On Mon, Apr 25, 2022 at 12:15 PM David Rientjes <rientjes@xxxxxxxxxx> wrote: > > On Mon, 25 Apr 2022, Yosry Ahmed wrote: > > > From: Shakeel Butt <shakeelb@xxxxxxxxxx> > > > > Introduce a memcg interface to trigger memory reclaim on a memory cgroup. > > > > Use case: Proactive Reclaim > > --------------------------- > > > > A userspace proactive reclaimer can continuously probe the memcg to > > reclaim a small amount of memory. This gives more accurate and > > up-to-date workingset estimation as the LRUs are continuously > > sorted and can potentially provide more deterministic memory > > overcommit behavior. The memory overcommit controller can provide > > more proactive response to the changing behavior of the running > > applications instead of being reactive. > > > > A userspace reclaimer's purpose in this case is not a complete replacement > > for kswapd or direct reclaim, it is to proactively identify memory savings > > opportunities and reclaim some amount of cold pages set by the policy > > to free up the memory for more demanding jobs or scheduling new jobs. > > > > A user space proactive reclaimer is used in Google data centers. > > Additionally, Meta's TMO paper recently referenced a very similar > > interface used for user space proactive reclaim: > > https://dl.acm.org/doi/pdf/10.1145/3503222.3507731 > > > > Benefits of a user space reclaimer: > > ----------------------------------- > > > > 1) More flexible on who should be charged for the cpu of the memory > > reclaim. For proactive reclaim, it makes more sense to be centralized. > > > > 2) More flexible on dedicating the resources (like cpu). The memory > > overcommit controller can balance the cost between the cpu usage and > > the memory reclaimed. > > > > 3) Provides a way to the applications to keep their LRUs sorted, so, > > under memory pressure better reclaim candidates are selected. This also > > gives more accurate and uptodate notion of working set for an > > application. > > > > Why memory.high is not enough? > > ------------------------------ > > > > - memory.high can be used to trigger reclaim in a memcg and can > > potentially be used for proactive reclaim. > > However there is a big downside in using memory.high. It can potentially > > introduce high reclaim stalls in the target application as the > > allocations from the processes or the threads of the application can hit > > the temporary memory.high limit. > > > > - Userspace proactive reclaimers usually use feedback loops to decide > > how much memory to proactively reclaim from a workload. The metrics > > used for this are usually either refaults or PSI, and these metrics > > will become messy if the application gets throttled by hitting the > > high limit. > > > > - memory.high is a stateful interface, if the userspace proactive > > reclaimer crashes for any reason while triggering reclaim it can leave > > the application in a bad state. > > > > - If a workload is rapidly expanding, setting memory.high to proactively > > reclaim memory can result in actually reclaiming more memory than > > intended. > > > > The benefits of such interface and shortcomings of existing interface > > were further discussed in this RFC thread: > > https://lore.kernel.org/linux-mm/5df21376-7dd1-bf81-8414-32a73cea45dd@xxxxxxxxxx/ > > > > Interface: > > ---------- > > > > Introducing a very simple memcg interface 'echo 10M > memory.reclaim' to > > trigger reclaim in the target memory cgroup. > > > > The interface is introduced as a nested-keyed file to allow for future > > optional arguments to be easily added to configure the behavior of > > reclaim. > > > > Possible Extensions: > > -------------------- > > > > - This interface can be extended with an additional parameter or flags > > to allow specifying one or more types of memory to reclaim from (e.g. > > file, anon, ..). > > > > - The interface can also be extended with a node mask to reclaim from > > specific nodes. This has use cases for reclaim-based demotion in memory > > tiering systens. > > > > - A similar per-node interface can also be added to support proactive > > reclaim and reclaim-based demotion in systems without memcg. > > > > - Add a timeout parameter to make it easier for user space to call the > > interface without worrying about being blocked for an undefined amount > > of time. > > > > For now, let's keep things simple by adding the basic functionality. > > > > [yosryahmed@xxxxxxxxxx: worked on versions v2 onwards, refreshed to > > current master, updated commit message based on recent > > discussions and use cases] > > > > Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx> > > Co-developed-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx> > > Signed-off-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx> > > Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> > > Acked-by: Michal Hocko <mhocko@xxxxxxxx> > > Acked-by: Wei Xu <weixugc@xxxxxxxxxx> > > Acked-by: Roman Gushchin <roman.gushchin@xxxxxxxxx> > > Acked-by: David Rientjes <rientjes@xxxxxxxxxx> > > "can over or under reclaim from the target cgroup" begs the question of > how much more memory the kernel can decide to reclaim :) I think it's > assumed that it's minimal and that matches the current implementation that > rounds up to SWAP_CLUSTER_MAX, though, so looks good. > > Thanks Yosry! I think it could be more complex than this. Some functions that get called during reclaim only use the nr_to_reclaim parameter to check if they need one more iteration, but not to limit the actual reclaimed pages per say. For example, nr_to_reclaim is not even passed to shrink_slab() or mem_cgroup_soft_limit_reclaim(), so they have no way to know that they should stop if nr_to_reclaim was already satisfied. I think the general assumption is that each of these calls normally does not reclaim a huge number of pages, so like you said, the kernel should not over-reclaim too much. However, I don't think there are guarantees about this.
