[Bug]: TPCH 1T OOM during daily regression on standlone mode

[aressu1985]

Is there an existing issue for the same bug?

• I have checked the existing issues.

Branch Name

main

Commit ID

1392f1f

Other Environment Information

- Hardware parameters: 64C 256G
- OS type:
- Others:

Actual Behavior

job link:
https://github.com/matrixorigin/mo-auto-test/actions/runs/12806494085/job/35714847133

heap:

LOG_7c4dccb4-4d3c-41f8-b482-5251dc7a41bf_heap_0194730b-d243-73d7-8677-bd962349d79a.gz
LOG_7c4dccb4-4d3c-41f8-b482-5251dc7a41bf_malloc_0194730c-5644-7caf-becb-3ff07048b42a.gz
LOG_7c4dccb4-4d3c-41f8-b482-5251dc7a41bf_malloc_0194730b-e521-7efe-b1cc-91f8c9eae971.gz
LOG_7c4dccb4-4d3c-41f8-b482-5251dc7a41bf_heap_0194730c-4772-7779-bcac-e42832a33207.gz

Expected Behavior

No response

Steps to Reproduce

DAILY REGRESSION

Additional information

No response

[badboynt1]

tpch1T很久都没oom过了 这几个profile也都很小，都在几g到十几g之间。 麻烦 @reusee 看一下？

[reusee]

https://shanghai.idc.matrixorigin.cn:30001/d/ce1wtrqp5urk0d/memory-metrics?orgId=1&refresh=30s&var-interval=1m&var-datasource=prometheus-standalone&var-instance=10.222.1.129%3A7001&from=1736823863930&to=1737428663930

堆外内存没有异常

https://shanghai.idc.matrixorigin.cn:30001/d/be1wtrqrb9m9sa/go-runtime-metrics?orgId=1&var-interval=1m&var-datasource=prometheus-standalone&var-instance=10.222.1.129%3A7001&from=1736006005787&to=1737428788396

go堆看上去也没有异常

OOM前，堆外内存或者go堆内存，都没有缓慢的上升。

[reusee]

@aressu1985 这个是怎么判断是OOM的呢？从日志看，只能确定是mo-service崩溃了，连接关闭了。但mo-service崩溃的原因，不一定是OOM。从内存metrics看，是没有上涨的。这个怎么看mo-service的日志？

[reusee]

后面第 #78 #79 次跑，都没有报这个错误。所以应该不是哪里用多了内存导致的，不然每次跑都会报错的：

https://github.com/matrixorigin/mo-auto-test/actions/runs/12826858905

https://github.com/matrixorigin/mo-auto-test/actions/runs/12843042858