Patchwork [5/6] tcp_cubic: fix clock dependency

login
register
mail settings
Submitter stephen hemminger
Date March 10, 2011, 4:51 p.m.
Message ID <20110310165329.187344604@vyatta.com>
Download mbox | patch
Permalink /patch/86314/
State Superseded
Delegated to: David Miller
Headers show

Comments

stephen hemminger - March 10, 2011, 4:51 p.m.
The hystart code was written with assumption that HZ=1000.
Replace the use of jiffies with bictcp_clock as a millisecond
real time clock. 

Warning: this is still experimental, there may still be mistakes
in units (ms vs. jiffies).

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

P.s: tried using ktime_t but 'struct bictcp' is bumping against limit
of CA_PRIV_SIZE.



--
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
Sangtae Ha - March 11, 2011, 4:26 p.m.
Thanks Stephen.

The patch is useful since I had to increase CA_PRIV_SIZE to use
ktime_t for the testing.
Indeed, CUBIC already used up the limit CA_PRIV_SIZE for its variables.

I've got compilation errors because of "jiffies_to_ms" and I corrected
it to "jiffies_to_msecs"

-       return jiffies_to_ms(jiffies);
+       return jiffies_to_msecs(jiffies);

Also, >= instead of <=, which Lucas already found and reported.

-                       if ((s32)(now - ca->round_start) <= ca->delay_min >> 4)
+                       if ((s32)(now - ca->round_start) >= ca->delay_min >> 4)


Sangtae

On Thu, Mar 10, 2011 at 11:51 AM, Stephen Hemminger
<shemminger@vyatta.com> wrote:
> The hystart code was written with assumption that HZ=1000.
> Replace the use of jiffies with bictcp_clock as a millisecond
> real time clock.
>
> Warning: this is still experimental, there may still be mistakes
> in units (ms vs. jiffies).
>
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
>
> P.s: tried using ktime_t but 'struct bictcp' is bumping against limit
> of CA_PRIV_SIZE.
>
> --- a/net/ipv4/tcp_cubic.c      2011-03-10 08:35:45.532695373 -0800
> +++ b/net/ipv4/tcp_cubic.c      2011-03-10 08:35:59.968882888 -0800
> @@ -88,7 +88,7 @@ struct bictcp {
>        u32     last_time;      /* time when updated last_cwnd */
>        u32     bic_origin_point;/* origin point of bic function */
>        u32     bic_K;          /* time to origin point from the beginning of the current epoch */
> -       u32     delay_min;      /* min delay */
> +       u32     delay_min;      /* min delay (msec << 3) */
>        u32     epoch_start;    /* beginning of an epoch */
>        u32     ack_cnt;        /* number of acks */
>        u32     tcp_cwnd;       /* estimated tcp cwnd */
> @@ -98,7 +98,7 @@ struct bictcp {
>        u8      found;          /* the exit point is found? */
>        u32     round_start;    /* beginning of each round */
>        u32     end_seq;        /* end_seq of the round */
> -       u32     last_jiffies;   /* last time when the ACK spacing is close */
> +       u32     last_ack;       /* last time when the ACK spacing is close */
>        u32     curr_rtt;       /* the minimum rtt of current round */
>  };
>
> @@ -119,12 +119,21 @@ static inline void bictcp_reset(struct b
>        ca->found = 0;
>  }
>
> +static inline u32 bictcp_clock(void)
> +{
> +#if HZ < 1000
> +       return ktime_to_ms(ktime_get_real());
> +#else
> +       return jiffies_to_ms(jiffies);
> +#endif
> +}
> +
>  static inline void bictcp_hystart_reset(struct sock *sk)
>  {
>        struct tcp_sock *tp = tcp_sk(sk);
>        struct bictcp *ca = inet_csk_ca(sk);
>
> -       ca->round_start = ca->last_jiffies = jiffies;
> +       ca->round_start = ca->last_ack = bictcp_clock();
>        ca->end_seq = tp->snd_nxt;
>        ca->curr_rtt = 0;
>        ca->sample_cnt = 0;
> @@ -239,7 +248,7 @@ static inline void bictcp_update(struct
>         */
>
>        /* change the unit from HZ to bictcp_HZ */
> -       t = ((tcp_time_stamp + (ca->delay_min>>3) - ca->epoch_start)
> +       t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) - ca->epoch_start)
>             << BICTCP_HZ) / HZ;
>
>        if (t < ca->bic_K)              /* t - K */
> @@ -342,14 +351,12 @@ static void hystart_update(struct sock *
>        struct bictcp *ca = inet_csk_ca(sk);
>
>        if (!(ca->found & hystart_detect)) {
> -               u32 curr_jiffies = jiffies;
> +               u32 now = bictcp_clock();
>
>                /* first detection parameter - ack-train detection */
> -               if ((s32)(curr_jiffies - ca->last_jiffies) <=
> -                   msecs_to_jiffies(hystart_ack_delta)) {
> -                       ca->last_jiffies = curr_jiffies;
> -                       if ((s32) (curr_jiffies - ca->round_start) <=
> -                           ca->delay_min >> 4)
> +               if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
> +                       ca->last_ack = now;
> +                       if ((s32)(now - ca->round_start) <= ca->delay_min >> 4)
>                                ca->found |= HYSTART_ACK_TRAIN;
>                }
>
> @@ -396,7 +403,7 @@ static void bictcp_acked(struct sock *sk
>        if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
>                return;
>
> -       delay = usecs_to_jiffies(rtt_us) << 3;
> +       delay = (rtt_us << 3) / USEC_PER_MSEC;
>        if (delay == 0)
>                delay = 1;
>
>
>
>
--
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

