Date: Tue, 4 Feb 2014 09:38:30 +0000 From: "Eggert, Lars" <lars@netapp.com> To: "freebsd-net@freebsd.org" <freebsd-net@freebsd.org> Cc: "varis81@hotmail.com" <varis81@hotmail.com> Subject: Patches for RFC6937 and draft-ietf-tcpm-newcwv-00 Message-ID: <259C9434-C6FE-42EA-823D-ECB024DBF3D7@netapp.com>
next in thread | raw e-mail | index | archive | help
--Apple-Mail=_5088A38A-DF43-450D-9E03-31C51BD176C7
Content-Type: multipart/mixed;
boundary="Apple-Mail=_E3102E34-B41D-47A0-AB2F-5E03D718EBE4"
--Apple-Mail=_E3102E34-B41D-47A0-AB2F-5E03D718EBE4
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain;
charset=us-ascii
Hi,
below are two patches that implement RFC6937 ("Proportional Rate =
Reduction for TCP") and draft-ietf-tcpm-newcwv-00 ("Updating TCP to =
support Rate-Limited Traffic"). They were done by Aris =
Angelogiannopoulos for his MS thesis, which is at =
https://eggert.org/students/angelogiannopoulos-thesis.pdf.
The patches should apply to -CURRENT as of Sep 17, 2013. (Sorry for the =
delay in sending them, we'd been trying to get some feedback from =
committers first, without luck.)
Please note that newcwv is still a work in progress in the IETF, and the =
patch has some limitations with regards to the "pipeACK Sampling Period" =
mentioned in the Internet-Draft. Aris says this in his thesis about what =
exactly he implemented:
"The second implementation choice, is in regards with the measurement of =
pipeACK. This variable is the most important introduced by the method =
and is used to compute the phase that the sender currently lies in. In =
order to compute pipeACK the approach suggested by the Internet Draft =
(ID) is followed [ncwv]. During initialization, pipeACK is set to the =
maximum possible value. A helper variable prevHighACK is introduced that =
is initialized to the initial sequence number (iss). prevHighACK holds =
the value of the highest acknowledged byte so far. pipeACK is measured =
once per RTT meaning that when an ACK covering prevHighACK is received, =
pipeACK becomes the difference between the current ACK and prevHighACK. =
This is called a pipeACK sample. A newer version of the draft suggests =
that multiple pipeACK samples can be used during the pipeACK sampling =
period."
Lars
--Apple-Mail=_E3102E34-B41D-47A0-AB2F-5E03D718EBE4
Content-Disposition: attachment;
filename=prr.patch
Content-Type: application/octet-stream;
name="prr.patch"
Content-Transfer-Encoding: 7bit
diff --git a/sys/netinet/tcp_input.c b/sys/netinet/tcp_input.c
index 75609fd..70c29a8 100644
--- a/sys/netinet/tcp_input.c
+++ b/sys/netinet/tcp_input.c
@@ -145,6 +145,18 @@ SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, drop_synfin, CTLFLAG_RW,
&VNET_NAME(drop_synfin), 0,
"Drop TCP packets with SYN+FIN set");
+VNET_DEFINE(int, tcp_do_prr_conservative) = 0;
+#define V_tcp_do_prr_conservative VNET(tcp_do_prr_conservative)
+SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, do_prr_conservative, CTLFLAG_RW,
+ &VNET_NAME(tcp_do_prr_conservative), 0,
+ "Do conservative PRR");
+
+VNET_DEFINE(int, tcp_do_prr) = 0;
+#define V_tcp_do_prr VNET(tcp_do_prr)
+SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, do_prr, CTLFLAG_RW,
+ &VNET_NAME(tcp_do_prr), 0,
+ "Do the Proportional Rate Reduction Algorithm");
+
VNET_DEFINE(int, tcp_do_rfc3042) = 1;
#define V_tcp_do_rfc3042 VNET(tcp_do_rfc3042)
SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, rfc3042, CTLFLAG_RW,
@@ -229,6 +241,7 @@ static void tcp_pulloutofband(struct socket *,
struct tcphdr *, struct mbuf *, int);
static void tcp_xmit_timer(struct tcpcb *, int);
static void tcp_newreno_partial_ack(struct tcpcb *, struct tcphdr *);
+static void tcp_prr_partial_ack(struct tcpcb *, struct tcphdr *);
static void inline tcp_fields_to_host(struct tcphdr *);
#ifdef TCP_SIGNATURE
static void inline tcp_fields_to_net(struct tcphdr *);
@@ -2460,7 +2473,50 @@ tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so,
else if (++tp->t_dupacks > tcprexmtthresh ||
IN_FASTRECOVERY(tp->t_flags)) {
cc_ack_received(tp, th, CC_DUPACK);
- if ((tp->t_flags & TF_SACK_PERMIT) &&
+ if (V_tcp_do_prr &&
+ IN_FASTRECOVERY(tp->t_flags) &&
+ (tp->t_flags & TF_SACK_PERMIT)) {
+ long snd_cnt = 0, limit = 0, del_data = 0, pipe = 0;
+ /*
+ *In a duplicate ACK del_data is only the
+ *diff_in_sack. If no SACK is used del_data will be 0.
+ *Pipe is the amount of data we estimate to be
+ *in the network.
+ */
+ del_data = tp->diff_in_sack;
+ pipe = (tp->snd_nxt - tp->snd_fack) +
+ tp->sackhint.sack_bytes_rexmit;
+ tp->prr_delivered += del_data;
+ if (pipe > tp->snd_ssthresh)
+ snd_cnt = (tp->prr_delivered * tp->snd_ssthresh /
+ tp->recover_fs) + 1 - tp->prr_out;
+ else {
+ if (V_tcp_do_prr_conservative)
+ limit = tp->prr_delivered - tp->prr_out;
+ else
+ if ((tp->prr_delivered - tp->prr_out) > del_data)
+ limit = tp->prr_delivered - tp->prr_out +
+ tp->t_maxseg;
+ else
+ limit = del_data + tp->t_maxseg;
+ if ((tp->snd_ssthresh - pipe) < limit)
+ snd_cnt = tp->snd_ssthresh - pipe;
+ else
+ snd_cnt = limit;
+ }
+ snd_cnt = (snd_cnt / tp->t_maxseg);
+ if (snd_cnt < 0)
+ snd_cnt = 0;
+ /*
+ * Send snd_cnt new data into the network in
+ * response to this ack.If there is gonna be a
+ * SACK retransmission, adjust snd_cwnd
+ * accordingly.
+ */
+ tp->snd_cwnd = tp->snd_nxt - tp->sack_newdata +
+ tp->sackhint.sack_bytes_rexmit + (snd_cnt*tp->t_maxseg);
+ }
+ else if ((tp->t_flags & TF_SACK_PERMIT) &&
IN_FASTRECOVERY(tp->t_flags)) {
int awnd;
@@ -2495,12 +2551,18 @@ tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so,
tcp_seq onxt = tp->snd_nxt;
/*
- * If we're doing sack, check to
- * see if we're already in sack
+ * If we're doing sack or prr, check to
+ * see if we're already in
* recovery. If we're not doing sack,
* check to see if we're in newreno
* recovery.
*/
+ if (V_tcp_do_prr) {
+ if (IN_FASTRECOVERY(tp->t_flags)) {
+ tp->t_dupacks = 0;
+ break;
+ }
+ }
if (tp->t_flags & TF_SACK_PERMIT) {
if (IN_FASTRECOVERY(tp->t_flags)) {
tp->t_dupacks = 0;
@@ -2518,6 +2580,15 @@ tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so,
cc_ack_received(tp, th, CC_DUPACK);
tcp_timer_activate(tp, TT_REXMT, 0);
tp->t_rtttime = 0;
+ if (V_tcp_do_prr) {
+ /*
+ * snd_ssthresh is already updated by cc_cong_signal.
+ */
+ tp->prr_delivered = 0;
+ tp->prr_out = 0;
+ if(!(tp->recover_fs = tp->snd_nxt - tp->snd_una))
+ tp->recover_fs = 1;
+ }
if (tp->t_flags & TF_SACK_PERMIT) {
TCPSTAT_INC(
tcps_sack_recovery_episode);
@@ -2614,7 +2685,9 @@ tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so,
*/
if (IN_FASTRECOVERY(tp->t_flags)) {
if (SEQ_LT(th->th_ack, tp->snd_recover)) {
- if (tp->t_flags & TF_SACK_PERMIT)
+ if (V_tcp_do_prr && (tp->t_flags & TF_SACK_PERMIT))
+ tcp_prr_partial_ack(tp, th);
+ else if (tp->t_flags & TF_SACK_PERMIT)
tcp_sack_partialack(tp, th);
else
tcp_newreno_partial_ack(tp, th);
@@ -3692,6 +3765,57 @@ tcp_mssopt(struct in_conninfo *inc)
return (mss);
}
+static void
+tcp_prr_partial_ack(struct tcpcb *tp, struct tcphdr *th)
+{
+ long snd_cnt = 0, limit = 0, del_data = 0, pipe = 0;
+
+ INP_WLOCK_ASSERT(tp->t_inpcb);
+
+ tcp_timer_activate(tp, TT_REXMT, 0);
+ tp->t_rtttime = 0;
+ /*
+ * Compute amount of data that this ACK is indicating (del_data)
+ * and an estimate of how many bytes are in the network.
+ */
+ if (SEQ_GEQ(th->th_ack,tp->snd_una))
+ del_data = BYTES_THIS_ACK(tp, th);
+ del_data += tp->diff_in_sack;
+ pipe = (tp->snd_nxt - tp->snd_fack) + tp->sackhint.sack_bytes_rexmit;
+ tp->prr_delivered += del_data;
+ /*
+ * Proportional Rate Reduction
+ */
+ if (pipe > tp->snd_ssthresh)
+ snd_cnt = (tp->prr_delivered * tp->snd_ssthresh / tp->recover_fs) -
+ tp->prr_out;
+ else {
+ if (V_tcp_do_prr_conservative)
+ limit = tp->prr_delivered - tp->prr_out;
+ else
+ if ((tp->prr_delivered - tp->prr_out) > del_data)
+ limit = tp->prr_delivered - tp->prr_out + tp->t_maxseg;
+ else
+ limit = del_data + tp->t_maxseg;
+ if ((tp->snd_ssthresh - pipe) < limit)
+ snd_cnt = tp->snd_ssthresh - pipe;
+ else
+ snd_cnt = limit;
+ }
+ snd_cnt = (snd_cnt / tp->t_maxseg);
+ if (snd_cnt < 0)
+ snd_cnt = 0;
+ /*
+ * Send snd_cnt new data into the network
+ * in response to this ack.
+ * If there is gonna be a SACK retransmission,
+ * adjust snd_cwnd accordingly.
+ */
+ tp->snd_cwnd = tp->snd_nxt - tp->sack_newdata +
+ tp->sackhint.sack_bytes_rexmit + (snd_cnt * tp->t_maxseg);
+ tp->t_flags |= TF_ACKNOW;
+ (void) tcp_output(tp);
+}
/*
* On a partial ack arrives, force the retransmission of the
diff --git a/sys/netinet/tcp_output.c b/sys/netinet/tcp_output.c
index 00d5415..7b4936d 100644
--- a/sys/netinet/tcp_output.c
+++ b/sys/netinet/tcp_output.c
@@ -1194,6 +1194,8 @@ send:
((so->so_options & SO_DONTROUTE) ? IP_ROUTETOIF : 0),
NULL, NULL, tp->t_inpcb);
+ if (V_tcp_do_prr && IN_FASTRECOVERY(tp->t_flags))
+ tp->prr_out += len;
if (error == EMSGSIZE && ro.ro_rt != NULL)
mtu = ro.ro_rt->rt_rmx.rmx_mtu;
RO_RTFREE(&ro);
@@ -1232,6 +1234,8 @@ send:
((so->so_options & SO_DONTROUTE) ? IP_ROUTETOIF : 0), 0,
tp->t_inpcb);
+ if (V_tcp_do_prr && IN_FASTRECOVERY(tp->t_flags))
+ tp->prr_out += len;
if (error == EMSGSIZE && ro.ro_rt != NULL)
mtu = ro.ro_rt->rt_rmx.rmx_mtu;
RO_RTFREE(&ro);
@@ -1323,6 +1327,8 @@ timer:
* XXX: It is a POLA question whether calling tcp_drop right
* away would be the really correct behavior instead.
*/
+ if (V_tcp_do_prr && IN_FASTRECOVERY(tp->t_flags))
+ tp->prr_out -= len;
if (((tp->t_flags & TF_FORCEDATA) == 0 ||
!tcp_timer_active(tp, TT_PERSIST)) &&
((flags & TH_SYN) == 0) &&
diff --git a/sys/netinet/tcp_sack.c b/sys/netinet/tcp_sack.c
index 440bd64..800df2f 100644
--- a/sys/netinet/tcp_sack.c
+++ b/sys/netinet/tcp_sack.c
@@ -348,9 +348,10 @@ tcp_sackhole_remove(struct tcpcb *tp, struct sackhole *hole)
void
tcp_sack_doack(struct tcpcb *tp, struct tcpopt *to, tcp_seq th_ack)
{
- struct sackhole *cur, *temp;
+ struct sackhole *cur, *temp, *temp1;
struct sackblk sack, sack_blocks[TCP_MAX_SACK + 1], *sblkp;
int i, j, num_sack_blks;
+ tcp_seq old = 0, new = 0;
INP_WLOCK_ASSERT(tp->t_inpcb);
@@ -382,13 +383,25 @@ tcp_sack_doack(struct tcpcb *tp, struct tcpopt *to, tcp_seq th_ack)
sack_blocks[num_sack_blks++] = sack;
}
}
+ if (TAILQ_EMPTY(&tp->snd_holes))
+ /*
+ * Empty scoreboard. Need to initialize snd_fack (it may be
+ * uninitialized or have a bogus value). Scoreboard holes
+ * (from the sack blocks received) are created later below
+ * (in the logic that adds holes to the tail of the
+ * scoreboard).
+ */
+ tp->snd_fack = SEQ_MAX(tp->snd_una, th_ack);
/*
* Return if SND.UNA is not advanced and no valid SACK block is
- * received.
+ * received.If no new valid SACK block the scoreboard remains
+ * the same, i.e. the difference is 0.
*/
- if (num_sack_blks == 0)
+ if (num_sack_blks == 0){
+ if (V_tcp_do_prr)
+ tp->diff_in_sack = 0;
return;
-
+ }
/*
* Sort the SACK blocks so we can update the scoreboard with just one
* pass. The overhead of sorting upto 4+1 elements is less than
@@ -403,15 +416,14 @@ tcp_sack_doack(struct tcpcb *tp, struct tcpopt *to, tcp_seq th_ack)
}
}
}
- if (TAILQ_EMPTY(&tp->snd_holes))
- /*
- * Empty scoreboard. Need to initialize snd_fack (it may be
- * uninitialized or have a bogus value). Scoreboard holes
- * (from the sack blocks received) are created later below
- * (in the logic that adds holes to the tail of the
- * scoreboard).
- */
- tp->snd_fack = SEQ_MAX(tp->snd_una, th_ack);
+ if (V_tcp_do_prr)
+ if(!TAILQ_EMPTY(&tp->snd_holes))
+ TAILQ_FOREACH(temp, &tp->snd_holes, scblink) {
+ if ((temp1 = TAILQ_NEXT(temp, scblink)) != NULL)
+ old += temp1->start - temp->end;
+ else if (SEQ_GT(tp->snd_fack, temp->end))
+ old += tp->snd_fack - temp->end;
+ }
/*
* In the while-loop below, incoming SACK blocks (sack_blocks[]) and
* SACK holes (snd_holes) are traversed from their tails with just
@@ -540,6 +552,19 @@ tcp_sack_doack(struct tcpcb *tp, struct tcpopt *to, tcp_seq th_ack)
else
sblkp--;
}
+ /*
+ * Calculate number of bytes in the scoreboard.
+ */
+ if (V_tcp_do_prr)
+ if (!TAILQ_EMPTY(&tp->snd_holes))
+ TAILQ_FOREACH(temp, &tp->snd_holes, scblink) {
+ if ((temp1 = TAILQ_NEXT(temp, scblink)) != NULL)
+ new += temp1->start - temp->end;
+ else if (SEQ_GT(tp->snd_fack, temp->end))
+ new += tp->snd_fack - temp->end;
+ }
+ /* Change in the scoreboard in # of bytes */
+ tp->diff_in_sack = new - old;
}
/*
diff --git a/sys/netinet/tcp_subr.c b/sys/netinet/tcp_subr.c
index 5d37b50..089d8c6 100644
--- a/sys/netinet/tcp_subr.c
+++ b/sys/netinet/tcp_subr.c
@@ -801,6 +801,7 @@ tcp_newtcpcb(struct inpcb *inp)
tp->t_rxtcur = TCPTV_RTOBASE;
tp->snd_cwnd = TCP_MAXWIN << TCP_MAX_WINSHIFT;
tp->snd_ssthresh = TCP_MAXWIN << TCP_MAX_WINSHIFT;
+ tp->diff_in_sack = 0;
tp->t_rcvtime = ticks;
/*
* IPv4 TTL initialization is necessary for an IPv6 socket as well,
diff --git a/sys/netinet/tcp_var.h b/sys/netinet/tcp_var.h
index aaaa4a4..fe1507e 100644
--- a/sys/netinet/tcp_var.h
+++ b/sys/netinet/tcp_var.h
@@ -161,6 +161,11 @@ struct tcpcb {
u_long t_rttupdated; /* number of times rtt sampled */
u_long max_sndwnd; /* largest window peer has offered */
+ tcp_seq prr_delivered; /* Total bytes delivered during PRR recovery */
+ tcp_seq prr_out; /* Total bytes sent during PRR recovery */
+ tcp_seq recover_fs; /* FlightSize at the start of PRR recovery */
+ tcp_seq diff_in_sack; /* (Signed) Difference of data in scoreboard due to the current ACK */
+
int t_softerror; /* possible error not yet reported */
/* out-of-band data */
char t_oobflags; /* have some */
@@ -174,6 +179,7 @@ struct tcpcb {
u_int32_t ts_offset; /* our timestamp offset */
tcp_seq last_ack_sent;
+
/* experimental */
u_long snd_cwnd_prev; /* cwnd prior to retransmit */
u_long snd_ssthresh_prev; /* ssthresh prior to retransmit */
@@ -627,8 +633,10 @@ VNET_DECLARE(int, tcp_abc_l_var);
#define V_tcp_abc_l_var VNET(tcp_abc_l_var)
VNET_DECLARE(int, tcp_do_sack); /* SACK enabled/disabled */
+VNET_DECLARE(int, tcp_do_prr); /* PRR enabled/disabled */
VNET_DECLARE(int, tcp_sc_rst_sock_fail); /* RST on sock alloc failure */
#define V_tcp_do_sack VNET(tcp_do_sack)
+#define V_tcp_do_prr VNET(tcp_do_prr)
#define V_tcp_sc_rst_sock_fail VNET(tcp_sc_rst_sock_fail)
VNET_DECLARE(int, tcp_do_ecn); /* TCP ECN enabled/disabled */
--Apple-Mail=_E3102E34-B41D-47A0-AB2F-5E03D718EBE4
Content-Disposition: attachment;
filename=newcwv.patch
Content-Type: application/octet-stream;
name="newcwv.patch"
Content-Transfer-Encoding: 7bit
diff --git a/sys/netinet/tcp_input.c b/sys/netinet/tcp_input.c
index 75609fd..0d11d9f 100644
--- a/sys/netinet/tcp_input.c
+++ b/sys/netinet/tcp_input.c
@@ -145,6 +145,12 @@ SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, drop_synfin, CTLFLAG_RW,
&VNET_NAME(drop_synfin), 0,
"Drop TCP packets with SYN+FIN set");
+VNET_DEFINE(int, tcp_do_ncwv) = 0;
+#define V_tcp_do_ncwv VNET(tcp_do_ncwv)
+SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, do_ncwv, CTLFLAG_RW,
+ &VNET_NAME(tcp_do_ncwv), 0,
+ "Do New-CWV targeted to rate-limited applications");
+
VNET_DEFINE(int, tcp_do_rfc3042) = 1;
#define V_tcp_do_rfc3042 VNET(tcp_do_rfc3042)
SYSCTL_VNET_INT(_net_inet_tcp, OID_AUTO, rfc3042, CTLFLAG_RW,
@@ -228,6 +234,7 @@ static void tcp_dropwithreset(struct mbuf *, struct tcphdr *,
static void tcp_pulloutofband(struct socket *,
struct tcphdr *, struct mbuf *, int);
static void tcp_xmit_timer(struct tcpcb *, int);
+static void ncwv_check_phase(struct tcpcb *, struct tcphdr *);
static void tcp_newreno_partial_ack(struct tcpcb *, struct tcphdr *);
static void inline tcp_fields_to_host(struct tcphdr *);
#ifdef TCP_SIGNATURE
@@ -289,6 +296,7 @@ static void inline
cc_ack_received(struct tcpcb *tp, struct tcphdr *th, uint16_t type)
{
INP_WLOCK_ASSERT(tp->t_inpcb);
+ int use_cc_algo=1;
tp->ccv->bytes_this_ack = BYTES_THIS_ACK(tp, th);
if (tp->snd_cwnd <= tp->snd_wnd)
@@ -310,7 +318,12 @@ cc_ack_received(struct tcpcb *tp, struct tcphdr *th, uint16_t type)
}
}
- if (CC_ALGO(tp)->ack_received != NULL) {
+ if (V_tcp_do_ncwv) {
+ ncwv_check_phase(tp,th);
+ if (!IN_VALPHASE(tp->t_flags))
+ use_cc_algo = 0;
+ }
+ if (use_cc_algo && CC_ALGO(tp)->ack_received != NULL) {
/* XXXLAS: Find a way to live without this */
tp->ccv->curack = th->th_ack;
CC_ALGO(tp)->ack_received(tp->ccv, type);
@@ -384,6 +397,10 @@ cc_conn_init(struct tcpcb *tp)
tp->snd_cwnd = 4 * tp->t_maxseg;
}
+ if (V_tcp_do_ncwv) {
+ tp->max_ack_prev = tp->iss;
+ tp->IW = tp->snd_cwnd;
+ }
if (CC_ALGO(tp)->conn_init != NULL)
CC_ALGO(tp)->conn_init(tp->ccv);
}
@@ -433,6 +450,28 @@ cc_cong_signal(struct tcpcb *tp, struct tcphdr *th, uint32_t type)
break;
}
+ /*
+ *Exit the NVP, that means, stop the 5 min counter.
+ *Flag on unset and stopped timer means that
+ *we have exited the NVP. Set pipeAck to max value.
+ *Record Flightsize so as to use it at the end
+ *of the congestion.
+ */
+ if (V_tcp_do_ncwv && type != CC_DUPACK && type != CC_RTO_ERR) {
+ /*
+ *Exit the NVP, that means, stop the 5 min counter.
+ *Flag on unset and stopped timer means that
+ *we have exited the NVP. Set pipeAck to max value.
+ *Record Flightsize so as to use it at the end
+ *of the congestion.
+ */
+ tp->lossflightsize = tp->snd_max - tp->snd_una;
+ tcp_timer_activate(tp, TT_NVP, 0);
+ EXIT_VALPHASE(tp->t_flags);
+ tp->pipeack = TCP_MAXWIN << TCP_MAX_WINSHIFT;
+ if(type != CC_RTO)
+ tp->snd_cwnd = min(tp->snd_cwnd/2,max(tp->pipeack,tp->lossflightsize));
+ }
if (CC_ALGO(tp)->cong_signal != NULL) {
if (th != NULL)
tp->ccv->curack = th->th_ack;
@@ -451,6 +490,16 @@ cc_post_recovery(struct tcpcb *tp, struct tcphdr *th)
tp->ccv->curack = th->th_ack;
CC_ALGO(tp)->post_recovery(tp->ccv);
}
+ if (V_tcp_do_ncwv)
+ /*
+ * Fast recovery will conclude after returning from this
+ * function. Reset the cwin to the value specified by the draft,
+ * cwnd = ((FlightSize - R)/2), if SACK is used, standard behaviour
+ * otherwise and also reset pipeACK
+ */
+ tp->pipeack = TCP_MAXWIN << TCP_MAX_WINSHIFT;
+ if ((tp->t_flags & TF_SACK_PERMIT))
+ tp->snd_cwnd = (tp->lossflightsize - tp->sackhint.sack_bytes_rexmit) / 2;
/* XXXLAS: EXIT_RECOVERY ? */
tp->t_bytes_acked = 0;
}
@@ -3692,6 +3741,30 @@ tcp_mssopt(struct in_conninfo *inc)
return (mss);
}
+/*
+ * Check whether the sender lies in the Validated or
+ * non-Validate period.
+ */
+static void
+ncwv_check_phase(struct tcpcb *tp, struct tcphdr *th)
+{
+ INP_WLOCK_ASSERT(tp->t_inpcb);
+
+ if (th->th_ack >= tp->max_ack_prev) {
+ tp->pipeack = tp->snd_max - tp->snd_una;
+ tp->max_ack_prev = th->th_ack;
+ tcp_timer_activate(tp, TT_PACK, max(3*tp->t_srtt,1000));
+ }
+ if (tp->pipeack >= (tp->snd_cwnd / 2)){
+ ENTER_VALPHASE(tp->t_flags);
+ if(tcp_timer_active(tp, TT_NVP))
+ tcp_timer_activate(tp, TT_NVP, 0);
+ } else {
+ EXIT_VALPHASE(tp->t_flags);
+ if(!tcp_timer_active(tp, TT_NVP))
+ tcp_timer_activate(tp, TT_NVP, 300000);
+ }
+}
/*
* On a partial ack arrives, force the retransmission of the
diff --git a/sys/netinet/tcp_output.c b/sys/netinet/tcp_output.c
index 00d5415..fc37006 100644
--- a/sys/netinet/tcp_output.c
+++ b/sys/netinet/tcp_output.c
@@ -158,8 +158,10 @@ cc_after_idle(struct tcpcb *tp)
{
INP_WLOCK_ASSERT(tp->t_inpcb);
- if (CC_ALGO(tp)->after_idle != NULL)
+ if (!V_tcp_do_ncwv && CC_ALGO(tp)->after_idle != NULL)
CC_ALGO(tp)->after_idle(tp->ccv);
+ else if(V_tcp_do_ncwv)
+ tp->pipeack = 0;
}
/*
diff --git a/sys/netinet/tcp_subr.c b/sys/netinet/tcp_subr.c
index 5d37b50..bd4151e 100644
--- a/sys/netinet/tcp_subr.c
+++ b/sys/netinet/tcp_subr.c
@@ -783,6 +783,8 @@ tcp_newtcpcb(struct inpcb *inp)
callout_init(&tp->t_timers->tt_keep, CALLOUT_MPSAFE);
callout_init(&tp->t_timers->tt_2msl, CALLOUT_MPSAFE);
callout_init(&tp->t_timers->tt_delack, CALLOUT_MPSAFE);
+ callout_init(&tp->t_timers->tt_nvp, CALLOUT_MPSAFE);
+ callout_init(&tp->t_timers->tt_pack, CALLOUT_MPSAFE);
if (V_tcp_do_rfc1323)
tp->t_flags = (TF_REQ_SCALE|TF_REQ_TSTMP);
@@ -802,6 +804,10 @@ tcp_newtcpcb(struct inpcb *inp)
tp->snd_cwnd = TCP_MAXWIN << TCP_MAX_WINSHIFT;
tp->snd_ssthresh = TCP_MAXWIN << TCP_MAX_WINSHIFT;
tp->t_rcvtime = ticks;
+ if (V_tcp_do_ncwv) {
+ tp->lossflightsize = 0;
+ tp->pipeack = TCP_MAXWIN << TCP_MAX_WINSHIFT;
+ }
/*
* IPv4 TTL initialization is necessary for an IPv6 socket as well,
* because the socket may be bound to an IPv6 wildcard address,
@@ -931,6 +937,8 @@ tcp_discardcb(struct tcpcb *tp)
callout_stop(&tp->t_timers->tt_keep);
callout_stop(&tp->t_timers->tt_2msl);
callout_stop(&tp->t_timers->tt_delack);
+ callout_stop(&tp->t_timers->tt_nvp);
+ callout_stop(&tp->t_timers->tt_pack);
/*
* If we got enough samples through the srtt filter,
diff --git a/sys/netinet/tcp_timer.c b/sys/netinet/tcp_timer.c
index 7c27397..a4f211f 100644
--- a/sys/netinet/tcp_timer.c
+++ b/sys/netinet/tcp_timer.c
@@ -646,6 +646,54 @@ out:
}
void
+tcp_timer_nvp(void * xtp)
+{
+ struct tcpcb *tp = xtp;
+ struct inpcb *inp;
+ CURVNET_SET(tp->t_vnet);
+ INP_INFO_WLOCK(&V_tcbinfo);
+ inp = tp->t_inpcb;
+ if (inp == NULL) {
+ tcp_timer_race++;
+ INP_INFO_WUNLOCK(&V_tcbinfo);
+ CURVNET_RESTORE();
+ return;
+ }
+ INP_WLOCK(inp);
+ callout_deactivate(&tp->t_timers->tt_nvp);
+ tp->snd_cwnd = max(tp->snd_cwnd / 2 , tp->IW );
+ tp->snd_ssthresh = max(tp->snd_ssthresh, 3 * tp->snd_cwnd /4);
+ if (tp != NULL)
+ INP_WUNLOCK(inp);
+ INP_INFO_WUNLOCK(&V_tcbinfo);
+ CURVNET_RESTORE();
+}
+
+void
+tcp_timer_pack(void * xtp)
+{
+ struct tcpcb *tp = xtp;
+ struct inpcb *inp;
+ CURVNET_SET(tp->t_vnet);
+ INP_INFO_WLOCK(&V_tcbinfo);
+ inp = tp->t_inpcb;
+ if (inp == NULL) {
+ tcp_timer_race++;
+ INP_INFO_WUNLOCK(&V_tcbinfo);
+ CURVNET_RESTORE();
+ return;
+ }
+ INP_WLOCK(inp);
+ callout_deactivate(&tp->t_timers->tt_pack);
+ tp->snd_cwnd = max(tp->snd_cwnd / 2, tp->IW );
+ tp->snd_ssthresh = max(tp->snd_ssthresh, 3 * tp->snd_cwnd /4);
+ if (tp != NULL)
+ INP_WUNLOCK(inp);
+ INP_INFO_WUNLOCK(&V_tcbinfo);
+ CURVNET_RESTORE();
+}
+
+void
tcp_timer_activate(struct tcpcb *tp, int timer_type, u_int delta)
{
struct callout *t_callout;
@@ -679,6 +727,14 @@ tcp_timer_activate(struct tcpcb *tp, int timer_type, u_int delta)
t_callout = &tp->t_timers->tt_2msl;
f_callout = tcp_timer_2msl;
break;
+ case TT_NVP:
+ t_callout = &tp->t_timers->tt_nvp;
+ f_callout = tcp_timer_nvp;
+ break;
+ case TT_PACK:
+ t_callout = &tp->t_timers->tt_pack;
+ f_callout = tcp_timer_pack;
+ break;
default:
panic("bad timer_type");
}
@@ -710,6 +766,12 @@ tcp_timer_active(struct tcpcb *tp, int timer_type)
case TT_2MSL:
t_callout = &tp->t_timers->tt_2msl;
break;
+ case TT_NVP:
+ t_callout = &tp->t_timers->tt_nvp;
+ break;
+ case TT_PACK:
+ t_callout = &tp->t_timers->tt_pack;
+ break;
default:
panic("bad timer_type");
}
@@ -738,5 +800,9 @@ tcp_timer_to_xtimer(struct tcpcb *tp, struct tcp_timer *timer,
xtimer->tt_keep = (timer->tt_keep.c_time - now) / SBT_1MS;
if (callout_active(&timer->tt_2msl))
xtimer->tt_2msl = (timer->tt_2msl.c_time - now) / SBT_1MS;
+ if (callout_active(&timer->tt_nvp))
+ xtimer->tt_nvp = ticks_to_msecs(timer->tt_nvp.c_time - ticks);
+ if (callout_active(&timer->tt_pack))
+ xtimer->tt_pack = ticks_to_msecs(timer->tt_pack.c_time - ticks);
xtimer->t_rcvtime = ticks_to_msecs(ticks - tp->t_rcvtime);
}
diff --git a/sys/netinet/tcp_timer.h b/sys/netinet/tcp_timer.h
index 3115fb3..7d038e8 100644
--- a/sys/netinet/tcp_timer.h
+++ b/sys/netinet/tcp_timer.h
@@ -146,12 +146,16 @@ struct tcp_timer {
struct callout tt_keep; /* keepalive */
struct callout tt_2msl; /* 2*msl TIME_WAIT timer */
struct callout tt_delack; /* delayed ACK timer */
+ struct callout tt_nvp; /* non validated timer period */
+ struct callout tt_pack; /* timer for pipeack measurement */
};
#define TT_DELACK 0x01
#define TT_REXMT 0x02
#define TT_PERSIST 0x04
#define TT_KEEP 0x08
#define TT_2MSL 0x10
+#define TT_NVP 0x20
+#define TT_PACK 0x40
#define TP_KEEPINIT(tp) ((tp)->t_keepinit ? (tp)->t_keepinit : tcp_keepinit)
#define TP_KEEPIDLE(tp) ((tp)->t_keepidle ? (tp)->t_keepidle : tcp_keepidle)
@@ -183,6 +187,8 @@ void tcp_timer_keep(void *xtp);
void tcp_timer_persist(void *xtp);
void tcp_timer_rexmt(void *xtp);
void tcp_timer_delack(void *xtp);
+void tcp_timer_nvp(void *xtp);
+void tcp_timer_pack(void *xtp);
void tcp_timer_to_xtimer(struct tcpcb *tp, struct tcp_timer *timer,
struct xtcp_timer *xtimer);
diff --git a/sys/netinet/tcp_var.h b/sys/netinet/tcp_var.h
index aaaa4a4..c8c148f 100644
--- a/sys/netinet/tcp_var.h
+++ b/sys/netinet/tcp_var.h
