* [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm
@ 2014-05-12 20:59 Florian Westphal
2014-05-12 20:59 ` [PATCH 1/5] net: tcp: assign tcp cong_ops when tcp sk is created Florian Westphal
` (5 more replies)
0 siblings, 6 replies; 15+ messages in thread
From: Florian Westphal @ 2014-05-12 20:59 UTC (permalink / raw)
To: netdev
This patch series adds support for the Datacenter TCP (DCTCP) congestion
control algorithm.
Please see individual patches' changelog for the details. A summary
of DCTCP and test results can be found in patch 5.
Joint work with Daniel Borkmann and Glenn Judd.
Daniel Borkmann (2):
net: tcp: add flag for ca to indicate that ECN is required
net: tcp: add DCTCP congestion algorithm
Florian Westphal (3):
net: tcp: assign tcp cong_ops when tcp sk is created
net: tcp: split ack slow/fast events from cwnd_event
net: tcp: more detailed ACK events, and events for CE marked packets
Documentation/networking/dctcp.txt | 232 +++++++++++++++++++++++++++
include/net/tcp.h | 70 ++++++---
net/ipv4/Kconfig | 28 +++-
net/ipv4/Makefile | 1 +
net/ipv4/tcp.c | 2 +-
net/ipv4/tcp_cong.c | 24 ++-
net/ipv4/tcp_dctcp.c | 311 +++++++++++++++++++++++++++++++++++++
net/ipv4/tcp_input.c | 30 +++-
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_minisocks.c | 2 +-
net/ipv4/tcp_output.c | 14 +-
net/ipv4/tcp_westwood.c | 30 ++--
net/ipv6/tcp_ipv6.c | 2 +-
13 files changed, 690 insertions(+), 58 deletions(-)
create mode 100644 Documentation/networking/dctcp.txt
create mode 100644 net/ipv4/tcp_dctcp.c
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCH 1/5] net: tcp: assign tcp cong_ops when tcp sk is created
2014-05-12 20:59 [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm Florian Westphal
@ 2014-05-12 20:59 ` Florian Westphal
2014-05-12 20:59 ` [PATCH 2/5] net: tcp: add flag for ca to indicate that ECN is required Florian Westphal
` (4 subsequent siblings)
5 siblings, 0 replies; 15+ messages in thread
From: Florian Westphal @ 2014-05-12 20:59 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal, Daniel Borkmann, Glenn Judd
Split assignment and initialization from one into two functions.
This is required by followup patches that add Datacenter TCP
(DCTCP) congestion control algorithm - we need to be able to
determine if the connection is moderated by DCTCP before the
3WHS has finished.
Joint work with Daniel Borkmann and Glenn Judd.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/tcp.h | 10 +++++++++-
net/ipv4/tcp.c | 2 +-
net/ipv4/tcp_cong.c | 24 ++++++++++--------------
net/ipv4/tcp_minisocks.c | 2 +-
4 files changed, 21 insertions(+), 17 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3c94184..8ae165f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -815,7 +815,7 @@ struct tcp_congestion_ops {
int tcp_register_congestion_control(struct tcp_congestion_ops *type);
void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
-void tcp_init_congestion_control(struct sock *sk);
+void tcp_assign_congestion_control(struct sock *sk);
void tcp_cleanup_congestion_control(struct sock *sk);
int tcp_set_default_congestion_control(const char *name);
void tcp_get_default_congestion_control(char *name);
@@ -831,6 +831,14 @@ u32 tcp_reno_ssthresh(struct sock *sk);
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;
+static inline void tcp_init_congestion_control(struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ca_ops->init)
+ icsk->icsk_ca_ops->init(sk);
+}
+
static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
{
struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index eb1dde3..f3ff83d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -405,7 +405,7 @@ void tcp_init_sock(struct sock *sk)
tp->reordering = sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
- icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+ tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 7b09d8b..65609ac 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -74,27 +74,23 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
/* Assign choice of congestion control. */
-void tcp_init_congestion_control(struct sock *sk)
+void tcp_assign_congestion_control(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_congestion_ops *ca;
- /* if no choice made yet assign the current value set as default */
- if (icsk->icsk_ca_ops == &tcp_init_congestion_ops) {
- rcu_read_lock();
- list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
- if (try_module_get(ca->owner)) {
- icsk->icsk_ca_ops = ca;
- break;
- }
-
- /* fallback to next available */
+ rcu_read_lock();
+ list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
+ if (try_module_get(ca->owner)) {
+ icsk->icsk_ca_ops = ca;
+ goto out;
}
- rcu_read_unlock();
}
- if (icsk->icsk_ca_ops->init)
- icsk->icsk_ca_ops->init(sk);
+ icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+
+ out:
+ rcu_read_unlock();
}
/* Manage refcounts on socket close. */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 05c1b15..b810071 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -422,7 +422,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
!try_module_get(newicsk->icsk_ca_ops->owner))
- newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
+ tcp_assign_congestion_control(newsk);
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
--
1.8.1.5
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 2/5] net: tcp: add flag for ca to indicate that ECN is required
2014-05-12 20:59 [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm Florian Westphal
2014-05-12 20:59 ` [PATCH 1/5] net: tcp: assign tcp cong_ops when tcp sk is created Florian Westphal
@ 2014-05-12 20:59 ` Florian Westphal
2014-05-12 23:51 ` Eric Dumazet
2014-05-12 20:59 ` [PATCH 3/5] net: tcp: split ack slow/fast events from cwnd_event Florian Westphal
` (3 subsequent siblings)
5 siblings, 1 reply; 15+ messages in thread
From: Florian Westphal @ 2014-05-12 20:59 UTC (permalink / raw)
To: netdev; +Cc: Daniel Borkmann, Glenn Judd, Florian Westphal
From: Daniel Borkmann <dborkman@redhat.com>
This patch adds a flag to TCP congestion algorithms that allows
for requesting to mark IPv4/IPv6 sockets with transport as ECN
capable, that is, ECT(0), when required by a congestion algorithm.
It is currently used and needed in DataCenter TCP (DCTCP), as it
requires both peers to assert ECT on all IP packets sent - it
uses ECN feedback (i.e. CE, Congestion Encountered) from switches
inside the data center to derive feedback to the end hosts.
Therefore, simply add a new flag to icsk_ca_ops. Note that DCTCP's
algorithm/behaviour slightly diverges from RFC3168, therefore this
is only (!) enabled iff the assigned congestion control ops module
has requested this. By that, we can tightly couple this logic really
only to provided congestion control ops.
Joint work with Florian Westphal and Glenn Judd.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/tcp.h | 45 ++++++++++++++++++++++++++++-----------------
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_output.c | 9 ++++++++-
net/ipv6/tcp_ipv6.c | 2 +-
4 files changed, 38 insertions(+), 20 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8ae165f..92d1600 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -734,23 +734,6 @@ struct tcp_skb_cb {
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
-/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
- *
- * If we receive a SYN packet with these bits set, it means a network is
- * playing bad games with TOS bits. In order to avoid possible false congestion
- * notifications, we disable TCP ECN negociation.
- */
-static inline void
-TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
- struct net *net)
-{
- const struct tcphdr *th = tcp_hdr(skb);
-
- if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr &&
- INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield))
- inet_rsk(req)->ecn_ok = 1;
-}
-
/* Due to TSO, an SKB can be composed of multiple actual
* packets. To keep these tracked properly, we use this.
*/
@@ -783,6 +766,7 @@ enum tcp_ca_event {
#define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
#define TCP_CONG_NON_RESTRICTED 0x1
+#define TCP_CONG_NEEDS_ECN 0x2
struct tcp_congestion_ops {
struct list_head list;
@@ -848,6 +832,13 @@ static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
icsk->icsk_ca_state = ca_state;
}
+static inline bool tcp_ca_needs_ecn(const struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
+}
+
static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -856,6 +847,26 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
icsk->icsk_ca_ops->cwnd_event(sk, event);
}
+/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
+ *
+ * If we receive a SYN packet with these bits set, it means a network is
+ * playing bad games with TOS bits. In order to avoid possible false congestion
+ * notifications, we disable TCP ECN negociation.
