draft-ietf-quic-recovery-02.txt   draft-ietf-quic-recovery-03.txt 
QUIC J. Iyengar, Ed. QUIC J. Iyengar, Ed.
Internet-Draft I. Swett, Ed. Internet-Draft I. Swett, Ed.
Intended status: Standards Track Google Intended status: Standards Track Google
Expires: September 14, 2017 March 13, 2017 Expires: November 22, 2017 May 21, 2017
QUIC Loss Detection and Congestion Control QUIC Loss Detection and Congestion Control
draft-ietf-quic-recovery-02 draft-ietf-quic-recovery-03
Abstract Abstract
QUIC is a new multiplexed and secure transport atop UDP. QUIC builds This document describes loss detection and congestion control
on decades of transport and security experience, and implements mechanisms for QUIC.
mechanisms that make it attractive as a modern general-purpose
transport. QUIC implements the spirit of known TCP loss detection
mechanisms, described in RFCs, various Internet-drafts, and also
those prevalent in the Linux TCP implementation. This document
describes QUIC loss detection and congestion control, and attributes
the TCP equivalent in RFCs, Internet-drafts, academic papers, and TCP
implementations.
Note to Readers Note to Readers
Discussion of this draft takes place on the QUIC working group Discussion of this draft takes place on the QUIC working group
mailing list (quic@ietf.org), which is archived at mailing list (quic@ietf.org), which is archived at
https://mailarchive.ietf.org/arch/search/?email_list=quic . https://mailarchive.ietf.org/arch/search/?email_list=quic .
Working Group information can be found at https://github.com/quicwg ; Working Group information can be found at https://github.com/quicwg ;
source code and issues list for this draft can be found at source code and issues list for this draft can be found at
https://github.com/quicwg/base-drafts/labels/recovery . https://github.com/quicwg/base-drafts/labels/recovery .
skipping to change at page 1, line 48 skipping to change at page 1, line 41
Internet-Drafts are working documents of the Internet Engineering Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet- working documents as Internet-Drafts. The list of current Internet-
Drafts is at http://datatracker.ietf.org/drafts/current/. Drafts is at http://datatracker.ietf.org/drafts/current/.
Internet-Drafts are draft documents valid for a maximum of six months Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress." material or to cite them other than as "work in progress."
This Internet-Draft will expire on September 14, 2017. This Internet-Draft will expire on November 22, 2017.
Copyright Notice Copyright Notice
Copyright (c) 2017 IETF Trust and the persons identified as the Copyright (c) 2017 IETF Trust and the persons identified as the
document authors. All rights reserved. document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents Provisions Relating to IETF Documents
(http://trustee.ietf.org/license-info) in effect on the date of (http://trustee.ietf.org/license-info) in effect on the date of
publication of this document. Please review these documents publication of this document. Please review these documents
skipping to change at page 2, line 31 skipping to change at page 2, line 23
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
1.1. Notational Conventions . . . . . . . . . . . . . . . . . 3 1.1. Notational Conventions . . . . . . . . . . . . . . . . . 3
2. Design of the QUIC Transmission Machinery . . . . . . . . . . 3 2. Design of the QUIC Transmission Machinery . . . . . . . . . . 3
2.1. Relevant Differences Between QUIC and TCP . . . . . . . . 4 2.1. Relevant Differences Between QUIC and TCP . . . . . . . . 4
2.1.1. Monotonically Increasing Packet Numbers . . . . . . . 4 2.1.1. Monotonically Increasing Packet Numbers . . . . . . . 4
2.1.2. No Reneging . . . . . . . . . . . . . . . . . . . . . 4 2.1.2. No Reneging . . . . . . . . . . . . . . . . . . . . . 4
2.1.3. More ACK Ranges . . . . . . . . . . . . . . . . . . . 5 2.1.3. More ACK Ranges . . . . . . . . . . . . . . . . . . . 5
2.1.4. Explicit Correction For Delayed Acks . . . . . . . . 5 2.1.4. Explicit Correction For Delayed Acks . . . . . . . . 5
3. Loss Detection . . . . . . . . . . . . . . . . . . . . . . . 5 3. Loss Detection . . . . . . . . . . . . . . . . . . . . . . . 5
3.1. Constants of interest . . . . . . . . . . . . . . . . . . 5 3.1. Overview . . . . . . . . . . . . . . . . . . . . . . . . 5
3.2. Variables of interest . . . . . . . . . . . . . . . . . . 6 3.2. Algorithm Details . . . . . . . . . . . . . . . . . . . . 6
3.3. Initialization . . . . . . . . . . . . . . . . . . . . . 7 3.2.1. Constants of interest . . . . . . . . . . . . . . . . 6
3.4. On Sending a Packet . . . . . . . . . . . . . . . . . . . 7 3.2.2. Variables of interest . . . . . . . . . . . . . . . . 6
3.5. On Ack Receipt . . . . . . . . . . . . . . . . . . . . . 8 3.2.3. Initialization . . . . . . . . . . . . . . . . . . . 7
3.6. On Packet Acknowledgment . . . . . . . . . . . . . . . . 8 3.2.4. On Sending a Packet . . . . . . . . . . . . . . . . . 8
3.7. Setting the Loss Detection Alarm . . . . . . . . . . . . 9 3.2.5. On Ack Receipt . . . . . . . . . . . . . . . . . . . 8
3.7.1. Handshake Packets . . . . . . . . . . . . . . . . . . 9 3.2.6. On Packet Acknowledgment . . . . . . . . . . . . . . 9
3.7.2. Tail Loss Probe and Retransmission Timeout . . . . . 9 3.2.7. Setting the Loss Detection Alarm . . . . . . . . . . 10
3.7.3. Early Retransmit . . . . . . . . . . . . . . . . . . 9 3.2.8. On Alarm Firing . . . . . . . . . . . . . . . . . . . 12
3.7.4. Pseudocode . . . . . . . . . . . . . . . . . . . . . 10 3.2.9. Detecting Lost Packets . . . . . . . . . . . . . . . 12
3.8. On Alarm Firing . . . . . . . . . . . . . . . . . . . . . 10 3.3. Discussion . . . . . . . . . . . . . . . . . . . . . . . 13
