task2 - Details for Query 7

Details for Query 7

Submitted Time: 2024/12/04 20:23:10
Duration: 10 s
Succeeded Jobs: 10

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 (6)\n \nduration: total (min, med, max (stageId: taskId))\n264 ms (0 ms, 0 ms, 24 ms (stage 31.0: task 2066))"; 2 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 80 ms (0 ms, 0 ms, 11 ms (stage 31.0: task 2066)) peak memory total (min, med, max (stageId: taskId)) 1842.0 MiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 31.0: task 2046)) number of output rows: 31 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1 (stage 31.0: task 2046))"]; } 3 [labelType="html" label="Exchange shuffle records written: 6,200 shuffle write time total (min, med, max (stageId: taskId)) 845 ms (3 ms, 3 ms, 7 ms (stage 30.0: task 1957)) records read: 6,200 local bytes read total (min, med, max (stageId: taskId)) 244.2 KiB (0.0 B, 0.0 B, 15.0 KiB (stage 31.0: task 2054)) fetch wait time total (min, med, max (stageId: taskId)) 11 ms (0 ms, 0 ms, 8 ms (stage 31.0: task 2066)) remote bytes read total (min, med, max (stageId: taskId)) 213.3 KiB (0.0 B, 0.0 B, 10.3 KiB (stage 31.0: task 2050)) local blocks read: 2,974 remote blocks read: 2,626 data size total (min, med, max (stageId: taskId)) 242.2 KiB (1240.0 B, 1240.0 B, 1240.0 B (stage 30.0: task 1847)) shuffle bytes written total (min, med, max (stageId: taskId)) 457.5 KiB (2.3 KiB, 2.3 KiB, 2.3 KiB (stage 30.0: task 2006))"]; subgraph cluster4 { isCluster="true"; label="WholeStageCodegen (5)\n \nduration: total (min, med, max (stageId: taskId))\n1.7 s (5 ms, 5 ms, 54 ms (stage 30.0: task 1932))"; 5 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 328 ms (1 ms, 1 ms, 25 ms (stage 30.0: task 2040)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 30.0: task 1847)) number of output rows: 6,200"]; 6 [labelType="html" label=" Project "]; 7 [labelType="html" label="SortMergeJoin number of output rows: 72,118"]; } subgraph cluster8 { isCluster="true"; label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n678 ms (0 ms, 3 ms, 43 ms (stage 30.0: task 1847))"; 9 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 30.0: task 1847)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 30.0: task 1847)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 30.0: task 1847))"]; } 10 [labelType="html" label="Exchange shuffle records written: 171,282 shuffle write time total (min, med, max (stageId: taskId)) 45 ms (16 ms, 29 ms, 29 ms (stage 28.0: task 1840)) records read: 171,282 local bytes read total (min, med, max (stageId: taskId)) 5.8 MiB (24.4 KiB, 29.4 KiB, 34.6 KiB (stage 30.0: task 1955)) fetch wait time total (min, med, max (stageId: taskId)) 31 ms (0 ms, 0 ms, 23 ms (stage 30.0: task 2040)) remote bytes read total (min, med, max (stageId: taskId)) 5.7 MiB (24.5 KiB, 28.7 KiB, 34.1 KiB (stage 30.0: task 1935)) local blocks read: 200 remote blocks read: 200 data size total (min, med, max (stageId: taskId)) 17.0 MiB (8.2 MiB, 8.8 MiB, 8.8 MiB (stage 28.0: task 1839)) shuffle bytes written total (min, med, max (stageId: taskId)) 11.4 MiB (5.5 MiB, 6.0 MiB, 6.0 MiB (stage 28.0: task 1839))"]; subgraph cluster11 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n3.1 s (1.3 s, 1.8 s, 1.8 s (stage 28.0: task 1840))"; 12 [labelType="html" label=" Project "]; 13 [labelType="html" label="Filter number of output rows: 171,282"]; } 14 [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: 171,282"]; subgraph cluster15 { isCluster="true"; label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n908 ms (0 ms, 3 ms, 176 ms (stage 30.0: task 1846))"; 16 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 30.0: task 1847)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 30.0: task 1847)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 30.0: task 1847))"]; } 17 [labelType="html" label="Exchange shuffle records written: 156,095 shuffle write time total (min, med, max (stageId: taskId)) 47 ms (0 ms, 0 ms, 34 ms (stage 29.0: task 1844)) records read: 156,095 local bytes read total (min, med, max (stageId: taskId)) 4.6 MiB (15.9 KiB, 19.3 KiB, 36.0 KiB (stage 30.0: task 1916)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 30.0: task 1847)) remote bytes read total (min, med, max (stageId: taskId)) 5.4 MiB (16.1 KiB, 32.0 KiB, 37.5 KiB (stage 30.0: task 1918)) local blocks read: 200 remote blocks read: 200 data size total (min, med, max (stageId: taskId)) 16.7 MiB (0.0 B, 0.0 B, 10.7 MiB (stage 29.0: task 1844)) shuffle bytes written total (min, med, max (stageId: taskId)) 10.0 MiB (0.0 B, 0.0 B, 6.4 MiB (stage 29.0: task 1844))"]; subgraph cluster18 { isCluster="true"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n8.8 s (131 ms, 1.6 s, 3.0 s (stage 29.0: task 1844))"; 19 [labelType="html" label=" Project "]; 20 [labelType="html" label="Filter number of output rows: 156,095"]; } 21 [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; 12->10; 13->12; 14->13; 16->7; 17->16; 19->17; 20->19; 21->20; }

