task2 - Details for Query 5

Details for Query 5

Submitted Time: 2024/12/04 20:23:25
Duration: 18 s
Succeeded Jobs: 7

Show the Stage ID and Task ID that corresponds to the max metric

digraph G { 0 [labelType="html" label=" TakeOrderedAndProject "]; subgraph cluster1 { isCluster="true"; label="WholeStageCodegen (7)\n \nduration: total (min, med, max (stageId: taskId))\n459 ms (0 ms, 1 ms, 20 ms (stage 15.0: task 834))"; 2 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 122 ms (0 ms, 0 ms, 8 ms (stage 15.0: task 834)) peak memory total (min, med, max (stageId: taskId)) 1650.0 MiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 15.0: task 830)) number of output rows: 30 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1 (stage 15.0: task 830))"]; } 3 [labelType="html" label="Exchange shuffle records written: 5,933 shuffle write time total (min, med, max (stageId: taskId)) 1.0 s (4 ms, 4 ms, 9 ms (stage 14.0: task 717)) records read: 5,933 local bytes read total (min, med, max (stageId: taskId)) 212.8 KiB (0.0 B, 0.0 B, 11.1 KiB (stage 15.0: task 830)) fetch wait time total (min, med, max (stageId: taskId)) 4 ms (0 ms, 0 ms, 1 ms (stage 15.0: task 837)) remote bytes read total (min, med, max (stageId: taskId)) 212.6 KiB (0.0 B, 0.0 B, 13.0 KiB (stage 15.0: task 849)) local blocks read: 2,480 remote blocks read: 2,467 data size total (min, med, max (stageId: taskId)) 278.1 KiB (1344.0 B, 1440.0 B, 1440.0 B (stage 14.0: task 632)) shuffle bytes written total (min, med, max (stageId: taskId)) 425.4 KiB (2011.0 B, 2.1 KiB, 2.2 KiB (stage 14.0: task 726))"]; subgraph cluster4 { isCluster="true"; label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n3.1 s (10 ms, 14 ms, 121 ms (stage 14.0: task 791))"; 5 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 1.4 s (3 ms, 5 ms, 109 ms (stage 14.0: task 791)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 14.0: task 630)) number of output rows: 5,933"]; 6 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 946 ms (2 ms, 3 ms, 106 ms (stage 14.0: task 790)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 14.0: task 630)) number of output rows: 28,128"]; } 7 [labelType="html" label="Exchange shuffle records written: 85,947 shuffle write time total (min, med, max (stageId: taskId)) 2.8 s (10 ms, 13 ms, 21 ms (stage 13.0: task 625)) records read: 85,947 local bytes read total (min, med, max (stageId: taskId)) 3.6 MiB (10.1 KiB, 17.9 KiB, 31.6 KiB (stage 14.0: task 739)) fetch wait time total (min, med, max (stageId: taskId)) 166 ms (0 ms, 0 ms, 101 ms (stage 14.0: task 791)) remote bytes read total (min, med, max (stageId: taskId)) 3.6 MiB (10.3 KiB, 17.5 KiB, 34.6 KiB (stage 14.0: task 747)) local blocks read: 17,886 remote blocks read: 17,426 data size total (min, med, max (stageId: taskId)) 7.9 MiB (27.4 KiB, 40.0 KiB, 54.3 KiB (stage 13.0: task 540)) shuffle bytes written total (min, med, max (stageId: taskId)) 7.2 MiB (28.0 KiB, 36.9 KiB, 46.0 KiB (stage 13.0: task 540))"]; subgraph cluster8 { isCluster="true"; label="WholeStageCodegen (5)\n \nduration: total (min, med, max (stageId: taskId))\n5.1 s (15 ms, 21 ms, 165 ms (stage 13.0: task 532))"; 9 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 942 ms (2 ms, 3 ms, 124 ms (stage 13.0: task 534)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 13.0: task 430)) number of output rows: 85,947"]; 10 [labelType="html" label=" Project "]; 11 [labelType="html" label="SortMergeJoin number of output rows: 173,805"]; } subgraph cluster12 { isCluster="true"; label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n1.4 s (0 ms, 7 ms, 135 ms (stage 13.0: task 430))"; 13 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 12 ms (0 ms, 0 ms, 6 ms (stage 13.0: task 627)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 13.0: task 431)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 13.0: task 430))"]; } 14 [labelType="html" label="Exchange shuffle records written: 504,708 shuffle write time total (min, med, max (stageId: taskId)) 82 ms (35 ms, 46 ms, 46 ms (stage 12.0: task 428)) records read: 504,708 local bytes read total (min, med, max (stageId: taskId)) 10.5 MiB (44.8 KiB, 53.0 KiB, 68.2 KiB (stage 13.0: task 532)) fetch wait time total (min, med, max (stageId: taskId)) 148 ms (0 ms, 0 ms, 117 ms (stage 13.0: task 534)) remote bytes read total (min, med, max (stageId: taskId)) 10.7 MiB (45.1 KiB, 54.3 KiB, 70.7 KiB (stage 13.0: task 539)) local blocks read: 200 remote blocks read: 200 data size total (min, med, max (stageId: taskId)) 69.3 MiB (32.5 MiB, 36.8 MiB, 36.8 MiB (stage 12.0: task 428)) shuffle bytes written total (min, med, max (stageId: taskId)) 21.2 MiB (10.0 MiB, 11.2 MiB, 11.2 MiB (stage 12.0: task 428))"]; subgraph cluster15 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n4.4 s (2.0 s, 2.4 s, 2.4 s (stage 12.0: task 428))"; 16 [labelType="html" label=" Project "]; 17 [labelType="html" label="Filter number of output rows: 504,708"]; } 18 [labelType="html" label="Scan csv number of files read: 1 metadata time: 0 ms size of files read: 173.6 MiB number of output rows: 504,708"]; subgraph cluster19 { isCluster="true"; label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n1.3 s (0 ms, 6 ms, 190 ms (stage 13.0: task 431))"; 20 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 13.0: task 430)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 13.0: task 430)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 13.0: task 430))"]; } 21 [labelType="html" label="Exchange shuffle records written: 144,178 shuffle write time total (min, med, max (stageId: taskId)) 54 ms (0 ms, 0 ms, 30 ms (stage 11.0: task 425)) records read: 144,178 local bytes read total (min, med, max (stageId: taskId)) 4.7 MiB (18.4 KiB, 24.1 KiB, 29.2 KiB (stage 13.0: task 465)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 13.0: task 430)) remote bytes read total (min, med, max (stageId: taskId)) 4.6 MiB (18.5 KiB, 23.3 KiB, 29.2 KiB (stage 13.0: task 509)) local blocks read: 200 remote blocks read: 200 data size total (min, med, max (stageId: taskId)) 15.4 MiB (0.0 B, 0.0 B, 8.2 MiB (stage 11.0: task 424)) shuffle bytes written total (min, med, max (stageId: taskId)) 9.3 MiB (0.0 B, 0.0 B, 4.9 MiB (stage 11.0: task 424))"]; subgraph cluster22 { isCluster="true"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n11.5 s (206 ms, 2.7 s, 2.9 s (stage 11.0: task 425))"; 23 [labelType="html" label=" Project "]; 24 [labelType="html" label="Filter number of output rows: 144,178"]; } 25 [labelType="html" label="Scan csv number of files read: 1 metadata time: 0 ms size of files read: 519.0 MiB number of output rows: 500,001"]; 2->0; 3->2; 5->3; 6->5; 7->6; 9->7; 10->9; 11->10; 13->11; 14->13; 16->14; 17->16; 18->17; 20->11; 21->20; 23->21; 24->23; 25->24; }

