Receive buffer exhaustion, if it were to actually occur, would be
catastrophic. However, when there are no reply buffers to post, that
means all of them have already been posted and are waiting for
incoming replies. By design, there can never be more RPCs in flight
than there are available receive buffers.
A receive buffer can be left posted after an RPC exits without a
received reply; say, due to a credential problem or a soft timeout.
This does not result in fewer posted receive buffers than there are
pending RPCs, and there is already logic in xprtrdma to deal
appropriately with this case.
It also looks like the "+ 2" that was removed was accidentally
accommodating the number of extra receive buffers needed for
receiving backchannel requests. That will need to be addressed by
another patch.
Fixes:
3d4cf35bd4fa ("xprtrdma: Reply buffer exhaustion can be...")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
}
INIT_LIST_HEAD(&buf->rb_recv_bufs);
- for (i = 0; i < buf->rb_max_requests; i++) {
+ for (i = 0; i < buf->rb_max_requests + 2; i++) {
struct rpcrdma_rep *rep;
rep = rpcrdma_create_rep(r_xprt);
/*
* Get a set of request/reply buffers.
+ *
+ * Reply buffer (if available) is attached to send buffer upon return.
*/
struct rpcrdma_req *
rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
out_reqbuf:
spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of request buffers (%p)\n", buffers);
+ pr_warn("RPC: %s: out of request buffers\n", __func__);
return NULL;
out_repbuf:
- list_add(&req->rl_free, &buffers->rb_send_bufs);
spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers);
- return NULL;
+ pr_warn("RPC: %s: out of reply buffers\n", __func__);
+ req->rl_reply = NULL;
+ return req;
}
/*