linux_old1/net/ipv4/Kconfig

741 lines
26 KiB
Plaintext
Raw Normal View History

# SPDX-License-Identifier: GPL-2.0-only
#
# IP configuration
#
config IP_MULTICAST
bool "IP: multicasting"
help
This is code for addressing several networked computers at once,
enlarging your kernel by about 2 KB. You need multicasting if you
intend to participate in the MBONE, a high bandwidth network on top
of the Internet which carries audio and video broadcasts. More
information about the MBONE is on the WWW at
<http://www.savetz.com/mbone/>. For most people, it's safe to say N.
config IP_ADVANCED_ROUTER
bool "IP: advanced router"
---help---
If you intend to run your Linux box mostly as a router, i.e. as a
computer that forwards and redistributes network packets, say Y; you
will then be presented with several options that allow more precise
control about the routing process.
The answer to this question won't directly affect the kernel:
answering N will just cause the configurator to skip all the
questions about advanced routing.
Note that your box can only act as a router if you enable IP
forwarding in your kernel; you can do that by saying Y to "/proc
file system support" and "Sysctl support" below and executing the
line
echo "1" > /proc/sys/net/ipv4/ip_forward
at boot time after the /proc file system has been mounted.
If you turn on IP forwarding, you should consider the rp_filter, which
automatically rejects incoming packets if the routing table entry
for their source address doesn't match the network interface they're
arriving on. This has security advantages because it prevents the
so-called IP spoofing, however it can pose problems if you use
asymmetric routing (packets from you to a host take a different path
than packets from that host to you) or if you operate a non-routing
host which has several IP addresses on different interfaces. To turn
rp_filter on use:
echo 1 > /proc/sys/net/ipv4/conf/<device>/rp_filter
or
echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter
Note that some distributions enable it in startup scripts.
For details about rp_filter strict and loose mode read
<file:Documentation/networking/ip-sysctl.txt>.
If unsure, say N here.
config IP_FIB_TRIE_STATS
bool "FIB TRIE statistics"
depends on IP_ADVANCED_ROUTER
---help---
Keep track of statistics on structure of FIB TRIE table.
Useful for testing and measuring TRIE performance.
config IP_MULTIPLE_TABLES
bool "IP: policy routing"
depends on IP_ADVANCED_ROUTER
select FIB_RULES
---help---
Normally, a router decides what to do with a received packet based
solely on the packet's final destination address. If you say Y here,
the Linux router will also be able to take the packet's source
address into account. Furthermore, the TOS (Type-Of-Service) field
of the packet can be used for routing decisions as well.
If you need more information, see the Linux Advanced
Routing and Traffic Control documentation at
<http://lartc.org/howto/lartc.rpdb.html>
If unsure, say N.
config IP_ROUTE_MULTIPATH
bool "IP: equal cost multipath"
depends on IP_ADVANCED_ROUTER
help
Normally, the routing tables specify a single action to be taken in
a deterministic manner for a given packet. If you say Y here
however, it becomes possible to attach several actions to a packet
pattern, in effect specifying several alternative paths to travel
for those packets. The router considers all these paths to be of
equal "cost" and chooses one of them in a non-deterministic fashion
if a matching packet arrives.
config IP_ROUTE_VERBOSE
bool "IP: verbose route monitoring"
depends on IP_ADVANCED_ROUTER
help
If you say Y here, which is recommended, then the kernel will print
verbose messages regarding the routing, for example warnings about
received packets which look strange and could be evidence of an
attack or a misconfigured system somewhere. The information is
handled by the klogd daemon which is responsible for kernel messages
("man klogd").
config IP_ROUTE_CLASSID
bool
config IP_PNP
bool "IP: kernel level autoconfiguration"
help
This enables automatic configuration of IP addresses of devices and
of the routing table during kernel boot, based on either information
supplied on the kernel command line or by BOOTP or RARP protocols.
You need to say Y only for diskless machines requiring network
access to boot (in which case you want to say Y to "Root file system
on NFS" as well), because all other machines configure the network
in their startup scripts.
config IP_PNP_DHCP
bool "IP: DHCP support"
depends on IP_PNP
---help---
If you want your Linux box to mount its whole root file system (the
one containing the directory /) from some other computer over the
net via NFS and you want the IP address of your computer to be
discovered automatically at boot time using the DHCP protocol (a
special protocol designed for doing this job), say Y here. In case
the boot ROM of your network card was designed for booting Linux and
does DHCP itself, providing all necessary information on the kernel
command line, you can say N here.
