62210eff55
We know that the librbd's read/write operations will be handled by a non spdk thread, so we can get rid of the epoll based group based polling and directly use the async completion. This makes the code is simple and easy to maintain. And we still need to keep the io_device registration for this module, because the I/Os are async. We need the channel reference on "rbd_if" in order to know which rbd disks are still active. Change-Id: I1c140a4b286dbfe113ed2a67bd2875de605e8f24 Signed-off-by: Ziye Yang <ziye.yang@intel.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9335 Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Ben Walker <benjamin.walker@intel.com> Reviewed-by: Changpeng Liu <changpeng.liu@intel.com> |
||
---|---|---|
.. | ||
bdev_rbd_rpc.c | ||
bdev_rbd.c | ||
bdev_rbd.h | ||
Makefile |