+ */
+static inline void
+TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
+ const struct sock *listen_sk)
+{
+ const struct tcphdr *th = tcp_hdr(skb);
+ const struct net *net = sock_net(listen_sk);
+
+ if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr &&
+ (INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield) ||
+ tcp_ca_needs_ecn(listen_sk))) {
+ inet_rsk(req)->ecn_ok = 1;
+ }
+}
+
/* These functions determine how the current flow behaves in respect of SACK
* handling. SACK is negotiated with the peer, and therefore it can vary
* between different flows.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ad166dc..d7d9c54 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1512,7 +1512,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_free;
if (!want_cookie || tmp_opt.tstamp_ok)
- TCP_ECN_create_request(req, skb, sock_net(sk));
+ TCP_ECN_create_request(req, skb, sk);
if (want_cookie) {
isn = cookie_v4_init_sequence(sk, skb, &req->mss);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 694711a..1f983dd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -331,7 +331,8 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
tp->ecn_flags = 0;
- if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
+ if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+ tcp_ca_needs_ecn(sk)) {
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
tp->ecn_flags = TCP_ECN_OK;
}
@@ -953,6 +954,9 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
TCP_ECN_send(sk, skb, tcp_header_size);
+ if (tcp_ca_needs_ecn(sk))
+ INET_ECN_xmit(sk);
+
#ifdef CONFIG_TCP_MD5SIG
/* Calculate the MD5 hash, as we have all we need now */
if (md5) {
@@ -2860,6 +2864,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
th->doff = (tcp_header_size >> 2);
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
+ if (tcp_ca_needs_ecn(sk))
+ INET_ECN_xmit(sk);
+
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
if (md5) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7fa6743..b1c8765 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1013,7 +1013,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
if (!want_cookie || tmp_opt.tstamp_ok)
- TCP_ECN_create_request(req, skb, sock_net(sk));
+ TCP_ECN_create_request(req, skb, sk);
ireq->ir_iif = sk->sk_bound_dev_if;
--
1.8.1.5
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 3/5] net: tcp: split ack slow/fast events from cwnd_event
2014-05-12 20:59 [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm Florian Westphal
2014-05-12 20:59 ` [PATCH 1/5] net: tcp: assign tcp cong_ops when tcp sk is created Florian Westphal
2014-05-12 20:59 ` [PATCH 2/5] net: tcp: add flag for ca to indicate that ECN is required Florian Westphal
@ 2014-05-12 20:59 ` Florian Westphal
2014-05-12 20:59 ` [PATCH 4/5] net: tcp: more detailed ACK events, and events for CE marked packets Florian Westphal
` (2 subsequent siblings)
5 siblings, 0 replies; 15+ messages in thread
From: Florian Westphal @ 2014-05-12 20:59 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal, Daniel Borkmann, Glenn Judd
The congestion control ops "cwnd_event" currently supports
CA_EVENT_FAST_ACK and CA_EVENT_SLOW_ACK events (among others).
Both FAST and SLOW_ACK are only used by Westwood CC algorithm.
This removes both flags from cwnd_event and adds a new in_ack_event
callback for this.
The goal is to be able to provide more detailed information
about ACKs, such as whether ECE flag was set, or wheter the ACK
resulted in a window update.
It is required for DataCenter TCP (DCTCP) congestion control
algorithm as it makes a different choice depending on ECE being
set or not.
Joint work with Daniel Borkmann and Glenn Judd.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/tcp.h | 8 ++++++--
net/ipv4/tcp_input.c | 12 ++++++++++--
net/ipv4/tcp_westwood.c | 30 ++++++++++++++++--------------
3 files changed, 32 insertions(+), 18 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 92d1600..0d767d2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -754,8 +754,10 @@ enum tcp_ca_event {
CA_EVENT_CWND_RESTART, /* congestion window restart */
CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
CA_EVENT_LOSS, /* loss timeout */
- CA_EVENT_FAST_ACK, /* in sequence ack */
- CA_EVENT_SLOW_ACK, /* other ack */
+};
+
+enum tcp_ca_ack_event_flags {
+ CA_ACK_SLOWPATH = (1 << 0),
};
/*
@@ -785,6 +787,8 @@ struct tcp_congestion_ops {
void (*set_state)(struct sock *sk, u8 new_state);
/* call when cwnd event occurs (optional) */
void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
+ /* call when ack arrives (optional) */
+ void (*in_ack_event)(struct sock *sk, u32 flags);
/* new value of cwnd after loss (optional) */
u32 (*undo_cwnd)(struct sock *sk);
/* hook for packet ack accounting (optional) */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 350b207..7fab1da 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3356,6 +3356,14 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
}
}
+static inline void tcp_in_ack_event(struct sock *sk, u32 flags)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ca_ops->in_ack_event)
+ icsk->icsk_ca_ops->in_ack_event(sk, flags);
+}
+
/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
@@ -3413,7 +3421,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tp->snd_una = ack;
flag |= FLAG_WIN_UPDATE;
- tcp_ca_event(sk, CA_EVENT_FAST_ACK);
+ tcp_in_ack_event(sk, 0);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
} else {
@@ -3431,7 +3439,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
- tcp_ca_event(sk, CA_EVENT_SLOW_ACK);
+ tcp_in_ack_event(sk, CA_ACK_SLOWPATH);
}
/* We passed data and got it acked, remove any soft error
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index b94a04a..1c5b0df 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -222,39 +222,41 @@ static u32 tcp_westwood_bw_rttmin(const struct sock *sk)
return max_t(u32, (w->bw_est * w->rtt_min) / tp->mss_cache, 2);
}
+static void tcp_westwood_ack(struct sock *sk, u32 ack_flags)
+{
+ if (ack_flags & CA_ACK_SLOWPATH) {
+ struct westwood *w = inet_csk_ca(sk);
+
+ westwood_update_window(sk);
+ w->bk += westwood_acked_count(sk);
+
+ update_rtt_min(w);
+ return;
+ }
+
+ westwood_fast_bw(sk);
+}
+
static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
{
struct tcp_sock *tp = tcp_sk(sk);
struct westwood *w = inet_csk_ca(sk);
switch (event) {
- case CA_EVENT_FAST_ACK:
- westwood_fast_bw(sk);
- break;
-
case CA_EVENT_COMPLETE_CWR:
tp->snd_cwnd = tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
break;
-
case CA_EVENT_LOSS:
tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
/* Update RTT_min when next ack arrives */
w->reset_rtt_min = 1;
break;
-
- case CA_EVENT_SLOW_ACK:
- westwood_update_window(sk);
- w->bk += westwood_acked_count(sk);
- update_rtt_min(w);
- break;
-
default:
/* don't care */
break;
}
}
-
/* Extract info for Tcp socket info provided via netlink. */
static void tcp_westwood_info(struct sock *sk, u32 ext,
struct sk_buff *skb)
@@ -271,12 +273,12 @@ static void tcp_westwood_info(struct sock *sk, u32 ext,
}
}
-
static struct tcp_congestion_ops tcp_westwood __read_mostly = {
.init = tcp_westwood_init,
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_reno_cong_avoid,
.cwnd_event = tcp_westwood_event,
+ .in_ack_event = tcp_westwood_ack,
.get_info = tcp_westwood_info,
.pkts_acked = tcp_westwood_pkts_acked,
--
1.8.1.5
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 4/5] net: tcp: more detailed ACK events, and events for CE marked packets
2014-05-12 20:59 [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm Florian Westphal
` (2 preceding siblings ...)
2014-05-12 20:59 ` [PATCH 3/5] net: tcp: split ack slow/fast events from cwnd_event Florian Westphal
@ 2014-05-12 20:59 ` Florian Westphal
2014-05-13 4:41 ` Yuchung Cheng
2014-05-12 20:59 ` [PATCH 5/5] net: tcp: add DCTCP congestion control algorithm Florian Westphal
2014-05-12 22:01 ` [next PATCH 0/5] net: tcp: " Cong Wang
5 siblings, 1 reply; 15+ messages in thread
From: Florian Westphal @ 2014-05-12 20:59 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal, Daniel Borkmann, Glenn Judd
DataCenter TCP (DCTCP) determines cwnd growth based on ECN information
and ACK properties, e.g. ACK that updates window is treated differently
than DUPACK.
Also DCTCP needs information whether ACK was delayed ACK. Furthermore,
DCTCP also implements a CE state machine that keeps track of CE markings
of incoming packets.
Therefore, extend the congestion control framework to provide these
event types, so that DCTCP can be properly implemented as a normal
congestion algorithm module outside the core stack.
Joint work with Daniel Borkmann and Glenn Judd.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/tcp.h | 9 ++++++++-
net/ipv4/tcp_input.c | 22 ++++++++++++++++++----
net/ipv4/tcp_output.c | 4 ++++
3 files changed, 30 insertions(+), 5 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0d767d2..56bf383 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -754,10 +754,17 @@ enum tcp_ca_event {
CA_EVENT_CWND_RESTART, /* congestion window restart */
CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
CA_EVENT_LOSS, /* loss timeout */
+ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
+ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
+ CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */
+ CA_EVENT_NON_DELAYED_ACK,
};
+/* information about inbound ACK, passed to cong_ops->in_ack_event() */
enum tcp_ca_ack_event_flags {
- CA_ACK_SLOWPATH = (1 << 0),
+ CA_ACK_SLOWPATH = (1 << 0), /* in slow path processing */
+ CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */
+ CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */
};
/*
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7fab1da..bf0f734 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -232,14 +232,21 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *s
tcp_enter_quickack_mode((struct sock *)tp);
break;
case INET_ECN_CE:
+ if (tcp_ca_needs_ecn((struct sock *)tp))
+ tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+
if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
/* Better not delay acks, sender can have a very low cwnd */
tcp_enter_quickack_mode((struct sock *)tp);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
- /* fallinto */
+ tp->ecn_flags |= TCP_ECN_SEEN;
+ break;
default:
+ if (tcp_ca_needs_ecn((struct sock *)tp))
+ tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
tp->ecn_flags |= TCP_ECN_SEEN;
+ break;
}
}
@@ -3421,10 +3428,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tp->snd_una = ack;
flag |= FLAG_WIN_UPDATE;
- tcp_in_ack_event(sk, 0);
+ tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
} else {
+ u32 ack_ev_flags = CA_ACK_SLOWPATH;
+
if (ack_seq != TCP_SKB_CB(skb)->end_seq)
flag |= FLAG_DATA;
else
@@ -3436,10 +3445,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
&sack_rtt_us);
- if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
+ if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) {
flag |= FLAG_ECE;
+ ack_ev_flags |= CA_ACK_ECE;
+ }
+
+ if (flag & FLAG_WIN_UPDATE)
+ ack_ev_flags |= CA_ACK_WIN_UPDATE;
- tcp_in_ack_event(sk, CA_ACK_SLOWPATH);
+ tcp_in_ack_event(sk, ack_ev_flags);
}
/* We passed data and got it acked, remove any soft error
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1f983dd..1f5e04a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3119,6 +3119,8 @@ void tcp_send_delayed_ack(struct sock *sk)
int ato = icsk->icsk_ack.ato;
unsigned long timeout;
+ tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
+
if (ato > TCP_DELACK_MIN) {
const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ / 2;
@@ -3175,6 +3177,8 @@ void tcp_send_ack(struct sock *sk)
if (sk->sk_state == TCP_CLOSE)
return;
+ tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
+
/* We are not putting this on the write queue, so
* tcp_transmit_skb() will set the ownership to this
* sock.
--
1.8.1.5
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 5/5] net: tcp: add DCTCP congestion control algorithm
2014-05-12 20:59 [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm Florian Westphal
` (3 preceding siblings ...)
2014-05-12 20:59 ` [PATCH 4/5] net: tcp: more detailed ACK events, and events for CE marked packets Florian Westphal
@ 2014-05-12 20:59 ` Florian Westphal
2014-05-12 22:01 ` [next PATCH 0/5] net: tcp: " Cong Wang
5 siblings, 0 replies; 15+ messages in thread
From: Florian Westphal @ 2014-05-12 20:59 UTC (permalink / raw)
To: netdev; +Cc: Daniel Borkmann, Glenn Judd, Florian Westphal
From: Daniel Borkmann <dborkman@redhat.com>
This work adds the DataCenter TCP (DCTCP) congestion control
algorithm [1], which has been first published at SIGCOMM 2010 [2],
resp. follow-up analysis at SIGMETRICS 2011 [3]. Also, as an
informational IETF draft available at [5].
DCTCP is an enhancement to the TCP congestion control algorithm for
data center networks. Typical data center workloads are e.g.
i) partition/aggregate (queries; bursty, delay sensitive), ii) short
messages e.g. 50KB-1MB (for coordination and control state; delay
sensitive), and iii) large flows e.g. 1MB-100MB (data update;
throughput sensitive). DCTCP has therefore been designed for such
environments to provide/achieve the following three requirements:
* High burst tolerance (incast due to partition/aggregate)
* Low latency (short flows, queries)
* High throughput (continuous data updates, large file
transfers) with commodity, shallow buffered switches
The basic idea of its design consists of two fundamentals: i) on
the switch side, packets are being marked when its internal queue
length > K; ii) the sender side maintains a moving average of the
fraction of marked packets, so each RTT, F is being updated as
follows:
F := X / Y, where X is # of marked ACKs, Y is total # of ACKs
alpha := (1 - g) * alpha + g * F, where g is a smoothing constant
The resulting alpha is then being used in order to adaptively
decrease the congestion window W:
W := (1 - (alpha / 2)) * W
The means for receiving marked packets resp. marking them on switch
side in DCTCP is the use of ECN. RFC3168 describes a mechanism for
using Explicit Congestion Notification from the switch for early
detection of congestion, rather than waiting for segment loss to
occur. However, this method only detects the presence of congestion,
not the extent. In the presence of mild congestion, it reduces the
TCP congestion window too aggressively and unnecessarily affects
the throughput of long flows [5]. DCTCP, as mentioned, enhances
Explicit Congestion Notification (ECN) processing to estimate the
fraction of bytes that encounter congestion, rather than simply
detecting that some congestion has occurred. DCTCP then scales the
TCP congestion window based on this estimate [5], thus it can derive
multibit feedback from the information present in the single-bit
sequence of marks in its control law and act in *proportion* to
the extent of congestion, not its *presence*. Switches therefore set
the Congestion Experienced (CE) codepoint in packets when internal
queue lengths exceed threshold K. Resulting, DCTCP delivers the same
or better throughput than normal TCP, while using 90% less buffer
space. From the Stanford paper, it says that in handling workloads
derived from operational measurements [2], it was found that DCTCP
enables the applications to handle 10x the current background traffic,
without impacting foreground traffic. Moreover, a 10x increase in
foreground traffic did not cause any timeouts, and thus largely
eliminates incast problems [2].
The algorithm itself has already seen deployments in large production
data centers. We have carefully implemented this patch set and did a
long-term stress-test and analysis in a data center and have found
similar results that we have noted down into a documentation section.
Details can be found there, in short, summary of our TCP incast tests
with iperf compared to cubic:
1) Timeouts (total over all flows, and per flow summaries):
CUBIC DCTCP
Total 3227 25
Mean 169.8421053 1.315789474
Median 183 1
Max 207 5
Min 123 0
Stddev 28.99092417 1.600438536
2) Throughput (per flow in Mbps):
CUBIC DCTCP
Mean 521.6842105 521.8947368
Median 464 523
Max 776 527
Min 403 519
Stddev 105.8909568 2.601169328
Fairness 0.962434227 0.999976467
3) Latency (in ms):
CUBIC DCTCP
Mean 4.0088 0.04219
Median 4.055 0.0395
Max 4.2 0.085
Min 3.32 0.028
Stddev 0.166692604 0.010640778
4) Convergence and stability test:
CUBIC DCTCP
Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2
0 9.93 0 0 9.92 0
0.5 9.87 0 0.5 9.86 0
1 8.73 2.25 1 6.46 4.88
1.5 7.29 2.8 1.5 4.9 4.99
2 6.96 3.1 2 4.92 4.94
2.5 6.67 3.34 2.5 4.93 5
3 6.39 3.57 3 4.92 4.99
3.5 6.24 3.75 3.5 4.94 4.74
4 6 3.94 4 5.34 4.71
4.5 5.88 4.09 4.5 4.99 4.97
5 5.27 4.98 5 4.83 5.01
5.5 4.93 5.04 5.5 4.89 4.99
6 4.9 4.99 6 4.92 5.04
6.5 4.93 5.1 6.5 4.91 4.97
7 4.28 5.8 7 4.97 4.97
7.5 4.62 4.91 7.5 4.99 4.82
8 5.05 4.45 8 5.16 4.76
8.5 5.93 4.09 8.5 4.94 4.98
9 5.73 4.2 9 4.92 5.02
9.5 5.62 4.32 9.5 4.87 5.03
10 6.12 3.2 10 4.91 5.01
10.5 6.91 3.11 10.5 4.87 5.04
11 8.48 0 11 8.49 4.94
11.5 9.87 0 11.5 9.9 0
Enabling DCTCP with this patch requires the following steps: DCTCP
must be running both on the sender and receiver side in your data
center, i.e.:
sysctl -w net.ipv4.tcp_congestion_control=dctcp
Also, ECN functionality must be enabled at all switches in your
data center for DCTCP to work. The default ECN marking threshold (K)
heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps,
and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]).
There are no code changes required to applications running in user
space. DCTCP has been implemented in full *isolation* of the rest of
the TCP code as its own congestion control module, so that it can run
without a need to expose code to the core of the TCP stack, and thus
nothing changes for non-DCTCP users.
Changes in the CA framework code are minimal, and DCTCP algorithm
operates on mechanisms that are already available in Silicon. The
gain (dctcp_shift_g) is currently a fixed constant (1/16) from the
paper, but we leave the option that it can be chosen carefully to
a different value by the user.
In case DCTCP is being used and ECN support on peer site is off,
DCTCP falls back after 3WHS to operate in normal TCP Reno mode.
The implementation itself is only around 300 loc of changes, the
rest is mainly documentation and our results in detail.
The implementation is heavily modified from an initial DCTCP patch
from [1] written by Abdul Kabbani, Masato Yasuda and Mohammad Alizadeh
from Stanford University. More information about DCTCP can be found
in [1-5].
[1] http://simula.stanford.edu/~alizade/Site/DCTCP.html
[2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
[3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
[4] http://www.ietf.org/proceedings/80/slides/iccrg-3.pdf
[5] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00
Joint work with Florian Westphal and Glenn Judd.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
Documentation/networking/dctcp.txt | 232 +++++++++++++++++++++++++++
net/ipv4/Kconfig | 28 +++-
net/ipv4/Makefile | 1 +
net/ipv4/tcp_dctcp.c | 311 +++++++++++++++++++++++++++++++++++++
net/ipv4/tcp_output.c | 1 +
5 files changed, 572 insertions(+), 1 deletion(-)
create mode 100644 Documentation/networking/dctcp.txt
create mode 100644 net/ipv4/tcp_dctcp.c
diff --git a/Documentation/networking/dctcp.txt b/Documentation/networking/dctcp.txt
new file mode 100644
index 0000000..b64d27f
--- /dev/null
+++ b/Documentation/networking/dctcp.txt
@@ -0,0 +1,232 @@
+DCTCP (DataCenter TCP)
+----------------------
+
+The below description provides an deployment example for people
+interested in running DCTCP in their data center network.
+
+1) Deployment scenario/example:
+
+The configuration for your data center is two-fold, it consists
+of a configuration of all switches and configuration on host
+side.
+
+1.1) Switch configuration:
+
+For each switch port, traffic was segregated into two queues.
+For any packet with a DSCP of 0x01 - or equivalently a TOS of
+0x04 - the packet was placed into the DCTCP queue. All other
+packets were placed into the default drop-tail queue. For the
+DCTCP queue, RED/ECN marking was enabled here with a marking
+threshold of 75 KB.
+
+1.2) Server configuration:
+
+The following configuration examples were used on the servers:
+
+1.2.1) DCTCP:
+
+# Set congestion control algorithm to DCTCP
+sysctl net.ipv4.tcp_congestion_control=dctcp
+# Set DSCP bits so that the switch can apply RED/ECN AQM to DCTCP traffic
+iptables -A OUTPUT -t mangle -p tcp -j TOS --or-tos 0x04
+
+1.2.2) CUBIC:
+
+# Set congestion control algorithm to CUBIC
+sysctl net.ipv4.tcp_congestion_control=cubic
+# Clear DSCP rule so that the switch applies drop-tail to CUBIC traffic
+iptables -D OUTPUT -t mangle -p tcp -j TOS --or-tos 0x04
+
+2) Example results:
+
+2.1) Incast test:
+
+This test measured DCTCP throughput and latency and compared
+it with CUBIC throughput and latency for an incast scenario.
+In this test, 19 senders sent at maximum rate to a single
+receiver. The receiver simply ran iperf -s.
+
+The senders ran iperf -c <receiver> -t 30. All senders started
+simultaneously (using local clocks synchronized by ntp).
+
+This test was repeated multiple times. Below shows the results
+from a single test. Other tests are similar. (DCTCP results were
+extremely consistent. CUBIC results show some variance induced
+by the TCP timeouts that CUBIC encountered.)
+
+For this test, we report statistics on the number of TCP timeouts,
+flow throughput, and traffic latency.
+
+2.1.1) Timeouts (total over all flows, and per flow summaries):
+
+ CUBIC DCTCP
+Total 3227 25
+Mean 169.8421053 1.315789474
+Median 183 1
+Max 207 5
+Min 123 0
+Stddev 28.99092417 1.600438536
+
+Timeout data is taken by measuring the net change in netstat -s
+"other TCP timeouts" reported. As a result, the timeout
+measurements above are not restricted to the test traffic, and
+we believe that it is likely that all of the "DCTCP timeouts" are
+actually timeouts for non-test traffic. We report them
+nevertheless. CUBIC will also include some non-test timeouts, but
+they are drawfed by bona fide test traffic timeouts for CUBIC.
+Clearly DCTCP does an excellent job of preventing TCP timeouts.
+DCTCP reduces timeouts by at least two orders of magnitude and
+may well have eliminated them in this scenario.
+
+2.1.2) Throughput (per flow in Mbps):
+
+ CUBIC DCTCP
+Mean 521.6842105 521.8947368
+Median 464 523
+Max 776 527
+Min 403 519
+Stddev 105.8909568 2.601169328
+Fairness 0.962434227 0.999976467
+
+Throughput data was simply the average throughput for each flow
+reported by iperf. By avoiding TCP timeouts, DCTCP is able to
+achieve much better per-flow results. In CUBIC, many flows
+experience TCP timeouts which makes flow throughput
+unpredictable and unfair. DCTCP, on the other hand, provides
+very clean predictable throughput without incurring TCP timeouts.
+Thus, the standard deviation of CUBIC throughput is dramatically
+higher than the standard deviation of DCTCP throughput.
+
+Mean throughput is nearly identical because even though cubic
+flows suffer TCP timeouts, other flows will step in and fill
+the unused bandwidth. Note that this test is something of a
+best case scenario for incast under CUBIC: it allows other flows
+to fill in for flows experiencing a timeout. Under situations
+where the receiver is issuing requests and then waiting for all
+flows to complete, flows cannot fill in for timed out flows and
+throughput will drop dramatically.
+
+2.1.3) Latency (in ms):
+
+ CUBIC DCTCP
+Mean 4.0088 0.04219
+Median 4.055 0.0395
+Max 4.2 0.085
+Min 3.32 0.028
+Stddev 0.166692604 0.010640778
+
+Latency for each protocol was computed by running "ping -i 0.2
+<receiver>" from a single sender to the receiver during the
+incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used
+to ensure that traffic traversed the DCTCP queue and was not
+dropped when the queue size was greater than the marking
+threshold. The summary statistics above are over all ping
+metrics measured between the single sender, receiver pair.
+
+The latency results for this test show a dramatic difference
+between CUBIC and DCTCP. CUBIC intentionally overflows the
+switch buffer which incurs the maximum queue latency (more
+buffer memory will lead to high latency.) DCTCP, on the other
+hand, deliberately attempts to keep queue occupancy low. The
+result is a two orders of magnitude reduction of latency with
+DCTCP - even with a switch with relatively little RAM. Switches
+with larger amounts of RAM will incur increasing amounts of
+latency for CUBIC, but not for DCTCP.
+
+2.2) Convergence and stability test:
+
+This test measured the time that DCTCP took to fairly
+redistribute bandwidth when a new flow commences. It also
+measured DCTCP's ability to remain stable at a fair
+bandwidth distribution. DCTCP is compared with CUBIC for
+this test.
+
+At the commencement of this test, a single flow is sending at
+maximum rate (near 10 Gbps) to a single receiver. One second
+after that first flow commences, a new flow from a distinct
+server begins sending to the same receiver as the first flow.
+After the second flow has sent data for 10 seconds, the second
+flow is terminated. The first flow sends for an additional
+second. Ideally, the bandwidth would be evenly shared as soon
+as the second flow starts, and recover as soon as it stops.
+
+The results of this test are shown below. Note that the flow
+bandwidth for the two flows was measured near the same time,
+but not simultaneously.
+
+DCTCP performs nearly perfectly within the measurement
+limitations of this test: bandwidth is quickly distributed
+fairly between the two flows, remains stable throughout the
+duration of the test, and recovers quickly. CUBIC, in contrast,
+is slow to divide the bandwidth fairly, and has trouble
+remaining stable.
+
+CUBIC DCTCP
+
+Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2
+ 0 9.93 0 0 9.92 0
+ 0.5 9.87 0 0.5 9.86 0
+ 1 8.73 2.25 1 6.46 4.88
+ 1.5 7.29 2.8 1.5 4.9 4.99
+ 2 6.96 3.1 2 4.92 4.94
+ 2.5 6.67 3.34 2.5 4.93 5
+ 3 6.39 3.57 3 4.92 4.99
+ 3.5 6.24 3.75 3.5 4.94 4.74
+ 4 6 3.94 4 5.34 4.71
+ 4.5 5.88 4.09 4.5 4.99 4.97
+ 5 5.27 4.98 5 4.83 5.01
+ 5.5 4.93 5.04 5.5 4.89 4.99
+ 6 4.9 4.99 6 4.92 5.04
+ 6.5 4.93 5.1 6.5 4.91 4.97
+ 7 4.28 5.8 7 4.97 4.97
+ 7.5 4.62 4.91 7.5 4.99 4.82
+ 8 5.05 4.45 8 5.16 4.76
+ 8.5 5.93 4.09 8.5 4.94 4.98
+ 9 5.73 4.2 9 4.92 5.02
+ 9.5 5.62 4.32 9.5 4.87 5.03
+10 6.12 3.2 10 4.91 5.01
+10.5 6.91 3.11 10.5 4.87 5.04
+11 8.48 0 11 8.49 4.94
+11.5 9.87 0 11.5 9.9 0
+
+2.3) SYN/ACK ECT test:
+
+This test demonstrates the importance of ECT on SYN and
+SYN-ACK packets by measuring the connection probability in
+the presence of competing flows for a DCTCP connection
+attempt *without* ECT in the SYN packet. The test was
+repeated five times for each number of competing flows.
+
+ Competing Flows 1 | 2 | 4 | 8 | 16
+ ------------------------------
+Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0
+Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0
+
+As the number of competing flows moves beyond 1, the
+connection probability drops rapidly.
+
+3) Further reading:
+
+3.1) DCTCP paper:
+
+The algorithm is further described in detail in the following two
+SIGCOMM/SIGMETRICS papers:
+
+ i) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye,
+ Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan:
+ "Data Center TCP (DCTCP)", Data Center Networks session
+ Proc. ACM SIGCOMM, New Delhi, 2010.
+ http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+
+ii) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar:
+ "Analysis of DCTCP: Stability, Convergence, and Fairness"
+ Proc. ACM SIGMETRICS, San Jose, 2011.
+ http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
+
+3.2) IETF informational draft:
+
+ http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00
+
+3.3) DCTCP site:
+
+ http://simula.stanford.edu/~alizade/Site/DCTCP.html
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 05c57f0..02827bd 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -556,6 +556,29 @@ config TCP_CONG_ILLINOIS
For further details see:
http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
+config TCP_CONG_DCTCP
+ tristate "DataCenter TCP (DCTCP)"
+ default n
+ ---help---
+ DCTCP leverages Explicit Congestion Notification (ECN) in the network to
+ provide multi-bit feedback to the end hosts. It is designed to provide:
+
+ - High burst tolerance (incast due to partition/aggregate),
+ - Low latency (short flows, queries),
+ - High throughput (continuous data updates, large file transfers) with
+ commodity, shallow-buffered switches.
+
+ All switches in the data center network running DCTCP must support
+ ECN marking and be configured for marking when reaching defined switch
+ buffer thresholds. The default ECN marking threshold heuristic for
+ DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
+ (~100KB) at 10Gbps.
+
+ If unsure what all that means, say N.
+
+ For further details see:
+ http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+
choice
prompt "Default TCP congestion control"
default DEFAULT_CUBIC
@@ -584,9 +607,11 @@ choice
config DEFAULT_WESTWOOD
bool "Westwood" if TCP_CONG_WESTWOOD=y
+ config DEFAULT_DCTCP
+ bool "DCTCP" if TCP_CONG_DCTCP=y
+
config DEFAULT_RENO
bool "Reno"
-
endchoice
endif
@@ -606,6 +631,7 @@ config DEFAULT_TCP_CONG
default "westwood" if DEFAULT_WESTWOOD
default "veno" if DEFAULT_VENO
default "reno" if DEFAULT_RENO
+ default "dctcp" if DEFAULT_DCTCP
default "cubic"
config TCP_MD5SIG
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index f032688..4497d40 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
+obj-$(CONFIG_TCP_CONG_DCTCP) += tcp_dctcp.o
obj-$(CONFIG_TCP_CONG_WESTWOOD) += tcp_westwood.o
obj-$(CONFIG_TCP_CONG_HSTCP) += tcp_highspeed.o
obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
new file mode 100644
index 0000000..bb9d9ef
--- /dev/null
+++ b/net/ipv4/tcp_dctcp.c
@@ -0,0 +1,311 @@
+/* DataCenter TCP (DCTCP) congestion control.
+ *
+ * http://simula.stanford.edu/~alizade/Site/DCTCP.html
+ *
+ * This is an implementation of DCTCP over Reno, an enhancement to the
+ * TCP congestion control algorithm designed for data centers. DCTCP
+ * leverages Explicit Congestion Notification (ECN) in the network to
+ * provide multi-bit feedback to the end hosts. DCTCP's goal is to meet
+ * the following three data center transport requirements:
+ *
+ * - High burst tolerance (incast due to partition/aggregate)
+ * - Low latency (short flows, queries)
+ * - High throughput (continuous data updates, large file transfers)
+ * with commodity shallow buffered switches
+ *
+ * The algorithm is described in detail in the following two papers:
+ *
+ * 1) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye,
+ * Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan:
+ * "Data Center TCP (DCTCP)", Data Center Networks session
+ * Proc. ACM SIGCOMM, New Delhi, 2010.
+ * http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+ *
+ * 2) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar:
+ * "Analysis of DCTCP: Stability, Convergence, and Fairness"
+ * Proc. ACM SIGMETRICS, San Jose, 2011.
+ * http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
+ *
+ * Implemented from an initial implementation of DCTCP from Abdul Kabbani,
+ * Masato Yasuda, and Mohammad Alizadeh.
+ *
+ * Authors:
+ *
+ * Daniel Borkmann <dborkman@redhat.com>
+ * Florian Westphal <fw@strlen.de>
+ * Glenn Judd <glenn.judd@morganstanley.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <net/tcp.h>
+
+#define DCTCP_MAX_ALPHA 1024U
+
+struct dctcp {
+ u32 acked_bytes_ecn;
+ u32 acked_bytes_total;
+ u32 prior_snd_una;
+ u32 prior_rcv_nxt;
+ u32 dctcp_alpha;
+ u32 next_seq;
+ /* false: last pkt was non-ce
+ * true: last pkt was ce
+ */
+ bool ce_state;
+ bool delayed_ack_reserved;
+};
+
+static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
+module_param(dctcp_shift_g, uint, 0644);
+MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha");
+
+static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
+module_param(dctcp_alpha_on_init, uint, 0644);
+MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
+
+static unsigned int dctcp_clamp_alpha_on_loss __read_mostly = 0;
+module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
+MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
+ "parameter for clamping alpha on loss");
+
+static struct tcp_congestion_ops dctcp_reno;
+
+static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
+{
+ ca->next_seq = tp->snd_nxt;
+
+ ca->acked_bytes_ecn = 0;
+ ca->acked_bytes_total = 0;
+}
+
+static void dctcp_init(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->ecn_flags & TCP_ECN_OK) {
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ ca->prior_snd_una = tp->snd_una;
+ ca->prior_rcv_nxt = tp->rcv_nxt;
+
+ ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
+
+ ca->delayed_ack_reserved = false;
+ ca->ce_state = false;
+
+ dctcp_reset(tp, ca);
+ return;
+ }
+
+ /* No ECN support? Fall back to Reno. */
+ inet_csk(sk)->icsk_ca_ops = &dctcp_reno;
+ pr_debug("sk:%p fallback to Reno due to missing ECN support\n", sk);
+}
+
+static u32 dctcp_ssthresh(struct sock *sk)
+{
+ const struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
+}
+
+static void dctcp_ce_state_0_to_1(struct sock *sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ /* State has changed from CE=0 to CE=1 and delayed
+ * ACK has not sent yet.
+ */
+ if (!ca->ce_state && ca->delayed_ack_reserved) {
+ u32 tmp_rcv_nxt;
+
+ /* Save current rcv_nxt. */
+ tmp_rcv_nxt = tp->rcv_nxt;
+
+ /* Generate previous ack with CE=0. */
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+ tp->rcv_nxt = ca->prior_rcv_nxt;
+
+ tcp_send_ack(sk);
+
+ /* Recover current rcv_nxt. */
+ tp->rcv_nxt = tmp_rcv_nxt;
+ }
+
+ ca->prior_rcv_nxt = tp->rcv_nxt;
+ ca->ce_state = true;
+
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+}
+
+static void dctcp_ce_state_1_to_0(struct sock *sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ /* State has changed from CE=1 to CE=0 and delayed
+ * ACK has not sent yet.
+ */
+ if (ca->ce_state && ca->delayed_ack_reserved) {
+ u32 tmp_rcv_nxt;
+
+ /* Save current rcv_nxt. */
+ tmp_rcv_nxt = tp->rcv_nxt;
+
+ /* Generate previous ack with CE=1. */
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ tp->rcv_nxt = ca->prior_rcv_nxt;
+
+ tcp_send_ack(sk);
+
+ /* Recover current rcv_nxt. */
+ tp->rcv_nxt = tmp_rcv_nxt;
+ }
+
+ ca->prior_rcv_nxt = tp->rcv_nxt;
+ ca->ce_state = false;
+
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static void dctcp_update_alpha(struct sock *sk, u32 flags)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+ u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
+
+ /* If ack did not advance snd_una, count dupack as MSS size.
+ * If ack did update window, do not count it at all.
+ */
+ if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
+ acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
+ if (acked_bytes) {
+ ca->acked_bytes_total += acked_bytes;
+ ca->prior_snd_una = tp->snd_una;
+
+ if (flags & CA_ACK_ECE)
+ ca->acked_bytes_ecn += acked_bytes;
+ }
+
+ /* Expired RTT */
+ if (!before(tp->snd_una, ca->next_seq)) {
+ /* For avoiding denominator == 1. */
+ if (ca->acked_bytes_total == 0)
+ ca->acked_bytes_total = 1;
+
+ /* alpha = (1 - g) * alpha + g * F */
+ ca->dctcp_alpha = ca->dctcp_alpha -
+ (ca->dctcp_alpha >> dctcp_shift_g) +
+ (ca->acked_bytes_ecn << (10U - dctcp_shift_g)) /
+ ca->acked_bytes_total;
+
+ if (ca->dctcp_alpha > DCTCP_MAX_ALPHA)
+ /* Clamp dctcp_alpha to max. */
+ ca->dctcp_alpha = DCTCP_MAX_ALPHA;
+
+ dctcp_reset(tp, ca);
+ }
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+ if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ /* If this extension is enabled, we clamp dctcp_alpha to
+ * max on packet loss; the motivation is that dctcp_alpha
+ * is an indicator to the extend of congestion and packet
+ * loss is an indicator of extreme congestion; setting
+ * this in practice turned out to be beneficial, and
+ * effectively assumes total congestion which reduces the
+ * window by half.
+ */
+ ca->dctcp_alpha = DCTCP_MAX_ALPHA;
+ }
+}
+
+static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ switch (ev) {
+ case CA_EVENT_DELAYED_ACK:
+ if (!ca->delayed_ack_reserved)
+ ca->delayed_ack_reserved = true;
+ break;
+ case CA_EVENT_NON_DELAYED_ACK:
+ if (ca->delayed_ack_reserved)
+ ca->delayed_ack_reserved = false;
+ break;
+ default:
+ /* Don't care for the rest. */
+ break;
+ }
+}
+
+static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
+{
+ switch (ev) {
+ case CA_EVENT_ECN_IS_CE:
+ dctcp_ce_state_0_to_1(sk);
+ break;
+ case CA_EVENT_ECN_NO_CE:
+ dctcp_ce_state_1_to_0(sk);
+ break;
+ case CA_EVENT_DELAYED_ACK:
+ case CA_EVENT_NON_DELAYED_ACK:
+ dctcp_update_ack_reserved(sk, ev);
+ break;
+ default:
+ /* Don't care for the rest. */
+ break;
+ }
+}
+
+static struct tcp_congestion_ops dctcp __read_mostly = {
+ .init = dctcp_init,
+ .in_ack_event = dctcp_update_alpha,
+ .cwnd_event = dctcp_cwnd_event,
+ .ssthresh = dctcp_ssthresh,
+ .cong_avoid = tcp_reno_cong_avoid,
+ .set_state = dctcp_state,
+ .flags = TCP_CONG_NEEDS_ECN,
+ .owner = THIS_MODULE,
+ .name = "dctcp",
+};
+
+static struct tcp_congestion_ops dctcp_reno __read_mostly = {
+ .ssthresh = tcp_reno_ssthresh,
+ .cong_avoid = tcp_reno_cong_avoid,
+ .owner = THIS_MODULE,
+ .name = "dctcp-reno",
+};
+
+static int __init dctcp_register(void)
+{
+ BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE);
+ return tcp_register_congestion_control(&dctcp);
+}
+
+static void __exit dctcp_unregister(void)
+{
+ tcp_unregister_congestion_control(&dctcp);
+}
+
+module_init(dctcp_register);
+module_exit(dctcp_unregister);
+
+MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_AUTHOR("Glenn Judd <glenn.judd@morganstanley.com>");
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("DataCenter TCP (DCTCP)");
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1f5e04a..d398b88 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3200,6 +3200,7 @@ void tcp_send_ack(struct sock *sk)
TCP_SKB_CB(buff)->when = tcp_time_stamp;
tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
}
+EXPORT_SYMBOL_GPL(tcp_send_ack);
/* This routine sends a packet with an out of date sequence
* number. It assumes the other end will try to ack it.
--
1.8.1.5
^ permalink raw reply related [flat|nested] 15+ messages in thread
* Re: [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm
2014-05-12 20:59 [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm Florian Westphal
` (4 preceding siblings ...)
2014-05-12 20:59 ` [PATCH 5/5] net: tcp: add DCTCP congestion control algorithm Florian Westphal
@ 2014-05-12 22:01 ` Cong Wang
2014-05-13 4:45 ` Stephen Hemminger
5 siblings, 1 reply; 15+ messages in thread
From: Cong Wang @ 2014-05-12 22:01 UTC (permalink / raw)
To: Florian Westphal; +Cc: netdev
On Mon, May 12, 2014 at 1:59 PM, Florian Westphal <fw@strlen.de> wrote:
> This patch series adds support for the Datacenter TCP (DCTCP) congestion
> control algorithm.
>
> Please see individual patches' changelog for the details. A summary
> of DCTCP and test results can be found in patch 5.
>
Is DCTCP draft accepted by IETF? It looks like there is some issue
with the design:
http://www.ietf.org/mail-archive/web/tcpm/current/msg08693.html
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 2/5] net: tcp: add flag for ca to indicate that ECN is required
2014-05-12 20:59 ` [PATCH 2/5] net: tcp: add flag for ca to indicate that ECN is required Florian Westphal
@ 2014-05-12 23:51 ` Eric Dumazet
2014-05-13 9:18 ` Florian Westphal
0 siblings, 1 reply; 15+ messages in thread
From: Eric Dumazet @ 2014-05-12 23:51 UTC (permalink / raw)
To: Florian Westphal; +Cc: netdev, Daniel Borkmann, Glenn Judd
On Mon, 2014-05-12 at 22:59 +0200, Florian Westphal wrote:
> From: Daniel Borkmann <dborkman@redhat.com>
>
> This patch adds a flag to TCP congestion algorithms that allows
> for requesting to mark IPv4/IPv6 sockets with transport as ECN
> capable, that is, ECT(0), when required by a congestion algorithm.
>
> It is currently used and needed in DataCenter TCP (DCTCP), as it
> requires both peers to assert ECT on all IP packets sent - it
> uses ECN feedback (i.e. CE, Congestion Encountered) from switches
> inside the data center to derive feedback to the end hosts.
>
> Therefore, simply add a new flag to icsk_ca_ops. Note that DCTCP's
> algorithm/behaviour slightly diverges from RFC3168, therefore this
> is only (!) enabled iff the assigned congestion control ops module
> has requested this. By that, we can tightly couple this logic really
> only to provided congestion control ops.
>
> Joint work with Florian Westphal and Glenn Judd.
>
> Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
> Signed-off-by: Florian Westphal <fw@strlen.de>
> ---
> include/net/tcp.h | 45 ++++++++++++++++++++++++++++-----------------
> net/ipv4/tcp_ipv4.c | 2 +-
> net/ipv4/tcp_output.c | 9 ++++++++-
> net/ipv6/tcp_ipv6.c | 2 +-
> 4 files changed, 38 insertions(+), 20 deletions(-)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 8ae165f..92d1600 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -734,23 +734,6 @@ struct tcp_skb_cb {
>
> #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
>
> -/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
> - *
> - * If we receive a SYN packet with these bits set, it means a network is
> - * playing bad games with TOS bits. In order to avoid possible false congestion
> - * notifications, we disable TCP ECN negociation.
> - */
> -static inline void
> -TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
> - struct net *net)
> -{
> - const struct tcphdr *th = tcp_hdr(skb);
> -
> - if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr &&
> - INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield))
> - inet_rsk(req)->ecn_ok = 1;
> -}
> -
> /* Due to TSO, an SKB can be composed of multiple actual
> * packets. To keep these tracked properly, we use this.
> */
> @@ -783,6 +766,7 @@ enum tcp_ca_event {
> #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
>
> #define TCP_CONG_NON_RESTRICTED 0x1
> +#define TCP_CONG_NEEDS_ECN 0x2
>
> struct tcp_congestion_ops {
> struct list_head list;
> @@ -848,6 +832,13 @@ static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
> icsk->icsk_ca_state = ca_state;
> }
>
> +static inline bool tcp_ca_needs_ecn(const struct sock *sk)
> +{
> + const struct inet_connection_sock *icsk = inet_csk(sk);
> +
> + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
> +}
> +
> static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
> {
> const struct inet_connection_sock *icsk = inet_csk(sk);
> @@ -856,6 +847,26 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
> icsk->icsk_ca_ops->cwnd_event(sk, event);
> }
>
> +/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
> + *
> + * If we receive a SYN packet with these bits set, it means a network is
> + * playing bad games with TOS bits. In order to avoid possible false congestion
> + * notifications, we disable TCP ECN negociation.
> + */
looks like comment needs a change.
> +static inline void
> +TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
> + const struct sock *listen_sk)
> +{
> + const struct tcphdr *th = tcp_hdr(skb);
> + const struct net *net = sock_net(listen_sk);
> +
> + if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr &&
> + (INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield) ||
> + tcp_ca_needs_ecn(listen_sk))) {
> + inet_rsk(req)->ecn_ok = 1;
> + }
> +}
> +
> /* These functions determine how the current flow behaves in respect of SACK
> * handling. SACK is negotiated with the peer, and therefore it can vary
> * between different flows.
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index ad166dc..d7d9c54 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1512,7 +1512,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
> goto drop_and_free;
>
> if (!want_cookie || tmp_opt.tstamp_ok)
> - TCP_ECN_create_request(req, skb, sock_net(sk));
> + TCP_ECN_create_request(req, skb, sk);
>
> if (want_cookie) {
> isn = cookie_v4_init_sequence(sk, skb, &req->mss);
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 694711a..1f983dd 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -331,7 +331,8 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
> struct tcp_sock *tp = tcp_sk(sk);
>
> tp->ecn_flags = 0;
> - if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
> + if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
> + tcp_ca_needs_ecn(sk)) {
> TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
> tp->ecn_flags = TCP_ECN_OK;
> }
> @@ -953,6 +954,9 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
> if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
> TCP_ECN_send(sk, skb, tcp_header_size);
>
> + if (tcp_ca_needs_ecn(sk))
> + INET_ECN_xmit(sk);
Why do we need this every time we send a packet ?
Its normally done in TCP_ECN_send(), where it probably makes sense to
change the logic and add a comment why DCTCP sets ECT even for rtx
packets ?
> +
> #ifdef CONFIG_TCP_MD5SIG
> /* Calculate the MD5 hash, as we have all we need now */
> if (md5) {
> @@ -2860,6 +2864,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
> th->doff = (tcp_header_size >> 2);
> TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
>
> + if (tcp_ca_needs_ecn(sk))
> + INET_ECN_xmit(sk);
Likewise, please do not change this listener field for every SYNACK,
this is going to hurt. This probably should be done _once_.
> +
> #ifdef CONFIG_TCP_MD5SIG
> /* Okay, we have all we need - do the md5 hash if needed */
> if (md5) {
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index 7fa6743..b1c8765 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1013,7 +1013,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
> ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
> ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
> if (!want_cookie || tmp_opt.tstamp_ok)
> - TCP_ECN_create_request(req, skb, sock_net(sk));
> + TCP_ECN_create_request(req, skb, sk);
>
> ireq->ir_iif = sk->sk_bound_dev_if;
>
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 4/5] net: tcp: more detailed ACK events, and events for CE marked packets
2014-05-12 20:59 ` [PATCH 4/5] net: tcp: more detailed ACK events, and events for CE marked packets Florian Westphal
@ 2014-05-13 4:41 ` Yuchung Cheng
2014-05-13 10:26 ` Florian Westphal
0 siblings, 1 reply; 15+ messages in thread
From: Yuchung Cheng @ 2014-05-13 4:41 UTC (permalink / raw)
To: Florian Westphal; +Cc: netdev, Daniel Borkmann, Glenn Judd
On Mon, May 12, 2014 at 1:59 PM, Florian Westphal <fw@strlen.de> wrote:
>
> DataCenter TCP (DCTCP) determines cwnd growth based on ECN information
> and ACK properties, e.g. ACK that updates window is treated differently
> than DUPACK.
>
> Also DCTCP needs information whether ACK was delayed ACK. Furthermore,
> DCTCP also implements a CE state machine that keeps track of CE markings
> of incoming packets.
>
> Therefore, extend the congestion control framework to provide these
> event types, so that DCTCP can be properly implemented as a normal
> congestion algorithm module outside the core stack.
>
> Joint work with Daniel Borkmann and Glenn Judd.
>
> Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
> Signed-off-by: Florian Westphal <fw@strlen.de>
> ---
> include/net/tcp.h | 9 ++++++++-
> net/ipv4/tcp_input.c | 22 ++++++++++++++++++----
> net/ipv4/tcp_output.c | 4 ++++
> 3 files changed, 30 insertions(+), 5 deletions(-)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 0d767d2..56bf383 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -754,10 +754,17 @@ enum tcp_ca_event {
> CA_EVENT_CWND_RESTART, /* congestion window restart */
> CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
> CA_EVENT_LOSS, /* loss timeout */
> + CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
> + CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
> + CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */
> + CA_EVENT_NON_DELAYED_ACK,
do we need NON_DELAYED_ACK event? is there a third kind?
> };
>
> +/* information about inbound ACK, passed to cong_ops->in_ack_event() */
> enum tcp_ca_ack_event_flags {
> - CA_ACK_SLOWPATH = (1 << 0),
> + CA_ACK_SLOWPATH = (1 << 0), /* in slow path processing */
> + CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */
> + CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */
> };
>
>
> /*
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index 7fab1da..bf0f734 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -232,14 +232,21 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *s
> tcp_enter_quickack_mode((struct sock *)tp);
> break;
> case INET_ECN_CE:
> + if (tcp_ca_needs_ecn((struct sock *)tp))
> + tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
> +
> if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
> /* Better not delay acks, sender can have a very low cwnd */
> tcp_enter_quickack_mode((struct sock *)tp);
> tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
> }
> - /* fallinto */
> + tp->ecn_flags |= TCP_ECN_SEEN;
> + break;
> default:
> + if (tcp_ca_needs_ecn((struct sock *)tp))
> + tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
> tp->ecn_flags |= TCP_ECN_SEEN;
> + break;
> }
> }
>
> @@ -3421,10 +3428,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
> tp->snd_una = ack;
> flag |= FLAG_WIN_UPDATE;
>
> - tcp_in_ack_event(sk, 0);
> + tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
These CA_ACK_xxx are identical to the ACK flag so might as well just
pass the flag to the event handler?
>
> NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
> } else {
> + u32 ack_ev_flags = CA_ACK_SLOWPATH;
> +
> if (ack_seq != TCP_SKB_CB(skb)->end_seq)
> flag |= FLAG_DATA;
> else
> @@ -3436,10 +3445,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
> flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
> &sack_rtt_us);
>
> - if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
> + if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) {
> flag |= FLAG_ECE;
> + ack_ev_flags |= CA_ACK_ECE;
> + }
> +
> + if (flag & FLAG_WIN_UPDATE)
> + ack_ev_flags |= CA_ACK_WIN_UPDATE;
>
> - tcp_in_ack_event(sk, CA_ACK_SLOWPATH);
> + tcp_in_ack_event(sk, ack_ev_flags);
> }
>
> /* We passed data and got it acked, remove any soft error
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 1f983dd..1f5e04a 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -3119,6 +3119,8 @@ void tcp_send_delayed_ack(struct sock *sk)
> int ato = icsk->icsk_ack.ato;
> unsigned long timeout;
>
> + tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
> +
> if (ato > TCP_DELACK_MIN) {
> const struct tcp_sock *tp = tcp_sk(sk);
> int max_ato = HZ / 2;
> @@ -3175,6 +3177,8 @@ void tcp_send_ack(struct sock *sk)
> if (sk->sk_state == TCP_CLOSE)
> return;
>
> + tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
> +
> /* We are not putting this on the write queue, so
> * tcp_transmit_skb() will set the ownership to this
> * sock.
> --
> 1.8.1.5
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm
2014-05-12 22:01 ` [next PATCH 0/5] net: tcp: " Cong Wang
@ 2014-05-13 4:45 ` Stephen Hemminger
2014-05-13 9:34 ` Hagen Paul Pfeifer
0 siblings, 1 reply; 15+ messages in thread
From: Stephen Hemminger @ 2014-05-13 4:45 UTC (permalink / raw)
To: Cong Wang; +Cc: Florian Westphal, netdev
On Mon, 12 May 2014 15:01:52 -0700
Cong Wang <cwang@twopensource.com> wrote:
> On Mon, May 12, 2014 at 1:59 PM, Florian Westphal <fw@strlen.de> wrote:
> > This patch series adds support for the Datacenter TCP (DCTCP) congestion
> > control algorithm.
> >
> > Please see individual patches' changelog for the details. A summary
> > of DCTCP and test results can be found in patch 5.
> >
>
> Is DCTCP draft accepted by IETF? It looks like there is some issue
> with the design:
>
> http://www.ietf.org/mail-archive/web/tcpm/current/msg08693.html
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
Far more worrying is the Microsoft IPR statement relative to the RFC.
https://datatracker.ietf.org/ipr/2319/
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 2/5] net: tcp: add flag for ca to indicate that ECN is required
2014-05-12 23:51 ` Eric Dumazet
@ 2014-05-13 9:18 ` Florian Westphal
0 siblings, 0 replies; 15+ messages in thread
From: Florian Westphal @ 2014-05-13 9:18 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Florian Westphal, netdev, Daniel Borkmann, Glenn Judd
Eric Dumazet <eric.dumazet@gmail.com> wrote:
> > +static inline bool tcp_ca_needs_ecn(const struct sock *sk)
> > +{
> > + const struct inet_connection_sock *icsk = inet_csk(sk);
> > +
> > + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
> > +}
> > +
> > static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
> > {
> > const struct inet_connection_sock *icsk = inet_csk(sk);
> > @@ -856,6 +847,26 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
> > icsk->icsk_ca_ops->cwnd_event(sk, event);
> > }
> >
> > +/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
> > + *
> > + * If we receive a SYN packet with these bits set, it means a network is
> > + * playing bad games with TOS bits. In order to avoid possible false congestion
> > + * notifications, we disable TCP ECN negociation.
> > + */
>
> looks like comment needs a change.
Right, thanks for catching this.
> > diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> > index 694711a..1f983dd 100644
> > --- a/net/ipv4/tcp_output.c
> > +++ b/net/ipv4/tcp_output.c
> > @@ -331,7 +331,8 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
> > struct tcp_sock *tp = tcp_sk(sk);
> >
> > tp->ecn_flags = 0;
> > - if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
> > + if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
> > + tcp_ca_needs_ecn(sk)) {
> > TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
> > tp->ecn_flags = TCP_ECN_OK;
> > }
> > @@ -953,6 +954,9 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
> > if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
> > TCP_ECN_send(sk, skb, tcp_header_size);
> >
> > + if (tcp_ca_needs_ecn(sk))
> > + INET_ECN_xmit(sk);
>
> Why do we need this every time we send a packet ?
Indeed... I'll change it.
> Its normally done in TCP_ECN_send(), where it probably makes sense to
> change the logic and add a comment why DCTCP sets ECT even for rtx
> packets ?
Sounds like an excellent suggestion, thanks Eric.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm
2014-05-13 4:45 ` Stephen Hemminger
@ 2014-05-13 9:34 ` Hagen Paul Pfeifer
2014-05-13 9:40 ` Eggert, Lars
2014-05-13 15:18 ` Stephen Hemminger
0 siblings, 2 replies; 15+ messages in thread
From: Hagen Paul Pfeifer @ 2014-05-13 9:34 UTC (permalink / raw)
To: Stephen Hemminger, lars; +Cc: Cong Wang, Florian Westphal, netdev
Some IETF background: IETF Meeting 79 (Beijing) Microsoft employees
presented DCTCP with the intention to standardize DCTCP. The rough
consensus was the DCTCP is datacenter specific, thus closed door
technique and in the result not of broader interest for TCPM working
group. Further effort slowed down quickly.
Last IETF meeting in London (IETF 89) Lars Eggert (cc'ed him) picked
up DCTCP again. My impression was that the willing to adopt or work on
DCTCP was limited (the way I see it) but not definitely buried.
The IPR statement licence it under Royalty-Free, Reasonable and
Non-Discriminatory licence.
Hagen
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm
2014-05-13 9:34 ` Hagen Paul Pfeifer
@ 2014-05-13 9:40 ` Eggert, Lars
2014-05-13 15:18 ` Stephen Hemminger
1 sibling, 0 replies; 15+ messages in thread
From: Eggert, Lars @ 2014-05-13 9:40 UTC (permalink / raw)
To: Hagen Paul Pfeifer
Cc: Stephen Hemminger, Cong Wang, Florian Westphal, netdev, sbens,
Dave Thaler
[-- Attachment #1: Type: text/plain, Size: 1322 bytes --]
Hi,
On 2014-5-13, at 11:34, Hagen Paul Pfeifer <hagen@jauu.net> wrote:
> Some IETF background: IETF Meeting 79 (Beijing) Microsoft employees
> presented DCTCP with the intention to standardize DCTCP. The rough
> consensus was the DCTCP is datacenter specific, thus closed door
> technique and in the result not of broader interest for TCPM working
> group. Further effort slowed down quickly.
>
> Last IETF meeting in London (IETF 89) Lars Eggert (cc'ed him) picked
> up DCTCP again. My impression was that the willing to adopt or work on
> DCTCP was limited (the way I see it) but not definitely buried.
I presented for Stephen Bensley from Microsoft (CC'ed), who is the main driver of the IETF spec. (My contribution was mostly having an intern do a FreeBSD implementation, which is being reviewed for inclusion over there.)
While the TCPM working group may or may not decide to take this spec on as a work item, there is also a newly starting "datacenter latency control (DCLC)" research group on the IRTF side that may give this a home if TCPM takes a pass. (Mailing list https://www.irtf.org/mailman/listinfo/dclc; wiki http://wiki.tools.ietf.org/group/irtf/trac/wiki/dclc)
Lars
> The IPR statement licence it under Royalty-Free, Reasonable and
> Non-Discriminatory licence.
>
> Hagen
[-- Attachment #2: Message signed with OpenPGP using GPGMail --]
[-- Type: application/pgp-signature, Size: 273 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 4/5] net: tcp: more detailed ACK events, and events for CE marked packets
2014-05-13 4:41 ` Yuchung Cheng
@ 2014-05-13 10:26 ` Florian Westphal
0 siblings, 0 replies; 15+ messages in thread
From: Florian Westphal @ 2014-05-13 10:26 UTC (permalink / raw)
To: Yuchung Cheng; +Cc: Florian Westphal, netdev, Daniel Borkmann, Glenn Judd
Yuchung Cheng <ycheng@google.com> wrote:
> On Mon, May 12, 2014 at 1:59 PM, Florian Westphal <fw@strlen.de> wrote:
> >
> > DataCenter TCP (DCTCP) determines cwnd growth based on ECN information
> > and ACK properties, e.g. ACK that updates window is treated differently
> > than DUPACK.
> >
> > Also DCTCP needs information whether ACK was delayed ACK. Furthermore,
> > DCTCP also implements a CE state machine that keeps track of CE markings
> > of incoming packets.
> >
> > Therefore, extend the congestion control framework to provide these
> > event types, so that DCTCP can be properly implemented as a normal
> > congestion algorithm module outside the core stack.
> >
> > Joint work with Daniel Borkmann and Glenn Judd.
> >
> > Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
> > Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
> > Signed-off-by: Florian Westphal <fw@strlen.de>
> > ---
> > include/net/tcp.h | 9 ++++++++-
> > net/ipv4/tcp_input.c | 22 ++++++++++++++++++----
> > net/ipv4/tcp_output.c | 4 ++++
> > 3 files changed, 30 insertions(+), 5 deletions(-)
> >
> > diff --git a/include/net/tcp.h b/include/net/tcp.h
> > index 0d767d2..56bf383 100644
> > --- a/include/net/tcp.h
> > +++ b/include/net/tcp.h
> > @@ -754,10 +754,17 @@ enum tcp_ca_event {
> > CA_EVENT_CWND_RESTART, /* congestion window restart */
> > CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
> > CA_EVENT_LOSS, /* loss timeout */
> > + CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
> > + CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
> > + CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */
> > + CA_EVENT_NON_DELAYED_ACK,
> do we need NON_DELAYED_ACK event? is there a third kind?
Could you elaborate? I am not sure what you mean.
> > @@ -3421,10 +3428,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
> > tp->snd_una = ack;
> > flag |= FLAG_WIN_UPDATE;
> >
> > - tcp_in_ack_event(sk, 0);
> > + tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
> These CA_ACK_xxx are identical to the ACK flag so might as well just
> pass the flag to the event handler?
We felt that exposing all the FLAG_xxx values (which are private to
tcp_input.c) to congestion modules would be overkill, especially
since we would fail to notify the cong_ops module(s) about all of these.
I think if we were to expose all of them we'd also have to call
rename tcp_in_ack_event() (since most of the flags are not ack related)
and then consistently call that for all the flag changes (which is just
needless overhead since no cong_ops module would react to these).
We can update the tcp_ca_ack_event_flags to include
all FLAG_xxx values and then convert tcp_input.c to use them, but it
would mean that cong_ops modules could only rely on a selected few of
these flags to actually be set/propagated consistently.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm
2014-05-13 9:34 ` Hagen Paul Pfeifer
2014-05-13 9:40 ` Eggert, Lars
@ 2014-05-13 15:18 ` Stephen Hemminger
1 sibling, 0 replies; 15+ messages in thread
From: Stephen Hemminger @ 2014-05-13 15:18 UTC (permalink / raw)
To: Hagen Paul Pfeifer; +Cc: lars, Cong Wang, Florian Westphal, netdev
On Tue, 13 May 2014 11:34:29 +0200
Hagen Paul Pfeifer <hagen@jauu.net> wrote:
> The IPR statement licence it under Royalty-Free, Reasonable and
> Non-Discriminatory licence.
This is not enough to allow distribution under GPL.
GPL has patent and redistribution clauses that as far as I know
are not compatible.
^ permalink raw reply [flat|nested] 15+ messages in thread
end of thread, other threads:[~2014-05-13 15:18 UTC | newest]
Thread overview: 15+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-05-12 20:59 [next PATCH 0/5] net: tcp: DCTCP congestion control algorithm Florian Westphal
2014-05-12 20:59 ` [PATCH 1/5] net: tcp: assign tcp cong_ops when tcp sk is created Florian Westphal
2014-05-12 20:59 ` [PATCH 2/5] net: tcp: add flag for ca to indicate that ECN is required Florian Westphal
2014-05-12 23:51 ` Eric Dumazet
2014-05-13 9:18 ` Florian Westphal
2014-05-12 20:59 ` [PATCH 3/5] net: tcp: split ack slow/fast events from cwnd_event Florian Westphal
2014-05-12 20:59 ` [PATCH 4/5] net: tcp: more detailed ACK events, and events for CE marked packets Florian Westphal
2014-05-13 4:41 ` Yuchung Cheng
2014-05-13 10:26 ` Florian Westphal
2014-05-12 20:59 ` [PATCH 5/5] net: tcp: add DCTCP congestion control algorithm Florian Westphal
2014-05-12 22:01 ` [next PATCH 0/5] net: tcp: " Cong Wang
2014-05-13 4:45 ` Stephen Hemminger
2014-05-13 9:34 ` Hagen Paul Pfeifer
2014-05-13 9:40 ` Eggert, Lars
2014-05-13 15:18 ` Stephen Hemminger
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).