License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
2005-11-06 04:14:03 +08:00
|
|
|
#ifndef __NET_SCHED_RED_H
|
|
|
|
#define __NET_SCHED_RED_H
|
|
|
|
|
|
|
|
#include <linux/types.h>
|
2011-11-24 09:12:59 +08:00
|
|
|
#include <linux/bug.h>
|
2005-11-06 04:14:03 +08:00
|
|
|
#include <net/pkt_sched.h>
|
|
|
|
#include <net/inet_ecn.h>
|
|
|
|
#include <net/dsfield.h>
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
#include <linux/reciprocal_div.h>
|
2005-11-06 04:14:03 +08:00
|
|
|
|
|
|
|
/* Random Early Detection (RED) algorithm.
|
|
|
|
=======================================
|
|
|
|
|
|
|
|
Source: Sally Floyd and Van Jacobson, "Random Early Detection Gateways
|
|
|
|
for Congestion Avoidance", 1993, IEEE/ACM Transactions on Networking.
|
|
|
|
|
|
|
|
This file codes a "divisionless" version of RED algorithm
|
|
|
|
as written down in Fig.17 of the paper.
|
|
|
|
|
|
|
|
Short description.
|
|
|
|
------------------
|
|
|
|
|
|
|
|
When a new packet arrives we calculate the average queue length:
|
|
|
|
|
|
|
|
avg = (1-W)*avg + W*current_queue_len,
|
|
|
|
|
|
|
|
W is the filter time constant (chosen as 2^(-Wlog)), it controls
|
|
|
|
the inertia of the algorithm. To allow larger bursts, W should be
|
|
|
|
decreased.
|
|
|
|
|
|
|
|
if (avg > th_max) -> packet marked (dropped).
|
|
|
|
if (avg < th_min) -> packet passes.
|
|
|
|
if (th_min < avg < th_max) we calculate probability:
|
|
|
|
|
|
|
|
Pb = max_P * (avg - th_min)/(th_max-th_min)
|
|
|
|
|
|
|
|
and mark (drop) packet with this probability.
|
|
|
|
Pb changes from 0 (at avg==th_min) to max_P (avg==th_max).
|
|
|
|
max_P should be small (not 1), usually 0.01..0.02 is good value.
|
|
|
|
|
|
|
|
max_P is chosen as a number, so that max_P/(th_max-th_min)
|
|
|
|
is a negative power of two in order arithmetics to contain
|
|
|
|
only shifts.
|
|
|
|
|
|
|
|
|
|
|
|
Parameters, settable by user:
|
|
|
|
-----------------------------
|
|
|
|
|
|
|
|
qth_min - bytes (should be < qth_max/2)
|
|
|
|
qth_max - bytes (should be at least 2*qth_min and less limit)
|
|
|
|
Wlog - bits (<32) log(1/W).
|
|
|
|
Plog - bits (<32)
|
|
|
|
|
|
|
|
Plog is related to max_P by formula:
|
|
|
|
|
|
|
|
max_P = (qth_max-qth_min)/2^Plog;
|
|
|
|
|
|
|
|
F.e. if qth_max=128K and qth_min=32K, then Plog=22
|
|
|
|
corresponds to max_P=0.02
|
|
|
|
|
|
|
|
Scell_log
|
|
|
|
Stab
|
|
|
|
|
|
|
|
Lookup table for log((1-W)^(t/t_ave).
|
|
|
|
|
|
|
|
|
|
|
|
NOTES:
|
|
|
|
|
|
|
|
Upper bound on W.
|
|
|
|
-----------------
|
|
|
|
|
|
|
|
If you want to allow bursts of L packets of size S,
|
|
|
|
you should choose W:
|
|
|
|
|
|
|
|
L + 1 - th_min/S < (1-(1-W)^L)/W
|
|
|
|
|
|
|
|
th_min/S = 32 th_min/S = 4
|
|
|
|
|
|
|
|
log(W) L
|
|
|
|
-1 33
|
|
|
|
-2 35
|
|
|
|
-3 39
|
|
|
|
-4 46
|
|
|
|
-5 57
|
|
|
|
-6 75
|
|
|
|
-7 101
|
|
|
|
-8 135
|
|
|
|
-9 190
|
|
|
|
etc.