Patch

--- a/net/ipv4/tcp_cubic.c	2011-03-10 08:35:45.532695373 -0800
+++ b/net/ipv4/tcp_cubic.c	2011-03-10 08:35:59.968882888 -0800
@@ -88,7 +88,7 @@  struct bictcp {
 	u32	last_time;	/* time when updated last_cwnd */
 	u32	bic_origin_point;/* origin point of bic function */
 	u32	bic_K;		/* time to origin point from the beginning of the current epoch */
-	u32	delay_min;	/* min delay */
+	u32	delay_min;	/* min delay (msec << 3) */
 	u32	epoch_start;	/* beginning of an epoch */
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
@@ -98,7 +98,7 @@  struct bictcp {
 	u8	found;		/* the exit point is found? */
 	u32	round_start;	/* beginning of each round */
 	u32	end_seq;	/* end_seq of the round */
-	u32	last_jiffies;	/* last time when the ACK spacing is close */
+	u32	last_ack;	/* last time when the ACK spacing is close */
 	u32	curr_rtt;	/* the minimum rtt of current round */
 };
 
@@ -119,12 +119,21 @@  static inline void bictcp_reset(struct b
 	ca->found = 0;
 }
 
+static inline u32 bictcp_clock(void)
+{
+#if HZ < 1000
+	return ktime_to_ms(ktime_get_real());
+#else
+	return jiffies_to_ms(jiffies);
+#endif
+}
+
 static inline void bictcp_hystart_reset(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	ca->round_start = ca->last_jiffies = jiffies;
+	ca->round_start = ca->last_ack = bictcp_clock();
 	ca->end_seq = tp->snd_nxt;
 	ca->curr_rtt = 0;
 	ca->sample_cnt = 0;
@@ -239,7 +248,7 @@  static inline void bictcp_update(struct
 	 */
 
 	/* change the unit from HZ to bictcp_HZ */
-	t = ((tcp_time_stamp + (ca->delay_min>>3) - ca->epoch_start)
+	t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) - ca->epoch_start)
 	     << BICTCP_HZ) / HZ;
 
 	if (t < ca->bic_K)		/* t - K */
@@ -342,14 +351,12 @@  static void hystart_update(struct sock *
 	struct bictcp *ca = inet_csk_ca(sk);
 
 	if (!(ca->found & hystart_detect)) {
-		u32 curr_jiffies = jiffies;
+		u32 now = bictcp_clock();
 
 		/* first detection parameter - ack-train detection */
-		if ((s32)(curr_jiffies - ca->last_jiffies) <=
-		    msecs_to_jiffies(hystart_ack_delta)) {
-			ca->last_jiffies = curr_jiffies;
-			if ((s32) (curr_jiffies - ca->round_start) <=
-			    ca->delay_min >> 4)
+		if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
+			ca->last_ack = now;
+			if ((s32)(now - ca->round_start) <= ca->delay_min >> 4)
 				ca->found |= HYSTART_ACK_TRAIN;
 		}
 
@@ -396,7 +403,7 @@  static void bictcp_acked(struct sock *sk
 	if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
 		return;
 
-	delay = usecs_to_jiffies(rtt_us) << 3;
+	delay = (rtt_us << 3) / USEC_PER_MSEC;
 	if (delay == 0)
 		delay = 1;