Skip to contentSkip to conversation

Avoid accumulation of large send credit

PATCH In review Arnaldo Carvalho de Melo 1 participant 1 message Apr 12, 2007 Networking

lore
Share & tools
lore
#0 lore raw

PATCH 2/29 Avoid accumulation of large send credit

Problem:
Large backlogs of packets will accumulate in the CCID3 TX module when
(i) the application idles and/or
(ii) the application emits at a rate slower than the allowed rate X/s and/or (iii) due to scheduling inaccuracy (resolution only up to HZ).

The consequence is that a huge burst of packets can be sent immediately, which violates the allowed sending rate and can (worst case) choke the network. Furthermore (iii) is especially likely when using high-speed (Gbit) links.

Fix:
Avoid any backlog of sending time which is greater than one whole t_ipi. This is a conservative tight bound which will ensure safe operation with regard to the allowed fair-share rate in a wide range of possible hardware configurations. The value is derived below with a simple model, showing that this choice is safe from an operational point of view.

---
 net/dccp/ccids/ccid3.c |   12 ++++++++++--
 1 files changed, 10 insertions(+), 2 deletions(-)
net/dccp/ccids/ccid3.c +10 -2
index d7d9ce7..c623761 100644
@@ -362,7 +362,15 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 	case TFRC_SSTATE_NO_FBACK:
 	case TFRC_SSTATE_FBACK:
 		delay = timeval_delta(&hctx->ccid3hctx_t_nom, &now);
-		ccid3_pr_debug("delay=%ld\n", (long)delay);
+		/*
+		 * Lagging behind for more than a full t_ipi: when this occurs,
+		 * a send credit accrues which causes packet storms, violating
+		 * even the average allowed sending rate. This case happens if
+		 * the application idles for some time, or if it emits packets
+		 * at a rate smaller than X/s. Avoid such accumulation.
+		 */
+		if (delay + (suseconds_t)hctx->ccid3hctx_t_ipi < 0)
+			hctx->ccid3hctx_t_nom = now;
 		/*
 		 *	Scheduling of packet transmissions [RFC 3448, 4.6]
 		 *
@@ -371,7 +379,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 		 * else
 		 *       // send the packet in (t_nom - t_now) milliseconds.
 		 */
-		if (delay - (suseconds_t)hctx->ccid3hctx_delta >= 0)
+		else if (delay - (suseconds_t)hctx->ccid3hctx_delta >= 0)
 			return delay / 1000L;
 
 		ccid3_hc_tx_update_win_count(hctx, &now);
Signature · 1 line
1.5.0.6