|
|
|
|
*/
|
|
|
|
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
/*
|
|
|
|
* Adaptative RED : An Algorithm for Increasing the Robustness of RED's AQM
|
|
|
|
* (Sally FLoyd, Ramakrishna Gummadi, and Scott Shenker) August 2001
|
|
|
|
*
|
|
|
|
* Every 500 ms:
|
|
|
|
* if (avg > target and max_p <= 0.5)
|
|
|
|
* increase max_p : max_p += alpha;
|
|
|
|
* else if (avg < target and max_p >= 0.01)
|
|
|
|
* decrease max_p : max_p *= beta;
|
|
|
|
*
|
|
|
|
* target :[qth_min + 0.4*(qth_min - qth_max),
|
|
|
|
* qth_min + 0.6*(qth_min - qth_max)].
|
|
|
|
* alpha : min(0.01, max_p / 4)
|
|
|
|
* beta : 0.9
|
|
|
|
* max_P is a Q0.32 fixed point number (with 32 bits mantissa)
|
|
|
|
* max_P between 0.01 and 0.5 (1% - 50%) [ Its no longer a negative power of two ]
|
|
|
|
*/
|
|
|
|
#define RED_ONE_PERCENT ((u32)DIV_ROUND_CLOSEST(1ULL<<32, 100))
|
|
|
|
|
|
|
|
#define MAX_P_MIN (1 * RED_ONE_PERCENT)
|
|
|
|
#define MAX_P_MAX (50 * RED_ONE_PERCENT)
|
|
|
|
#define MAX_P_ALPHA(val) min(MAX_P_MIN, val / 4)
|
|
|
|
|
2005-11-06 04:14:03 +08:00
|
|
|
#define RED_STAB_SIZE 256
|
|
|
|
#define RED_STAB_MASK (RED_STAB_SIZE - 1)
|
|
|
|
|
2009-11-03 11:26:03 +08:00
|
|
|
struct red_stats {
|
2005-11-06 04:14:03 +08:00
|
|
|
u32 prob_drop; /* Early probability drops */
|
|
|
|
u32 prob_mark; /* Early probability marks */
|
|
|
|
u32 forced_drop; /* Forced drops, qavg > max_thresh */
|
|
|
|
u32 forced_mark; /* Forced marks, qavg > max_thresh */
|
|
|
|
u32 pdrop; /* Drops due to queue limits */
|
|
|
|
u32 other; /* Drops due to drop() calls */
|
|
|
|
};
|
|
|
|
|
2009-11-03 11:26:03 +08:00
|
|
|
struct red_parms {
|
2005-11-06 04:14:03 +08:00
|
|
|
/* Parameters */
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
u32 qth_min; /* Min avg length threshold: Wlog scaled */
|
|
|
|
u32 qth_max; /* Max avg length threshold: Wlog scaled */
|
2005-11-06 04:14:03 +08:00
|
|
|
u32 Scell_max;
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
u32 max_P; /* probability, [0 .. 1.0] 32 scaled */
|
reciprocal_divide: update/correction of the algorithm
Jakub Zawadzki noticed that some divisions by reciprocal_divide()
were not correct [1][2], which he could also show with BPF code
after divisions are transformed into reciprocal_value() for runtime
invariance which can be passed to reciprocal_divide() later on;
reverse in BPF dump ended up with a different, off-by-one K in
some situations.
This has been fixed by Eric Dumazet in commit aee636c4809fa5
("bpf: do not use reciprocal divide"). This follow-up patch
improves reciprocal_value() and reciprocal_divide() to work in
all cases by using Granlund and Montgomery method, so that also
future use is safe and without any non-obvious side-effects.
Known problems with the old implementation were that division by 1
always returned 0 and some off-by-ones when the dividend and divisor
where very large. This seemed to not be problematic with its
current users, as far as we can tell. Eric Dumazet checked for
the slab usage, we cannot surely say so in the case of flex_array.
