From aefe4847f0891e2e71bedf5478d1cf350f86fc61 Mon Sep 17 00:00:00 2001 From: Tao Cui Date: Thu, 14 May 2026 14:50:33 +0800 Subject: cgroup/rdma: add rdma.events.local for per-cgroup allocation failure attribution Add per-cgroup local event counters to track RDMA resource limit exhaustion from the perspective of individual cgroups. The rdma.events.local file reports two per-resource counters: - max: number of times this cgroup's limit was the one that blocked an allocation in the subtree - alloc_fail: number of allocation attempts originating from this cgroup that failed due to an ancestor's limit This mirrors the design of pids.events.local, where events are attributed to the cgroup that imposed the limit, not necessarily the cgroup where the allocation was attempted. Also extend rdma.events with a hierarchical alloc_fail counter that tracks allocation failures propagating upward from the requesting cgroup, complementing the existing max counter, so that rdma.events and rdma.events.local share the same output format. Signed-off-by: Tao Cui Signed-off-by: Tejun Heo --- include/linux/cgroup_rdma.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h index ac691fe7d3f5..404e746552ca 100644 --- a/include/linux/cgroup_rdma.h +++ b/include/linux/cgroup_rdma.h @@ -25,8 +25,9 @@ struct rdma_cgroup { */ struct list_head rpools; - /* Handle for rdma.events */ + /* Handles for rdma.events[.local] */ struct cgroup_file events_file; + struct cgroup_file events_local_file; }; struct rdmacg_device { -- cgit v1.2.3