If unsure, say Y. Note that if you want to use DHCP, a DHCP server
must be operating on your network. Read
<file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_BOOTP
bool "IP: BOOTP support"
depends on IP_PNP
---help---
If you want your Linux box to mount its whole root file system (the
one containing the directory /) from some other computer over the
net via NFS and you want the IP address of your computer to be
discovered automatically at boot time using the BOOTP protocol (a
special protocol designed for doing this job), say Y here. In case
the boot ROM of your network card was designed for booting Linux and
does BOOTP itself, providing all necessary information on the kernel
command line, you can say N here. If unsure, say Y. Note that if you
want to use BOOTP, a BOOTP server must be operating on your network.
Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_RARP
bool "IP: RARP support"
depends on IP_PNP
help
If you want your Linux box to mount its whole root file system (the
one containing the directory /) from some other computer over the
net via NFS and you want the IP address of your computer to be
discovered automatically at boot time using the RARP protocol (an
older protocol which is being obsoleted by BOOTP and DHCP), say Y
here. Note that if you want to use RARP, a RARP server must be
operating on your network. Read
<file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config NET_IPIP
tristate "IP: tunneling"
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 17:12:13 +08:00
select INET_TUNNEL
select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
encapsulating protocol. This particular tunneling driver implements
encapsulation of IP within IP, which sounds kind of pointless, but
can be useful if you want to make your (or some other) machine
appear on a different network than it physically is, or to use
mobile-IP facilities (allowing laptops to seamlessly move between
networks without changing their IP addresses).
Saying Y to this option will produce two modules ( = code which can
be inserted in and removed from the running kernel whenever you
want). Most people won't need this and can say N.
config NET_IPGRE_DEMUX
tristate "IP: GRE demultiplexer"
help
This is helper module to demultiplex GRE packets on GRE version field criteria.
Required by ip_gre and pptp modules.
config NET_IP_TUNNEL
tristate
select DST_CACHE
select GRO_CELLS
default n
config NET_IPGRE
tristate "IP: GRE tunnels over IP"
depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX
select NET_IP_TUNNEL
help
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
encapsulating protocol. This particular tunneling driver implements
GRE (Generic Routing Encapsulation) and at this time allows
encapsulating of IPv4 or IPv6 over existing IPv4 infrastructure.
This driver is useful if the other endpoint is a Cisco router: Cisco
likes GRE much better than the other Linux tunneling driver ("IP
tunneling" above). In addition, GRE allows multicast redistribution
through the tunnel.
config NET_IPGRE_BROADCAST
bool "IP: broadcast GRE over IP"
depends on IP_MULTICAST && NET_IPGRE
help
One application of GRE/IP is to construct a broadcast WAN (Wide Area
Network), which looks like a normal Ethernet LAN (Local Area
Network), but can be distributed all over the Internet. If you want
to do that, say Y here and to "IP multicast routing" below.
config IP_MROUTE_COMMON
bool
depends on IP_MROUTE || IPV6_MROUTE
config IP_MROUTE
bool "IP: multicast routing"
depends on IP_MULTICAST
select IP_MROUTE_COMMON
help
This is used if you want your machine to act as a router for IP
packets that have several destination addresses. It is needed on the
MBONE, a high bandwidth network on top of the Internet which carries
audio and video broadcasts. In order to do that, you would most
likely run the program mrouted. If you haven't heard about it, you
don't need it.
config IP_MROUTE_MULTIPLE_TABLES
bool "IP: multicast policy routing"
depends on IP_MROUTE && IP_ADVANCED_ROUTER
select FIB_RULES
help
Normally, a multicast router runs a userspace daemon and decides
what to do with a multicast packet based on the source and
destination addresses. If you say Y here, the multicast router
will also be able to take interfaces and packet marks into
account and run multiple instances of userspace daemons
simultaneously, each one handling a single table.
If unsure, say N.
config IP_PIMSM_V1
bool "IP: PIM-SM version 1 support"
depends on IP_MROUTE
help
Kernel side support for Sparse Mode PIM (Protocol Independent
Multicast) version 1. This multicast routing protocol is used widely
because Cisco supports it. You need special software to use it
(pimd-v1). Please see <http://netweb.usc.edu/pim/> for more
information about PIM.
