Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
kernel-fxtec-pro1x/net/dccp/ccids/ccid3.h
Gerrit Renker 20cbd3e120 dccp ccid-3: A lower bound for the inter-packet scheduling algorithm 
This fixes a subtle bug in the calculation of the inter-packet gap and shows
that t_delta, as it is currently used, is not needed.

The algorithm from RFC 5348, 8.3 below continually computes a send time t_nom,
which is initialised with the current time t_now; t_gran = 1E6 / HZ specifies
the scheduling granularity, s the packet size, and X the sending rate:

  t_distance = t_nom - t_now;		// in microseconds
  t_delta    = min(t_ipi, t_gran) / 2;	// `delta' parameter in microseconds

  if (t_distance >= t_delta) {
	reschedule after (t_distance / 1000) milliseconds;
  } else {
  	t_ipi  = s / X;			// inter-packet interval in usec
	t_nom += t_ipi;			// compute the next send time
	send packet now;
  }

Problem:
--------
Rescheduling requires a conversion into milliseconds (sk_reset_timer()). The
highest jiffy resolution with HZ=1000 is 1 millisecond, so using a higher
granularity does not make much sense here.

As a consequence, values of t_distance < 1000 are truncated to 0. This issue
has so far been resolved by using instead

  if (t_distance >= t_delta + 1000)
	reschedule after (t_distance / 1000) milliseconds;

This is unnecessarily large, a lower bound is t_delta' = max(t_delta, 1000).
And it implies a further simplification:

 a) when HZ >= 500, then t_delta <= t_gran/2 = 10^6/(2*HZ) <= 1000, so that
    t_delta' = MAX(1000, t_delta) = 1000 (constant value);

 b) when HZ < 500, then t_delta = 1/2*MIN(rtt, t_ipi, t_gran) <= t_gran/2,
    so that 1000 <= t_delta' <= t_gran/2.

The maximum error of using a constant t_delta in (b) is less than half a jiffy.

Fix:
----
The patch replaces t_delta with a constant, whose value depends on CONFIG_HZ,
changing the above algorithm to:

  if (t_distance >= t_delta')
	reschedule after (t_distance / 1000) milliseconds;

where t_delta' = 10^6/(2*HZ) if HZ < 500, and t_delta' = 1000 otherwise.

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2010-09-15 12:36:01 +02:00

172 lines
5.7 KiB
C
Raw Blame History

/*
* Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand.
* Copyright (c) 2007 The University of Aberdeen, Scotland, UK
*
* An implementation of the DCCP protocol
*
* This code has been developed by the University of Waikato WAND
* research group. For further information please see http://www.wand.net.nz/
* or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz
*
* This code also uses code from Lulea University, rereleased as GPL by its
* authors:
* Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
*
* Changes to meet Linux coding standards, to make it meet latest ccid3 draft
* and to make it work as a loadable module in the DCCP stack written by
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
*
* Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _DCCP_CCID3_H_
#define _DCCP_CCID3_H_
#include <linux/ktime.h>
#include <linux/list.h>
#include <linux/types.h>
#include <linux/tfrc.h>
#include "lib/tfrc.h"
#include "../ccid.h"
/* Two seconds as per RFC 5348, 4.2 */
#define TFRC_INITIAL_TIMEOUT (2 * USEC_PER_SEC)
/* Parameter t_mbi from [RFC 3448, 4.3]: backoff interval in seconds */
#define TFRC_T_MBI 64
/*
* The t_delta parameter (RFC 5348, 8.3): delays of less than %USEC_PER_MSEC are
* rounded down to 0, since sk_reset_timer() here uses millisecond granularity.
* Hence we can use a constant t_delta = %USEC_PER_MSEC when HZ >= 500. A coarse
* resolution of HZ < 500 means that the error is below one timer tick (t_gran)
* when using the constant t_delta = t_gran / 2 = %USEC_PER_SEC / (2 * HZ).
*/
#if (HZ >= 500)
# define TFRC_T_DELTA USEC_PER_MSEC
#else
# define TFRC_T_DELTA (USEC_PER_SEC / (2 * HZ))
#endif
enum ccid3_options {
TFRC_OPT_LOSS_EVENT_RATE = 192,
TFRC_OPT_LOSS_INTERVALS = 193,
TFRC_OPT_RECEIVE_RATE = 194,
};
struct ccid3_options_received {
u64 ccid3or_seqno:48,
ccid3or_loss_intervals_idx:16;
u16 ccid3or_loss_intervals_len;
u32 ccid3or_loss_event_rate;
u32 ccid3or_receive_rate;
};
/* TFRC sender states */
enum ccid3_hc_tx_states {
TFRC_SSTATE_NO_SENT = 1,
TFRC_SSTATE_NO_FBACK,
TFRC_SSTATE_FBACK,
TFRC_SSTATE_TERM,
};
/**
* struct ccid3_hc_tx_sock - CCID3 sender half-connection socket
* @tx_x: Current sending rate in 64 * bytes per second
* @tx_x_recv: Receive rate in 64 * bytes per second
* @tx_x_calc: Calculated rate in bytes per second
* @tx_rtt: Estimate of current round trip time in usecs
* @tx_p: Current loss event rate (0-1) scaled by 1000000
* @tx_s: Packet size in bytes
* @tx_t_rto: Nofeedback Timer setting in usecs
* @tx_t_ipi: Interpacket (send) interval (RFC 3448, 4.6) in usecs
* @tx_state: Sender state, one of %ccid3_hc_tx_states
* @tx_last_win_count: Last window counter sent
* @tx_t_last_win_count: Timestamp of earliest packet
* with last_win_count value sent
* @tx_no_feedback_timer: Handle to no feedback timer
* @tx_t_ld: Time last doubled during slow start
* @tx_t_nom: Nominal send time of next packet
* @tx_hist: Packet history
* @tx_options_received: Parsed set of retrieved options
*/
struct ccid3_hc_tx_sock {
u64 tx_x;
u64 tx_x_recv;
u32 tx_x_calc;
u32 tx_rtt;
u32 tx_p;
u32 tx_t_rto;
u32 tx_t_ipi;
u16 tx_s;
enum ccid3_hc_tx_states tx_state:8;
u8 tx_last_win_count;
ktime_t tx_t_last_win_count;
struct timer_list tx_no_feedback_timer;
ktime_t tx_t_ld;
ktime_t tx_t_nom;
struct tfrc_tx_hist_entry *tx_hist;
struct ccid3_options_received tx_options_received;
};
static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk)
{
struct ccid3_hc_tx_sock *hctx = ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid);
BUG_ON(hctx == NULL);
return hctx;
}
/* TFRC receiver states */
enum ccid3_hc_rx_states {
TFRC_RSTATE_NO_DATA = 1,
TFRC_RSTATE_DATA,
TFRC_RSTATE_TERM = 127,
};
/**
* struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket
* @rx_last_counter: Tracks window counter (RFC 4342, 8.1)
* @rx_state: Receiver state, one of %ccid3_hc_rx_states
* @rx_bytes_recv: Total sum of DCCP payload bytes
* @rx_x_recv: Receiver estimate of send rate (RFC 3448, sec. 4.3)
* @rx_rtt: Receiver estimate of RTT
* @rx_tstamp_last_feedback: Time at which last feedback was sent
* @rx_hist: Packet history (loss detection + RTT sampling)
* @rx_li_hist: Loss Interval database
* @rx_s: Received packet size in bytes
* @rx_pinv: Inverse of Loss Event Rate (RFC 4342, sec. 8.5)
*/
struct ccid3_hc_rx_sock {
u8 rx_last_counter:4;
enum ccid3_hc_rx_states rx_state:8;
u32 rx_bytes_recv;
u32 rx_x_recv;
u32 rx_rtt;
ktime_t rx_tstamp_last_feedback;
struct tfrc_rx_hist rx_hist;
struct tfrc_loss_hist rx_li_hist;
u16 rx_s;
#define rx_pinv rx_li_hist.i_mean
};
static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk)
{
struct ccid3_hc_rx_sock *hcrx = ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid);
BUG_ON(hcrx == NULL);
return hcrx;
}
#endif /* _DCCP_CCID3_H_ */
Reference in a new issue View git blame Copy permalink