flink-user-zh mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From 邓成刚【qq】 <bnnbb...@qq.com>
Subject 求助,blink资源配置的问题,为什么资源还不足啊。。。
Date Thu, 04 Apr 2019 10:06:08 GMT
求助,blink资源配置的问题,为什么资源还不足啊。。。
盼回复,谢谢!

为什么

2019-04-04 17:49:32,495 INFO  org.apache.flink.runtime.jobmaster.slotpool.SlotPool    
     - Requesting slot with profile
ResourceProfile{cpuCores=26.40000000000004, heapMemoryInMB=4144, directMemoryInMB=0, nativeMemoryInMB=0,
networkMemoryInMB=101, MANAGED_MEMORY_MB=0.0,
FLOATING_MANAGED_MEMORY_MB=0.0} from resource manager (request = ba5acbd5a1fdeb37bcfc05e43695a622).
2019-04-04 17:49:32,496 INFO  org.apache.flink.runtime.resourcemanager.StandaloneResourceManager
 - Request slot with profile
ResourceProfile{cpuCores=26.40000000000004, heapMemoryInMB=4144, directMemoryInMB=0, nativeMemoryInMB=0,
networkMemoryInMB=101, MANAGED_MEMORY_MB=0.0,
FLOATING_MANAGED_MEMORY_MB=0.0} for job eef62bb1555d0450fa097f1eccc9d6d8 with allocation id
91e5bb6ded9ef90104db0179c1415ade.
2019-04-04 17:54:32,460 INFO  org.apache.flink.runtime.executiongraph.ExecutionGraph    
   - Batch request 88 slots, but only 0 are fulfilled.


TS 和CPU 都有 200,UserHeap MEM:500G,Managed MEM:300G,Network MEM:320M

配置如下: 共5 台机器 参数配置都一模一样的。

jobmanager.heap.mb: 20480

taskmanager.heap.mb: 102400

taskmanager.memory.off-heap: true

taskmanager.memory.size : 61440

taskmanager.cpu.core: 40

taskmanager.numberOfTaskSlots: 40

邓成刚【qq】
Mime
View raw message