Say Y if you want to use PIM-SM v1. Note that you can say N here if
you just want to use Dense Mode PIM.
config IP_PIMSM_V2
bool "IP: PIM-SM version 2 support"
depends on IP_MROUTE
help
Kernel side support for Sparse Mode PIM version 2. In order to use
this, you need an experimental routing daemon supporting it (pimd or
gated-5). This routing protocol is not used widely, so say N unless
you want to play with it.
config SYN_COOKIES
bool "IP: TCP syncookie support"
---help---
Normal TCP/IP networking is open to an attack known as "SYN
flooding". This denial-of-service attack prevents legitimate remote
users from being able to connect to your computer during an ongoing
attack and requires very little work from the attacker, who can
operate from anywhere on the Internet.
SYN cookies provide protection against this type of attack. If you
say Y here, the TCP/IP stack will use a cryptographic challenge
protocol known as "SYN cookies" to enable legitimate users to
continue to connect, even when your machine is under attack. There
is no need for the legitimate users to change their TCP/IP software;
SYN cookies work transparently to them. For technical information
about SYN cookies, check out <http://cr.yp.to/syncookies.html>.
If you are SYN flooded, the source address reported by the kernel is
likely to have been forged by the attacker; it is only reported as
an aid in tracing the packets to their actual source and should not
be taken as absolute truth.
SYN cookies may prevent correct error reporting on clients when the
server is really overloaded. If this happens frequently better turn
them off.
If you say Y here, you can disable SYN cookies at run time by
saying Y to "/proc file system support" and
"Sysctl support" below and executing the command
echo 0 > /proc/sys/net/ipv4/tcp_syncookies
after the /proc file system has been mounted.
If unsure, say N.
config NET_IPVTI
tristate "Virtual (secure) IP: tunneling"
select INET_TUNNEL
select NET_IP_TUNNEL
select XFRM
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
encapsulating protocol. This can be used with xfrm mode tunnel to give
the notion of a secure tunnel for IPSEC and then use routing protocol
on top.
config NET_UDP_TUNNEL
tristate
select NET_IP_TUNNEL
default n
config NET_FOU
tristate "IP: Foo (IP protocols) over UDP"
select XFRM
select NET_UDP_TUNNEL
---help---
Foo over UDP allows any IP protocol to be directly encapsulated
over UDP include tunnels (IPIP, GRE, SIT). By encapsulating in UDP
network mechanisms and optimizations for UDP (such as ECMP
and RSS) can be leveraged to provide better service.
config NET_FOU_IP_TUNNELS
bool "IP: FOU encapsulation of IP tunnels"
depends on NET_IPIP || NET_IPGRE || IPV6_SIT
select NET_FOU
---help---
Allow configuration of FOU or GUE encapsulation for IP tunnels.
When this option is enabled IP tunnels can be configured to use
FOU or GUE encapsulation.
config INET_AH
tristate "IP: AH transformation"
select XFRM_ALGO
select CRYPTO
select CRYPTO_HMAC
select CRYPTO_MD5
select CRYPTO_SHA1
---help---
Support for IPsec AH.
If unsure, say Y.
config INET_ESP
tristate "IP: ESP transformation"
select XFRM_ALGO
select CRYPTO
select CRYPTO_AUTHENC
select CRYPTO_HMAC
select CRYPTO_MD5
select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
select CRYPTO_ECHAINIV
---help---
Support for IPsec ESP.
If unsure, say Y.
config INET_ESP_OFFLOAD
tristate "IP: ESP transformation offload"
depends on INET_ESP
select XFRM_OFFLOAD
default n
---help---
Support for ESP transformation offload. This makes sense
only if this system really does IPsec and want to do it
with high throughput. A typical desktop system does not
need it, even if it does IPsec.
If unsure, say N.
config INET_ESPINTCP
bool "IP: ESP in TCP encapsulation (RFC 8229)"
depends on XFRM && INET_ESP
select STREAM_PARSER
select NET_SOCK_MSG
help
Support for RFC 8229 encapsulation of ESP and IKE over
TCP/IPv4 sockets.
If unsure, say N.
config INET_IPCOMP
tristate "IP: IPComp transformation"
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 17:12:13 +08:00
select INET_XFRM_TUNNEL
select XFRM_IPCOMP
---help---
Support for IP Payload Compression Protocol (IPComp) (RFC3173),
typically needed for IPsec.