3.9. Detecting Lost Packets . . . . . . . . . . . . . . . . . 11 4. Congestion Control . . . . . . . . . . . . . . . . . . . . . 14
3.9.1. Handshake Packets . . . . . . . . . . . . . . . . . . 11 4.1. Slow Start . . . . . . . . . . . . . . . . . . . . . . . 14
3.9.2. Pseudocode . . . . . . . . . . . . . . . . . . . . . 11 4.2. Recovery . . . . . . . . . . . . . . . . . . . . . . . . 14
4. Congestion Control . . . . . . . . . . . . . . . . . . . . . 12 4.3. Constants of interest . . . . . . . . . . . . . . . . . . 14
5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 12 4.4. Variables of interest . . . . . . . . . . . . . . . . . . 14
6. References . . . . . . . . . . . . . . . . . . . . . . . . . 12 4.5. Initialization . . . . . . . . . . . . . . . . . . . . . 15
6.1. Normative References . . . . . . . . . . . . . . . . . . 12 4.6. On Packet Acknowledgement . . . . . . . . . . . . . . . . 15
6.2. Informative References . . . . . . . . . . . . . . . . . 13 4.7. On Packets Lost . . . . . . . . . . . . . . . . . . . . . 15
Appendix A. Acknowledgments . . . . . . . . . . . . . . . . . . 13 4.8. On Retransmission Timeout Verified . . . . . . . . . . . 16
Appendix B. Change Log . . . . . . . . . . . . . . . . . . . . . 13 4.9. Pacing Packets . . . . . . . . . . . . . . . . . . . . . 16
B.1. Since draft-ietf-quic-recovery-01 . . . . . . . . . . . . 14 5. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 16
B.2. Since draft-ietf-quic-recovery-00: . . . . . . . . . . . 14 6. References . . . . . . . . . . . . . . . . . . . . . . . . . 16
B.3. Since draft-iyengar-quic-loss-recovery-01: . . . . . . . 14 6.1. Normative References . . . . . . . . . . . . . . . . . . 16
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 14 6.2. Informative References . . . . . . . . . . . . . . . . . 16
Appendix A. Acknowledgments . . . . . . . . . . . . . . . . . . 17
Appendix B. Change Log . . . . . . . . . . . . . . . . . . . . . 17
B.1. Since draft-ietf-quic-recovery-02 . . . . . . . . . . . . 17
B.2. Since draft-ietf-quic-recovery-01 . . . . . . . . . . . . 18
B.3. Since draft-ietf-quic-recovery-00 . . . . . . . . . . . . 18
B.4. Since draft-iyengar-quic-loss-recovery-01 . . . . . . . . 18
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 18
1. Introduction 1. Introduction
QUIC is a new multiplexed and secure transport atop UDP. QUIC builds QUIC is a new multiplexed and secure transport atop UDP. QUIC builds
on decades of transport and security experience, and implements on decades of transport and security experience, and implements
mechanisms that make it attractive as a modern general-purpose mechanisms that make it attractive as a modern general-purpose
transport. The QUIC protocol is described in [QUIC-TRANSPORT]. transport. The QUIC protocol is described in [QUIC-TRANSPORT].
QUIC implements the spirit of known TCP loss recovery mechanisms, QUIC implements the spirit of known TCP loss recovery mechanisms,
described in RFCs, various Internet-drafts, and also those prevalent described in RFCs, various Internet-drafts, and also those prevalent
in the Linux TCP implementation. This document describes QUIC in the Linux TCP implementation. This document describes QUIC
congestion control and loss recovery, and where applicable, congestion control and loss recovery, and where applicable,
attributes the TCP equivalent in RFCs, Internet-drafts, academic attributes the TCP equivalent in RFCs, Internet-drafts, academic
papers, and/or TCP implementations. papers, and/or TCP implementations.
This document first describes pre-requisite parts of the QUIC
transmission machinery, then discusses QUIC's default congestion
control and loss detection mechanisms, and finally lists the various
TCP mechanisms that QUIC loss detection implements (in spirit.)
1.1. Notational Conventions 1.1. Notational Conventions
The words "MUST", "MUST NOT", "SHOULD", and "MAY" are used in this The words "MUST", "MUST NOT", "SHOULD", and "MAY" are used in this
document. It's not shouting; when they are capitalized, they have document. It's not shouting; when they are capitalized, they have
the special meaning defined in [RFC2119]. the special meaning defined in [RFC2119].
2. Design of the QUIC Transmission Machinery 2. Design of the QUIC Transmission Machinery
All transmissions in QUIC are sent with a packet-level header, which All transmissions in QUIC are sent with a packet-level header, which
includes a packet sequence number (referred to below as a packet includes a packet sequence number (referred to below as a packet
skipping to change at page 4, line 5 skipping to change at page 3, line 48
loss detection mechanisms. loss detection mechanisms.
Every packet may contain several frames. We outline the frames that Every packet may contain several frames. We outline the frames that
are important to the loss detection and congestion control machinery are important to the loss detection and congestion control machinery
below. below.
o Retransmittable frames are frames requiring reliable delivery. o Retransmittable frames are frames requiring reliable delivery.
The most common are STREAM frames, which typically contain The most common are STREAM frames, which typically contain
application data. application data.
o Crypto handshake data is also sent as STREAM data, and uses the o Crypto handshake data is sent on stream 0, and uses the
reliability machinery of QUIC underneath. reliability machinery of QUIC underneath.
o ACK frames contain acknowledgment information. QUIC uses a SACK- o ACK frames contain acknowledgment information. QUIC uses a SACK-
based scheme, where acks express up to 256 ranges. The ACK frame based scheme, where acks express up to 256 ranges. The ACK frame
also includes a receive timestamp for each packet newly acked. also includes a receive timestamp for each packet newly acked.
