xprtrdma: Use xprt_pin_rqst in rpcrdma_reply_handler

Adopt the use of xprt_pin_rqst to eliminate contention between
Call-side users of rb_lock and the use of rb_lock in
rpcrdma_reply_handler.

This replaces the mechanism introduced in 431af645cf ("xprtrdma:
Fix client lock-up after application signal fires").

Use recv_lock to quickly find the completing rqst, pin it, then
drop the lock. At that point invalidation and pull-up of the Reply
XDR can be done. Both are often expensive operations.

Finally, take recv_lock again to signal completion to the RPC
layer. It also protects adjustment of "cwnd".

This greatly reduces the amount of time a lock is held by the
reply handler. Comparing lock_stat results shows a marked decrease
in contention on rb_lock and recv_lock.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
[trond.myklebust@primarydata.com: Remove call to rpcrdma_buffer_put() from
   the "out_norqst:" path in rpcrdma_reply_handler.]
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
This commit is contained in:
Chuck Lever
2017-08-23 17:05:58 -04:00
committed by Trond Myklebust
parent f9773b22a2
commit 9590d083c1
5 changed files with 19 additions and 77 deletions

View File

@@ -855,6 +855,7 @@ void xprt_pin_rqst(struct rpc_rqst *req)
{
set_bit(RPC_TASK_MSG_RECV, &req->rq_task->tk_runstate);
}
EXPORT_SYMBOL_GPL(xprt_pin_rqst);
/**
* xprt_unpin_rqst - Unpin a request on the transport receive list
@@ -870,6 +871,7 @@ void xprt_unpin_rqst(struct rpc_rqst *req)
if (test_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate))
wake_up_bit(&task->tk_runstate, RPC_TASK_MSG_RECV);
}
EXPORT_SYMBOL_GPL(xprt_unpin_rqst);
static void xprt_wait_on_pinned_rqst(struct rpc_rqst *req)
__must_hold(&req->rq_xprt->recv_lock)