If unsure, say Y.
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 17:12:13 +08:00
config INET_XFRM_TUNNEL
tristate
select INET_TUNNEL
default n
config INET_TUNNEL
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 17:12:13 +08:00
tristate
default n
config INET_DIAG
tristate "INET: socket monitoring interface"
default y
---help---
Support for INET (TCP, DCCP, etc) socket monitoring interface used by
native Linux tools such as ss. ss is included in iproute2, currently
Docs/Kconfig: Update: osdl.org -> linuxfoundation.org Some of the documentation refers to web pages under the domain `osdl.org'. However, `osdl.org' now redirects to `linuxfoundation.org'. Rather than rely on redirections, this patch updates the addresses appropriately; for the most part, only documentation that is meant to be current has been updated. The patch should be pretty quick to scan and check; each new web-page url was gotten by trying out the original URL in a browser and then simply copying the the redirected URL (formatting as necessary). There is some conflict as to which one of these domain names is preferred: linuxfoundation.org linux-foundation.org So, I wrote: info@linuxfoundation.org and got this reply: Message-ID: <4CE17EE6.9040807@linuxfoundation.org> Date: Mon, 15 Nov 2010 10:41:42 -0800 From: David Ames <david@linuxfoundation.org> ... linuxfoundation.org is preferred. The canonical name for our web site is www.linuxfoundation.org. Our list site is actually lists.linux-foundation.org. Regarding email linuxfoundation.org is preferred there are a few people who choose to use linux-foundation.org for their own reasons. Consequently, I used `linuxfoundation.org' for web pages and `lists.linux-foundation.org' for mailing-list web pages and email addresses; the only personal email address I updated from `@osdl.org' was that of Andrew Morton, who prefers `linux-foundation.org' according `git log'. Signed-off-by: Michael Witten <mfwitten@gmail.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2010-11-16 03:55:34 +08:00
downloadable at:
Docs/Kconfig: Update: osdl.org -> linuxfoundation.org Some of the documentation refers to web pages under the domain `osdl.org'. However, `osdl.org' now redirects to `linuxfoundation.org'. Rather than rely on redirections, this patch updates the addresses appropriately; for the most part, only documentation that is meant to be current has been updated. The patch should be pretty quick to scan and check; each new web-page url was gotten by trying out the original URL in a browser and then simply copying the the redirected URL (formatting as necessary). There is some conflict as to which one of these domain names is preferred: linuxfoundation.org linux-foundation.org So, I wrote: info@linuxfoundation.org and got this reply: Message-ID: <4CE17EE6.9040807@linuxfoundation.org> Date: Mon, 15 Nov 2010 10:41:42 -0800 From: David Ames <david@linuxfoundation.org> ... linuxfoundation.org is preferred. The canonical name for our web site is www.linuxfoundation.org. Our list site is actually lists.linux-foundation.org. Regarding email linuxfoundation.org is preferred there are a few people who choose to use linux-foundation.org for their own reasons. Consequently, I used `linuxfoundation.org' for web pages and `lists.linux-foundation.org' for mailing-list web pages and email addresses; the only personal email address I updated from `@osdl.org' was that of Andrew Morton, who prefers `linux-foundation.org' according `git log'. Signed-off-by: Michael Witten <mfwitten@gmail.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2010-11-16 03:55:34 +08:00
http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2
If unsure, say Y.
config INET_TCP_DIAG
depends on INET_DIAG
def_tristate INET_DIAG
config INET_UDP_DIAG
tristate "UDP: socket monitoring interface"
depends on INET_DIAG && (IPV6 || IPV6=n)
default n
---help---
Support for UDP socket monitoring interface used by the ss tool.
If unsure, say Y.
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 18:03:44 +08:00
config INET_RAW_DIAG
tristate "RAW: socket monitoring interface"
depends on INET_DIAG && (IPV6 || IPV6=n)
default n
---help---
Support for RAW socket monitoring interface used by the ss tool.
If unsure, say Y.
config INET_DIAG_DESTROY
bool "INET: allow privileged process to administratively close sockets"
depends on INET_DIAG
default n
---help---
Provides a SOCK_DESTROY operation that allows privileged processes
(e.g., a connection manager or a network administration tool such as
ss) to close sockets opened by other processes. Closing a socket in
this way interrupts any blocking read/write/connect operations on
the socket and causes future socket calls to behave as if the socket
had been disconnected.
