digraph G {
0 [labelType="html" label="<br><b>WriteToDataSourceV2</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n520 ms (1 ms, 2 ms, 26 ms (stage 3.0: task 211))";
2 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>46 ms (0 ms, 0 ms, 23 ms (stage 3.0: task 243))<br>peak memory total (min, med, max (stageId: taskId))<br>242.0 MiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 3.0: task 211))<br>number of output rows: 3<br>avg hash probe bucket list iters (min, med, max (stageId: taskId)):<br>(1, 1, 1 (stage 3.0: task 211))"];
}
3 [labelType="html" label="<b>StateStoreSave</b><br><br>number of total state rows: 3<br>memory used by state total (min, med, max (stageId: taskId))<br>74.0 KiB (376.0 B, 376.0 B, 584.0 B (stage 3.0: task 306))<br>count of cache hit on states cache in provider: 400<br>number of output rows: 3<br>estimated size of state only on current version total (min, med, max (stageId: taskId))<br>17.8 KiB (88.0 B, 88.0 B, 296.0 B (stage 3.0: task 306))<br>time to commit changes total (min, med, max (stageId: taskId))<br>15.1 s (43 ms, 75 ms, 190 ms (stage 3.0: task 206))<br>time to remove total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 3.0: task 204))<br>number of updated state rows: 3<br>time to update total (min, med, max (stageId: taskId))<br>774 ms (1 ms, 2 ms, 154 ms (stage 3.0: task 212))"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (5)\n \nduration: total (min, med, max (stageId: taskId))\n777 ms (1 ms, 2 ms, 155 ms (stage 3.0: task 212))";
5 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>28 ms (0 ms, 0 ms, 28 ms (stage 3.0: task 243))<br>peak memory total (min, med, max (stageId: taskId))<br>114.0 MiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 3.0: task 243))<br>number of output rows: 3<br>avg hash probe bucket list iters: 1"];
}
6 [labelType="html" label="<b>StateStoreRestore</b><br><br>number of output rows: 3"];
subgraph cluster7 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n2.1 s (4 ms, 9 ms, 163 ms (stage 3.0: task 212))";
8 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>47 ms (0 ms, 0 ms, 38 ms (stage 3.0: task 211))<br>peak memory total (min, med, max (stageId: taskId))<br>114.0 MiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 3.0: task 243))<br>number of output rows: 3<br>avg hash probe bucket list iters: 1"];
}
9 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 4<br>shuffle write time total (min, med, max (stageId: taskId))<br>36 ms (16 ms, 19 ms, 19 ms (stage 2.0: task 202))<br>records read: 4<br>local bytes read total (min, med, max (stageId: taskId))<br>155.0 B (0.0 B, 0.0 B, 94.0 B (stage 3.0: task 306))<br>fetch wait time total (min, med, max (stageId: taskId))<br>26 ms (0 ms, 0 ms, 26 ms (stage 3.0: task 211))<br>remote bytes read total (min, med, max (stageId: taskId))<br>181.0 B (0.0 B, 0.0 B, 94.0 B (stage 3.0: task 306))<br>local blocks read: 2<br>remote blocks read: 2<br>data size total (min, med, max (stageId: taskId))<br>192.0 B (56.0 B, 136.0 B, 136.0 B (stage 2.0: task 202))<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>336.0 B (94.0 B, 242.0 B, 242.0 B (stage 2.0: task 202))"];
subgraph cluster10 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n106 ms (37 ms, 69 ms, 69 ms (stage 2.0: task 202))";
11 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>69 ms (20 ms, 49 ms, 49 ms (stage 2.0: task 202))<br>peak memory total (min, med, max (stageId: taskId))<br>64.5 MiB (256.0 KiB, 64.3 MiB, 64.3 MiB (stage 2.0: task 202))<br>number of output rows: 4<br>avg hash probe bucket list iters: 1"];
