On Mon, 18 Apr 2022 09:07:31 GMT, xpbob <d...@openjdk.java.net> wrote:
> set memory.swappiness to 0,swap space will not be used > determine the value of memory.swappiness > https://www.kernel.org/doc/Documentation/cgroup-v1/memory.txt > > > Memory Limit: 50.00M > Memory Soft Limit: Unlimited > Memory & Swap Limit: 100.00M > Maximum Processes Limit: 4194305 > > => > > Memory Limit: 50.00M > Memory Soft Limit: Unlimited > Memory & Swap Limit: 50.00M > Maximum Processes Limit: 4194305 Both the PR and the bug report are not clear about exactly what the problem is. Could you provide a test case that demonstrates the relationship between `memory.memsw.limit_in_bytes` and `memory.swappiness`? It will be best if you can upload a shell script into the bug report so we know the exact steps to reproduce the problem. Ultimately we should add a new jtreg test case. # scenario 1 memory.memsw.limit_in_bytes = 1000M memory.limit_in_bytes = 50M memory.swappiness = 1 -> "java -Xms60m -XX:+AlwaysPreTouch -version" can successfully complete # scenario 2 memory.memsw.limit_in_bytes = 1000M memory.limit_in_bytes = 50M memory.swappiness = 0 -> "java -Xms60m -XX:+AlwaysPreTouch -version" will be killed by cgroups Related to your other PR (https://github.com/openjdk/jdk/pull/8256), I think `CgroupV1Subsystem::memory_and_swap_limit_in_bytes()` also need to be changed so that it will return 50M in scenario 2. ------------- PR: https://git.openjdk.java.net/jdk/pull/8285