Still, in order to fix that, we propose an extension from the
original implementation from commit 6a2d7a955d8d resp. [3][4],
by using the algorithm proposed in "Division by Invariant Integers
Using Multiplication" [5], Torbjörn Granlund and Peter L.
Montgomery, that is, pseudocode for q = n/d where q, n, d is in
u32 universe:
1) Initialization:
int l = ceil(log_2 d)
uword m' = floor((1<<32)*((1<<l)-d)/d)+1
int sh_1 = min(l,1)
int sh_2 = max(l-1,0)
2) For q = n/d, all uword:
uword t = (n*m')>>32
q = (t+((n-t)>>sh_1))>>sh_2
The assembler implementation from Agner Fog [6] also helped a lot
while implementing. We have tested the implementation on x86_64,
ppc64, i686, s390x; on x86_64/haswell we're still half the latency
compared to normal divide.
Joint work with Daniel Borkmann.
[1] http://www.wireshark.org/~darkjames/reciprocal-buggy.c
[2] http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c
[3] https://gmplib.org/~tege/division-paper.pdf
[4] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html
[5] http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2556
[6] http://www.agner.org/optimize/asmlib.zip
Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Austin S Hemmelgarn <ahferroin7@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: Jesse Gross <jesse@nicira.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 09:29:41 +08:00
|
|
|
/* reciprocal_value(max_P / qth_delta) */
|
|
|
|
struct reciprocal_value max_P_reciprocal;
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
u32 qth_delta; /* max_th - min_th */
|
|
|
|
u32 target_min; /* min_th + 0.4*(max_th - min_th) */
|
|
|
|
u32 target_max; /* min_th + 0.6*(max_th - min_th) */
|
2005-11-06 04:14:03 +08:00
|
|
|
u8 Scell_log;
|
|
|
|
u8 Wlog; /* log(W) */
|
|
|
|
u8 Plog; /* random number bits */
|
|
|
|
u8 Stab[RED_STAB_SIZE];
|
2012-01-05 10:25:16 +08:00
|
|
|
};
|
2005-11-06 04:14:03 +08:00
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
struct red_vars {
|
2005-11-06 04:14:03 +08:00
|
|
|
/* Variables */
|
|
|
|
int qcount; /* Number of packets since last random
|
|
|
|
number generation */
|
|
|
|
u32 qR; /* Cached random number */
|
|
|
|
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
unsigned long qavg; /* Average queue length: Wlog scaled */
|
2011-11-30 20:10:53 +08:00
|
|
|
ktime_t qidlestart; /* Start of current idle period */
|
2005-11-06 04:14:03 +08:00
|
|
|
};
|
|
|
|
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
static inline u32 red_maxp(u8 Plog)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
return Plog < 32 ? (~0U >> Plog) : ~0U;
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline void red_set_vars(struct red_vars *v)
|
|
|
|
{
|
|
|
|
/* Reset average queue length, the value is strictly bound
|
|
|
|
* to the parameters below, reseting hurts a bit but leaving
|
|
|
|
* it might result in an unreasonable qavg for a while. --TGR
|
|
|
|
*/
|
|
|
|
v->qavg = 0;
|
|
|
|
|
|
|
|
v->qcount = -1;
|
|
|
|
}
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
|
2021-03-11 00:26:41 +08:00
|
|
|
static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog,
|
|
|
|
u8 Scell_log, u8 *stab)
|
2017-12-04 19:31:11 +08:00
|
|
|
{
|
2021-03-26 02:14:53 +08:00
|
|
|
if (fls(qth_min) + Wlog >= 32)
|
2017-12-04 19:31:11 +08:00
|
|
|
return false;
|
2021-03-26 02:14:53 +08:00
|
|
|
if (fls(qth_max) + Wlog >= 32)
|
2017-12-04 19:31:11 +08:00
|
|
|
return false;
|
2020-12-25 14:23:44 +08:00
|
|
|
if (Scell_log >= 32)
|
|
|
|
return false;
|
2017-12-04 19:31:11 +08:00
|
|
|
if (qth_max < qth_min)
|
|
|
|
return false;
|
2021-03-11 00:26:41 +08:00
|
|
|
if (stab) {
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < RED_STAB_SIZE; i++)
|
|
|
|
if (stab[i] >= 32)
|
|
|
|
return false;
|
|
|
|
}
|
2017-12-04 19:31:11 +08:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
net: sched: Allow extending set of supported RED flags
The qdiscs RED, GRED, SFQ and CHOKE use different subsets of the same pool
of global RED flags. These are passed in tc_red_qopt.flags. However none of
these qdiscs validate the flag field, and just copy it over wholesale to
internal structures, and later dump it back. (An exception is GRED, which
does validate for VQs -- however not for the main setup.)
