1 =============== 2 RDMA Controller 3 =============== 4 5 .. Contents 6 7 1. Overview 8 1-1. What is RDMA controller? 9 1-2. Why RDMA controller needed? 10 1-3. How is RDMA controller implemented? 11 2. Usage Examples 12 13 1. Overview 14 =========== 15 16 1-1. What is RDMA controller? 17 ----------------------------- 18 19 RDMA controller allows user to limit RDMA/IB specific resources that a given 20 set of processes can use. These processes are grouped using RDMA controller. 21 22 RDMA controller defines two resources which can be limited for processes of a 23 cgroup. 24 25 1-2. Why RDMA controller needed? 26 -------------------------------- 27 28 Currently user space applications can easily take away all the rdma verb 29 specific resources such as AH, CQ, QP, MR etc. Due to which other applications 30 in other cgroup or kernel space ULPs may not even get chance to allocate any 31 rdma resources. This can lead to service unavailability. 32 33 Therefore RDMA controller is needed through which resource consumption 34 of processes can be limited. Through this controller different rdma 35 resources can be accounted. 36 37 1-3. How is RDMA controller implemented? 38 ---------------------------------------- 39 40 RDMA cgroup allows limit configuration of resources. Rdma cgroup maintains 41 resource accounting per cgroup, per device using resource pool structure. 42 Each such resource pool is limited up to 64 resources in given resource pool 43 by rdma cgroup, which can be extended later if required. 44 45 This resource pool object is linked to the cgroup css. Typically there 46 are 0 to 4 resource pool instances per cgroup, per device in most use cases. 47 But nothing limits to have it more. At present hundreds of RDMA devices per 48 single cgroup may not be handled optimally, however there is no 49 known use case or requirement for such configuration either. 50 51 Since RDMA resources can be allocated from any process and can be freed by any 52 of the child processes which shares the address space, rdma resources are 53 always owned by the creator cgroup css. This allows process migration from one 54 to other cgroup without major complexity of transferring resource ownership; 55 because such ownership is not really present due to shared nature of 56 rdma resources. Linking resources around css also ensures that cgroups can be 57 deleted after processes migrated. This allow progress migration as well with 58 active resources, even though that is not a primary use case. 59 60 Whenever RDMA resource charging occurs, owner rdma cgroup is returned to 61 the caller. Same rdma cgroup should be passed while uncharging the resource. 62 This also allows process migrated with active RDMA resource to charge 63 to new owner cgroup for new resource. It also allows to uncharge resource of 64 a process from previously charged cgroup which is migrated to new cgroup, 65 even though that is not a primary use case. 66 67 Resource pool object is created in following situations. 68 (a) User sets the limit and no previous resource pool exist for the device 69 of interest for the cgroup. 70 (b) No resource limits were configured, but IB/RDMA stack tries to 71 charge the resource. So that it correctly uncharge them when applications are 72 running without limits and later on when limits are enforced during uncharging, 73 otherwise usage count will drop to negative. 74 75 Resource pool is destroyed if all the resource limits are set to max and 76 it is the last resource getting deallocated. 77 78 User should set all the limit to max value if it intents to remove/unconfigure 79 the resource pool for a particular device. 80 81 IB stack honors limits enforced by the rdma controller. When application 82 query about maximum resource limits of IB device, it returns minimum of 83 what is configured by user for a given cgroup and what is supported by 84 IB device. 85 86 Following resources can be accounted by rdma controller. 87 88 ========== ============================= 89 hca_handle Maximum number of HCA Handles 90 hca_object Maximum number of HCA Objects 91 ========== ============================= 92 93 2. Usage Examples 94 ================= 95 96 (a) Configure resource limit:: 97 98 echo mlx4_0 hca_handle=2 hca_object=2000 > /sys/fs/cgroup/rdma/1/rdma.max 99 echo ocrdma1 hca_handle=3 > /sys/fs/cgroup/rdma/2/rdma.max 100 101 (b) Query resource limit:: 102 103 cat /sys/fs/cgroup/rdma/2/rdma.max 104 #Output: 105 mlx4_0 hca_handle=2 hca_object=2000 106 ocrdma1 hca_handle=3 hca_object=max 107 108 (c) Query current usage:: 109 110 cat /sys/fs/cgroup/rdma/2/rdma.current 111 #Output: 112 mlx4_0 hca_handle=1 hca_object=20 113 ocrdma1 hca_handle=1 hca_object=23 114 115 (d) Delete resource limit:: 116 117 echo mlx4_0 hca_handle=max hca_object=max > /sys/fs/cgroup/rdma/1/rdma.max
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.