我对其中一个数据流作业有一些问题。有时我会收到这个错误消息。似乎在这个错误之后,作业一直运行得很好,但是,今天晚上它实际上卡住了,或者它开始缓慢地处理元素。您还可以从屏幕截图中看到,工作人员的行为开始变得非常奇怪,如下面屏幕截图中的CPU使用率图表所示。
Error message from worker:
generic::aborted: SDK harness sdk-0-1 disconnected.
generic::aborted: SDK harness sdk-0-1 disconnected.
generic::aborted: SDK harness sdk-0-1 disconnected.
generic::aborted: SDK harness sdk-0-1 disconnected.
passed through: ==> dist_proc/dax/workflow/worker/fnapi_service.cc:631 generic::aborted: SDK harness sdk-0-1 disconnected.
generic::aborted: SDK harness sdk-0-1 disconnected.
passed through: ==> dist_proc/dax/workflow/worker/fnapi_service.cc:631 generic::aborted: SDK harness sdk-0-1 disconnected.
passed through: ==> dist_proc/dax/workflow/worker/fnapi_service.cc:631 generic::aborted: SDK harness sdk-0-1 disconnected.
passed through: ==> dist_proc/dax/workflow/worker/fnapi_service.cc:631 generic::aborted: SDK harness sdk-0-1 disconnected.
generic::aborted: SDK harness sdk-0-1 disconnected.
passed through: ==> dist_proc/dax/workflow/worker/fnapi_service.cc:631 generic::aborted: SDK harness sdk-0-1 disconnected.
generic::aborted: SDK harness sdk-0-1 disconnected.

发布于 2021-05-28 09:31:25
该错误消息可能是由于多种原因造成的,因此除非错误消息伴随着用户描述的其他行为,否则这可能是由于任意数量的errors造成的。
在我的例子中,这是由于IO错误:磁盘上没有剩余空间
进一步研究的一个好方法是通过查看

https://stackoverflow.com/questions/67122067
复制相似问题