12 [labelType="html" label="<br><b>Project</b><br><br>"];
}
13 [labelType="html" label="<br><b>EventTimeWatermark</b><br><br>"];
subgraph cluster14 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n80 ms (25 ms, 55 ms, 55 ms (stage 2.0: task 202))";
15 [labelType="html" label="<br><b>Project</b><br><br>"];
}
16 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 21"];
subgraph cluster17 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n85 ms (27 ms, 58 ms, 58 ms (stage 2.0: task 202))";
18 [labelType="html" label="<br><b>Project</b><br><br>"];
}
19 [labelType="html" label="<b>MicroBatchScan</b><br><br>number of output rows: 19"];
2->0;
3->2;
5->3;
6->5;
8->6;
9->8;
11->9;
12->11;
13->12;
15->13;
16->15;
18->16;
19->18;
}
20
WriteToDataSourceV2 org.apache.spark.sql.execution.streaming.sources.MicroBatchWrite@4a95fc30
HashAggregate(keys=[hostname#12, responsecode#38], functions=[count(1)])
WholeStageCodegen (6)
StateStoreSave [hostname#12, responsecode#38], state info [ checkpoint = file:/tmp/temporary-1de1ee23-414b-4a88-8dc3-b55201323fb3/state, runId = 05d0ae24-6241-4634-a3bd-732191bb756e, opId = 0, ver = 1, numPartitions = 200], Complete, 0, 2
HashAggregate(keys=[hostname#12, responsecode#38], functions=[merge_count(1)])
WholeStageCodegen (5)
StateStoreRestore [hostname#12, responsecode#38], state info [ checkpoint = file:/tmp/temporary-1de1ee23-414b-4a88-8dc3-b55201323fb3/state, runId = 05d0ae24-6241-4634-a3bd-732191bb756e, opId = 0, ver = 1, numPartitions = 200], 2
HashAggregate(keys=[hostname#12, responsecode#38], functions=[merge_count(1)])
WholeStageCodegen (4)
Exchange hashpartitioning(hostname#12, responsecode#38, 200), true, [id=#152]
HashAggregate(keys=[hostname#12, responsecode#38], functions=[partial_count(1)])
Project [split(logs#5, ,, -1)[1] AS hostname#12, split(logs#5, ,, -1)[5] AS responsecode#38]
WholeStageCodegen (3)
EventTimeWatermark timestamp#1: timestamp, 5 seconds
Project [logs#5, timestamp#1]
WholeStageCodegen (2)
Generate explode(split(value#0, , -1)), [timestamp#1], false, [logs#5]
Project [value#0, timestamp#1]
WholeStageCodegen (1)
MicroBatchScan[value#0, timestamp#1] class org.apache.spark.sql.execution.streaming.sources.TextSocketTable$$anon$1
== Parsed Logical Plan ==
WriteToDataSourceV2 org.apache.spark.sql.execution.streaming.sources.MicroBatchWrite@4a95fc30
+- Aggregate [hostname#12, responsecode#38], [hostname#12, responsecode#38, count(1) AS count#67L]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, method#23, resource#30, responsecode#38, split(logs#5, ,, -1)[6] AS bytes#47]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, method#23, resource#30, split(logs#5, ,, -1)[5] AS responsecode#38]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, method#23, split(logs#5, ,, -1)[4] AS resource#30]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, split(logs#5, ,, -1)[3] AS method#23]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, split(logs#5, ,, -1)[2] AS time#17]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, split(logs#5, ,, -1)[1] AS hostname#12]
+- Project [logs#5, timestamp#1-T5000ms, split(logs#5, ,, -1)[0] AS idx#8]
+- EventTimeWatermark timestamp#1: timestamp, 5 seconds
+- Project [logs#5, timestamp#1]
+- Generate explode(split(value#0, , -1)), false, [logs#5]
+- StreamingDataSourceV2Relation [value#0, timestamp#1], org.apache.spark.sql.execution.streaming.sources.TextSocketTable$$anon$1@3bb35f79, TextSocketV2[host: stream-emulator.data-science-tools.svc.cluster.local, port: 5551], -1, 18
== Analyzed Logical Plan ==