If unsure, say N.
menuconfig TCP_CONG_ADVANCED
bool "TCP: advanced congestion control"
---help---
Support for selection of various TCP congestion control
modules.
Nearly all users can safely say no here, and a safe default
selection will be made (CUBIC with new Reno as a fallback).
If unsure, say N.
if TCP_CONG_ADVANCED
config TCP_CONG_BIC
tristate "Binary Increase Congestion (BIC) control"
default m
---help---
BIC-TCP is a sender-side only change that ensures a linear RTT
fairness under large windows while offering both scalability and
bounded TCP-friendliness. The protocol combines two schemes
called additive increase and binary search increase. When the
congestion window is large, additive increase with a large
increment ensures linear RTT fairness as well as good
scalability. Under small congestion windows, binary search
increase provides TCP friendliness.
See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
config TCP_CONG_CUBIC
tristate "CUBIC TCP"
default y
---help---
This is version 2.0 of BIC-TCP which uses a cubic growth function
among other techniques.
See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
config TCP_CONG_WESTWOOD
tristate "TCP Westwood+"
default m
---help---
TCP Westwood+ is a sender-side only modification of the TCP Reno
protocol stack that optimizes the performance of TCP congestion
control. It is based on end-to-end bandwidth estimation to set
congestion window and slow start threshold after a congestion
episode. Using this estimation, TCP Westwood+ adaptively sets a
slow start threshold and a congestion window which takes into
account the bandwidth used at the time congestion is experienced.
TCP Westwood+ significantly increases fairness wrt TCP Reno in
wired networks and throughput over wireless links.
config TCP_CONG_HTCP
tristate "H-TCP"
default m
---help---
H-TCP is a send-side only modifications of the TCP Reno
protocol stack that optimizes the performance of TCP
congestion control for high speed network links. It uses a
modeswitch to change the alpha and beta parameters of TCP Reno
based on network conditions and in a way so as to be fair with
other Reno and H-TCP flows.
config TCP_CONG_HSTCP
tristate "High Speed TCP"
default n
---help---
Sally Floyd's High Speed TCP (RFC 3649) congestion control.
A modification to TCP's congestion control mechanism for use
with large congestion windows. A table indicates how much to
increase the congestion window by when an ACK is received.
For more detail see http://www.icir.org/floyd/hstcp.html
config TCP_CONG_HYBLA
tristate "TCP-Hybla congestion control algorithm"
default n
---help---
TCP-Hybla is a sender-side only change that eliminates penalization of
long-RTT, large-bandwidth connections, like when satellite legs are
involved, especially when sharing a common bottleneck with normal
terrestrial connections.
config TCP_CONG_VEGAS
tristate "TCP Vegas"
default n
---help---
TCP Vegas is a sender-side only change to TCP that anticipates
the onset of congestion by estimating the bandwidth. TCP Vegas
adjusts the sending rate by modifying the congestion
window. TCP Vegas should provide less packet loss, but it is
not as aggressive as TCP Reno.
config TCP_CONG_NV
tristate "TCP NV"
default n
---help---
TCP NV is a follow up to TCP Vegas. It has been modified to deal with
10G networks, measurement noise introduced by LRO, GRO and interrupt
coalescence. In addition, it will decrease its cwnd multiplicatively
instead of linearly.
Note that in general congestion avoidance (cwnd decreased when # packets
queued grows) cannot coexist with congestion control (cwnd decreased only
when there is packet loss) due to fairness issues. One scenario when they
can coexist safely is when the CA flows have RTTs << CC flows RTTs.
For further details see http://www.brakmo.org/networking/tcp-nv/
config TCP_CONG_SCALABLE
tristate "Scalable TCP"
default n
---help---
Scalable TCP is a sender-side only change to TCP which uses a
MIMD congestion control algorithm which has some nice scaling
properties, though is known to have fairness issues.
See http://www.deneholme.net/tom/scalable/
config TCP_CONG_LP
tristate "TCP Low Priority"
default n
---help---
TCP Low Priority (TCP-LP), a distributed algorithm whose goal is
to utilize only the excess network bandwidth as compared to the
``fair share`` of bandwidth as targeted by TCP.
