Linux-RDMA Archive on lore.kernel.org
 help / color / Atom feed
From: Chuck Lever <chuck.lever@oracle.com>
To: trondmy@hammerspace.com
Cc: linux-nfs@vger.kernel.org, linux-rdma@vger.kernel.org
Subject: [PATCH v3 17/26] xprtrdma: Avoid Send Queue wrapping
Date: Mon, 19 Apr 2021 14:03:25 -0400
Message-ID: <161885540540.38598.8756855506309086070.stgit@manet.1015granger.net> (raw)
In-Reply-To: <161885481568.38598.16682844600209775665.stgit@manet.1015granger.net>

Send WRs can be signalled or unsignalled. A signalled Send WR
always has a matching Send completion, while a unsignalled Send
has a completion only if the Send WR fails.

xprtrdma has a Send account mechanism that is designed to reduce
the number of signalled Send WRs. This in turn mitigates the
interrupt rate of the underlying device.

RDMA consumers can't leave all Sends unsignaled, however, because
providers rely on Send completions to maintain their Send Queue head
and tail pointers. xprtrdma counts the number of unsignaled Send WRs
that have been posted to ensure that Sends are signalled often
enough to prevent the Send Queue from wrapping.

This mechanism neglected to account for FastReg WRs, which are
posted on the Send Queue but never signalled. As a result, the
Send Queue wrapped on occasion, resulting in duplication completions
of FastReg and LocalInv WRs.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/xprtrdma/frwr_ops.c |   17 +++++++++++++++--
 net/sunrpc/xprtrdma/verbs.c    |   16 +---------------
 2 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 951ae20485f3..43a412ea337a 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -390,11 +390,13 @@ static void frwr_cid_init(struct rpcrdma_ep *ep,
  */
 int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
+	struct ib_send_wr *post_wr, *send_wr = &req->rl_wr;
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
-	struct ib_send_wr *post_wr;
 	struct rpcrdma_mr *mr;
+	unsigned int num_wrs;
 
-	post_wr = &req->rl_wr;
+	num_wrs = 1;
+	post_wr = send_wr;
 	list_for_each_entry(mr, &req->rl_registered, mr_list) {
 		struct rpcrdma_frwr *frwr;
 
@@ -409,8 +411,19 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 		frwr->fr_regwr.wr.send_flags = 0;
 
 		post_wr = &frwr->fr_regwr.wr;
+		++num_wrs;
 	}
 
+	if ((kref_read(&req->rl_kref) > 1) || num_wrs > ep->re_send_count) {
+		send_wr->send_flags |= IB_SEND_SIGNALED;
+		ep->re_send_count = min_t(unsigned int, ep->re_send_batch,
+					  num_wrs - ep->re_send_count);
+	} else {
+		send_wr->send_flags &= ~IB_SEND_SIGNALED;
+		ep->re_send_count -= num_wrs;
+	}
+
+	trace_xprtrdma_post_send(req);
 	return ib_post_send(ep->re_id->qp, post_wr, NULL);
 }
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index d4e573eef416..55c45cad2c8a 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1365,21 +1365,7 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb)
  */
 int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
-	struct ib_send_wr *send_wr = &req->rl_wr;
-	struct rpcrdma_ep *ep = r_xprt->rx_ep;
-	int rc;
-
-	if (!ep->re_send_count || kref_read(&req->rl_kref) > 1) {
-		send_wr->send_flags |= IB_SEND_SIGNALED;
-		ep->re_send_count = ep->re_send_batch;
-	} else {
-		send_wr->send_flags &= ~IB_SEND_SIGNALED;
-		--ep->re_send_count;
-	}
-
-	trace_xprtrdma_post_send(req);
-	rc = frwr_send(r_xprt, req);
-	if (rc)
+	if (frwr_send(r_xprt, req))
 		return -ENOTCONN;
 	return 0;
 }



