Module 3

Congestion Control
Approaches towards congestion control
two broad approaches towards congestion control:

end-end congestion network-assisted congestion

control: control:

no explicit feedback  routers provide

from network feedback to end
systems
congestion inferred
 single bit indicating
from end-system congestion (SNA, DECbit,
observed loss, delay TCP/IP ECN, ATM)
 explicit rate for sender to
approach taken by send at
TCP
 Network Assisted Congestion Control

• Direct feedback may be sent from a network

router to the sender. This form of notification
typically takes the form of a choke packet.

• The second form : when a router

marks/updates a field in a packet to indicate
congestion.
Upon receipt of a marked packet, the
receiver then notifies the sender of the congestion
indication.

Two feedback pathways for network-indicated

congestion information
Case study: ATM ABR congestion control
ABR: available bit rate: RM (resource management) cells:

▪ sent by sender, interspersed with

▪ “elastic service” data cells
▪ if sender’s path ▪ Each data cell contains an explicit
“underloaded”: forward congestion indication
(EFCI) bit.
▪ sender should use available
bandwidth ▪ bits in RM cell set by switches
(“network-assisted”)
▪ if sender’s path ▪ NI bit: no increase in rate (mild congestion)
congested: ▪ CI bit: congestion indication

▪ sender throttled to minimum ▪ RM cells returned to sender by

guaranteed rate receiver, with bits intact
Case study: ATM ABR congestion control
RM cell data cell

▪ two-byte ER (explicit rate) field in RM cell

▪ congested switch may lower ER value in cell
▪ Sender’s send rate thus max supportable rate on path

▪ EFCI bit in data cells: set to 1 in congested switch

▪ if data cell preceding RM cell has EFCI set, receiver sets CI bit in
returned RM cell
TCP congestion control: additive increase
multiplicative decrease
 approach: sender increases transmission rate (window
size), probing for usable bandwidth, until loss occurs
 additive increase: increase cwnd by 1 MSS every
RTT until loss detected
 multiplicative decrease: cut cwnd in half after loss
additively increase window size …
…. until loss occurs (then cut window in half)

congestion window size

cwnd: TCP sender
AIMD saw tooth
behavior: probing
for bandwidth

time
Congestion Control Introduction
▪ If no congestion : increase the rate
▪ If congestion : reduces the send rate
▪ This approach raises three questions:
▪ how does a TCP sender limit the rate at which it sends traffic into its connection
▪ how does a TCP sender perceive that there is congestion on the path between itself and
the destination
▪ what algorithm should the sender use to change its send rate
TCP Congestion Control: details
How does a TCP sender limit the rate at which it sends traffic into its connection
sender sequence number space
cwnd TCP sending rate:
roughly: send cwnd bytes,
wait RTT for ACKS, then send
more bytes
last byte last byte
ACKed sent, not- sent
yet ACKed
(“in-flight”)
cwnd
 sender limits transmission: rate ~
~ bytes/sec
RTT
LastByteSent-
< cwnd
LastByteAcked
 the amount of unacknowledged data at a sender
may not exceed the minimum of cwnd and rwnd
 cwnd is dynamic, function of perceived network
congestion
Congestion details
▪ How a TCP sender perceives that there is congestion on the path between
itself and the destination
▪ “loss event” at a TCP sender
▪ occurrence of either a timeout or
▪ the receipt of three duplicate ACKs from the receiver

▪ Loss event is the indication of congestion on the sender-to-receiver path

▪ When a loss event doesn’t occur
▪ acknowledgments for previously unacknowledged segments will be received at the TCP
sender
Congestion Details
▪ How should a TCP sender determine the rate at which it should send
▪ Three guiding principles:
▪ A lost segment implies congestion, and hence, the TCP sender’s rate should be
decreased when a segment is lost
▪ An acknowledged segment indicates that the network is delivering the sender’s
segments to the receiver, and hence, the sender’s rate can be increased when an ACK
arrives for a previously unacknowledged segment.
▪ Bandwidth probing :
▪ ACKs – increase rate
▪ Loss event – decrease rate
TCP Congestion Control Algorithm
▪ First described in [Jacobson 1988]

▪ Standardized in [RFC 5681].

▪ The algorithm has three major components :

▪ (1) slow start :
▪ value of cwnd begins at 1 MSS and increases by 1 MSS every time a transmitted segment is first
acknowledged
▪ (2) congestion avoidance :
▪ value of cwnd equals ssthresh, congestion avoidance mode starts. Tcp increases cwnd more
cautiously
▪ (3) fast recovery :
▪ if three duplicate ACKs are detected, in which case TCP performs a fast retransmit
TCP Slow Start
Host A Host B
when connection begins, increase
rate exponentially until first loss
event:
one s e gm
 initially cwnd = 1 MSS ent

RTT
 double cwnd every RTT
two segm
 done by incrementing cwnd for en ts
every ACK received

summary: initial rate is slow but

four segm
ramps up exponentially fast ents

Exponential growth ends:

▪ Loss event occurs
▪ Cwnd equals ssthresh, slow start
time
ends and TCP enters congestion
avoidance
TCP: detecting, reacting to loss
 loss indicated by timeout:
 cwnd set to 1 MSS;
 window then grows exponentially (as in slow start) to threshold, then grows linearly
 loss indicated by 3 duplicate ACKs: TCP RENO

 dup ACKs indicate network capable of delivering some segments

 cwnd is cut in half window then grows linearly
 TCP Tahoe always sets cwnd to 1 (timeout or 3 duplicate acks)
TCP: switching from slow start to
CA
Q: when should the
exponential increase
switch to linear?
A: when cwnd gets to 1/2
of its value before
timeout.

Implementation:

variable ssthresh
on loss event, ssthresh is
set to 1/2 of cwnd just
before loss event
Summary: TCP Congestion Control
New
New ACK!
ACK!
duplicate ACK
dupACKcount++ new ACK
new ACK
.
cwnd = cwnd + MSS (MSS/cwnd)
dupACKcount = 0
cwnd = cwnd+MSS transmit new segment(s), as allowed
dupACKcount = 0
L transmit new segment(s), as allowed
cwnd = 1 MSS
ssthresh = 64 KB cwnd > ssthresh
dupACKcount = 0
slow L congestion
start timeout avoidance
ssthresh = cwnd/2
cwnd = 1 MSS duplicate ACK
timeout dupACKcount = 0 dupACKcount++
ssthresh = cwnd/2 retransmit missing segment
cwnd = 1 MSS
dupACKcount = 0
retransmit missing segment
timeout
New
ACK!
ssthresh = cwnd/2
cwnd = 1 New ACK
dupACKcount = 0
retransmit missing segment cwnd = ssthresh dupACKcount == 3
dupACKcount == 3 dupACKcount = 0
ssthresh= cwnd/2 ssthresh= cwnd/2
cwnd = ssthresh + 3 cwnd = ssthresh + 3
retransmit missing segment retransmit missing segment
fast
recovery
duplicate ACK
cwnd = cwnd + MSS
transmit new segment(s), as allowed