@@ -137,7 +137,7 @@ struct tcpcb {
* for slow start exponential to
* linear switch
*/
- u_long snd_spare2; /* unused */
+ u_long IW; /* initial cong window */
tcp_seq snd_recover; /* for use in NewReno Fast Recovery */
u_int t_maxopd; /* mss plus options */
@@ -147,8 +147,9 @@ struct tcpcb {
u_int t_rtttime; /* RTT measurement start time */
tcp_seq t_rtseq; /* sequence number being timed */
- u_int t_bw_spare1; /* unused */
- tcp_seq t_bw_spare2; /* unused */
+ u_long lossflightsize; /* flightsize at the beggining of current recovery event */
+ u_long pipeack; /* amount of data acked per RTT */
+ tcp_seq max_ack_prev; /* caching of previous value of snd_max when rtt was measured */
int t_rxtcur; /* current retransmit value (ticks) */
u_int t_maxseg; /* maximum segment size */
@@ -247,6 +248,11 @@ struct tcpcb {
#define TF_ECN_SND_ECE 0x10000000 /* ECN ECE in queue */
#define TF_CONGRECOVERY 0x20000000 /* congestion recovery mode */
#define TF_WASCRECOVERY 0x40000000 /* was in congestion recovery */
+#define TF_RLIMPHASE 0x80000000 /* ncwv phase */
+
+#define IN_VALPHASE(t_flags) (t_flags & TF_RLIMPHASE)
+#define ENTER_VALPHASE(t_flags) t_flags |= TF_RLIMPHASE
+#define EXIT_VALPHASE(t_flags) t_flags &= ~TF_RLIMPHASE
#define IN_FASTRECOVERY(t_flags) (t_flags & TF_FASTRECOVERY)
#define ENTER_FASTRECOVERY(t_flags) t_flags |= TF_FASTRECOVERY
@@ -561,6 +567,8 @@ struct xtcp_timer {
int tt_keep; /* keepalive */
int tt_2msl; /* 2*msl TIME_WAIT timer */
int tt_delack; /* delayed ACK timer */
+ int tt_nvp; /* non-Validation period timer */
+ int tt_pack; /* pipeack sample timer */
int t_rcvtime; /* Time since last packet received */
};
struct xtcpcb {
@@ -627,8 +635,10 @@ VNET_DECLARE(int, tcp_abc_l_var);
#define V_tcp_abc_l_var VNET(tcp_abc_l_var)
VNET_DECLARE(int, tcp_do_sack); /* SACK enabled/disabled */
+VNET_DECLARE(int, tcp_do_ncwv); /* New-CWV enabled/disabled */
VNET_DECLARE(int, tcp_sc_rst_sock_fail); /* RST on sock alloc failure */
#define V_tcp_do_sack VNET(tcp_do_sack)
+#define V_tcp_do_ncwv VNET(tcp_do_ncwv)
#define V_tcp_sc_rst_sock_fail VNET(tcp_sc_rst_sock_fail)
VNET_DECLARE(int, tcp_do_ecn); /* TCP ECN enabled/disabled */
--Apple-Mail=_E3102E34-B41D-47A0-AB2F-5E03D718EBE4
Content-Transfer-Encoding: 7bit
Content-Type: text/plain;
charset=us-ascii
--Apple-Mail=_E3102E34-B41D-47A0-AB2F-5E03D718EBE4--
--Apple-Mail=_5088A38A-DF43-450D-9E03-31C51BD176C7
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment; filename="signature.asc"
Content-Type: application/pgp-signature; name="signature.asc"
Content-Description: Message signed with OpenPGP using GPGMail
-----BEGIN PGP SIGNATURE-----
iQCVAwUBUvC1ENZcnpRveo1xAQKL0AQApMvaMxZPDSPEuEkTD2YRg8Q0YSYiSS7I
PT0PE/sOUZ8k9kx2K78APzb8uZ3rnBnvhi9sRskd1m0iWHwTROnbKbkxz6PVQSHQ
L7OCcUbAZkHGI/t3NTpxAPS5b8MZs81OUpjKFezJvnU3qvXObsN81Oh5u/eUZB2A
p259UbG6SaY=
=pyap
-----END PGP SIGNATURE-----
--Apple-Mail=_5088A38A-DF43-450D-9E03-31C51BD176C7--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?259C9434-C6FE-42EA-823D-ECB024DBF3D7>