2.1. Relevant Differences Between QUIC and TCP 2.1. Relevant Differences Between QUIC and TCP
There are some notable differences between QUIC and TCP which are Readers familiar with TCP's loss detection and congestion control
important for reasoning about the differences between the loss will find algorithms here that parallel well-known TCP ones.
recovery mechanisms employed by the two protocols. We briefly Protocol differences between QUIC and TCP however contribute to
describe these differences below. algorithmic differences. We briefly describe these protocol
differences below.
2.1.1. Monotonically Increasing Packet Numbers 2.1.1. Monotonically Increasing Packet Numbers
TCP conflates transmission sequence number at the sender with TCP conflates transmission sequence number at the sender with
delivery sequence number at the receiver, which results in delivery sequence number at the receiver, which results in
retransmissions of the same data carrying the same sequence number, retransmissions of the same data carrying the same sequence number,
and consequently to problems caused by "retransmission ambiguity". and consequently to problems caused by "retransmission ambiguity".
QUIC separates the two: QUIC uses a packet sequence number (referred QUIC separates the two: QUIC uses a packet sequence number (referred
to as the "packet number") for transmissions, and any data that is to to as the "packet number") for transmissions, and any data that is to
be delivered to the receiving application(s) is sent in one or more be delivered to the receiving application(s) is sent in one or more
skipping to change at page 5, line 23 skipping to change at page 5, line 23
between when a packet is received and when the corresponding ACK is between when a packet is received and when the corresponding ACK is
sent. This allows the receiver of the ACK to adjust for receiver sent. This allows the receiver of the ACK to adjust for receiver
delays, specifically the delayed ack timer, when estimating the path delays, specifically the delayed ack timer, when estimating the path
RTT. This mechanism also allows a receiver to measure and report the RTT. This mechanism also allows a receiver to measure and report the
delay from when a packet was received by the OS kernel, which is delay from when a packet was received by the OS kernel, which is
useful in receivers which may incur delays such as context-switch useful in receivers which may incur delays such as context-switch
latency before a userspace QUIC receiver processes a received packet. latency before a userspace QUIC receiver processes a received packet.
3. Loss Detection 3. Loss Detection
We now describe QUIC's loss detection as functions that should be 3.1. Overview
called on packet transmission, when a packet is acked, and timer
expiration events.
3.1. Constants of interest QUIC uses a combination of ack information and alarms to detect lost
packets. An unacknowledged QUIC packet is marked as lost in one of
the following ways:
Constants used in loss recovery and congestion control are based on a o A packet is marked as lost if at least one packet that was sent a
combination of RFCs, papers, and common practice. Some may need to threshold number of packets (kReorderingThreshold) after it has
be changed or negotiated in order to better suit a variety of been acknowledged. This indicates that the unacknowledged packet
environments. is either lost or reordered beyond the specified threshold. This
mechanism combines both TCP's FastRetransmit and FACK mechanisms.
o If a packet is near the tail, where fewer than
kReorderingThreshold packets are sent after it, the sender cannot
expect to detect loss based on the previous mechanism. In this
case, a sender uses both ack information and an alarm to detect
loss. Specifically, when the last sent packet is acknowledged,
the sender waits a short period of time to allow for reordering
and then marks any unacknowledged packets as lost. This mechanism
is based on the Linux implementation of TCP Early Retransmit.
o If a packet is sent at the tail, there are no packets sent after
it, and the sender cannot use ack information to detect its loss.
The sender therefore relies on an alarm to detect such tail
losses. This mechanism is based on TCP's Tail Loss Probe.
o If all else fails, a Retransmission Timeout (RTO) alarm is always
set when any retransmittable packet is outstanding. When this
alarm fires, all unacknowledged packets are marked as lost.
o Instead of a packet threshold to tolerate reordering, a QUIC
sender may use a time threshold. This allows for senders to be
tolerant of short periods of significant reordering. In this
mechanism, a QUIC sender marks a packet as lost when a packet
larger than it is acknowledged and a threshold amount of time has
passed since the packet was sent.
o Handshake packets, which contain STREAM frames for stream 0, are
critical to QUIC transport and crypto negotiation, so a separate
alarm period is used for them.
3.2. Algorithm Details
3.2.1. Constants of interest
Constants used in loss recovery are based on a combination of RFCs,
papers, and common practice. Some may need to be changed or
negotiated in order to better suit a variety of environments.
kMaxTLPs (default 2): Maximum number of tail loss probes before an kMaxTLPs (default 2): Maximum number of tail loss probes before an
RTO fires. RTO fires.
kReorderingThreshold (default 3): Maximum reordering in packet kReorderingThreshold (default 3): Maximum reordering in packet
number space before FACK style loss detection considers a packet number space before FACK style loss detection considers a packet
lost. lost.
kTimeReorderingFraction (default 1/8): Maximum reordering in time kTimeReorderingFraction (default 1/8): Maximum reordering in time
sapce before time based loss detection considers a packet lost. space before time based loss detection considers a packet lost.
In fraction of an RTT. In fraction of an RTT.
kMinTLPTimeout (default 10ms): Minimum time in the future a tail kMinTLPTimeout (default 10ms): Minimum time in the future a tail
loss probe alarm may be set for. loss probe alarm may be set for.
kMinRTOTimeout (default 200ms): Minimum time in the future an RTO kMinRTOTimeout (default 200ms): Minimum time in the future an RTO
alarm may be set for. alarm may be set for.
kDelayedAckTimeout (default 25ms): The length of the peer's delayed kDelayedAckTimeout (default 25ms): The length of the peer's delayed
ack timer. ack timer.
kDefaultInitialRtt (default 100ms): The default RTT used before an kDefaultInitialRtt (default 100ms): The default RTT used before an
RTT sample is taken. RTT sample is taken.
