task2 - Details for Query 5

Details for Query 5

Submitted Time: 2024/10/29 20:23:06
Duration: 15 s
Succeeded Jobs: 5 6

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

digraph G { 0 [labelType="html" label="Execute InsertIntoHadoopFsRelationCommand number of written files: 1 written output: 661.0 B number of output rows: 30 number of dynamic part: 0"]; 1 [labelType="html" label=" Coalesce "]; subgraph cluster2 { isCluster="true"; label="WholeStageCodegen (8)\n \nduration: 2 ms"; 3 [labelType="html" label="Sort sort time: 0 ms peak memory: 1921.9 MiB spill size: 0.0 B"]; } 4 [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 18.0: task 1031)) 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 18.0: task 1042)) shuffle bytes written total (min, med, max (stageId: taskId)) 2.5 KiB (0.0 B, 0.0 B, 258.0 B (stage 18.0: task 1042))"]; subgraph cluster5 { isCluster="true"; label="WholeStageCodegen (7)\n \nduration: total (min, med, max (stageId: taskId))\n154 ms (0 ms, 0 ms, 4 ms (stage 13.0: task 823))"; 6 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 98 ms (0 ms, 0 ms, 2 ms (stage 13.0: task 823)) peak memory total (min, med, max (stageId: taskId)) 3.2 GiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 13.0: task 823)) number of output rows: 60 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1 (stage 13.0: task 823))"]; } 7 [labelType="html" label="Exchange shuffle records written: 5,933 shuffle write time total (min, med, max (stageId: taskId)) 686 ms (3 ms, 3 ms, 5 ms (stage 12.0: task 643)) records read: 11,866 local bytes read total (min, med, max (stageId: taskId)) 425.9 KiB (0.0 B, 0.0 B, 12.5 KiB (stage 18.0: task 1042)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 13.0: task 823)) remote bytes read total (min, med, max (stageId: taskId)) 424.9 KiB (0.0 B, 0.0 B, 12.5 KiB (stage 13.0: task 842)) local blocks read: 4,954 remote blocks read: 4,940 data size total (min, med, max (stageId: taskId)) 278.1 KiB (1344.0 B, 1440.0 B, 1440.0 B (stage 12.0: task 625)) shuffle bytes written total (min, med, max (stageId: taskId)) 425.4 KiB (2016.0 B, 2.1 KiB, 2.2 KiB (stage 12.0: task 719))"]; subgraph cluster8 { isCluster="true"; label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n1.8 s (6 ms, 7 ms, 39 ms (stage 12.0: task 724))"; 9 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 644 ms (2 ms, 3 ms, 30 ms (stage 12.0: task 725)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 12.0: task 623)) number of output rows: 5,933"]; 10 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 408 ms (1 ms, 2 ms, 29 ms (stage 12.0: task 725)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 12.0: task 623)) number of output rows: 28,128"]; } 11 [labelType="html" label="Exchange shuffle records written: 85,947 shuffle write time total (min, med, max (stageId: taskId)) 2.0 s (7 ms, 9 ms, 100 ms (stage 11.0: task 594)) records read: 85,947 local bytes read total (min, med, max (stageId: taskId)) 3.6 MiB (10.3 KiB, 17.7 KiB, 33.1 KiB (stage 12.0: task 637)) fetch wait time total (min, med, max (stageId: taskId)) 47 ms (0 ms, 0 ms, 27 ms (stage 12.0: task 725)) remote bytes read total (min, med, max (stageId: taskId)) 3.6 MiB (9.8 KiB, 17.9 KiB, 35.1 KiB (stage 12.0: task 740)) local blocks read: 17,802 remote blocks read: 17,510 data size total (min, med, max (stageId: taskId)) 7.9 MiB (27.4 KiB, 40.0 KiB, 54.3 KiB (stage 11.0: task 533)) shuffle bytes written total (min, med, max (stageId: taskId)) 7.2 MiB (28.0 KiB, 36.9 KiB, 46.0 KiB (stage 11.0: task 533))"]; subgraph cluster12 { isCluster="true"; label="WholeStageCodegen (5)\n \nduration: total (min, med, max (stageId: taskId))\n4.4 s (11 ms, 15 ms, 191 ms (stage 11.0: task 424))"; 13 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 899 ms (1 ms, 2 ms, 133 ms (stage 11.0: task 424)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 11.0: task 423)) number of output rows: 85,947"]; 14 [labelType="html" label=" Project "]; 15 [labelType="html" label="SortMergeJoin number of output rows: 173,805"]; } subgraph cluster16 { isCluster="true"; label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n1.1 s (0 ms, 5 ms, 201 ms (stage 11.0: task 424))"; 17 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 11.0: task 423)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 11.0: task 423)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 11.0: task 423))"]; } 18 [labelType="html" label="Exchange shuffle records written: 144,178 shuffle write time total (min, med, max (stageId: taskId)) 35 ms (0 ms, 0 ms, 19 ms (stage 9.0: task 417)) records read: 144,178 local bytes read total (min, med, max (stageId: taskId)) 4.6 MiB (19.1 KiB, 23.2 KiB, 28.0 KiB (stage 11.0: task 446)) fetch wait time total (min, med, max (stageId: taskId)) 138 ms (0 ms, 0 ms, 84 ms (stage 11.0: task 608)) remote bytes read total (min, med, max (stageId: taskId)) 4.7 MiB (18.4 KiB, 24.1 KiB, 29.2 KiB (stage 11.0: task 502)) 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 9.0: task 417)) shuffle bytes written total (min, med, max (stageId: taskId)) 9.3 MiB (0.0 B, 0.0 B, 4.9 MiB (stage 9.0: task 417))"]; subgraph cluster19 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n7.8 s (133 ms, 1.9 s, 2.1 s (stage 9.0: task 419))"; 20 [labelType="html" label=" Project "]; 21 [labelType="html" label="Filter number of output rows: 144,178"]; } 22 [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 cluster23 { isCluster="true"; label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n941 ms (0 ms, 4 ms, 101 ms (stage 11.0: task 423))"; 24 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 3 ms (0 ms, 0 ms, 3 ms (stage 11.0: task 430)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 11.0: task 424)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 11.0: task 423))"]; } 25 [labelType="html" label="Exchange shuffle records written: 504,708 shuffle write time total (min, med, max (stageId: taskId)) 61 ms (26 ms, 35 ms, 35 ms (stage 10.0: task 422)) records read: 504,708 local bytes read total (min, med, max (stageId: taskId)) 10.6 MiB (44.8 KiB, 54.1 KiB, 68.2 KiB (stage 11.0: task 525)) fetch wait time total (min, med, max (stageId: taskId)) 85 ms (0 ms, 0 ms, 85 ms (stage 11.0: task 595)) remote bytes read total (min, med, max (stageId: taskId)) 10.5 MiB (45.1 KiB, 53.3 KiB, 70.7 KiB (stage 11.0: task 532)) 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 10.0: task 421)) shuffle bytes written total (min, med, max (stageId: taskId)) 21.2 MiB (10.0 MiB, 11.2 MiB, 11.2 MiB (stage 10.0: task 421))"]; subgraph cluster26 { isCluster="true"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n2.8 s (1.3 s, 1.4 s, 1.4 s (stage 10.0: task 421))"; 27 [labelType="html" label=" Project "]; 28 [labelType="html" label="Filter number of output rows: 504,708"]; } 29 [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"]; 1->0; 3->1; 4->3; 6->4; 7->6; 9->7; 10->9; 11->10; 13->11; 14->13; 15->14; 17->15; 18->17; 20->18; 21->20; 22->21; 24->15; 25->24; 27->25; 28->27; 29->28; }