A broken userspace can therefore configure a qdisc with arbitrary
unsupported flags, and later expect to see the flags on qdisc dump. The
current ABI therefore allows storage of several bits of custom data to
qdisc instances of the types mentioned above. How many bits, depends on
which flags are meaningful for the qdisc in question. E.g. SFQ recognizes
flags ECN and HARDDROP, and the rest is not interpreted.
If SFQ ever needs to support ADAPTATIVE, it needs another way of doing it,
and at the same time it needs to retain the possibility to store 6 bits of
uninterpreted data. Likewise RED, which adds a new flag later in this
patchset.
To that end, this patch adds a new function, red_get_flags(), to split the
passed flags of RED-like qdiscs to flags and user bits, and
red_validate_flags() to validate the resulting configuration. It further
adds a new attribute, TCA_RED_FLAGS, to pass arbitrary flags.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-13 07:10:56 +08:00
|
|
|
static inline int red_get_flags(unsigned char qopt_flags,
|
|
|
|
unsigned char historic_mask,
|
|
|
|
struct nlattr *flags_attr,
|
|
|
|
unsigned char supported_mask,
|
|
|
|
struct nla_bitfield32 *p_flags,
|
|
|
|
unsigned char *p_userbits,
|
|
|
|
struct netlink_ext_ack *extack)
|
|
|
|
{
|
|
|
|
struct nla_bitfield32 flags;
|
|
|
|
|
|
|
|
if (qopt_flags && flags_attr) {
|
|
|
|
NL_SET_ERR_MSG_MOD(extack, "flags should be passed either through qopt, or through a dedicated attribute");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (flags_attr) {
|
|
|
|
flags = nla_get_bitfield32(flags_attr);
|
|
|
|
} else {
|
|
|
|
flags.selector = historic_mask;
|
|
|
|
flags.value = qopt_flags & historic_mask;
|
|
|
|
}
|
|
|
|
|
|
|
|
*p_flags = flags;
|
|
|
|
*p_userbits = qopt_flags & ~historic_mask;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int red_validate_flags(unsigned char flags,
|
|
|
|
struct netlink_ext_ack *extack)
|
|
|
|
{
|
2020-03-13 07:10:57 +08:00
|
|
|
if ((flags & TC_RED_NODROP) && !(flags & TC_RED_ECN)) {
|
|
|
|
NL_SET_ERR_MSG_MOD(extack, "nodrop mode is only meaningful with ECN");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
net: sched: Allow extending set of supported RED flags
The qdiscs RED, GRED, SFQ and CHOKE use different subsets of the same pool
of global RED flags. These are passed in tc_red_qopt.flags. However none of
these qdiscs validate the flag field, and just copy it over wholesale to
internal structures, and later dump it back. (An exception is GRED, which
does validate for VQs -- however not for the main setup.)
A broken userspace can therefore configure a qdisc with arbitrary
unsupported flags, and later expect to see the flags on qdisc dump. The
current ABI therefore allows storage of several bits of custom data to
qdisc instances of the types mentioned above. How many bits, depends on
which flags are meaningful for the qdisc in question. E.g. SFQ recognizes
flags ECN and HARDDROP, and the rest is not interpreted.
If SFQ ever needs to support ADAPTATIVE, it needs another way of doing it,
and at the same time it needs to retain the possibility to store 6 bits of
uninterpreted data. Likewise RED, which adds a new flag later in this
patchset.