3.2. Variables of interest 3.2.2. Variables of interest
We first describe the variables required to implement the loss Variables required to implement the congestion control mechanisms are
detection mechanisms described in this section. described in this section.
loss_detection_alarm: Multi-modal alarm used for loss detection. loss_detection_alarm: Multi-modal alarm used for loss detection.
handshake_count: The number of times the handshake packets have been handshake_count: The number of times the handshake packets have been
retransmitted without receiving an ack. retransmitted without receiving an ack.
tlp_count: The number of times a tail loss probe has been sent tlp_count: The number of times a tail loss probe has been sent
without receiving an ack. without receiving an ack.
rto_count: The number of times an rto has been sent without rto_count: The number of times an rto has been sent without
receiving an ack. receiving an ack.
largest_sent_before_rto: The last packet number sent prior to the
first retransmission timeout.
smoothed_rtt: The smoothed RTT of the connection, computed as smoothed_rtt: The smoothed RTT of the connection, computed as
described in [RFC6298] described in [RFC6298]
rttvar: The RTT variance, computed as described in [RFC6298] rttvar: The RTT variance, computed as described in [RFC6298]
initial_rtt: The initial RTT used before any RTT measurements have
been made.
reordering_threshold: The largest delta between the largest acked reordering_threshold: The largest delta between the largest acked
retransmittable packet and a packet containing retransmittable retransmittable packet and a packet containing retransmittable
frames before it's declared lost. frames before it's declared lost.
time_reordering_fraction: The reordering window as a fraction of time_reordering_fraction: The reordering window as a fraction of
max(smoothed_rtt, latest_rtt). max(smoothed_rtt, latest_rtt).
loss_time: The time at which the next packet will be considered lost loss_time: The time at which the next packet will be considered lost
based on early transmit or exceeding the reordering window in based on early transmit or exceeding the reordering window in
time. time.
sent_packets: An association of packet numbers to information about sent_packets: An association of packet numbers to information about
them, including a number field indicating the packet number, a them, including a number field indicating the packet number, a
time field indicating the time a packet was sent, and a bytes time field indicating the time a packet was sent, and a bytes
field indicating the packet's size. sent_packets is ordered by field indicating the packet's size. sent_packets is ordered by
packet number, and packets remain in sent_packets until packet number, and packets remain in sent_packets until
acknowledged or lost. acknowledged or lost.
3.3. Initialization 3.2.3. Initialization
At the beginning of the connection, initialize the loss detection At the beginning of the connection, initialize the loss detection
variables as follows: variables as follows:
loss_detection_alarm.reset() loss_detection_alarm.reset()
handshake_count = 0 handshake_count = 0
tlp_count = 0 tlp_count = 0
rto_count = 0 rto_count = 0
if (UsingTimeLossDetection()) if (UsingTimeLossDetection())
reordering_threshold = infinite reordering_threshold = infinite
time_reordering_fraction = kTimeReorderingFraction time_reordering_fraction = kTimeReorderingFraction
else: else:
reordering_threshold = kReorderingThreshold reordering_threshold = kReorderingThreshold
time_reordering_fraction = infinite time_reordering_fraction = infinite
loss_time = 0 loss_time = 0
smoothed_rtt = 0 smoothed_rtt = 0
rttvar = 0 rttvar = 0
initial_rtt = kDefaultInitialRtt largest_sent_before_rto = 0
3.4. On Sending a Packet 3.2.4. On Sending a Packet
After any packet is sent, be it a new transmission or a rebundled After any packet is sent, be it a new transmission or a rebundled
transmission, the following OnPacketSent function is called. The transmission, the following OnPacketSent function is called. The
parameters to OnPacketSent are as follows: parameters to OnPacketSent are as follows:
o packet_number: The packet number of the sent packet. o packet_number: The packet number of the sent packet.
o is_retransmittble: A boolean that indicates whether the packet o is_retransmittable: A boolean that indicates whether the packet
contains at least one frame requiring reliable deliver. The contains at least one frame requiring reliable deliver. The
retransmittability of various QUIC frames is described in retransmittability of various QUIC frames is described in
[QUIC-TRANSPORT]. If false, it is still acceptable for an ack to [QUIC-TRANSPORT]. If false, it is still acceptable for an ack to
be received for this packet. However, a caller MUST NOT set be received for this packet. However, a caller MUST NOT set
is_retransmittable to true if an ack is not expected. is_retransmittable to true if an ack is not expected.
o sent_bytes: The number of bytes sent in the packet. o sent_bytes: The number of bytes sent in the packet.
Pseudocode for OnPacketSent follows: Pseudocode for OnPacketSent follows:
OnPacketSent(packet_number, is_retransmittable, sent_bytes): OnPacketSent(packet_number, is_retransmittable, sent_bytes):
sent_packets[packet_number].packet_number = packet_number sent_packets[packet_number].packet_number = packet_number
sent_packets[packet_number].time = now sent_packets[packet_number].time = now
if is_retransmittable: if is_retransmittable:
sent_packets[packet_number].bytes = sent_bytes sent_packets[packet_number].bytes = sent_bytes
SetLossDetectionAlarm() SetLossDetectionAlarm()
3.5. On Ack Receipt 3.2.5. On Ack Receipt
When an ack is received, it may acknowledge 0 or more packets. When an ack is received, it may acknowledge 0 or more packets.
The sender MUST abort the connection if it receives an ACK for a
packet it never sent, see [QUIC-TRANSPORT].