TakeOrderedAndProject(limit=21, orderBy=[formatted_date#136 ASC NULLS FIRST], output=[formatted_date#136,block_count#362,unique_senders_count_number#363])

HashAggregate(keys=[formatted_date#136], functions=[count(block_hash#72), count(distinct from_address#75)])

WholeStageCodegen (7)

Exchange hashpartitioning(formatted_date#136, 200), true, [id=#223]

HashAggregate(keys=[formatted_date#136], functions=[merge_count(block_hash#72), partial_count(distinct from_address#75)])

HashAggregate(keys=[formatted_date#136, from_address#75], functions=[merge_count(block_hash#72)])

WholeStageCodegen (6)

Exchange hashpartitioning(formatted_date#136, from_address#75, 200), true, [id=#218]

HashAggregate(keys=[formatted_date#136, from_address#75], functions=[partial_count(block_hash#72)])

Project [block_hash#72, from_address#75, formatted_date#136]

SortMergeJoin [block_hash#72], [hash#17], Inner

WholeStageCodegen (5)

Sort [block_hash#72 ASC NULLS FIRST], false, 0

WholeStageCodegen (2)

Exchange hashpartitioning(block_hash#72, 200), true, [id=#200]

Project [block_hash#72, from_address#75]

Filter isnotnull(block_hash#72)

WholeStageCodegen (1)

FileScan csv [block_hash#72,from_address#75] Batched: false, DataFilters: [isnotnull(block_hash#72)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/transactions.csv], PartitionFilters: [], PushedFilters: [IsNotNull(block_hash)], ReadSchema: struct<block_hash:string,from_address:string>

Sort [hash#17 ASC NULLS FIRST], false, 0

WholeStageCodegen (4)

Exchange hashpartitioning(hash#17, 200), true, [id=#209]

Project [hash#17, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]

Filter (((date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) >= 2015-09-01) AND (date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) <= 2015-09-30)) AND isnotnull(hash#17))

WholeStageCodegen (3)

FileScan csv [hash#17,timestamp#32] Batched: false, DataFilters: [(date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as..., Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/blocks.csv], PartitionFilters: [], PushedFilters: [IsNotNull(hash)], ReadSchema: struct<hash:string,timestamp:int>

Details

== Parsed Logical Plan ==
GlobalLimit 21
+- LocalLimit 21
   +- Project [cast(formatted_date#136 as string) AS formatted_date#361, cast(block_count#352L as string) AS block_count#362, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#363]
      +- Sort [formatted_date#136 ASC NULLS FIRST], true
         +- Aggregate [formatted_date#136], [formatted_date#136, count(block_hash#72) AS block_count#352L, count(distinct from_address#75) AS unique_senders_count_number#353L]
            +- Filter ((formatted_date#136 >= 2015-09-01) AND (formatted_date#136 <= 2015-09-30))
               +- Join Inner, (block_hash#72 = hash#17)
                  :- Relation[hash#70,nonce#71,block_hash#72,block_number#73,transaction_index#74,from_address#75,to_address#76,value#77,gas#78,gas_price#79L,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv
                  +- Project [number#16, hash#17, parent_hash#18, nonce#19, sha3_uncles#20, logs_bloom#21, transactions_root#22, state_root#23, receipts_root#24, miner#25, difficulty#26L, total_difficulty#27, size#28, extra_data#29, gas_limit#30, gas_used#31, timestamp#32, transaction_count#33, base_fee_per_gas#34, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                     +- Relation[number#16,hash#17,parent_hash#18,nonce#19,sha3_uncles#20,logs_bloom#21,transactions_root#22,state_root#23,receipts_root#24,miner#25,difficulty#26L,total_difficulty#27,size#28,extra_data#29,gas_limit#30,gas_used#31,timestamp#32,transaction_count#33,base_fee_per_gas#34] csv

== Analyzed Logical Plan ==
formatted_date: string, block_count: string, unique_senders_count_number: string
GlobalLimit 21
+- LocalLimit 21
   +- Project [cast(formatted_date#136 as string) AS formatted_date#361, cast(block_count#352L as string) AS block_count#362, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#363]
      +- Sort [formatted_date#136 ASC NULLS FIRST], true
         +- Aggregate [formatted_date#136], [formatted_date#136, count(block_hash#72) AS block_count#352L, count(distinct from_address#75) AS unique_senders_count_number#353L]
            +- Filter ((formatted_date#136 >= 2015-09-01) AND (formatted_date#136 <= 2015-09-30))
               +- Join Inner, (block_hash#72 = hash#17)
                  :- Relation[hash#70,nonce#71,block_hash#72,block_number#73,transaction_index#74,from_address#75,to_address#76,value#77,gas#78,gas_price#79L,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv
                  +- Project [number#16, hash#17, parent_hash#18, nonce#19, sha3_uncles#20, logs_bloom#21, transactions_root#22, state_root#23, receipts_root#24, miner#25, difficulty#26L, total_difficulty#27, size#28, extra_data#29, gas_limit#30, gas_used#31, timestamp#32, transaction_count#33, base_fee_per_gas#34, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                     +- Relation[number#16,hash#17,parent_hash#18,nonce#19,sha3_uncles#20,logs_bloom#21,transactions_root#22,state_root#23,receipts_root#24,miner#25,difficulty#26L,total_difficulty#27,size#28,extra_data#29,gas_limit#30,gas_used#31,timestamp#32,transaction_count#33,base_fee_per_gas#34] csv

