summaryrefslogtreecommitdiff
path: root/drivers/infiniband/core/device.c
diff options
context:
space:
mode:
authorYamin Friedman <yaminf@mellanox.com>2020-05-27 11:34:53 +0300
committerJason Gunthorpe <jgg@mellanox.com>2020-05-29 22:09:02 +0300
commitc7ff819aefea04944dfcec5f0731b97277df6a9c (patch)
tree9ea88cf0c441c822769beee3d858692925ab41d6 /drivers/infiniband/core/device.c
parent3446cbd2d523fdaf37f3772082071d1154c419d9 (diff)
downloadlinux-c7ff819aefea04944dfcec5f0731b97277df6a9c.tar.xz
RDMA/core: Introduce shared CQ pool API
Allow a ULP to ask the core to provide a completion queue based on a least-used search on a per-device CQ pools. The device CQ pools grow in a lazy fashion when more CQs are requested. This feature reduces the amount of interrupts when using many QPs. Using shared CQs allows for more effcient completion handling. It also reduces the amount of overhead needed for CQ contexts. Test setup: Intel(R) Xeon(R) Platinum 8176M CPU @ 2.10GHz servers. Running NVMeoF 4KB read IOs over ConnectX-5EX across Spectrum switch. TX-depth = 32. The patch was applied in the nvme driver on both the target and initiator. Four controllers are accessed from each core. In the current test case we have exposed sixteen NVMe namespaces using four different subsystems (four namespaces per subsystem) from one NVM port. Each controller allocated X queues (RDMA QPs) and attached to Y CQs. Before this series we had X == Y, i.e for four controllers we've created total of 4X QPs and 4X CQs. In the shared case, we've created 4X QPs and only X CQs which means that we have four controllers that share a completion queue per core. Until fourteen cores there is no significant change in performance and the number of interrupts per second is less than a million in the current case. ================================================== |Cores|Current KIOPs |Shared KIOPs |improvement| |-----|---------------|--------------|-----------| |14 |2332 |2723 |16.7% | |-----|---------------|--------------|-----------| |20 |2086 |2712 |30% | |-----|---------------|--------------|-----------| |28 |1971 |2669 |35.4% | |================================================= |Cores|Current avg lat|Shared avg lat|improvement| |-----|---------------|--------------|-----------| |14 |767us |657us |14.3% | |-----|---------------|--------------|-----------| |20 |1225us |943us |23% | |-----|---------------|--------------|-----------| |28 |1816us |1341us |26.1% | ======================================================== |Cores|Current interrupts|Shared interrupts|improvement| |-----|------------------|-----------------|-----------| |14 |1.6M/sec |0.4M/sec |72% | |-----|------------------|-----------------|-----------| |20 |2.8M/sec |0.6M/sec |72.4% | |-----|------------------|-----------------|-----------| |28 |2.9M/sec |0.8M/sec |63.4% | ==================================================================== |Cores|Current 99.99th PCTL lat|Shared 99.99th PCTL lat|improvement| |-----|------------------------|-----------------------|-----------| |14 |67ms |6ms |90.9% | |-----|------------------------|-----------------------|-----------| |20 |5ms |6ms |-10% | |-----|------------------------|-----------------------|-----------| |28 |8.7ms |6ms |25.9% | |=================================================================== Performance improvement with sixteen disks (sixteen CQs per core) is comparable. Link: https://lore.kernel.org/r/1590568495-101621-3-git-send-email-yaminf@mellanox.com Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Reviewed-by: Max Gurtovoy <maxg@mellanox.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Diffstat (limited to 'drivers/infiniband/core/device.c')
-rw-r--r--drivers/infiniband/core/device.c2
1 files changed, 2 insertions, 0 deletions
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index d9f565a779df..53f541f41ff3 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1393,6 +1393,7 @@ int ib_register_device(struct ib_device *device, const char *name)
goto dev_cleanup;
}
+ ib_cq_pool_init(device);
ret = enable_device_and_get(device);
dev_set_uevent_suppress(&device->dev, false);
/* Mark for userspace that device is ready */
@@ -1447,6 +1448,7 @@ static void __ib_unregister_device(struct ib_device *ib_dev)
goto out;
disable_device(ib_dev);
+ ib_cq_pool_destroy(ib_dev);
/* Expedite removing unregistered pointers from the hash table */
free_netdevs(ib_dev);