uring: remove user's ring file descriptor operation.

According to the description of io_uring_queue_exit:

Tear down function for io_uring. Unmaps all setup shared ring buffers
and closes the low-level io_uring file descriptor returned by the kernel.

So we should remove the close operatoin on ring fd.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I910c6e8acd935925b7985c2aa750df385004eb55
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2922
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
This commit is contained in:
Ziye Yang 2020-06-17 22:48:09 +08:00 committed by Tomasz Zawadzki
parent 1d903d69e6
commit a37fd6e03d
2 changed files with 0 additions and 2 deletions

View File

@ -436,7 +436,6 @@ bdev_uring_group_destroy_cb(void *io_device, void *ctx_buf)
{
struct bdev_uring_group_channel *ch = ctx_buf;
close(ch->uring.ring_fd);
io_uring_queue_exit(&ch->uring);
spdk_poller_unregister(&ch->poller);

View File

@ -1281,7 +1281,6 @@ uring_sock_group_impl_close(struct spdk_sock_group_impl *_group)
assert(group->io_inflight == 0);
assert(group->io_avail == SPDK_SOCK_GROUP_QUEUE_DEPTH);
close(group->uring.ring_fd);
io_uring_queue_exit(&group->uring);
free(group);