To that end, this patch adds a new function, red_get_flags(), to split the
passed flags of RED-like qdiscs to flags and user bits, and
red_validate_flags() to validate the resulting configuration. It further
adds a new attribute, TCA_RED_FLAGS, to pass arbitrary flags.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-13 07:10:56 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-11-06 04:14:03 +08:00
|
|
|
static inline void red_set_parms(struct red_parms *p,
|
|
|
|
u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog,
|
2011-12-09 10:46:45 +08:00
|
|
|
u8 Scell_log, u8 *stab, u32 max_P)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
int delta = qth_max - qth_min;
|
2011-12-09 10:46:45 +08:00
|
|
|
u32 max_p_delta;
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
|
2005-11-06 04:14:03 +08:00
|
|
|
p->qth_min = qth_min << Wlog;
|
|
|
|
p->qth_max = qth_max << Wlog;
|
|
|
|
p->Wlog = Wlog;
|
|
|
|
p->Plog = Plog;
|
2017-12-04 19:31:10 +08:00
|
|
|
if (delta <= 0)
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
delta = 1;
|
|
|
|
p->qth_delta = delta;
|
2011-12-09 10:46:45 +08:00
|
|
|
if (!max_P) {
|
|
|
|
max_P = red_maxp(Plog);
|
|
|
|
max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */
|
|
|
|
}
|
|
|
|
p->max_P = max_P;
|
|
|
|
max_p_delta = max_P / delta;
|
|
|
|
max_p_delta = max(max_p_delta, 1U);
|
|
|
|
p->max_P_reciprocal = reciprocal_value(max_p_delta);
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
|
|
|
|
/* RED Adaptative target :
|
|
|
|
* [min_th + 0.4*(min_th - max_th),
|
|
|
|
* min_th + 0.6*(min_th - max_th)].
|
|
|
|
*/
|
|
|
|
delta /= 5;
|
|
|
|
p->target_min = qth_min + 2*delta;
|
|
|
|
p->target_max = qth_min + 3*delta;
|
|
|
|
|
2005-11-06 04:14:03 +08:00
|
|
|
p->Scell_log = Scell_log;
|
|
|
|
p->Scell_max = (255 << Scell_log);
|
|
|
|
|
net_sched: sfq: add optional RED on top of SFQ
Adds an optional Random Early Detection on each SFQ flow queue.
Traditional SFQ limits count of packets, while RED permits to also
control number of bytes per flow, and adds ECN capability as well.
1) We dont handle the idle time management in this RED implementation,
since each 'new flow' begins with a null qavg. We really want to address
backlogged flows.
2) if headdrop is selected, we try to ecn mark first packet instead of
currently enqueued packet. This gives faster feedback for tcp flows
compared to traditional RED [ marking the last packet in queue ]
Example of use :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 4sec sfq \
limit 3000 headdrop flows 512 divisor 16384 \
redflowlimit 100000 min 8000 max 60000 probability 0.20 ecn
qdisc sfq 10: parent 1:1 limit 3000p quantum 1514b depth 127 headdrop
flows 512/16384 divisor 16384
ewma 6 min 8000b max 60000b probability 0.2 ecn
prob_mark 0 prob_mark_head 4876 prob_drop 6131
forced_mark 0 forced_mark_head 0 forced_drop 0
Sent 1175211782 bytes 777537 pkt (dropped 6131, overlimits 11007
requeues 0)
rate 99483Kbit 8219pps backlog 689392b 456p requeues 0
In this test, with 64 netperf TCP_STREAM sessions, 50% using ECN enabled
flows, we can see number of packets CE marked is smaller than number of
drops (for non ECN flows)
If same test is run, without RED, we can check backlog is much bigger.