  parent reply index

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-19 18:01 [PATCH v3 00/26] NFS/RDMA client patches for next Chuck Lever
2021-04-19 18:01 ` [PATCH v3 01/26] SUNRPC: Move fault injection call sites Chuck Lever
2021-04-19 18:05   ` Chuck Lever III
2021-04-19 18:01 ` [PATCH v3 02/26] SUNRPC: Remove trace_xprt_transmit_queued Chuck Lever
2021-04-19 18:01 ` [PATCH v3 03/26] SUNRPC: Add tracepoint that fires when an RPC is retransmitted Chuck Lever
2021-04-19 18:02 ` [PATCH v3 04/26] xprtrdma: Avoid Receive Queue wrapping Chuck Lever
2021-04-19 18:02 ` [PATCH v3 05/26] xprtrdma: Do not refresh Receive Queue while it is draining Chuck Lever
2021-04-19 18:02 ` [PATCH v3 06/26] xprtrdma: Put flushed Receives on free list instead of destroying them Chuck Lever
2021-04-19 18:02 ` [PATCH v3 07/26] xprtrdma: Improve locking around rpcrdma_rep destruction Chuck Lever
2021-04-23 21:06   ` Trond Myklebust
2021-04-24 17:39     ` Chuck Lever III
2021-04-24 17:59       ` Trond Myklebust
2021-04-19 18:02 ` [PATCH v3 08/26] xprtrdma: Improve commentary around rpcrdma_reps_unmap() Chuck Lever
2021-04-19 18:02 ` [PATCH v3 09/26] xprtrdma: Improve locking around rpcrdma_rep creation Chuck Lever
2021-04-19 18:02 ` [PATCH v3 10/26] xprtrdma: Fix cwnd update ordering Chuck Lever
2021-04-19 18:02 ` [PATCH v3 11/26] xprtrdma: Delete rpcrdma_recv_buffer_put() Chuck Lever
2021-04-19 18:02 ` [PATCH v3 12/26] xprtrdma: rpcrdma_mr_pop() already does list_del_init() Chuck Lever
2021-04-19 18:03 ` [PATCH v3 13/26] xprtrdma: Rename frwr_release_mr() Chuck Lever
2021-04-19 18:03 ` [PATCH v3 14/26] xprtrdma: Clarify use of barrier in frwr_wc_localinv_done() Chuck Lever
2021-04-19 18:03 ` [PATCH v3 15/26] xprtrdma: Do not recycle MR after FastReg/LocalInv flushes Chuck Lever
2021-04-25 14:19   ` Dan Aloni
2021-04-25 16:21     ` Chuck Lever III
2021-04-25 17:00       ` Dan Aloni
2021-04-19 18:03 ` [PATCH v3 16/26] xprtrdma: Do not wake RPC consumer on a failed LocalInv Chuck Lever
2021-04-19 18:03 ` Chuck Lever [this message]
2021-04-19 18:03 ` [PATCH v3 18/26] xprtrdma: Add tracepoints showing FastReg WRs and remote invalidation Chuck Lever
2021-04-19 18:03 ` [PATCH v3 19/26] xprtrdma: Add an rpcrdma_mr_completion_class Chuck Lever
2021-04-19 18:03 ` [PATCH v3 20/26] xprtrdma: Don't display r_xprt memory addresses in tracepoints Chuck Lever
2021-04-19 18:03 ` [PATCH v3 21/26] xprtrdma: Remove the RPC/RDMA QP event handler Chuck Lever
2021-04-19 18:03 ` [PATCH v3 22/26] xprtrdma: Move fr_cid to struct rpcrdma_mr Chuck Lever
2021-04-19 18:04 ` [PATCH v3 23/26] xprtrdma: Move cqe " Chuck Lever
2021-04-19 18:04 ` [PATCH v3 24/26] xprtrdma: Move fr_linv_done field " Chuck Lever
2021-04-19 18:04 ` [PATCH v3 25/26] xprtrdma: Move the Work Request union " Chuck Lever
2021-04-19 18:04 ` [PATCH v3 26/26] xprtrdma: Move fr_mr field " Chuck Lever

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=161885540540.38598.8756855506309086070.stgit@manet.1015granger.net \
    --to=chuck.lever@oracle.com \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=trondmy@hammerspace.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-RDMA Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rdma/0 linux-rdma/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rdma linux-rdma/ https://lore.kernel.org/linux-rdma \
		linux-rdma@vger.kernel.org
	public-inbox-index linux-rdma

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rdma


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git