doc/nvmf_tgt_pg: Update the description about assigning the created qpair to a poll group

The operation to assign the created qpair to a poll group has been
moved from event library to nvmf library. Update the corresponding
part slightly.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I80b9b8257b84ba92004baa36a057d1a8cee387bb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3623
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This commit is contained in:
Shuhei Matsumoto 2020-08-02 07:20:27 +09:00 committed by Jim Harris
parent 4ba5e90176
commit d49d316e63

View File

@ -91,13 +91,12 @@ spdk_nvmf_poll_group_create(). They automatically request to begin polling
upon creation on the thread from which they were created. Most importantly, *a
poll group may only be accessed from the thread on which it was created.*
When spdk_nvmf_tgt_accept() detects a new connection, it will construct a new
struct spdk_nvmf_qpair object and call the user provided `new_qpair_fn`
callback for each new qpair. In response to this callback, the user must
assign the qpair to a poll group by calling spdk_nvmf_poll_group_add().
Remember, a poll group may only be accessed from the thread on which it was created,
so making a call to spdk_nvmf_poll_group_add() may require passing a message
to the appropriate thread.
When spdk_nvmf_tgt_accept() detects a new connection, it chooses an optimal
poll group by first calling spdk_nvmf_get_optimal_poll_group(), which calls down
into the transport, and then assigns the qpair to the optimal poll group by
calling spdk_nvmf_poll_group_add(). This all happens within the NVMe-oF target
library and the NVMe-oF target application is not required to do anything other
than continue to periodically poll spdk_nvmf_tgt_accept().
## Access Control