On Thu, Feb 2, 2023 at 7:56 AM Johannes Weiner <hannes@xxxxxxxxxxx> wrote: > > Christian reports the following situation in a cgroup that doesn't > have memory.swap.max configured: > > $ cat memory.swap.events > high 0 > max 0 > fail 6218 > > Upon closer examination, this is an ARM64 machine that doesn't support > swapping out THPs. In that case, the first get_swap_page() fails, and > the kernel falls back to splitting the THP and swapping the 4k > constituents one by one. /proc/vmstat confirms this with a high rate > of thp_swpout_fallback events. > > While the behavior can ultimately be explained, it's unexpected and > confusing. I see three choices how to address this: > > a) Specifically exlude THP fallbacks from being counted, as the > failure is transient and the memory is ultimately swapped. > > Arguably, though, the user would like to know if their cgroup's > swap limit is causing high rates of THP splitting during swapout. > > b) Only count cgroup swap events when they are actually due to a > cgroup's own limit. Exclude failures that are due to physical swap > shortage or other system-level conditions (like !THP_SWAP). Also > count them at the level where the limit is configured, which may be > above the local cgroup that holds the page-to-be-swapped. > > This is in line with how memory.swap.high, memory.high and > memory.max events are counted. > > However, it's a change in documented behavior. > > c) Leave it as is. The documentation says system-level events are > counted, so stick to that. > > This is the conservative option, but isn't very user friendly. > Cgroup events are usually due to a local control choice made by the > user. Mixing in events that are beyond the user's control makes it > difficult to id root causes and configure the system properly. > > Implement option b). I prefer option b too. > > Reported-by: Christian Brauner <brauner@xxxxxxxxxx> > Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx> Acked-by: Shakeel Butt <shakeelb@xxxxxxxxxx> I think we should CC stable as well for early exposure.