WriteToDataSourceV2 org.apache.spark.sql.execution.streaming.sources.MicroBatchWrite@4a95fc30
+- Aggregate [hostname#12, responsecode#38], [hostname#12, responsecode#38, count(1) AS count#67L]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, method#23, resource#30, responsecode#38, split(logs#5, ,, -1)[6] AS bytes#47]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, method#23, resource#30, split(logs#5, ,, -1)[5] AS responsecode#38]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, method#23, split(logs#5, ,, -1)[4] AS resource#30]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, time#17, split(logs#5, ,, -1)[3] AS method#23]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, hostname#12, split(logs#5, ,, -1)[2] AS time#17]
+- Project [logs#5, timestamp#1-T5000ms, idx#8, split(logs#5, ,, -1)[1] AS hostname#12]
+- Project [logs#5, timestamp#1-T5000ms, split(logs#5, ,, -1)[0] AS idx#8]
+- EventTimeWatermark timestamp#1: timestamp, 5 seconds
+- Project [logs#5, timestamp#1]
+- Generate explode(split(value#0, , -1)), false, [logs#5]
+- StreamingDataSourceV2Relation [value#0, timestamp#1], org.apache.spark.sql.execution.streaming.sources.TextSocketTable$$anon$1@3bb35f79, TextSocketV2[host: stream-emulator.data-science-tools.svc.cluster.local, port: 5551], -1, 18
== Optimized Logical Plan ==
WriteToDataSourceV2 org.apache.spark.sql.execution.streaming.sources.MicroBatchWrite@4a95fc30
+- Aggregate [hostname#12, responsecode#38], [hostname#12, responsecode#38, count(1) AS count#67L]
+- Project [split(logs#5, ,, -1)[1] AS hostname#12, split(logs#5, ,, -1)[5] AS responsecode#38]
+- EventTimeWatermark timestamp#1: timestamp, 5 seconds
+- Project [logs#5, timestamp#1]
+- Generate explode(split(value#0, , -1)), [0], false, [logs#5]
+- StreamingDataSourceV2Relation [value#0, timestamp#1], org.apache.spark.sql.execution.streaming.sources.TextSocketTable$$anon$1@3bb35f79, TextSocketV2[host: stream-emulator.data-science-tools.svc.cluster.local, port: 5551], -1, 18
== Physical Plan ==
WriteToDataSourceV2 org.apache.spark.sql.execution.streaming.sources.MicroBatchWrite@4a95fc30
+- *(6) HashAggregate(keys=[hostname#12, responsecode#38], functions=[count(1)], output=[hostname#12, responsecode#38, count#67L])
+- StateStoreSave [hostname#12, responsecode#38], state info [ checkpoint = file:/tmp/temporary-1de1ee23-414b-4a88-8dc3-b55201323fb3/state, runId = 05d0ae24-6241-4634-a3bd-732191bb756e, opId = 0, ver = 1, numPartitions = 200], Complete, 0, 2
+- *(5) HashAggregate(keys=[hostname#12, responsecode#38], functions=[merge_count(1)], output=[hostname#12, responsecode#38, count#75L])
+- StateStoreRestore [hostname#12, responsecode#38], state info [ checkpoint = file:/tmp/temporary-1de1ee23-414b-4a88-8dc3-b55201323fb3/state, runId = 05d0ae24-6241-4634-a3bd-732191bb756e, opId = 0, ver = 1, numPartitions = 200], 2
+- *(4) HashAggregate(keys=[hostname#12, responsecode#38], functions=[merge_count(1)], output=[hostname#12, responsecode#38, count#75L])
+- Exchange hashpartitioning(hostname#12, responsecode#38, 200), true, [id=#152]
+- *(3) HashAggregate(keys=[hostname#12, responsecode#38], functions=[partial_count(1)], output=[hostname#12, responsecode#38, count#75L])
+- *(3) Project [split(logs#5, ,, -1)[1] AS hostname#12, split(logs#5, ,, -1)[5] AS responsecode#38]
+- EventTimeWatermark timestamp#1: timestamp, 5 seconds
+- *(2) Project [logs#5, timestamp#1]
+- Generate explode(split(value#0, , -1)), [timestamp#1], false, [logs#5]
+- *(1) Project [value#0, timestamp#1]
+- MicroBatchScan[value#0, timestamp#1] class org.apache.spark.sql.execution.streaming.sources.TextSocketTable$$anon$1
