task2 - Details for Query 6

Details for Query 6

Submitted Time: 2024/10/29 20:23:21
Duration: 11 s
Succeeded Jobs: 7 8

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

digraph G { 0 [labelType="html" label=" CollectLimit "]; subgraph cluster1 { isCluster="true"; label="WholeStageCodegen (9)\n \nduration: 48 ms"; 2 [labelType="html" label=" Project "]; } 3 [labelType="html" label=" Coalesce "]; subgraph cluster4 { isCluster="true"; label="WholeStageCodegen (8)\n \nduration: 21 ms"; 5 [labelType="html" label="Sort sort time: 0 ms peak memory: 1921.9 MiB spill size: 0.0 B"]; } 6 [labelType="html" label="Exchange shuffle records written: 30 shuffle write time total (min, med, max (stageId: taskId)) 12 ms (0 ms, 0 ms, 0 ms (stage 29.0: task 1832)) records read: 30 local bytes read: 1290.0 B fetch wait time: 0 ms remote bytes read: 1290.0 B local blocks read: 15 remote blocks read: 15 data size total (min, med, max (stageId: taskId)) 1440.0 B (0.0 B, 0.0 B, 144.0 B (stage 29.0: task 1850)) shuffle bytes written total (min, med, max (stageId: taskId)) 2.5 KiB (0.0 B, 0.0 B, 258.0 B (stage 29.0: task 1850))"]; subgraph cluster7 { isCluster="true"; label="WholeStageCodegen (7)\n \nduration: total (min, med, max (stageId: taskId))\n269 ms (0 ms, 0 ms, 67 ms (stage 24.0: task 1633))"; 8 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 228 ms (0 ms, 0 ms, 67 ms (stage 24.0: task 1633)) peak memory total (min, med, max (stageId: taskId)) 3.2 GiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 24.0: task 1632)) number of output rows: 60 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1 (stage 24.0: task 1632))"]; } 9 [labelType="html" label="Exchange shuffle records written: 5,933 shuffle write time total (min, med, max (stageId: taskId)) 696 ms (3 ms, 3 ms, 9 ms (stage 23.0: task 1585)) records read: 11,866 local bytes read total (min, med, max (stageId: taskId)) 425.9 KiB (0.0 B, 0.0 B, 12.1 KiB (stage 24.0: task 1650)) fetch wait time total (min, med, max (stageId: taskId)) 61 ms (0 ms, 0 ms, 61 ms (stage 24.0: task 1633)) remote bytes read total (min, med, max (stageId: taskId)) 425.1 KiB (0.0 B, 0.0 B, 11.9 KiB (stage 24.0: task 1650)) local blocks read: 4,951 remote blocks read: 4,943 data size total (min, med, max (stageId: taskId)) 278.1 KiB (1344.0 B, 1440.0 B, 1440.0 B (stage 23.0: task 1433)) shuffle bytes written total (min, med, max (stageId: taskId)) 425.5 KiB (2006.0 B, 2.1 KiB, 2.2 KiB (stage 23.0: task 1527))"]; subgraph cluster10 { isCluster="true"; label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n1.7 s (6 ms, 8 ms, 35 ms (stage 23.0: task 1567))"; 11 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 583 ms (2 ms, 3 ms, 25 ms (stage 23.0: task 1457)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 23.0: task 1431)) number of output rows: 5,933"]; 12 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 382 ms (1 ms, 2 ms, 24 ms (stage 23.0: task 1457)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 23.0: task 1431)) number of output rows: 28,128"]; } 13 [labelType="html" label="Exchange shuffle records written: 85,947 shuffle write time total (min, med, max (stageId: taskId)) 1.8 s (7 ms, 8 ms, 11 ms (stage 22.0: task 1398)) records read: 85,947 local bytes read total (min, med, max (stageId: taskId)) 3.6 MiB (12.0 KiB, 18.1 KiB, 29.4 KiB (stage 23.0: task 1548)) fetch wait time total (min, med, max (stageId: taskId)) 46 ms (0 ms, 0 ms, 21 ms (stage 23.0: task 1457)) remote bytes read total (min, med, max (stageId: taskId)) 3.6 MiB (11.7 KiB, 17.8 KiB, 31.7 KiB (stage 23.0: task 1548)) local blocks read: 17,627 remote blocks read: 17,685 data size total (min, med, max (stageId: taskId)) 7.9 MiB (27.4 KiB, 40.0 KiB, 54.3 KiB (stage 22.0: task 1341)) shuffle bytes written total (min, med, max (stageId: taskId)) 7.2 MiB (28.0 KiB, 36.9 KiB, 46.0 KiB (stage 22.0: task 1341))"]; subgraph cluster14 { isCluster="true"; label="WholeStageCodegen (5)\n \nduration: total (min, med, max (stageId: taskId))\n3.2 s (11 ms, 13 ms, 48 ms (stage 22.0: task 1419))"; 15 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 435 ms (1 ms, 2 ms, 37 ms (stage 22.0: task 1419)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 22.0: task 1231)) number of output rows: 85,947"]; 16 [labelType="html" label=" Project "]; 17 [labelType="html" label="SortMergeJoin number of output rows: 173,805"]; } subgraph cluster18 { isCluster="true"; label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n671 ms (0 ms, 4 ms, 41 ms (stage 22.0: task 1419))"; 19 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 22.0: task 1231)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 22.0: task 1231)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 22.0: task 1231))"]; } 20 [labelType="html" label="Exchange shuffle records written: 144,178 shuffle write time total (min, med, max (stageId: taskId)) 29 ms (0 ms, 0 ms, 15 ms (stage 21.0: task 1227)) records read: 144,178 local bytes read total (min, med, max (stageId: taskId)) 4.7 MiB (18.4 KiB, 24.0 KiB, 29.2 KiB (stage 22.0: task 1310)) fetch wait time total (min, med, max (stageId: taskId)) 82 ms (0 ms, 0 ms, 35 ms (stage 22.0: task 1419)) remote bytes read total (min, med, max (stageId: taskId)) 4.6 MiB (18.5 KiB, 23.4 KiB, 29.2 KiB (stage 22.0: task 1266)) 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 21.0: task 1227)) shuffle bytes written total (min, med, max (stageId: taskId)) 9.3 MiB (0.0 B, 0.0 B, 4.9 MiB (stage 21.0: task 1227))"]; subgraph cluster21 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n7.0 s (153 ms, 1.7 s, 1.9 s (stage 21.0: task 1228))"; 22 [labelType="html" label=" Project "]; 23 [labelType="html" label="Filter number of output rows: 144,178"]; } 24 [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"]; subgraph cluster25 { isCluster="true"; label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n655 ms (0 ms, 3 ms, 78 ms (stage 22.0: task 1282))"; 26 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 22.0: task 1231)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 22.0: task 1232)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 22.0: task 1231))"]; } 27 [labelType="html" label="Exchange shuffle records written: 504,708 shuffle write time total (min, med, max (stageId: taskId)) 42 ms (20 ms, 21 ms, 21 ms (stage 20.0: task 1224)) records read: 504,708 local bytes read total (min, med, max (stageId: taskId)) 10.6 MiB (44.8 KiB, 53.3 KiB, 65.4 KiB (stage 22.0: task 1401)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 22.0: task 1231)) remote bytes read total (min, med, max (stageId: taskId)) 10.6 MiB (45.1 KiB, 54.0 KiB, 70.7 KiB (stage 22.0: task 1340)) 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 20.0: task 1224)) shuffle bytes written total (min, med, max (stageId: taskId)) 21.2 MiB (10.0 MiB, 11.2 MiB, 11.2 MiB (stage 20.0: task 1224))"]; subgraph cluster28 { isCluster="true"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n2.5 s (1.2 s, 1.3 s, 1.3 s (stage 20.0: task 1224))"; 29 [labelType="html" label=" Project "]; 30 [labelType="html" label="Filter number of output rows: 504,708"]; } 31 [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"]; 2->0; 3->2; 5->3; 6->5; 8->6; 9->8; 11->9; 12->11; 13->12; 15->13; 16->15; 17->16; 19->17; 20->19; 22->20; 23->22; 24->23; 26->17; 27->26; 29->27; 30->29; 31->30; }

