【已解决】profile分析:只查看数据扫描总时间应该看哪个指标

Viewed 101

只列了一部分

Query:
Summary:
- Profile ID: 932d72aada9d4357-8f5d8b9926f0b8fa
- Task Type: QUERY
- Start Time: 2024-04-25 17:02:39
- End Time: 2024-04-25 17:03:10
- Total: 31s504ms
- Task State: EOF
- User: root
- Default Db:
- Sql Statement: SELECT platform,hpid,SUBSTRING(provincecode,5,4) as pCode,SUBSTRING(citycode,5,4) as cCode,count(1) as imp,count(distinct mac) as uv
from ad_monitor.huan_ad_monitor_impression_log_test6 where provinceCode !='' and cityCode !=''
and ((platform = 'huanunion_adx' and hpid in ('5284','5285','5289','5290','5616','5617')) )
group by platform,hpid,pCode,cCode limit 200
Execution Summary:
- Workload Group: normal
- Analysis Time: 2ms
- Plan Time: 13ms
- JoinReorder Time: N/A
- CreateSingleNode Time: N/A
- QueryDistributed Time: N/A
- Init Scan Node Time: N/A
- Finalize Scan Node Time: N/A
- Get Splits Time: N/A
- Get PARTITIONS Time: N/A
- Get PARTITION FILES Time: N/A
- Create Scan Range Time: N/A
- Schedule Time: 33ms
- Fetch Result Time: 31s455ms
- Write Result Time: 1ms
- Wait and Fetch Result Time: 31s456ms
- Doris Version: doris-2.0.7-dc065ead16
- Is Nereids: Yes
- Is Pipeline: Yes
- Is Cached: No
- Total Instances Num: 65
- Instances Num Per BE: ali-doris-test-01:8060:16,ali-doris-test-02:8060:16,ali-doris-test-03:8060:17,ali-doris-test-04:8060:16
- Parallel Fragment Exec Instance Num: 8
- Trace ID:
Execution Profile 932d72aada9d4357-8f5d8b9926f0b8fa:(Active: 31s504ms, % non-child: 0.00%)
Fragments:
Fragment 0:
Instance 932d72aada9d4357-8f5d8b9926f0b93b (host=TNetworkAddress(hostname:ali-doris-test-03, port:9060)):
VDataBufferSender (dst_fragment_instance_id=-6cd28d552562bca9--70a27466d90f46c5):
- AppendBatchTime: 371.157us
- CopyBufferTime: 0ns
- ResultSendTime: 193.226us
- TupleConvertTime: 116.246us
- BytesSent: 7.70 KB
- NumSentRows: 200
VEXCHANGE_NODE (id=1025):(Active: 40.250us, % non-child: 0.00%)
- BlocksProduced: 1
- BytesReceived: 1.45 KB
- DataArrivalWaitTime: 0ns
- DecompressBytes: 3.82 KB
- DecompressTime: 5.287us
- DeserializeRowBatchTimer: 28.531us
- FirstBatchArrivalWaitTime: 0ns
- LocalBytesReceived: 26.50 KB
- MemoryUsage:
- Blocks: 11.50 KB
- PeakMemoryUsage: 3.41 KB
- ProjectionTime: 0ns
- RowsProduced: 63
- RowsReturned: 200
- RowsReturnedRate: 4.968944M /sec
- SendersBlockedTotalTimer(*): 0ns
PipelineContext:(Active: 31s462ms, % non-child: 0.00%)
- PrepareTime: 107.999us
- StartTime: 2.555us
Pipeline (pipeline id=0):
PipelineTask (index=0):(Active: 481.385us, % non-child: 0.00%)
- Sink: ResultSinkOperator(dst_id=10000)
- OperatorIds(source2root): [ExchangeSourceOperator(node_id=1025)]
- CoreChangeTimes: 5
- ExecuteTime: 464.97us
- CloseTime: 7.981us
- FinalizeTime: 70ns
- GetBlockTime: 45.464us
- OpenTime: 1.473us
- PrepareTime: 3.35us
- SinkTime: 376.958us
- GetBlockCounter: 4
- NumBlockedBySinkTimes: 0
- NumBlockedBySrcTimes: 4
- NumBlockedTimes: 6
- NumScheduleTimes: 6
- NumYieldTimes: 0
- Task1BeginExecuteTime: 18.719ms
- Task2EosTime: 31s462ms
- Task3SrcPendingFinishOverTime: 31s462ms
- Task4DstPendingFinishOverTime: 31s462ms
- Task5TotalTime: 31s462ms
- Task6ClosePipelineTime: 31s462ms
- TaskCpuTime: 353.13us
- WaitBfTime: 0ns
- WaitSinkTime: 0ns
- WaitSourceTime: 31s443ms
- WaitWorkerTime: 114.891us

1 Answers

可以看看SCAN相关的节点,参考下profile参数解析;后续这块也会更新说明。