== Optimized Logical Plan ==
GlobalLimit 21
+- LocalLimit 21
   +- Project [formatted_date#136, cast(block_count#352L as string) AS block_count#362, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#363]
      +- Sort [formatted_date#136 ASC NULLS FIRST], true
         +- Aggregate [formatted_date#136], [formatted_date#136, count(block_hash#72) AS block_count#352L, count(distinct from_address#75) AS unique_senders_count_number#353L]
            +- Project [block_hash#72, from_address#75, formatted_date#136]
               +- Join Inner, (block_hash#72 = hash#17)
                  :- Project [block_hash#72, from_address#75]
                  :  +- Filter isnotnull(block_hash#72)
                  :     +- Relation[hash#70,nonce#71,block_hash#72,block_number#73,transaction_index#74,from_address#75,to_address#76,value#77,gas#78,gas_price#79L,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv
                  +- Project [hash#17, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                     +- Filter (((date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) >= 2015-09-01) AND (date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) <= 2015-09-30)) AND isnotnull(hash#17))
                        +- Relation[number#16,hash#17,parent_hash#18,nonce#19,sha3_uncles#20,logs_bloom#21,transactions_root#22,state_root#23,receipts_root#24,miner#25,difficulty#26L,total_difficulty#27,size#28,extra_data#29,gas_limit#30,gas_used#31,timestamp#32,transaction_count#33,base_fee_per_gas#34] csv

== Physical Plan ==
TakeOrderedAndProject(limit=21, orderBy=[formatted_date#136 ASC NULLS FIRST], output=[formatted_date#136,block_count#362,unique_senders_count_number#363])
+- *(7) HashAggregate(keys=[formatted_date#136], functions=[count(block_hash#72), count(distinct from_address#75)], output=[formatted_date#136, block_count#352L, unique_senders_count_number#353L])
   +- Exchange hashpartitioning(formatted_date#136, 200), true, [id=#223]
      +- *(6) HashAggregate(keys=[formatted_date#136], functions=[merge_count(block_hash#72), partial_count(distinct from_address#75)], output=[formatted_date#136, count#368L, count#371L])
         +- *(6) HashAggregate(keys=[formatted_date#136, from_address#75], functions=[merge_count(block_hash#72)], output=[formatted_date#136, from_address#75, count#368L])
            +- Exchange hashpartitioning(formatted_date#136, from_address#75, 200), true, [id=#218]
               +- *(5) HashAggregate(keys=[formatted_date#136, from_address#75], functions=[partial_count(block_hash#72)], output=[formatted_date#136, from_address#75, count#368L])
                  +- *(5) Project [block_hash#72, from_address#75, formatted_date#136]
                     +- *(5) SortMergeJoin [block_hash#72], [hash#17], Inner
                        :- *(2) Sort [block_hash#72 ASC NULLS FIRST], false, 0
                        :  +- Exchange hashpartitioning(block_hash#72, 200), true, [id=#200]
                        :     +- *(1) Project [block_hash#72, from_address#75]
                        :        +- *(1) Filter isnotnull(block_hash#72)
                        :           +- FileScan csv [block_hash#72,from_address#75] Batched: false, DataFilters: [isnotnull(block_hash#72)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/transactions.csv], PartitionFilters: [], PushedFilters: [IsNotNull(block_hash)], ReadSchema: struct<block_hash:string,from_address:string>
                        +- *(4) Sort [hash#17 ASC NULLS FIRST], false, 0
                           +- Exchange hashpartitioning(hash#17, 200), true, [id=#209]
                              +- *(3) Project [hash#17, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                                 +- *(3) Filter (((date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) >= 2015-09-01) AND (date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) <= 2015-09-30)) AND isnotnull(hash#17))
                                    +- FileScan csv [hash#17,timestamp#32] Batched: false, DataFilters: [(date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as..., Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/blocks.csv], PartitionFilters: [], PushedFilters: [IsNotNull(hash)], ReadSchema: struct<hash:string,timestamp:int>