qdisc sfq 10: parent 1:1 limit 3000p quantum 1514b depth 127 headdrop
flows 512/16384 divisor 16384
Sent 1148683617 bytes 795006 pkt (dropped 0, overlimits 0 requeues 0)
rate 98429Kbit 8521pps backlog 1221290b 841p requeues 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Stephen Hemminger <shemminger@vyatta.com>
CC: Dave Taht <dave.taht@gmail.com>
Tested-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-01-06 14:31:44 +08:00
|
|
|
if (stab)
|
|
|
|
memcpy(p->Stab, stab, sizeof(p->Stab));
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline int red_is_idling(const struct red_vars *v)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
2016-12-25 18:38:40 +08:00
|
|
|
return v->qidlestart != 0;
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline void red_start_of_idle_period(struct red_vars *v)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
2012-01-05 10:25:16 +08:00
|
|
|
v->qidlestart = ktime_get();
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline void red_end_of_idle_period(struct red_vars *v)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
2016-12-25 18:38:40 +08:00
|
|
|
v->qidlestart = 0;
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline void red_restart(struct red_vars *v)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
2012-01-05 10:25:16 +08:00
|
|
|
red_end_of_idle_period(v);
|
|
|
|
v->qavg = 0;
|
|
|
|
v->qcount = -1;
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms *p,
|
|
|
|
const struct red_vars *v)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
2012-01-05 10:25:16 +08:00
|
|
|
s64 delta = ktime_us_delta(ktime_get(), v->qidlestart);
|
2011-11-30 20:10:53 +08:00
|
|
|
long us_idle = min_t(s64, delta, p->Scell_max);
|
2005-11-06 04:14:03 +08:00
|
|
|
int shift;
|
|
|
|
|
|
|
|
/*
|
2021-03-19 12:46:23 +08:00
|
|
|
* The problem: ideally, average length queue recalculation should
|
2005-11-06 04:14:03 +08:00
|
|
|
* be done over constant clock intervals. This is too expensive, so
|
|
|
|
* that the calculation is driven by outgoing packets.
|
|
|
|
* When the queue is idle we have to model this clock by hand.
|
|
|
|
*
|
|
|
|
* SF+VJ proposed to "generate":
|
|
|
|
*
|
|
|
|
* m = idletime / (average_pkt_size / bandwidth)
|
|
|
|
*
|
|
|
|
* dummy packets as a burst after idle time, i.e.
|
|
|
|
*
|
2012-04-16 11:17:22 +08:00
|
|
|
* v->qavg *= (1-W)^m
|
2005-11-06 04:14:03 +08:00
|
|
|
*
|
|
|
|
* This is an apparently overcomplicated solution (f.e. we have to
|
|
|
|
* precompute a table to make this calculation in reasonable time)
|
|
|
|
* I believe that a simpler model may be used here,
|
|
|
|
* but it is field for experiments.
|
|
|
|
*/
|
|
|
|
|
|
|
|
shift = p->Stab[(us_idle >> p->Scell_log) & RED_STAB_MASK];
|
|
|
|
|
|
|
|
if (shift)
|
2012-01-05 10:25:16 +08:00
|
|
|
return v->qavg >> shift;
|
2005-11-06 04:14:03 +08:00
|
|
|
else {
|
|
|
|
/* Approximate initial part of exponent with linear function:
|
|
|
|
*
|
|
|
|
* (1-W)^m ~= 1-mW + ...
|
|
|
|
*
|
|
|
|
* Seems, it is the best solution to
|
|
|
|
* problem of too coarse exponent tabulation.
|
|
|
|
*/
|
2012-01-05 10:25:16 +08:00
|
|
|
us_idle = (v->qavg * (u64)us_idle) >> p->Scell_log;
|
2005-11-06 04:14:03 +08:00
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
if (us_idle < (v->qavg >> 1))
|
|
|
|
return v->qavg - us_idle;
|
2005-11-06 04:14:03 +08:00
|
|
|
else
|
2012-01-05 10:25:16 +08:00
|
|
|
return v->qavg >> 1;
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p,
|
2012-01-05 10:25:16 +08:00
|
|
|
const struct red_vars *v,
|
2005-11-06 04:14:03 +08:00
|
|
|
unsigned int backlog)
|
|
|
|
{
|
|
|
|
/*
|
2012-04-16 11:17:22 +08:00
|
|
|
* NOTE: v->qavg is fixed point number with point at Wlog.