See http://www-ece.rice.edu/networks/TCP-LP/
config TCP_CONG_VENO
tristate "TCP Veno"
default n
---help---
TCP Veno is a sender-side only enhancement of TCP to obtain better
throughput over wireless networks. TCP Veno makes use of state
distinguishing to circumvent the difficult judgment of the packet loss
type. TCP Veno cuts down less congestion window in response to random
loss packets.
See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
config TCP_CONG_YEAH
tristate "YeAH TCP"
select TCP_CONG_VEGAS
default n
---help---
YeAH-TCP is a sender-side high-speed enabled TCP congestion control
algorithm, which uses a mixed loss/delay approach to compute the
congestion window. It's design goals target high efficiency,
internal, RTT and Reno fairness, resilience to link loss while
keeping network elements load as low as possible.
For further details look here:
http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
config TCP_CONG_ILLINOIS
tristate "TCP Illinois"
default n
---help---
TCP-Illinois is a sender-side modification of TCP Reno for
high speed long delay links. It uses round-trip-time to
adjust the alpha and beta parameters to achieve a higher average
throughput and maintain fairness.
For further details see:
http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
net: tcp: add DCTCP congestion control algorithm This work adds the DataCenter TCP (DCTCP) congestion control algorithm [1], which has been first published at SIGCOMM 2010 [2], resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more recently as an informational IETF draft available at [4]). DCTCP is an enhancement to the TCP congestion control algorithm for data center networks. Typical data center workloads are i.e. i) partition/aggregate (queries; bursty, delay sensitive), ii) short messages e.g. 50KB-1MB (for coordination and control state; delay sensitive), and iii) large flows e.g. 1MB-100MB (data update; throughput sensitive). DCTCP has therefore been designed for such environments to provide/achieve the following three requirements: * High burst tolerance (incast due to partition/aggregate) * Low latency (short flows, queries) * High throughput (continuous data updates, large file transfers) with commodity, shallow buffered switches The basic idea of its design consists of two fundamentals: i) on the switch side, packets are being marked when its internal queue length > threshold K (K is chosen so that a large enough headroom for marked traffic is still available in the switch queue); ii) the sender/host side maintains a moving average of the fraction of marked packets, so each RTT, F is being updated as follows: F := X / Y, where X is # of marked ACKs, Y is total # of ACKs alpha := (1 - g) * alpha + g * F, where g is a smoothing constant The resulting alpha (iow: probability that switch queue is congested) is then being used in order to adaptively decrease the congestion window W: W := (1 - (alpha / 2)) * W The means for receiving marked packets resp. marking them on switch side in DCTCP is the use of ECN. RFC3168 describes a mechanism for using Explicit Congestion Notification from the switch for early detection of congestion, rather than waiting for segment loss to occur. However, this method only detects the presence of congestion, not the *extent*. In the presence of mild congestion, it reduces the TCP congestion window too aggressively and unnecessarily affects the throughput of long flows [4]. DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN) processing to estimate the fraction of bytes that encounter congestion, rather than simply detecting that some congestion has occurred. DCTCP then scales the TCP congestion window based on this estimate [4], thus it can derive multibit feedback from the information present in the single-bit sequence of marks in its control law. And thus act in *proportion* to the extent of congestion, not its *presence*. Switches therefore set the Congestion Experienced (CE) codepoint in packets when internal queue lengths exceed threshold K. Resulting, DCTCP delivers the same or better throughput than normal TCP, while using 90% less buffer space. It was found in [2] that DCTCP enables the applications to handle 10x the current background traffic, without impacting foreground traffic. Moreover, a 10x increase in foreground traffic did not cause any timeouts, and thus largely eliminates TCP incast collapse problems. The algorithm itself has already seen deployments in large production data centers since then. We did a long-term stress-test and analysis in a data center, short summary of our TCP incast tests with iperf compared to cubic: This test measured DCTCP throughput and latency and compared it with CUBIC throughput and latency for an incast scenario. In this test, 19 senders sent at maximum rate to a single receiver. The receiver simply ran iperf -s. The senders ran iperf -c <receiver> -t 30. All senders started simultaneously (using local clocks synchronized by ntp). This test was repeated multiple times. Below shows the results from a single test. Other tests are similar. (DCTCP results were extremely consistent, CUBIC results show some variance induced by the TCP timeouts that CUBIC encountered.) For this test, we report statistics on the number of TCP timeouts, flow throughput, and traffic latency. 1) Timeouts (total over all flows, and per flow summaries): CUBIC DCTCP Total 3227 25 Mean 169.842 1.316 Median 183 1 Max 207 5 Min 123 0 Stddev 28.991 1.600 Timeout data is taken by measuring the net change in netstat -s "other TCP timeouts" reported. As a result, the timeout measurements above are not restricted to the test traffic, and we believe that it is likely that all of the "DCTCP timeouts" are actually timeouts for non-test traffic. We report them nevertheless. CUBIC will also include some non-test timeouts, but they are drawfed by bona fide test traffic timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing TCP timeouts. DCTCP reduces timeouts by at least two orders of magnitude and may well have eliminated them in this scenario. 2) Throughput (per flow in Mbps): CUBIC DCTCP Mean 521.684 521.895 Median 464 523 Max 776 527 Min 403 519 Stddev 105.891 2.601 Fairness 0.962 0.999 Throughput data was simply the average throughput for each flow reported by iperf. By avoiding TCP timeouts, DCTCP is able to achieve much better per-flow results. In CUBIC, many flows experience TCP timeouts which makes flow throughput unpredictable and unfair. DCTCP, on the other hand, provides very clean predictable throughput without incurring TCP timeouts. Thus, the standard deviation of CUBIC throughput is dramatically higher than the standard deviation of DCTCP throughput. Mean throughput is nearly identical because even though cubic flows suffer TCP timeouts, other flows will step in and fill the unused bandwidth. Note that this test is something of a best case scenario for incast under CUBIC: it allows other flows to fill in for flows experiencing a timeout. Under situations where the receiver is issuing requests and then waiting for all flows to complete, flows cannot fill in for timed out flows and throughput will drop dramatically. 3) Latency (in ms): CUBIC DCTCP Mean 4.0088 0.04219 Median 4.055 0.0395 Max 4.2 0.085 Min 3.32 0.028 Stddev 0.1666 0.01064 Latency for each protocol was computed by running "ping -i 0.2 <receiver>" from a single sender to the receiver during the incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure that traffic traversed the DCTCP queue and was not dropped when the queue size was greater than the marking threshold. The summary statistics above are over all ping metrics measured between the single sender, receiver pair. The latency results for this test show a dramatic difference between CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer which incurs the maximum queue latency (more buffer memory will lead to high latency.) DCTCP, on the other hand, deliberately attempts to keep queue occupancy low. The result is a two orders of magnitude reduction of latency with DCTCP - even with a switch with relatively little RAM. Switches with larger amounts of RAM will incur increasing amounts of latency for CUBIC, but not for DCTCP. 4) Convergence and stability test: This test measured the time that DCTCP took to fairly redistribute bandwidth when a new flow commences. It also measured DCTCP's ability to remain stable at a fair bandwidth distribution. DCTCP is compared with CUBIC for this test. At the commencement of this test, a single flow is sending at maximum rate (near 10 Gbps) to a single receiver. One second after that first flow commences, a new flow from a distinct server begins sending to the same receiver as the first flow. After the second flow has sent data for 10 seconds, the second flow is terminated. The first flow sends for an additional second. Ideally, the bandwidth would be evenly shared as soon as the second flow starts, and recover as soon as it stops. The results of this test are shown below. Note that the flow bandwidth for the two flows was measured near the same time, but not simultaneously. DCTCP performs nearly perfectly within the measurement limitations of this test: bandwidth is quickly distributed fairly between the two flows, remains stable throughout the duration of the test, and recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth fairly, and has trouble remaining stable. CUBIC DCTCP Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2 0 9.93 0 0 9.92 0 0.5 9.87 0 0.5 9.86 0 1 8.73 2.25 1 6.46 4.88 1.5 7.29 2.8 1.5 4.9 4.99 2 6.96 3.1 2 4.92 4.94 2.5 6.67 3.34 2.5 4.93 5 3 6.39 3.57 3 4.92 4.99 3.5 6.24 3.75 3.5 4.94 4.74 4 6 3.94 4 5.34 4.71 4.5 5.88 4.09 4.5 4.99 4.97 5 5.27 4.98 5 4.83 5.01 5.5 4.93 5.04 5.5 4.89 4.99 6 4.9 4.99 6 4.92 5.04 6.5 4.93 5.1 6.5 4.91 4.97 7 4.28 5.8 7 4.97 4.97 7.5 4.62 4.91 7.5 4.99 4.82 8 5.05 4.45 8 5.16 4.76 8.5 5.93 4.09 8.5 4.94 4.98 9 5.73 4.2 9 4.92 5.02 9.5 5.62 4.32 9.5 4.87 5.03 10 6.12 3.2 10 4.91 5.01 10.5 6.91 3.11 10.5 4.87 5.04 11 8.48 0 11 8.49 4.94 11.5 9.87 0 11.5 9.9 0 SYN/ACK ECT test: This