Execute InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september), Overwrite, [formatted_date, block_count, unique_senders_count_number]

Coalesce 1

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

WholeStageCodegen (8)

Exchange rangepartitioning(formatted_date#136 ASC NULLS FIRST, 200), true, [id=#240]

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

WholeStageCodegen (7)

Exchange hashpartitioning(formatted_date#136, 200), true, [id=#236]

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=#231]

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=#213]

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=#222]

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 ==
InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september), Overwrite, [formatted_date, block_count, unique_senders_count_number]
+- 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 ==

InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september), Overwrite, [formatted_date, block_count, unique_senders_count_number]
+- 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 ==
InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september), Overwrite, [formatted_date, block_count, unique_senders_count_number]
+- 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 ==
Execute InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec21590-0f30a127-4a67-4141-bbea-16743f6395f8/processed_data/september), Overwrite, [formatted_date, block_count, unique_senders_count_number]
+- Coalesce 1
   +- *(8) Sort [formatted_date#136 ASC NULLS FIRST], true, 0
      +- Exchange rangepartitioning(formatted_date#136 ASC NULLS FIRST, 200), true, [id=#240]
         +- *(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=#236]
               +- *(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=#231]
                        +- *(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=#213]
                                 :     +- *(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=#222]
                                       +- *(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>