|
2005-11-06 04:14:03 +08:00
|
|
|
* The formula below is equvalent to floating point
|
|
|
|
* version:
|
|
|
|
*
|
|
|
|
* qavg = qavg*(1-W) + backlog*W;
|
|
|
|
*
|
|
|
|
* --ANK (980924)
|
|
|
|
*/
|
2012-01-05 10:25:16 +08:00
|
|
|
return v->qavg + (backlog - (v->qavg >> p->Wlog));
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
static inline unsigned long red_calc_qavg(const struct red_parms *p,
|
2012-01-05 10:25:16 +08:00
|
|
|
const struct red_vars *v,
|
2005-11-06 04:14:03 +08:00
|
|
|
unsigned int backlog)
|
|
|
|
{
|
2012-01-05 10:25:16 +08:00
|
|
|
if (!red_is_idling(v))
|
|
|
|
return red_calc_qavg_no_idle_time(p, v, backlog);
|
2005-11-06 04:14:03 +08:00
|
|
|
else
|
2012-01-05 10:25:16 +08:00
|
|
|
return red_calc_qavg_from_idle_time(p, v);
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
|
|
|
|
static inline u32 red_random(const struct red_parms *p)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
2014-01-11 20:15:59 +08:00
|
|
|
return reciprocal_divide(prandom_u32(), p->max_P_reciprocal);
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline int red_mark_probability(const struct red_parms *p,
|
|
|
|
const struct red_vars *v,
|
|
|
|
unsigned long qavg)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
|
|
|
/* The formula used below causes questions.
|
|
|
|
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
OK. qR is random number in the interval
|
|
|
|
(0..1/max_P)*(qth_max-qth_min)
|
2005-11-06 04:14:03 +08:00
|
|
|
i.e. 0..(2^Plog). If we used floating point
|
|
|
|
arithmetics, it would be: (2^Plog)*rnd_num,
|
|
|
|
where rnd_num is less 1.
|
|
|
|
|
|
|
|
Taking into account, that qavg have fixed
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
point at Wlog, two lines
|
2005-11-06 04:14:03 +08:00
|
|
|
below have the following floating point equivalent:
|
|
|
|
|
|
|
|
max_P*(qavg - qth_min)/(qth_max-qth_min) < rnd/qcount
|
|
|
|
|
|
|
|
Any questions? --ANK (980924)
|
|
|
|
*/
|
2012-01-05 10:25:16 +08:00
|
|
|
return !(((qavg - p->qth_min) >> p->Wlog) * v->qcount < v->qR);
|
2005-11-06 04:14:03 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
enum {
|
|
|
|
RED_BELOW_MIN_THRESH,
|
|
|
|
RED_BETWEEN_TRESH,
|
|
|
|
RED_ABOVE_MAX_TRESH,
|
|
|
|
};
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline int red_cmp_thresh(const struct red_parms *p, unsigned long qavg)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
|
|
|
if (qavg < p->qth_min)
|
|
|
|
return RED_BELOW_MIN_THRESH;
|
|
|
|
else if (qavg >= p->qth_max)
|
|
|
|
return RED_ABOVE_MAX_TRESH;
|
|
|
|
else
|
|
|
|
return RED_BETWEEN_TRESH;
|
|
|
|
}
|
|
|
|
|
|
|
|
enum {
|
|
|
|
RED_DONT_MARK,
|
|
|
|
RED_PROB_MARK,
|
|
|
|
RED_HARD_MARK,
|
|
|
|
};
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline int red_action(const struct red_parms *p,
|
|
|
|
struct red_vars *v,
|
|
|
|
unsigned long qavg)
|
2005-11-06 04:14:03 +08:00
|
|
|
{
|
|
|
|
switch (red_cmp_thresh(p, qavg)) {
|
|
|
|
case RED_BELOW_MIN_THRESH:
|
2012-01-05 10:25:16 +08:00
|
|
|
v->qcount = -1;
|
2005-11-06 04:14:03 +08:00
|
|
|
return RED_DONT_MARK;
|
|
|
|
|
|
|
|
case RED_BETWEEN_TRESH:
|
2012-01-05 10:25:16 +08:00
|
|
|
if (++v->qcount) {
|
|
|
|
if (red_mark_probability(p, v, qavg)) {
|
|
|
|
v->qcount = 0;
|
|
|
|
