Re: [PATCH v2 net-next 1/2] tcp: account for memory pressure signaled by cgroup

On Thu, Jul 17, 2025 at 8:31 AM Daniel Sedlak [off-list ref] wrote:

On 7/16/25 8:07 PM, Kuniyuki Iwashima wrote:

quoted

quoted

Incrementing it here will give a very different semantic to this stat
compared to LINUX_MIB_TCPMEMORYPRESSURES. Here the increments mean the
number of times the kernel check if a given socket is under memcg
pressure for a net namespace. Is that what we want?

I'm trying to decouple sk_memcg from the global tcp_memory_allocated
as you and Wei planned before, and the two accounting already have the
different semantics from day1 and will keep that, so a new stat having a
different semantics would be fine.

But I think per-memcg stat like memory.stat.XXX would be a good fit
rather than pre-netns because one netns could be shared by multiple
cgroups and multiple sockets in the same cgroup could be spread across
multiple netns.

I can move the counter to memory.stat.XXX in favor of this patch

Please do so.  Per-netns stats could be confusing in some setup above.

Thanks!