summaryrefslogtreecommitdiff
path: root/net/tipc/msg.c
diff options
context:
space:
mode:
authorJon Maloy <jon.maloy@ericsson.com>2019-10-30 14:00:41 +0100
committerDavid S. Miller <davem@davemloft.net>2019-10-30 12:16:22 -0700
commitc0bceb97db9efc72629dd00cd0d9812f24d4ba2d (patch)
treeef59f9fd3c35956cac623194894faef3ff6d192f /net/tipc/msg.c
parent6c814e8c4e78c2b38e667a754edbe9dbaccdb698 (diff)
tipc: add smart nagle feature
We introduce a feature that works like a combination of TCP_NAGLE and TCP_CORK, but without some of the weaknesses of those. In particular, we will not observe long delivery delays because of delayed acks, since the algorithm itself decides if and when acks are to be sent from the receiving peer. - The nagle property as such is determined by manipulating a new 'maxnagle' field in struct tipc_sock. If certain conditions are met, 'maxnagle' will define max size of the messages which can be bundled. If it is set to zero no messages are ever bundled, implying that the nagle property is disabled. - A socket with the nagle property enabled enters nagle mode when more than 4 messages have been sent out without receiving any data message from the peer. - A socket leaves nagle mode whenever it receives a data message from the peer. In nagle mode, messages smaller than 'maxnagle' are accumulated in the socket write queue. The last buffer in the queue is marked with a new 'ack_required' bit, which forces the receiving peer to send a CONN_ACK message back to the sender upon reception. The accumulated contents of the write queue is transmitted when one of the following events or conditions occur. - A CONN_ACK message is received from the peer. - A data message is received from the peer. - A SOCK_WAKEUP pseudo message is received from the link level. - The write queue contains more than 64 1k blocks of data. - The connection is being shut down. - There is no CONN_ACK message to expect. I.e., there is currently no outstanding message where the 'ack_required' bit was set. As a consequence, the first message added after we enter nagle mode is always sent directly with this bit set. This new feature gives a 50-100% improvement of throughput for small (i.e., less than MTU size) messages, while it might add up to one RTT to latency time when the socket is in nagle mode. Acked-by: Ying Xue <ying.xue@windreiver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/tipc/msg.c')
-rw-r--r--net/tipc/msg.c53
1 files changed, 53 insertions, 0 deletions
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 922d262e153f..973795a1a968 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -190,6 +190,59 @@ err:
return 0;
}
+/**
+ * tipc_msg_append(): Append data to tail of an existing buffer queue
+ * @hdr: header to be used
+ * @m: the data to be appended
+ * @mss: max allowable size of buffer
+ * @dlen: size of data to be appended
+ * @txq: queue to appand to
+ * Returns the number og 1k blocks appended or errno value
+ */
+int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
+ int mss, struct sk_buff_head *txq)
+{
+ struct sk_buff *skb, *prev;
+ int accounted, total, curr;
+ int mlen, cpy, rem = dlen;
+ struct tipc_msg *hdr;
+
+ skb = skb_peek_tail(txq);
+ accounted = skb ? msg_blocks(buf_msg(skb)) : 0;
+ total = accounted;
+
+ while (rem) {
+ if (!skb || skb->len >= mss) {
+ prev = skb;
+ skb = tipc_buf_acquire(mss, GFP_KERNEL);
+ if (unlikely(!skb))
+ return -ENOMEM;
+ skb_orphan(skb);
+ skb_trim(skb, MIN_H_SIZE);
+ hdr = buf_msg(skb);
+ skb_copy_to_linear_data(skb, _hdr, MIN_H_SIZE);
+ msg_set_hdr_sz(hdr, MIN_H_SIZE);
+ msg_set_size(hdr, MIN_H_SIZE);
+ __skb_queue_tail(txq, skb);
+ total += 1;
+ if (prev)
+ msg_set_ack_required(buf_msg(prev), 0);
+ msg_set_ack_required(hdr, 1);
+ }
+ hdr = buf_msg(skb);
+ curr = msg_blocks(hdr);
+ mlen = msg_size(hdr);
+ cpy = min_t(int, rem, mss - mlen);
+ if (cpy != copy_from_iter(skb->data + mlen, cpy, &m->msg_iter))
+ return -EFAULT;
+ msg_set_size(hdr, mlen + cpy);
+ skb_put(skb, cpy);
+ rem -= cpy;
+ total += msg_blocks(hdr) - curr;
+ }
+ return total - accounted;
+}
+
/* tipc_msg_validate - validate basic format of received message
*
* This routine ensures a TIPC message has an acceptable header, and at least