Pseudocode for OnAckReceived and UpdateRtt follow: Pseudocode for OnAckReceived and UpdateRtt follow:
OnAckReceived(ack): OnAckReceived(ack):
// If the largest acked is newly acked, update the RTT. // If the largest acked is newly acked, update the RTT.
if (sent_packets[ack.largest_acked]): if (sent_packets[ack.largest_acked]):
rtt_sample = now - sent_packets[ack.largest_acked].time rtt_sample = now - sent_packets[ack.largest_acked].time
if (rtt_sample > ack.ack_delay): if (rtt_sample > ack.ack_delay):
rtt_sample -= ack.delay rtt_sample -= ack.delay
UpdateRtt(rtt_sample) UpdateRtt(rtt_sample)
// The sender may skip packets for detecting optimistic ACKs
if (packets acked that the sender skipped):
abortConnection()
// Find all newly acked packets. // Find all newly acked packets.
for acked_packet_number in DetermineNewlyAckedPackets(): for acked_packet in DetermineNewlyAckedPackets():
OnPacketAcked(acked_packet_number) OnPacketAcked(acked_packet.packet_number)
DetectLostPackets(ack.largest_acked_packet) DetectLostPackets(ack.largest_acked_packet)
SetLossDetectionAlarm() SetLossDetectionAlarm()
UpdateRtt(rtt_sample): UpdateRtt(rtt_sample):
// Based on {{RFC6298}}. // Based on {{RFC6298}}.
if (smoothed_rtt == 0): if (smoothed_rtt == 0):
smoothed_rtt = rtt_sample smoothed_rtt = rtt_sample
rttvar = rtt_sample / 2 rttvar = rtt_sample / 2
else: else:
rttvar = 3/4 * rttvar + 1/4 * (smoothed_rtt - rtt_sample) rttvar = 3/4 * rttvar + 1/4 * (smoothed_rtt - rtt_sample)
smoothed_rtt = 7/8 * smoothed_rtt + 1/8 * rtt_sample smoothed_rtt = 7/8 * smoothed_rtt + 1/8 * rtt_sample
3.6. On Packet Acknowledgment 3.2.6. On Packet Acknowledgment
When a packet is acked for the first time, the following When a packet is acked for the first time, the following
OnPacketAcked function is called. Note that a single ACK frame may OnPacketAcked function is called. Note that a single ACK frame may
newly acknowledge several packets. OnPacketAcked must be called once newly acknowledge several packets. OnPacketAcked must be called once
for each of these newly acked packets. for each of these newly acked packets.
OnPacketAcked takes one parameter, acked_packet, which is the packet OnPacketAcked takes one parameter, acked_packet, which is the packet
number of the newly acked packet, and returns a list of packet number of the newly acked packet, and returns a list of packet
numbers that are detected as lost. numbers that are detected as lost.
If this is the first acknowledgement following RTO, check if the
smallest newly acknowledged packet is one sent by the RTO, and if so,
inform congestion control of a verified RTO, similar to F-RTO
[RFC5682]
Pseudocode for OnPacketAcked follows: Pseudocode for OnPacketAcked follows:
OnPacketAcked(acked_packet_number): OnPacketAcked(acked_packet_number):
// If a packet sent prior to RTO was acked, then the RTO
// was spurious. Otherwise, inform congestion control.
if (rto_count > 0 &&
acked_packet_number > largest_sent_before_rto)
OnRetransmissionTimeoutVerified()
handshake_count = 0 handshake_count = 0
tlp_count = 0 tlp_count = 0
rto_count = 0 rto_count = 0
sent_packets.remove(acked_packet_number) sent_packets.remove(acked_packet_number)
3.7. Setting the Loss Detection Alarm 3.2.7. Setting the Loss Detection Alarm
QUIC loss detection uses a single alarm for all timer-based loss QUIC loss detection uses a single alarm for all timer-based loss
detection. The duration of the alarm is based on the alarm's mode, detection. The duration of the alarm is based on the alarm's mode,
which is set in the packet and timer events further below. The which is set in the packet and timer events further below. The
function SetLossDetectionAlarm defined below shows how the single function SetLossDetectionAlarm defined below shows how the single
timer is set based on the alarm mode. timer is set based on the alarm mode.
3.7.1. Handshake Packets 3.2.7.1. Handshake Packets
The initial flight has no prior RTT sample. A client SHOULD remember The initial flight has no prior RTT sample. A client SHOULD remember
the previous RTT it observed when resumption is attempted and use the previous RTT it observed when resumption is attempted and use
that for an initial RTT value. If no previous RTT is available, the that for an initial RTT value. If no previous RTT is available, the
initial RTT defaults to 200ms. Once an RTT measurement is taken, it initial RTT defaults to 200ms.
MUST replace initial_rtt.
Endpoints MUST retransmit handshake frames if not acknowledged within Endpoints MUST retransmit handshake frames if not acknowledged within
a time limit. This time limit will start as the largest of twice the a time limit. This time limit will start as the largest of twice the
rtt value and MinTLPTimeout. Each consecutive handshake rtt value and MinTLPTimeout. Each consecutive handshake
retransmission doubles the time limit, until an acknowledgement is retransmission doubles the time limit, until an acknowledgement is
received. received.
Handshake frames may be cancelled by handshake state transitions. In Handshake frames may be cancelled by handshake state transitions. In
particular, all non-protected frames SHOULD be no longer be particular, all non-protected frames SHOULD be no longer be
transmitted once packet protection is available. transmitted once packet protection is available.
When stateless rejects are in use, the connection is considered When stateless rejects are in use, the connection is considered
immediately closed once a reject is sent, so no timer is set to immediately closed once a reject is sent, so no timer is set to
retransmit the reject. retransmit the reject.
Version negotiation packets are always stateless, and MUST be sent Version negotiation packets are always stateless, and MUST be sent
once per per handshake packet that uses an unsupported QUIC version, once per per handshake packet that uses an unsupported QUIC version,
and MAY be sent in response to 0RTT packets. and MAY be sent in response to 0RTT packets.
3.7.2. Tail Loss Probe and Retransmission Timeout 3.2.7.2. Tail Loss Probe and Retransmission Timeout
Tail loss probes [I-D.dukkipati-tcpm-tcp-loss-probe] and Tail loss probes [LOSS-PROBE] and retransmission timeouts [RFC6298]
retransmission timeouts[RFC6298] are an alarm based mechanism to are an alarm based mechanism to recover from cases when there are
recover from cases when there are outstanding retransmittable outstanding retransmittable packets, but an acknowledgement has not
packets, but an acknowledgement has not been received in a timely been received in a timely manner.
manner.
