From: David Howells <dhowells@redhat.com>
To: netdev@vger.kernel.org
Cc: dhowells@redhat.com, tim@electronghost.co.uk,
linux-afs@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [PATCH 7/8] af_rxrpc: Request an ACK for every alternate DATA packet [ver #2]
Date: Thu, 06 Mar 2014 12:47:04 +0000 [thread overview]
Message-ID: <20140306124704.16645.84887.stgit@warthog.procyon.org.uk> (raw)
In-Reply-To: <20140306124614.16645.50744.stgit@warthog.procyon.org.uk>
Set the RxRPC header flag to request an ACK packet for every odd-numbered DATA
packet unless it's the last one (which implicitly requests an ACK anyway).
This is similar to how librx appears to work.
If we don't do this, we'll send out a full window of packets and then just sit
there until the other side gets bored and sends an ACK to indicate that it's
been idle for a while and has received no new packets.
Requesting a lot of ACKs shouldn't be a problem as ACKs should be merged when
possible.
As AF_RXRPC currently works, it will schedule an ACK to be generated upon
receipt of a DATA packet with the ACK-request packet set - and in the time
taken to schedule this in a work queue, several other packets are likely to
arrive and then all get ACK'd together.
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/ar-output.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index 4814d882bcb4..0b4b9a79f5ab 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -669,6 +669,7 @@ static int rxrpc_send_data(struct kiocb *iocb,
/* add the packet to the send queue if it's now full */
if (sp->remain <= 0 || (segment == 0 && !more)) {
struct rxrpc_connection *conn = call->conn;
+ uint32_t seq;
size_t pad;
/* pad out if we're using security */
@@ -681,11 +682,12 @@ static int rxrpc_send_data(struct kiocb *iocb,
memset(skb_put(skb, pad), 0, pad);
}
+ seq = atomic_inc_return(&call->sequence);
+
sp->hdr.epoch = conn->epoch;
sp->hdr.cid = call->cid;
sp->hdr.callNumber = call->call_id;
- sp->hdr.seq =
- htonl(atomic_inc_return(&call->sequence));
+ sp->hdr.seq = htonl(seq);
sp->hdr.serial =
htonl(atomic_inc_return(&conn->serial));
sp->hdr.type = RXRPC_PACKET_TYPE_DATA;
@@ -700,6 +702,8 @@ static int rxrpc_send_data(struct kiocb *iocb,
else if (CIRC_SPACE(call->acks_head, call->acks_tail,
call->acks_winsz) > 1)
sp->hdr.flags |= RXRPC_MORE_PACKETS;
+ if (more && seq & 1)
+ sp->hdr.flags |= RXRPC_REQUEST_ACK;
ret = rxrpc_secure_packet(
call, skb, skb->mark,
next prev parent reply other threads:[~2014-03-06 12:47 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-06 12:46 [PATCH 0/8] AF_RXRPC fixes and development " David Howells
2014-03-06 12:46 ` [PATCH 1/8] af_rxrpc: Remove incorrect checksum calculation from rxrpc_recvmsg() " David Howells
2014-03-06 12:46 ` [PATCH 2/8] af_rxrpc: Prevent RxRPC peers from ABORT-storming one another " David Howells
2014-03-06 12:46 ` [PATCH 3/8] af_rxrpc: Fix UDP MTU calculation from ICMP_FRAG_NEEDED " David Howells
2014-03-06 12:46 ` [PATCH 4/8] af_rxrpc: Add sysctls for configuring RxRPC parameters " David Howells
2014-03-06 12:46 ` [PATCH 5/8] af_rxrpc: Improve ACK production " David Howells
2014-03-06 12:46 ` [PATCH 6/8] af_rxrpc: Expose more RxRPC parameters via sysctls " David Howells
2014-03-06 12:47 ` David Howells [this message]
2014-03-06 12:47 ` [PATCH 8/8] af_rxrpc: Keep rxrpc_call pointers in a hashtable " David Howells
2014-03-06 19:37 ` [PATCH 0/8] AF_RXRPC fixes and development " David Miller
2014-03-06 22:15 ` David Howells
2014-03-06 22:16 ` David Miller
2014-03-06 22:31 ` David Howells
2014-03-07 21:12 ` David Miller
2014-03-06 22:32 ` David Howells
2014-03-06 22:38 ` David Miller
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=20140306124704.16645.84887.stgit@warthog.procyon.org.uk \
--to=dhowells@redhat.com \
--cc=linux-afs@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=tim@electronghost.co.uk \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome