| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 19 Jan 2015 18:37:16 -0800
From: Dave Taht <dave.taht@...il.com>
To: Eric Dumazet <eric.dumazet@...il.com>
Cc: Eyal Perry <eyalpe@...lanox.com>,
Yuchung Cheng <ycheng@...gle.com>,
Neal Cardwell <ncardwell@...gle.com>,
Eyal Perry <eyalpe@....mellanox.co.il>,
Or Gerlitz <gerlitz.or@...il.com>,
Linux Netdev List <netdev@...r.kernel.org>,
Amir Vadai <amirv@...lanox.com>,
Yevgeny Petrilin <yevgenyp@...lanox.com>,
Saeed Mahameed <saeedm@...lanox.com>,
Ido Shamay <idos@...lanox.com>, Amir Ancel <amira@...lanox.com>
Subject: Re: BW regression after "tcp: refine TSO autosizing"
On Mon, Jan 19, 2015 at 6:16 PM, Eric Dumazet <eric.dumazet@...il.com> wrote:
> On Sun, 2015-01-18 at 23:40 +0200, Eyal Perry wrote:
>
>> So indeed, interrupt mitigation (tx-usecs 1 tx-frames 1) improves things up
>> for the "refined TSO autosizing" kernel (from 18.4Gbps to 19.7Gbps). but
>> in the
>> other kernel, the BW is remains the same with and without the coalescing.
>
> OK thanks for testing.
>
> I believe the regression comes from inability for cc to cope with
> stretch acks.
>
> Nowadays on fast networks, each ACK packet acknowledges ~45 MSS, but
> CUBIC (and others cc) got support for this only during slow start, with
> commit 9f9843a751d0a2057f9f3d313886e7e5e6ebaac9
> ("tcp: properly handle stretch acks in slow start")
>
> I guess it is time to also handle congestion avoidance phase.
Are you saying that at long last, delayed acks as we knew them are
dead, dead, dead?
> With following patch (very close to what we use here at Google) I
> reached 37Gbps instead of 20Gbps :
>
> ethtool -C eth1 tx-usecs 4 tx-frames 4
What is the default here?
What happens with the default here?
>
> DUMP_TCP_INFO=1 ./netperf -H remote -T2,2 -t TCP_STREAM -l 20
> MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to remote () port 0 AF_INET : cpu bind
> rto=201000 ato=0 pmtu=1500 rcv_ssthresh=29200 rtt=67 rttvar=6 snd_ssthresh=263 cwnd=265 reordering=3 total_retrans=4569 ca_state=0
The above statistics are not dumped by my netperf, and look extremely
desirable to capture in netperf-wrapper. This is a script parsing some
other kernel data at the conclusion of the run? or a better netperf?
If ECN was on the bottleneck link, I imagine total_retrans would be 0,
or are packets getting dropped in the kernel?
> Recv Send Send
> Socket Socket Message Elapsed
> Size Size Size Time Throughput
> bytes bytes bytes secs. 10^6bits/sec
>
> 87380 16384 16384 20.00 37213.05
>
> I guess this is a world record, my previous one was 34Gbps.
>
>
> include/net/tcp.h | 2
> net/ipv4/tcp_cong.c | 4 +
> net/ipv4/tcp_cubic.c | 91 +++++++++++++++++++----------------------
> 3 files changed, 47 insertions(+), 50 deletions(-)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index b8fdc6bab3f3..05815fbb490f 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -843,7 +843,7 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
> void tcp_get_allowed_congestion_control(char *buf, size_t len);
> int tcp_set_allowed_congestion_control(char *allowed);
> int tcp_set_congestion_control(struct sock *sk, const char *name);
> -void tcp_slow_start(struct tcp_sock *tp, u32 acked);
> +int tcp_slow_start(struct tcp_sock *tp, u32 acked);
> void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
>
> u32 tcp_reno_ssthresh(struct sock *sk);
> diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
> index 63c29dba68a8..f0fc696b9333 100644
> --- a/net/ipv4/tcp_cong.c
> +++ b/net/ipv4/tcp_cong.c
> @@ -360,13 +360,15 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
> * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
> * returns the leftover acks to adjust cwnd in congestion avoidance mode.
> */
> -void tcp_slow_start(struct tcp_sock *tp, u32 acked)
> +int tcp_slow_start(struct tcp_sock *tp, u32 acked)
> {
> u32 cwnd = tp->snd_cwnd + acked;
>
> if (cwnd > tp->snd_ssthresh)
> cwnd = tp->snd_ssthresh + 1;
> + acked -= cwnd - tp->snd_cwnd;
> tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
> + return acked;
> }
> EXPORT_SYMBOL_GPL(tcp_slow_start);
>
> diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
> index 6b6002416a73..c0e048929b74 100644
> --- a/net/ipv4/tcp_cubic.c
> +++ b/net/ipv4/tcp_cubic.c
> @@ -81,7 +81,6 @@ MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (mse
>
> /* BIC TCP Parameters */
> struct bictcp {
> - u32 cnt; /* increase cwnd by 1 after ACKs */
> u32 last_max_cwnd; /* last maximum snd_cwnd */
> u32 loss_cwnd; /* congestion window at last loss */
> u32 last_cwnd; /* the last snd_cwnd */
> @@ -93,20 +92,18 @@ struct bictcp {
> u32 epoch_start; /* beginning of an epoch */
> u32 ack_cnt; /* number of acks */
> u32 tcp_cwnd; /* estimated tcp cwnd */
> -#define ACK_RATIO_SHIFT 4
> -#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
> - u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */
> u8 sample_cnt; /* number of samples to decide curr_rtt */
> u8 found; /* the exit point is found? */
> u32 round_start; /* beginning of each round */
> u32 end_seq; /* end_seq of the round */
> u32 last_ack; /* last time when the ACK spacing is close */
> u32 curr_rtt; /* the minimum rtt of current round */
> + u32 last_bic_target;/* last target cwnd computed by cubic
> + * (not tcp_friendliness mode) */
> };
>
> static inline void bictcp_reset(struct bictcp *ca)
> {
> - ca->cnt = 0;
> ca->last_max_cwnd = 0;
> ca->last_cwnd = 0;
> ca->last_time = 0;
> @@ -114,7 +111,6 @@ static inline void bictcp_reset(struct bictcp *ca)
> ca->bic_K = 0;
> ca->delay_min = 0;
> ca->epoch_start = 0;
> - ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
> ca->ack_cnt = 0;
> ca->tcp_cwnd = 0;
> ca->found = 0;
> @@ -205,12 +201,14 @@ static u32 cubic_root(u64 a)
> /*
> * Compute congestion window to use.
> */
> -static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
> +static inline void bictcp_update(struct bictcp *ca, u32 pkts_acked, u32 cwnd)
> {
> - u32 delta, bic_target, max_cnt;
> + u32 delta, bic_target;
> u64 offs, t;
>
> - ca->ack_cnt++; /* count the number of ACKs */
> + ca->ack_cnt += pkts_acked; /* count the number of packets that
> + * have been ACKed
> + */
>
> if (ca->last_cwnd == cwnd &&
> (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
> @@ -221,7 +219,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
>
> if (ca->epoch_start == 0) {
> ca->epoch_start = tcp_time_stamp; /* record beginning */
> - ca->ack_cnt = 1; /* start counting */
> + ca->ack_cnt = pkts_acked; /* start counting */
> ca->tcp_cwnd = cwnd; /* syn with cubic */
>
> if (ca->last_max_cwnd <= cwnd) {
> @@ -269,19 +267,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
> else /* above origin*/
> bic_target = ca->bic_origin_point + delta;
>
> - /* cubic function - calc bictcp_cnt*/
> - if (bic_target > cwnd) {
> - ca->cnt = cwnd / (bic_target - cwnd);
> - } else {
> - ca->cnt = 100 * cwnd; /* very small increment*/
> - }
> -
> - /*
> - * The initial growth of cubic function may be too conservative
> - * when the available bandwidth is still unknown.
> - */
> - if (ca->last_max_cwnd == 0 && ca->cnt > 20)
> - ca->cnt = 20; /* increase cwnd 5% per RTT */
> + ca->last_bic_target = bic_target;
>
> /* TCP Friendly */
> if (tcp_friendliness) {
> @@ -292,18 +278,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
> ca->ack_cnt -= delta;
> ca->tcp_cwnd++;
> }
> -
> - if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */
> - delta = ca->tcp_cwnd - cwnd;
> - max_cnt = cwnd / delta;
> - if (ca->cnt > max_cnt)
> - ca->cnt = max_cnt;
> - }
> }
> -
> - ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
> - if (ca->cnt == 0) /* cannot be zero */
> - ca->cnt = 1;
> }
>
> static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
> @@ -314,13 +289,43 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
> if (!tcp_is_cwnd_limited(sk))
> return;
>
> + /* cwnd may first advance in slow start then move on to congestion
> + * control mode on a stretch ACK.
> + */
> if (tp->snd_cwnd <= tp->snd_ssthresh) {
> if (hystart && after(ack, ca->end_seq))
> bictcp_hystart_reset(sk);
> - tcp_slow_start(tp, acked);
> - } else {
> - bictcp_update(ca, tp->snd_cwnd);
> - tcp_cong_avoid_ai(tp, ca->cnt);
> + acked = tcp_slow_start(tp, acked);
> + }
> +
> + if (acked && tp->snd_cwnd > tp->snd_ssthresh) {
> + u32 target, cnt;
> +
> + bictcp_update(ca, acked, tp->snd_cwnd);
> + /* Compute target cwnd based on bic_target and tcp_cwnd
> + * (whichever is faster)
> + */
> + target = (ca->last_bic_target >= ca->tcp_cwnd) ?
> + ca->last_bic_target : ca->tcp_cwnd;
> + while (acked > 0) {
> + if (target > tp->snd_cwnd)
> + cnt = tp->snd_cwnd / (target - tp->snd_cwnd);
> + else
> + cnt = 100 * tp->snd_cwnd;
> +
> + /* The initial growth of cubic function may be
> + * too conservative when the available
> + * bandwidth is still unknown.
> + */
> + if (ca->last_max_cwnd == 0 && cnt > 20)
> + cnt = 20; /* increase cwnd 5% per RTT */
> +
> + if (cnt == 0) /* cannot be zero */
> + cnt = 1;
> +
> + tcp_cong_avoid_ai(tp, cnt);
> + acked--;
> + }
> }
> }
>
> @@ -411,20 +416,10 @@ static void hystart_update(struct sock *sk, u32 delay)
> */
> static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
> {
> - const struct inet_connection_sock *icsk = inet_csk(sk);
> const struct tcp_sock *tp = tcp_sk(sk);
> struct bictcp *ca = inet_csk_ca(sk);
> u32 delay;
>
> - if (icsk->icsk_ca_state == TCP_CA_Open) {
> - u32 ratio = ca->delayed_ack;
> -
> - ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
> - ratio += cnt;
> -
> - ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
> - }
> -
> /* Some calls are for duplicates without timetamps */
> if (rtt_us < 0)
> return;
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Dave Täht
http://www.bufferbloat.net/projects/bloat/wiki/Upcoming_Talks
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists