This is a multi-part message in MIME format.
Attached is a short patch against version 2.4.22 to implement the recent
rfc3517 for SACK in TCP (see ftp://ftp.rfc-editor.org/in-notes/rfc3517.txt).
This modifies how packets which fail to be sacked are marked as lost. At
present, any packets falling into sack holes are marked lost after the first
successful retransmit. The new code marks packets in sack holes as lost as
soon as tp->reordering or more packets with higher sequence number are
sacked. This is consistent with how reordering is handled elsewhere and
should lead to faster retransmission and recovery when multiple drops occur.
Comments appreciated.
Regards,
Doug Leith
www.hamilton.ie
diff -u -wbrP --exclude=config.save linux-2.4.22/net/ipv4/tcp_input.c linux-
2.4.22-retrans/net/ipv4/tcp_input.c
--- linux-2.4.22/net/ipv4/tcp_input.c 2003-06-13 15:51:39.000000000 +0100
+++ linux-2.4.22-retrans/net/ipv4/tcp_input.c 2003-10-09 07:59:48.000000000
+0100
@@ -61,6 +61,7 @@
* Panu Kuhlberg: Experimental audit of TCP (re)
transmission
* engine. Lots of bugs are found.
* Pasi Sarolahti: F-RTO for dealing with spurious RTOs
+ * Doug Leith: Early retransmission of packets
falling into sack holes.
*/
#include <linux/config.h>
@@ -757,6 +758,10 @@
* for retransmitted and already SACKed segment -> reordering..
* Both of these heuristics are not used in Loss state, when we cannot
* account for retransmits accurately.
+ *
+ * Retransmission of packets
+ * -------------------------
+ * Extension of Hoe's retransmit to allow early retransmission of packets
which fall into sack holes
*/
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32
prior_snd_una)
@@ -770,6 +775,7 @@
u32 lost_retrans = 0;
int flag = 0;
int i;
+ u32 prior_sacked_out=tp->sacked_out;
if (!tp->sacked_out)
tp->fackets_out = 0;
@@ -781,6 +787,7 @@
__u32 end_seq = ntohl(sp->end_seq);
int fack_count = 0;
int dup_sack = 0;
+ u32 sack_count=0;
/* Check for D-SACK. */
if (i == 0) {
@@ -828,6 +835,8 @@
break;
fack_count++;
+ if (sacked&TCPCB_RETRANS)
+ sack_count++;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
!before(end_seq, TCP_SKB_CB(skb)->end_seq);
@@ -860,8 +869,14 @@
(!lost_retrans || after(end_seq, lost_retrans)))
lost_retrans = end_seq;
- if (!in_sack)
+ if (!in_sack) {
+ /* force early retransmit ? */
+ if (!(sacked&TCPCB_TAGBITS) && (prior_sacked_out
> sack_count + tp->reordering)) {
+ TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+ tp->lost_out++;
+ }
continue;
+ }
if (!(sacked&TCPCB_SACKED_ACKED)) {
if (sacked & TCPCB_SACKED_RETRANS) {
@@ -1599,7 +1614,7 @@
if ((flag&FLAG_DATA_LOST) &&
before(tp->snd_una, tp->high_seq) &&
tp->ca_state != TCP_CA_Open &&
- tp->fackets_out > tp->reordering) {
+ tp->fackets_out > tp->reordering && IsReno(tp) ) {
tcp_mark_head_lost(sk, tp, tp->fackets_out-tp->reordering, tp-
>high_seq);
NET_INC_STATS_BH(TCPLoss);
}
@@ -1714,7 +1729,7 @@
tp->ca_state = TCP_CA_Recovery;
}
- if (is_dupack || tcp_head_timedout(sk, tp))
+ if ( (is_dupack || tcp_head_timedout(sk, tp)) && IsReno(tp) )
tcp_update_scoreboard(sk, tp);
tcp_cwnd_down(tp);
tcp_xmit_retransmit_queue(sk);
diff -u -wbrP --exclude=config.save linux-2.4.22/net/ipv4/tcp_input.c linux-2.4.22-retrans/net/ipv4/tcp_input.c
--- linux-2.4.22/net/ipv4/tcp_input.c 2003-06-13 15:51:39.000000000 +0100
+++ linux-2.4.22-retrans/net/ipv4/tcp_input.c 2003-10-09 07:59:48.000000000 +0100
@@ -61,6 +61,7 @@
* Panu Kuhlberg: Experimental audit of TCP (re)transmission
* engine. Lots of bugs are found.
* Pasi Sarolahti: F-RTO for dealing with spurious RTOs
+ * Doug Leith: Early retransmission of packets falling into sack holes.
*/
#include <linux/config.h>
@@ -757,6 +758,10 @@
* for retransmitted and already SACKed segment -> reordering..
* Both of these heuristics are not used in Loss state, when we cannot
* account for retransmits accurately.
+ *
+ * Retransmission of packets
+ * -------------------------
+ * Extension of Hoe's retransmit to allow early retransmission of packets which fall into sack holes
*/
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
@@ -770,6 +775,7 @@
u32 lost_retrans = 0;
int flag = 0;
int i;
+ u32 prior_sacked_out=tp->sacked_out;
if (!tp->sacked_out)
tp->fackets_out = 0;
@@ -781,6 +787,7 @@
__u32 end_seq = ntohl(sp->end_seq);
int fack_count = 0;
int dup_sack = 0;
+ u32 sack_count=0;
/* Check for D-SACK. */
if (i == 0) {
@@ -828,6 +835,8 @@
break;
fack_count++;
+ if (sacked&TCPCB_RETRANS)
+ sack_count++;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
!before(end_seq, TCP_SKB_CB(skb)->end_seq);
@@ -860,8 +869,14 @@
(!lost_retrans || after(end_seq, lost_retrans)))
lost_retrans = end_seq;
- if (!in_sack)
+ if (!in_sack) {
+ /* force early retransmit ? */
+ if (!(sacked&TCPCB_TAGBITS) && (prior_sacked_out > sack_count + tp->reordering)) {
+ TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+ tp->lost_out++;
+ }
continue;
+ }
if (!(sacked&TCPCB_SACKED_ACKED)) {
if (sacked & TCPCB_SACKED_RETRANS) {
@@ -1599,7 +1614,7 @@
if ((flag&FLAG_DATA_LOST) &&
before(tp->snd_una, tp->high_seq) &&
tp->ca_state != TCP_CA_Open &&
- tp->fackets_out > tp->reordering) {
+ tp->fackets_out > tp->reordering && IsReno(tp) ) {
tcp_mark_head_lost(sk, tp, tp->fackets_out-tp->reordering, tp->high_seq);
NET_INC_STATS_BH(TCPLoss);
}
@@ -1714,7 +1729,7 @@
tp->ca_state = TCP_CA_Recovery;
}
- if (is_dupack || tcp_head_timedout(sk, tp))
+ if ( (is_dupack || tcp_head_timedout(sk, tp)) && IsReno(tp) )
tcp_update_scoreboard(sk, tp);
tcp_cwnd_down(tp);
tcp_xmit_retransmit_queue(sk);
¢éì¹» ®&Þ~º&¶¬?+-±éݶ¥?w®?Ë?±Êâméb?ìgzا¶?¡Ü¨}©?²Æ zÚ&j:+v?¨¾«?êçzZ+?Ê+zf£¢·h??§~??Ûiÿûàz¹ ®w¥¢¸??¨èÚ&¢)ߢf
