wfxuxh
wfxuxh

But when the memory is full, the shuffle server pod restart,this case my spark application faild
It is restart by k8s, reason is memory is too high.I think if memory release ,it will not be appear
It is 32G now,I can not give more
XMX_SIZE ? it is 30G now.
I have reduced it to 8G,but the pod restart too
Tispark is no longer maintained?
Organization: WanFang Data Region: Beijing, China Contact: [email protected] Usage Scenario: We use Apache Celeborn to improve the stability and efficiency of Spark shuffle on k8s 
spark version: 3.3.3 , iceberg version: 1.4.3 ,same stack trace for me. my table is: > CREATE TABLE iceberg_catalog.doi.doi_log ( date_time TIMESTAMP, ip STRING, protocol STRING, operation STRING, response STRING,...