CollectLimit 31

Project [formatted_date#136, cast(block_count#352L as string) AS block_count#375, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#376]

WholeStageCodegen (9)

Coalesce 1

Sort [formatted_date#136 ASC NULLS FIRST], true, 0

WholeStageCodegen (8)

Exchange rangepartitioning(formatted_date#136 ASC NULLS FIRST, 200), true, [id=#349]

HashAggregate(keys=[formatted_date#136], functions=[count(1), count(distinct from_address#75)])

WholeStageCodegen (7)

Exchange hashpartitioning(formatted_date#136, 200), true, [id=#345]

HashAggregate(keys=[formatted_date#136], functions=[merge_count(1), partial_count(distinct from_address#75)])

HashAggregate(keys=[formatted_date#136, from_address#75], functions=[merge_count(1)])

WholeStageCodegen (6)

Exchange hashpartitioning(formatted_date#136, from_address#75, 200), true, [id=#340]

HashAggregate(keys=[formatted_date#136, from_address#75], functions=[partial_count(1)])

Project [formatted_date#136, from_address#75]

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

WholeStageCodegen (5)

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

WholeStageCodegen (2)

Exchange hashpartitioning(hash#17, 200), true, [id=#322]

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 (1)

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:string>

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

WholeStageCodegen (4)

Exchange hashpartitioning(block_hash#72, 200), true, [id=#331]

Project [block_hash#72, from_address#75]

Filter isnotnull(block_hash#72)

WholeStageCodegen (3)

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>

Details

== Parsed Logical Plan ==
GlobalLimit 31
+- LocalLimit 31
   +- Project [cast(formatted_date#136 as string) AS formatted_date#374, cast(block_count#352L as string) AS block_count#375, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#376]
      +- Repartition 1, false
         +- Sort [formatted_date#136 ASC NULLS FIRST], true
            +- Aggregate [formatted_date#136], [formatted_date#136, count(1) 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, (hash#17 = block_hash#72)
                     :- 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#26, 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#26,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
                     +- 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#79,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv

== Analyzed Logical Plan ==
formatted_date: string, block_count: string, unique_senders_count_number: string
GlobalLimit 31
+- LocalLimit 31
   +- Project [cast(formatted_date#136 as string) AS formatted_date#374, cast(block_count#352L as string) AS block_count#375, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#376]
      +- Repartition 1, false
         +- Sort [formatted_date#136 ASC NULLS FIRST], true
            +- Aggregate [formatted_date#136], [formatted_date#136, count(1) 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, (hash#17 = block_hash#72)
                     :- 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#26, 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#26,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
                     +- 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#79,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv

== Optimized Logical Plan ==
GlobalLimit 31
+- LocalLimit 31
   +- Project [formatted_date#136, cast(block_count#352L as string) AS block_count#375, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#376]
      +- Repartition 1, false
         +- Sort [formatted_date#136 ASC NULLS FIRST], true
            +- Aggregate [formatted_date#136], [formatted_date#136, count(1) AS block_count#352L, count(distinct from_address#75) AS unique_senders_count_number#353L]
               +- Project [formatted_date#136, from_address#75]
                  +- Join Inner, (hash#17 = block_hash#72)
                     :- 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#26,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
                     +- 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#79,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv

== Physical Plan ==
CollectLimit 31
+- *(9) Project [formatted_date#136, cast(block_count#352L as string) AS block_count#375, cast(unique_senders_count_number#353L as string) AS unique_senders_count_number#376]
   +- Coalesce 1
      +- *(8) Sort [formatted_date#136 ASC NULLS FIRST], true, 0
         +- Exchange rangepartitioning(formatted_date#136 ASC NULLS FIRST, 200), true, [id=#349]
            +- *(7) HashAggregate(keys=[formatted_date#136], functions=[count(1), 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=#345]
                  +- *(6) HashAggregate(keys=[formatted_date#136], functions=[merge_count(1), partial_count(distinct from_address#75)], output=[formatted_date#136, count#362L, count#365L])
                     +- *(6) HashAggregate(keys=[formatted_date#136, from_address#75], functions=[merge_count(1)], output=[formatted_date#136, from_address#75, count#362L])
                        +- Exchange hashpartitioning(formatted_date#136, from_address#75, 200), true, [id=#340]
                           +- *(5) HashAggregate(keys=[formatted_date#136, from_address#75], functions=[partial_count(1)], output=[formatted_date#136, from_address#75, count#362L])
                              +- *(5) Project [formatted_date#136, from_address#75]
                                 +- *(5) SortMergeJoin [hash#17], [block_hash#72], Inner
                                    :- *(2) Sort [hash#17 ASC NULLS FIRST], false, 0
                                    :  +- Exchange hashpartitioning(hash#17, 200), true, [id=#322]
                                    :     +- *(1) 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]
                                    :        +- *(1) 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:string>
                                    +- *(4) Sort [block_hash#72 ASC NULLS FIRST], false, 0
                                       +- Exchange hashpartitioning(block_hash#72, 200), true, [id=#331]
                                          +- *(3) Project [block_hash#72, from_address#75]
                                             +- *(3) 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>