v->qR = red_random(p);
|
2005-11-06 04:14:03 +08:00
|
|
|
return RED_PROB_MARK;
|
|
|
|
}
|
|
|
|
} else
|
2012-01-05 10:25:16 +08:00
|
|
|
v->qR = red_random(p);
|
2005-11-06 04:14:03 +08:00
|
|
|
|
|
|
|
return RED_DONT_MARK;
|
|
|
|
|
|
|
|
case RED_ABOVE_MAX_TRESH:
|
2012-01-05 10:25:16 +08:00
|
|
|
v->qcount = -1;
|
2005-11-06 04:14:03 +08:00
|
|
|
return RED_HARD_MARK;
|
|
|
|
}
|
|
|
|
|
|
|
|
BUG();
|
|
|
|
return RED_DONT_MARK;
|
|
|
|
}
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
static inline void red_adaptative_algo(struct red_parms *p, struct red_vars *v)
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
{
|
|
|
|
unsigned long qavg;
|
|
|
|
u32 max_p_delta;
|
|
|
|
|
2012-01-05 10:25:16 +08:00
|
|
|
qavg = v->qavg;
|
|
|
|
if (red_is_idling(v))
|
|
|
|
qavg = red_calc_qavg_from_idle_time(p, v);
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
|
2012-04-16 11:17:22 +08:00
|
|
|
/* v->qavg is fixed point number with point at Wlog */
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
qavg >>= p->Wlog;
|
|
|
|
|
|
|
|
if (qavg > p->target_max && p->max_P <= MAX_P_MAX)
|
|
|
|
p->max_P += MAX_P_ALPHA(p->max_P); /* maxp = maxp + alpha */
|
|
|
|
else if (qavg < p->target_min && p->max_P >= MAX_P_MIN)
|
|
|
|
p->max_P = (p->max_P/10)*9; /* maxp = maxp * Beta */
|
|
|
|
|
|
|
|
max_p_delta = DIV_ROUND_CLOSEST(p->max_P, p->qth_delta);
|
2011-12-09 10:46:45 +08:00
|
|
|
max_p_delta = max(max_p_delta, 1U);
|
sch_red: Adaptative RED AQM
Adaptative RED AQM for linux, based on paper from Sally FLoyd,
Ramakrishna Gummadi, and Scott Shenker, August 2001 :
http://icir.org/floyd/papers/adaptiveRed.pdf
Goal of Adaptative RED is to make max_p a dynamic value between 1% and
50% to reach the target average queue : (max_th - min_th) / 2
Every 500 ms:
if (avg > target and max_p <= 0.5)
increase max_p : max_p += alpha;
else if (avg < target and max_p >= 0.01)
decrease max_p : max_p *= beta;
target :[min_th + 0.4*(min_th - max_th),
min_th + 0.6*(min_th - max_th)].
alpha : min(0.01, max_p / 4)
beta : 0.9
max_P is a Q0.32 fixed point number (unsigned, with 32 bits mantissa)
Changes against our RED implementation are :
max_p is no longer a negative power of two (1/(2^Plog)), but a Q0.32
fixed point number, to allow full range described in Adatative paper.
To deliver a random number, we now use a reciprocal divide (thats really
a multiply), but this operation is done once per marked/droped packet
when in RED_BETWEEN_TRESH window, so added cost (compared to previous
AND operation) is near zero.
dump operation gives current max_p value in a new TCA_RED_MAX_P
attribute.
Example on a 10Mbit link :
tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 8sec red \
limit 400000 min 30000 max 90000 avpkt 1000 \
burst 55 ecn adaptative bandwidth 10Mbit
# tc -s -d qdisc show dev eth3
...
qdisc red 10: parent 1:1 limit 400000b min 30000b max 90000b ecn
adaptative ewma 5 max_p=0.113335 Scell_log 15
Sent 50414282 bytes 34504 pkt (dropped 35, overlimits 1392 requeues 0)
rate 9749Kbit 831pps backlog 72056b 16p requeues 0
marked 1357 early 35 pdrop 0 other 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-08 14:06:03 +08:00
|
|
|
p->max_P_reciprocal = reciprocal_value(max_p_delta);
|
|
|
|
}
|
2005-11-06 04:14:03 +08:00
|
|
|
#endif
|