size
└─HashJoin 3863988.24 root anti semi join, equal:[eq(tpch.partsupp.ps_suppkey, tpch.supplier.s_suppkey)]
├─TableReader(Build) 400000.00 root data:Selection
│ └─Selection 400000.00 cop[tikv] like(tpch.supplier.s_comment, "%Customer%Complaints%", 92)
│ └─TableFullScan 500000.00 cop[tikv] table:supplier keep order:false
└─Projection(Probe) 4829985.30 root tpch.partsupp.ps_suppkey, tpch.part.p_brand, tpch.part.p_type, tpch.part.p_size
└─IndexHashJoin 4829985.30 root inner join, inner:IndexReader, outer key:tpch.part.p_partkey, inner key:tpch.partsupp.ps_partkey, equal cond:eq(tpch.part.p_partkey, tpch.partsupp.ps_partkey)
├─TableReader(Build) 1200618.43 root data:Selection
│ └─Selection 1200618.43 cop[tikv] in(tpch.part.p_size, 48, 19, 12, 4, 41, 7, 21, 39), ne(tpch.part.p_brand, "Brand#34"), not(like(tpch.part.p_type, "LARGE BRUSHED%", 92))
│ └─TableFullScan 10000000.00 cop[tikv] table:part keep order:false
└─IndexReader(Probe) 4829985.30 root index:IndexRangeScan
└─IndexRangeScan 4829985.30 cop[tikv] table:partsupp, index:PRIMARY(PS_PARTKEY, PS_SUPPKEY) range: decided by [eq(tpch.partsupp.ps_partkey, tpch.part.p_partkey)], keep order:false
/*
Q17 Small-Quantity-Order Revenue Query
This query determines how much average yearly revenue would be lost if orders were no longer filled for small
quantities of certain parts. This may reduce overhead expenses by concentrating sales on larger shipments.
The Small-Quantity-Order Revenue Query considers parts of a given brand and with a given container type and
determines the average lineitem quantity of such parts ordered for all orders (past and pending) in the 7-year database.
What would be the average yearly gross (undiscounted) loss in revenue if orders for these parts with a quantity
of less than 20% of this average were no longer taken?
Planner enahancement: aggregation pull up through join.
*/
explain format = 'brief'
select
sum(l_extendedprice) / 7.0 as avg_yearly
from
lineitem,
part
where
p_partkey = l_partkey
and p_brand = 'Brand#44'
and p_container = 'WRAP PKG'
and l_quantity < (
select
0.2 * avg(l_quantity)
from
lineitem
where
l_partkey = p_partkey
);
id estRows task access object operator info
Projection 1.00 root div(Column#46, 7.0)->Column#47
└─HashAgg 1.00 root funcs:sum(tpch.lineitem.l_extendedprice)->Column#46
└─HashJoin 293773.83 root inner join, equal:[eq(tpch.part.p_partkey, tpch.lineitem.l_partkey)], other cond:lt(tpch.lineitem.l_quantity, mul(0.2, Column#44))
├─HashJoin(Build) 293773.83 root inner join, equal:[eq(tpch.part.p_partkey, tpch.lineitem.l_partkey)]
│ ├─TableReader(Build) 9736.49 root data:Selection
│ │ └─Selection 9736.49 cop[tikv] eq(tpch.part.p_brand, "Brand#44"), eq(tpch.part.p_container, "WRAP PKG")
│ │ └─TableFullScan 10000000.00 cop[tikv] table:part keep order:false
│ └─TableReader(Probe) 300005811.00 root data:TableFullScan
│ └─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
└─HashAgg(Probe) 9943040.00 root group by:tpch.lineitem.l_partkey, funcs:avg(Column#50, Column#51)->Column#44, funcs:firstrow(tpch.lineitem.l_partkey)->tpch.lineitem.l_partkey
└─TableReader 9943040.00 root data:HashAgg
└─HashAgg 9943040.00 cop[tikv] group by:tpch.lineitem.l_partkey, funcs:count(tpch.lineitem.l_quantity)->Column#50, funcs:sum(tpch.lineitem.l_quantity)->Column#51
└─TableFullScan 300005811.00 cop[tikv] table:lineitem keep order:false
/*
Q18 Large Volume Customer Query
The Large Volume Customer Query ranks customers based on their having placed a large quantity order. Large
quantity orders are defined as those orders whose total quantity is above a certain level.
The Large Volume Customer Query finds a list of the top 100 customers who have ever placed large quantity orders.
The query lists the customer name, customer key, the order key, date and total price and the quantity for the order.
Planner enhancement: cost estimation is not so good, join reorder. The inner subquery's result is only 300+ rows.
*/
explain format = 'brief'
select
c_name,
c_custkey,
o_orderkey,
o_orderdate,