TakeOrderedAndProject(limit=21, orderBy=[formatted_date#136 ASC NULLS FIRST], output=[formatted_date#136,total_transaction_fee#440])

HashAggregate(keys=[formatted_date#136], functions=[sum(cast((cast(gas#78 as float) * cast(gas_price#79L as float)) as double))])

WholeStageCodegen (6)

Exchange hashpartitioning(formatted_date#136, 200), true, [id=#428]

HashAggregate(keys=[formatted_date#136], functions=[partial_sum(cast((cast(gas#78 as float) * cast(gas_price#79L as float)) as double))])

Project [gas#78, gas_price#79L, 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=#410]

Project [block_hash#72, gas#78, gas_price#79L]

Filter ((isnotnull(transaction_index#74) AND (transaction_index#74 = 0)) AND isnotnull(block_hash#72))

WholeStageCodegen (1)

FileScan csv [block_hash#72,transaction_index#74,gas#78,gas_price#79L] Batched: false, DataFilters: [isnotnull(transaction_index#74), (transaction_index#74 = 0), isnotnull(block_hash#72)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/transactions.csv], PartitionFilters: [], PushedFilters: [IsNotNull(transaction_index), EqualTo(transaction_index,0), IsNotNull(block_hash)], ReadSchema: struct<block_hash:string,transaction_index:int,gas:int,gas_price:bigint>

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

WholeStageCodegen (4)

Exchange hashpartitioning(hash#17, 200), true, [id=#419]

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, Some(GMT)) = 2015-10) 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#439, cast(total_transaction_fee#434 as string) AS total_transaction_fee#440]
      +- Sort [formatted_date#136 ASC NULLS FIRST], true
         +- Aggregate [formatted_date#136], [formatted_date#136, sum(cast((cast(gas#78 as float) * cast(gas_price#79L as float)) as double)) AS total_transaction_fee#434]
            +- Filter (transaction_index#74 = 0)
               +- Filter (date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM, Some(GMT)) = 2015-10)
                  +- 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, total_transaction_fee: string
GlobalLimit 21
+- LocalLimit 21
   +- Project [cast(formatted_date#136 as string) AS formatted_date#439, cast(total_transaction_fee#434 as string) AS total_transaction_fee#440]
      +- Sort [formatted_date#136 ASC NULLS FIRST], true
         +- Aggregate [formatted_date#136], [formatted_date#136, sum(cast((cast(gas#78 as float) * cast(gas_price#79L as float)) as double)) AS total_transaction_fee#434]
            +- Filter (transaction_index#74 = 0)
               +- Filter (date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM, Some(GMT)) = 2015-10)
                  +- 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(total_transaction_fee#434 as string) AS total_transaction_fee#440]
      +- Sort [formatted_date#136 ASC NULLS FIRST], true
         +- Aggregate [formatted_date#136], [formatted_date#136, sum(cast((cast(gas#78 as float) * cast(gas_price#79L as float)) as double)) AS total_transaction_fee#434]
            +- Project [gas#78, gas_price#79L, formatted_date#136]
               +- Join Inner, (block_hash#72 = hash#17)
                  :- Project [block_hash#72, gas#78, gas_price#79L]
                  :  +- Filter ((isnotnull(transaction_index#74) AND (transaction_index#74 = 0)) AND 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, Some(GMT)) = 2015-10) 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,total_transaction_fee#440])
+- *(6) HashAggregate(keys=[formatted_date#136], functions=[sum(cast((cast(gas#78 as float) * cast(gas_price#79L as float)) as double))], output=[formatted_date#136, total_transaction_fee#434])
   +- Exchange hashpartitioning(formatted_date#136, 200), true, [id=#428]
      +- *(5) HashAggregate(keys=[formatted_date#136], functions=[partial_sum(cast((cast(gas#78 as float) * cast(gas_price#79L as float)) as double))], output=[formatted_date#136, sum#444])
         +- *(5) Project [gas#78, gas_price#79L, 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=#410]
               :     +- *(1) Project [block_hash#72, gas#78, gas_price#79L]
               :        +- *(1) Filter ((isnotnull(transaction_index#74) AND (transaction_index#74 = 0)) AND isnotnull(block_hash#72))
               :           +- FileScan csv [block_hash#72,transaction_index#74,gas#78,gas_price#79L] Batched: false, DataFilters: [isnotnull(transaction_index#74), (transaction_index#74 = 0), isnotnull(block_hash#72)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/transactions.csv], PartitionFilters: [], PushedFilters: [IsNotNull(transaction_index), EqualTo(transaction_index,0), IsNotNull(block_hash)], ReadSchema: struct<block_hash:string,transaction_index:int,gas:int,gas_price:bigint>
               +- *(4) Sort [hash#17 ASC NULLS FIRST], false, 0
                  +- Exchange hashpartitioning(hash#17, 200), true, [id=#419]
                     +- *(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, Some(GMT)) = 2015-10) 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>