| commit | 14c862dbb0a0e0a9baec20480d441e32cb54b2b9 | [log] [tgz] |
|---|---|---|
| author | Sagi Grimberg <sagi@grimberg.me> | Sun Nov 06 11:03:59 2016 +0200 |
| committer | Sagi Grimberg <sagi@grimberg.me> | Mon Nov 14 02:08:53 2016 +0200 |
| tree | 18cc13ffb25ab02c05f50a09f2b4d63fff77144a | |
| parent | c8dbc37cd81d4705fce51123f5d81ea3267a5b88 [diff] |
nvmet-rdma: drain the queue-pair just before freeing it draining the qp right after disconnect might not suffice because the nvmet sq is not fully drained (in nvmet_sq_destroy) and we might see completions after the drain. Instead, drain right before the qp destroy which comes after the sq destruction and we can be sure that no posts come after the drain. Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me>