3.7.3. Early Retransmit 3.2.7.3. Early Retransmit
Early retransmit [RFC5827] is implemented with a 1/4 RTT timer. It Early retransmit [RFC5827] is implemented with a 1/4 RTT timer. It
is part of QUIC's time based loss detection, but is always enabled, is part of QUIC's time based loss detection, but is always enabled,
even when only packet reordering loss detection is enabled. even when only packet reordering loss detection is enabled.
3.7.4. Pseudocode 3.2.7.4. Pseudocode
Pseudocode for SetLossDetectionAlarm follows: Pseudocode for SetLossDetectionAlarm follows:
SetLossDetectionAlarm(): SetLossDetectionAlarm():
if (retransmittable packets are not outstanding): if (retransmittable packets are not outstanding):
loss_detection_alarm.cancel(); loss_detection_alarm.cancel()
return return
if (handshake packets are outstanding): if (handshake packets are outstanding):
// Handshake retransmission alarm. // Handshake retransmission alarm.
if (smoothed_rtt == 0): if (smoothed_rtt == 0):
alarm_duration = 2 * initial_rtt alarm_duration = 2 * kDefaultInitialRtt
else: else:
alarm_duration = 2 * smoothed_rtt alarm_duration = 2 * smoothed_rtt
alarm_duration = max(alarm_duration, kMinTLPTimeout) alarm_duration = max(alarm_duration, kMinTLPTimeout)
alarm_duration = alarm_duration << handshake_count alarm_duration = alarm_duration * (2 ^ handshake_count)
else if (loss_time != 0): else if (loss_time != 0):
// Early retransmit timer or time loss detection. // Early retransmit timer or time loss detection.
alarm_duration = loss_time - now alarm_duration = loss_time - now
else if (tlp_count < kMaxTLPs): else if (tlp_count < kMaxTLPs):
// Tail Loss Probe // Tail Loss Probe
if (retransmittable_packets_outstanding = 1): if (retransmittable_packets_outstanding = 1):
alarm_duration = 1.5 * smoothed_rtt + kDelayedAckTimeout alarm_duration = 1.5 * smoothed_rtt + kDelayedAckTimeout
else: else:
alarm_duration = kMinTLPTimeout alarm_duration = kMinTLPTimeout
alarm_duration = max(alarm_duration, 2 * smoothed_rtt) alarm_duration = max(alarm_duration, 2 * smoothed_rtt)
else: else:
// RTO alarm // RTO alarm
if (rto_count = 0): alarm_duration = smoothed_rtt + 4 * rttvar
alarm_duration = smoothed_rtt + 4 * rttvar alarm_duration = max(alarm_duration, kMinRTOTimeout)
alarm_duration = max(alarm_duration, kMinRTOTimeout) alarm_duration = alarm_duration * (2 ^ rto_count)
else:
alarm_duration = loss_detection_alarm.get_delay() << 1
loss_detection_alarm.set(now + alarm_duration) loss_detection_alarm.set(now + alarm_duration)
3.8. On Alarm Firing 3.2.8. On Alarm Firing
QUIC uses one loss recovery alarm, which when set, can be in one of QUIC uses one loss recovery alarm, which when set, can be in one of
several modes. When the alarm fires, the mode determines the action several modes. When the alarm fires, the mode determines the action
to be performed. to be performed.
Pseudocode for OnLossDetectionAlarm follows: Pseudocode for OnLossDetectionAlarm follows:
OnLossDetectionAlarm(): OnLossDetectionAlarm():
if (handshake packets are outstanding): if (handshake packets are outstanding):
// Handshake retransmission alarm. // Handshake retransmission alarm.
RetransmitAllHandshakePackets(); RetransmitAllHandshakePackets()
handshake_count++; handshake_count++
// TODO: Clarify early retransmit and time loss.
else if (loss_time != 0): else if (loss_time != 0):
// Early retransmit or Time Loss Detection // Early retransmit or Time Loss Detection
DetectLostPackets(largest_acked_packet) DetectLostPackets(largest_acked_packet)
else if (tlp_count < kMaxTLPs): else if (tlp_count < kMaxTLPs):
// Tail Loss Probe. // Tail Loss Probe.
if (HasNewDataToSend()): SendOnePacket()
SendOnePacketOfNewData()
else:
RetransmitOldestPacket()
tlp_count++ tlp_count++
else: else:
// RTO. // RTO.
RetransmitOldestTwoPackets() if (rto_count == 0)
largest_sent_before_rto = largest_sent_packet
SendTwoPackets()
rto_count++ rto_count++
SetLossDetectionAlarm() SetLossDetectionAlarm()
3.9. Detecting Lost Packets 3.2.9. Detecting Lost Packets
Packets in QUIC are only considered lost once a larger packet number Packets in QUIC are only considered lost once a larger packet number
is acknowledged. DetectLostPackets is called every time an ack is is acknowledged. DetectLostPackets is called every time an ack is
received. If the loss detection alarm fires and the loss_time is received. If the loss detection alarm fires and the loss_time is
set, the previous largest acked packet is supplied. set, the previous largest acked packet is supplied.
3.9.1. Handshake Packets 3.2.9.1. Handshake Packets
The receiver MUST ignore unprotected packets that ack protected The receiver MUST ignore unprotected packets that ack protected
packets. The receiver MUST trust protected acks for unprotected packets. The receiver MUST trust protected acks for unprotected
packets, however. Aside from this, loss detection for handshake packets, however. Aside from this, loss detection for handshake
packets when an ack is processed is identical to other packets. packets when an ack is processed is identical to other packets.
3.9.2. Pseudocode 3.2.9.2. Pseudocode
DetectLostPackets takes one parameter, acked, which is the largest DetectLostPackets takes one parameter, acked, which is the largest
acked packet. acked packet.
Pseudocode for DetectLostPackets follows: Pseudocode for DetectLostPackets follows:
DetectLostPackets(largest_acked): DetectLostPackets(largest_acked):
loss_time = 0 loss_time = 0
lost_packets = {} lost_packets = {}
delay_until_lost = infinite; delay_until_lost = infinite
if (time_reordering_fraction != infinite): if (time_reordering_fraction != infinite):
delay_until_lost = delay_until_lost =
(1 + time_reordering_fraction) * max(latest_rtt, smoothed_rtt) (1 + time_reordering_fraction) * max(latest_rtt, smoothed_rtt)
else if (largest_acked.packet_number == largest_sent_packet): else if (largest_acked.packet_number == largest_sent_packet):
// Early retransmit alarm. // Early retransmit alarm.
delay_until_lost = 9/8 * max(latest_rtt, smoothed_rtt) delay_until_lost = 9/8 * max(latest_rtt, smoothed_rtt)
foreach (unacked less than largest_acked.packet_number): foreach (unacked < largest_acked.packet_number):
time_since_sent = now() - unacked.time_sent time_since_sent = now() - unacked.time_sent
packet_delta = largest_acked.packet_number - unacked.packet_number packet_delta = largest_acked.packet_number - unacked.packet_number
if (time_since_sent > delay_until_lost): if (time_since_sent > delay_until_lost):
lost_packets.insert(unacked) lost_packets.insert(unacked)
else if (packet_delta > reordering_threshold) else if (packet_delta > reordering_threshold)
lost_packets.insert(unacked) lost_packets.insert(unacked)
else if (loss_time == 0 && delay_until_lost != infinite): else if (loss_time == 0 && delay_until_lost != infinite):
loss_time = delay_until_lost - time_since_sent loss_time = now() + delay_until_lost - time_since_sent
// Inform the congestion controller of lost packets and // Inform the congestion controller of lost packets and
// lets it decide whether to retransmit immediately. // lets it decide whether to retransmit immediately.
OnPacketsLost(lost_packets) if (!lost_packets.empty())
foreach (packet in lost_packets) OnPacketsLost(lost_packets)
sent_packets.remove(packet.packet_number) foreach (packet in lost_packets)
sent_packets.remove(packet.packet_number)
3.3. Discussion
The majority of constants were derived from best common practices
among widely deployed TCP implementations on the internet.
Exceptions follow.
A shorter delayed ack time of 25ms was chosen because longer delayed
acks can delay loss recovery and for the small number of connections
where less than packet per 25ms is delivered, acking every packet is
beneficial to congestion control and loss recovery.
The default initial RTT of 100ms was chosen because it is slightly
higher than both the median and mean min_rtt typically observed on
the public internet.
4. Congestion Control 4. Congestion Control
(describe NewReno-style congestion control [RFC6582] for QUIC.) QUIC's congestion control is based on TCP NewReno[RFC6582] congestion
(describe appropriate byte counting.) (define recovery based on control to determine the congestion window and pacing rate.
packet numbers.) (describe min_rtt based hystart.) (describe how
QUIC's F-RTO [RFC5682] delays reducing CWND.) (describe PRR 4.1. Slow Start
[RFC6937])
QUIC begins every connection in slow start and exits slow start upon
loss. While in slow start, QUIC increases the congestion window by
the number of acknowledged bytes when each ack is processed.
4.2. Recovery
Recovery is a period of time beginning with detection of a lost
packet. It ends when all packets outstanding at the time recovery
began have been acknowledged or lost. During recovery, the
congestion window is not increased or decreased.
4.3. Constants of interest
Constants used in congestion control are based on a combination of
RFCs, papers, and common practice. Some may need to be changed or
negotiated in order to better suit a variety of environments.
kDefaultMss (default 1460 bytes): The default max packet size used
for calculating default and minimum congestion windows.
kInitialWindow (default 10 * kDefaultMss): Default limit on the
amount of outstanding data in bytes.
kMinimumWindow (default 2 * kDefaultMss): Default minimum congestion
window.
kLossReductionFactor (default 0.5): Reduction in congestion window
when a new loss event is detected.
4.4. Variables of interest
Variables required to implement the congestion control mechanisms are
described in this section.
bytes_in_flight: The sum of the size in bytes of all sent packets
that contain at least one retransmittable frame, and have not been
acked or declared lost.
congestion_window: Maximum number of bytes in flight that may be
sent.
end_of_recovery: The packet number after which QUIC will no longer
be in recovery.
ssthresh Slow start threshold in bytes. When the congestion window
is below ssthresh, it grows by the number of bytes acknowledged
for each ack.
4.5. Initialization
At the beginning of the connection, initialize the loss detection
variables as follows:
congestion_window = kInitialWindow
bytes_in_flight = 0
end_of_recovery = 0
ssthresh = infinite
4.6. On Packet Acknowledgement
Invoked at the same time loss detection's OnPacketAcked is called and
supplied with the acked_packet from sent_packets.
Pseudocode for OnPacketAcked follows:
OnPacketAcked(acked_packet):
if (acked_packet.packet_number < end_of_recovery):
return
if (congestion_window < ssthresh):
congestion_window += acket_packets.bytes
else:
congestion_window +=
acked_packets.bytes / congestion_window
4.7. On Packets Lost
Invoked by loss detection from DetectLostPackets when new packets are
detected lost.
OnPacketsLost(lost_packets):
largest_lost_packet = lost_packets.last()
// Start a new recovery epoch if the lost packet is larger
// than the end of the previous recovery epoch.
if (end_of_recovery < largest_lost_packet.packet_number):
end_of_recovery = largest_sent_packet
congestion_window *= kLossReductionFactor
congestion_window = max(congestion_window, kMinimumWindow)
ssthresh = congestion_window
4.8. On Retransmission Timeout Verified
QUIC decreases the congestion window to the minimum value once the
retransmission timeout has been confirmed to not be spurious when the
first post-RTO acknowledgement is processed.
OnRetransmissionTimeoutVerified()
congestion_window = kMinimumWindow
4.9. Pacing Packets
QUIC sends a packet if there is available congestion window and
sending the packet does not exceed the pacing rate.
TimeToSend returns infinite if the congestion controller is
congestion window limited, a time in the past if the packet can be
sent immediately, and a time in the future if sending is pacing
limited.
TimeToSend(packet_size):
if (bytes_in_flight + packet_size > congestion_window)
return infinite
return time_of_last_sent_packet +
(packet_size * smoothed_rtt) / congestion_window
5. IANA Considerations 5. IANA Considerations
This document has no IANA actions. Yet. This document has no IANA actions. Yet.
6. References 6. References
6.1. Normative References 6.1. Normative References
[QUIC-TRANSPORT] [QUIC-TRANSPORT]
Iyengar, J., Ed. and M. Thomson, Ed., "QUIC: A UDP-Based Iyengar, J., Ed. and M. Thomson, Ed., "QUIC: A UDP-Based
Multiplexed and Secure Transport". Multiplexed and Secure Transport", draft-ietf-quic-
transport (work in progress), May 2017.
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119, Requirement Levels", BCP 14, RFC 2119,
DOI 10.17487/RFC2119, March 1997, DOI 10.17487/RFC2119, March 1997,
<http://www.rfc-editor.org/info/rfc2119>. <http://www.rfc-editor.org/info/rfc2119>.
6.2. Informative References 6.2. Informative References
[I-D.dukkipati-tcpm-tcp-loss-probe] [LOSS-PROBE]
Dukkipati, N., Cardwell, N., Cheng, Y., and M. Mathis, Dukkipati, N., Cardwell, N., Cheng, Y., and M. Mathis,
"Tail Loss Probe (TLP): An Algorithm for Fast Recovery of "Tail Loss Probe (TLP): An Algorithm for Fast Recovery of
Tail Losses", draft-dukkipati-tcpm-tcp-loss-probe-01 (work Tail Losses", draft-dukkipati-tcpm-tcp-loss-probe-01 (work
in progress), February 2013. in progress), February 2013.
[RFC5682] Sarolahti, P., Kojo, M., Yamamoto, K., and M. Hata, [RFC5682] Sarolahti, P., Kojo, M., Yamamoto, K., and M. Hata,
"Forward RTO-Recovery (F-RTO): An Algorithm for Detecting "Forward RTO-Recovery (F-RTO): An Algorithm for Detecting
Spurious Retransmission Timeouts with TCP", RFC 5682, Spurious Retransmission Timeouts with TCP", RFC 5682,
DOI 10.17487/RFC5682, September 2009, DOI 10.17487/RFC5682, September 2009,
<http://www.rfc-editor.org/info/rfc5682>. <http://www.rfc-editor.org/info/rfc5682>.
skipping to change at page 13, line 40 skipping to change at page 17, line 33
[RFC6298] Paxson, V., Allman, M., Chu, J., and M. Sargent, [RFC6298] Paxson, V., Allman, M., Chu, J., and M. Sargent,
"Computing TCP's Retransmission Timer", RFC 6298, "Computing TCP's Retransmission Timer", RFC 6298,
DOI 10.17487/RFC6298, June 2011, DOI 10.17487/RFC6298, June 2011,
<http://www.rfc-editor.org/info/rfc6298>. <http://www.rfc-editor.org/info/rfc6298>.
[RFC6582] Henderson, T., Floyd, S., Gurtov, A., and Y. Nishida, "The [RFC6582] Henderson, T., Floyd, S., Gurtov, A., and Y. Nishida, "The
NewReno Modification to TCP's Fast Recovery Algorithm", NewReno Modification to TCP's Fast Recovery Algorithm",
RFC 6582, DOI 10.17487/RFC6582, April 2012, RFC 6582, DOI 10.17487/RFC6582, April 2012,
<http://www.rfc-editor.org/info/rfc6582>. <http://www.rfc-editor.org/info/rfc6582>.
[RFC6937] Mathis, M., Dukkipati, N., and Y. Cheng, "Proportional
Rate Reduction for TCP", RFC 6937, DOI 10.17487/RFC6937,
May 2013, <http://www.rfc-editor.org/info/rfc6937>.
Appendix A. Acknowledgments Appendix A. Acknowledgments
Appendix B. Change Log Appendix B. Change Log
*RFC Editor's Note:* Please remove this section prior to *RFC Editor's Note:* Please remove this section prior to
publication of a final version of this document. publication of a final version of this document.
B.1. Since draft-ietf-quic-recovery-01 B.1. Since draft-ietf-quic-recovery-02
o Integrate F-RTO (#544, #409)
o Add congestion control (#545, #395)
o Require connection abort if a skipped packet was acknowledged
(#415)
o Simplify RTO calculations (#142, #417)
B.2. Since draft-ietf-quic-recovery-01
o Overview added to loss detection
o Changes initial default RTT to 100ms o Changes initial default RTT to 100ms
o Added time-based loss detection and fixes early retransmit o Added time-based loss detection and fixes early retransmit
o Clarified loss recovery for handshake packets o Clarified loss recovery for handshake packets
o Fixed references and made TCP references informative o Fixed references and made TCP references informative
B.2. Since draft-ietf-quic-recovery-00: B.3. Since draft-ietf-quic-recovery-00
o Improved description of constants and ACK behavior o Improved description of constants and ACK behavior
B.3. Since draft-iyengar-quic-loss-recovery-01: B.4. Since draft-iyengar-quic-loss-recovery-01
o Adopted as base for draft-ietf-quic-recovery. o Adopted as base for draft-ietf-quic-recovery
o Updated authors/editors list. o Updated authors/editors list
o Added table of contents. o Added table of contents
Authors' Addresses Authors' Addresses
Jana Iyengar (editor) Jana Iyengar (editor)
Google Google
Email: jri@google.com Email: jri@google.com
Ian Swett (editor) Ian Swett (editor)
Google Google
 End of changes. 59 change blocks. 
126 lines changed or deleted 309 lines changed or added

This html diff was produced by rfcdiff 1.45. The latest version is available from http://tools.ietf.org/tools/rfcdiff/