Quoting Eddie Kohler: | Gerrit, | | This is cool, but it would be nice to still have the option to use a nominal | packet size 's' and do packet-based congestion control. | Send us a patch and we will see ... | Eddie | | | Gerrit Renker wrote: | > [CCID 3]: Track RX/TX packet size `s' using moving-average | > | > | > Problem: | > -------- | > Currently, the receiver/sender packet size `s' of the TCP throughput | > equation [RFC 3448, 3.1] has to be communicated manually via socket options | > to the CCID 3 module. This has been discussed on dccp@vger, see e.g. | > http://www.mail-archive.com/dccp@xxxxxxxxxxxxxxx/msg00582.html | > | > Solution | > -------- | > This patch implements automatically tracking the packet size `s', for receiver and | > sender. Socket options to commmunicate the packet size are then no longer needed. | > It implements the strategy presented on | > http://www.mail-archive.com/dccp@xxxxxxxxxxxxxxx/msg00581.html | > | > | > Signed-off-by: Gerrit Renker <gerrit@xxxxxxxxxxxxxx> | > | > | > J u s t i f i c a t i o n [not meant as commit message] | > ======================================================== | > | > The packet size `s' is one of the main parameters of the TFRC mechanism. The TFRC sender uses | > `s' in the (i) throughput equation, in the setting of the (ii) maximum receive rate, | > (iii) minimum sending rate, and (iv) the nofeedback timer; the TFRC receiver `s' (aka segment | > size) to compute the initial loss history, after the first loss event. | > | > Hence using socket options to communicate `s' is error-prone whenever the user-space program | > communicates values of `s' to the CCID 3 module that differ from the real value of `s'; | > ultimately such differences not only increase the possibility of error but can also decrease | > the performance. | > | > Using the mean value of the packet size is an accepted practice, supported e.g. by | > * RFC 4342, sec. 5.3: | > "A CCID 3 implementation MAY calculate s as the segment size averaged over | > multiple round trip times [...]." | > | > * RFC 3448, sec. 4.1: | > "It should normally be safe to use an estimate of the mean packet size for s." | > | > * draft-ietf-dccp-rfc3448bis-00.txt, sec. | > "[... ] where the segment size varies depending on the data, the sender MAY estimate | > the segment size s as the average segment size over the last four loss intervals. The | > sender MAY also estimate the average segment size over longer time intervals [...]." | > | > This solution is robust: if packet sizes are varying, the moving average is a reliable | > predictor of the (long-term) mean value; if packet sizes are fixed then s stays constant. | > | > The solution uses DCCP payload packet sizes, i.e. IP payload size minus DCCP Data Offset | > value. This is consistent with the recommendations in RFC 4342, section 5.3: | > "Alternately, a CCID 3 implementation MAY use the Maximum Packet Size | > to derive s. In this case, s is set to the Maximum Segment Size | > (MSS), the maximum size in bytes for the data segment, not including | > the default DCCP and IP packet headers." | > It is further consistent with the definition of MSS in RFC 879 and the use of payload size | > as length value in the DCCP module. | > [See also http://www.mail-archive.com/dccp@xxxxxxxxxxxxxxx/msg00534.html ] | > | > --- | > net/dccp/ccids/ccid3.c | 48 +++++++++++++++++++++++++++++------------------- | > 1 file changed, 29 insertions(+), 19 deletions(-) | > | > --- a/net/dccp/ccids/ccid3.c | > +++ b/net/dccp/ccids/ccid3.c | > @@ -151,6 +151,18 @@ static void ccid3_hc_tx_update_x(struct | > } | > } | > | > +/* | > + * Track the mean packet size `s' (cf. RFC 4342, 5.3 and RFC 3448, 4.1) | > + * @len: DCCP packet payload size in bytes | > + */ | > +static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len) | > +{ | > + DCCP_BUG_ON(len == 0); | > + | > + hctx->ccid3hctx_s = (hctx->ccid3hctx_s == 0)? len | > + : (9 * hctx->ccid3hctx_s + len) / 10; | > +} | > + | > static void ccid3_hc_tx_no_feedback_timer(unsigned long data) | > { | > struct sock *sk = (struct sock *)data; | > @@ -347,6 +359,8 @@ static void ccid3_hc_tx_packet_sent(stru | > unsigned long quarter_rtt; | > struct dccp_tx_hist_entry *packet; | > | > + ccid3_hc_tx_update_s(hctx, len); | > + | > packet = dccp_tx_hist_head(&hctx->ccid3hctx_hist); | > if (unlikely(packet == NULL)) { | > DCCP_WARN("packet doesn't exist in history!\n"); | > @@ -625,17 +639,9 @@ static int ccid3_hc_tx_parse_options(str | > | > static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) | > { | > - struct dccp_sock *dp = dccp_sk(sk); | > struct ccid3_hc_tx_sock *hctx = ccid_priv(ccid); | > | > - if (dp->dccps_packet_size >= TFRC_MIN_PACKET_SIZE && | > - dp->dccps_packet_size <= TFRC_MAX_PACKET_SIZE) | > - hctx->ccid3hctx_s = dp->dccps_packet_size; | > - else | > - hctx->ccid3hctx_s = TFRC_STD_PACKET_SIZE; | > - | > - /* Set transmission rate to 1 packet per second */ | > - hctx->ccid3hctx_x = hctx->ccid3hctx_s; | > + hctx->ccid3hctx_s = 0; | > hctx->ccid3hctx_t_rto = USEC_PER_SEC; | > hctx->ccid3hctx_state = TFRC_SSTATE_NO_SENT; | > INIT_LIST_HEAD(&hctx->ccid3hctx_hist); | > @@ -690,6 +696,14 @@ static void ccid3_hc_rx_set_state(struct | > hcrx->ccid3hcrx_state = state; | > } | > | > +static inline void ccid3_hc_rx_update_s(struct ccid3_hc_rx_sock *hcrx, int len) | > +{ | > + DCCP_BUG_ON(len == 0); | > + | > + hcrx->ccid3hcrx_s = (hcrx->ccid3hcrx_s == 0)? len | > + : (9 * hcrx->ccid3hcrx_s + len) / 10; | > +} | > + | > static void ccid3_hc_rx_send_feedback(struct sock *sk) | > { | > struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); | > @@ -966,7 +980,7 @@ static void ccid3_hc_rx_packet_recv(stru | > struct dccp_rx_hist_entry *packet; | > struct timeval now; | > u32 p_prev, rtt_prev, r_sample, t_elapsed; | > - int loss; | > + int loss, payload_size; | > | > BUG_ON(hcrx == NULL); | > | > @@ -1021,6 +1035,9 @@ static void ccid3_hc_rx_packet_recv(stru | > if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK) | > return; | > | > + payload_size = skb->len - dccp_hdr(skb)->dccph_doff * 4; | > + ccid3_hc_rx_update_s(hcrx, payload_size); | > + | > switch (hcrx->ccid3hcrx_state) { | > case TFRC_RSTATE_NO_DATA: | > ccid3_pr_debug("%s, sk=%p(%s), skb=%p, sending initial " | > @@ -1031,8 +1048,7 @@ static void ccid3_hc_rx_packet_recv(stru | > ccid3_hc_rx_set_state(sk, TFRC_RSTATE_DATA); | > return; | > case TFRC_RSTATE_DATA: | > - hcrx->ccid3hcrx_bytes_recv += skb->len - | > - dccp_hdr(skb)->dccph_doff * 4; | > + hcrx->ccid3hcrx_bytes_recv += payload_size; | > if (loss) | > break; | > | > @@ -1072,22 +1088,16 @@ static void ccid3_hc_rx_packet_recv(stru | > | > static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk) | > { | > - struct dccp_sock *dp = dccp_sk(sk); | > struct ccid3_hc_rx_sock *hcrx = ccid_priv(ccid); | > | > ccid3_pr_debug("%s, sk=%p\n", dccp_role(sk), sk); | > | > - if (dp->dccps_packet_size >= TFRC_MIN_PACKET_SIZE && | > - dp->dccps_packet_size <= TFRC_MAX_PACKET_SIZE) | > - hcrx->ccid3hcrx_s = dp->dccps_packet_size; | > - else | > - hcrx->ccid3hcrx_s = TFRC_STD_PACKET_SIZE; | > - | > hcrx->ccid3hcrx_state = TFRC_RSTATE_NO_DATA; | > INIT_LIST_HEAD(&hcrx->ccid3hcrx_hist); | > INIT_LIST_HEAD(&hcrx->ccid3hcrx_li_hist); | > dccp_timestamp(sk, &hcrx->ccid3hcrx_tstamp_last_ack); | > hcrx->ccid3hcrx_tstamp_last_feedback = hcrx->ccid3hcrx_tstamp_last_ack; | > + hcrx->ccid3hcrx_s = 0; | > hcrx->ccid3hcrx_rtt = 5000; /* XXX 5ms for now... */ | > return 0; | > } | > - | > To unsubscribe from this list: send the line "unsubscribe dccp" in | > the body of a message to majordomo@xxxxxxxxxxxxxxx | > More majordomo info at http://vger.kernel.org/majordomo-info.html | | - To unsubscribe from this list: send the line "unsubscribe dccp" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