test demonstrates the importance of ECT on SYN and SYN-ACK packets by measuring the connection probability in the presence of competing flows for a DCTCP connection attempt *without* ECT in the SYN packet. The test was repeated five times for each number of competing flows. Competing Flows 1 | 2 | 4 | 8 | 16 ------------------------------ Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0 Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0 As the number of competing flows moves beyond 1, the connection probability drops rapidly. Enabling DCTCP with this patch requires the following steps: DCTCP must be running both on the sender and receiver side in your data center, i.e.: sysctl -w net.ipv4.tcp_congestion_control=dctcp Also, ECN functionality must be enabled on all switches in your data center for DCTCP to work. The default ECN marking threshold (K) heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]). In above tests, for each switch port, traffic was segregated into two queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of 0x04 - the packet was placed into the DCTCP queue. All other packets were placed into the default drop-tail queue. For the DCTCP queue, RED/ECN marking was enabled, here, with a marking threshold of 75 KB. More details however, we refer you to the paper [2] under section 3). There are no code changes required to applications running in user space. DCTCP has been implemented in full *isolation* of the rest of the TCP code as its own congestion control module, so that it can run without a need to expose code to the core of the TCP stack, and thus nothing changes for non-DCTCP users. Changes in the CA framework code are minimal, and DCTCP algorithm operates on mechanisms that are already available in most Silicon. The gain (dctcp_shift_g) is currently a fixed constant (1/16) from the paper, but we leave the option that it can be chosen carefully to a different value by the user. In case DCTCP is being used and ECN support on peer site is off, DCTCP falls back after 3WHS to operate in normal TCP Reno mode. ss {-4,-6} -t -i diag interface: ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054 ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584 send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15 reordering:101 rcv_space:29200 ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448 cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate 325.5Mbps rcv_rtt:1.5 rcv_space:29200 More information about DCTCP can be found in [1-4]. [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00 Joint work with Florian Westphal and Glenn Judd. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-27 04:37:36 +08:00
config TCP_CONG_DCTCP
tristate "DataCenter TCP (DCTCP)"
default n
---help---
DCTCP leverages Explicit Congestion Notification (ECN) in the network to
provide multi-bit feedback to the end hosts. It is designed to provide:
net: tcp: add DCTCP congestion control algorithm This work adds the DataCenter TCP (DCTCP) congestion control algorithm [1], which has been first published at SIGCOMM 2010 [2], resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more recently as an informational IETF draft available at [4]). DCTCP is an enhancement to the TCP congestion control algorithm for data center networks. Typical data center workloads are i.e. i) partition/aggregate (queries; bursty, delay sensitive), ii) short messages e.g. 50KB-1MB (for coordination and control state; delay sensitive), and iii) large flows e.g. 1MB-100MB (data update; throughput sensitive). DCTCP has therefore been designed for such environments to provide/achieve the following three requirements: * High burst tolerance (incast due to partition/aggregate) * Low latency (short flows, queries) * High throughput (continuous data updates, large file transfers) with commodity, shallow buffered switches The basic idea of its design consists of two fundamentals: i) on the switch side, packets are being marked when its internal queue length > threshold K (K is chosen so that a large enough headroom for marked traffic is still available in the switch queue); ii) the sender/host side maintains a moving average of the fraction of marked packets, so each RTT, F is being updated as follows: F := X / Y, where X is # of marked ACKs, Y is total # of ACKs alpha := (1 - g) * alpha + g * F, where g is a smoothing constant The resulting alpha (iow: probability that switch queue is congested) is then being used in order to adaptively decrease the congestion window W: W := (1 - (alpha / 2)) * W The means for receiving marked packets resp. marking them on switch side in DCTCP is the use of ECN. RFC3168 describes a mechanism for using Explicit Congestion Notification from the switch for early detection of congestion, rather than waiting for segment loss to occur. However, this method only detects the presence of congestion, not the *extent*. In the presence of mild congestion, it reduces the TCP congestion window too aggressively and unnecessarily affects the throughput of long flows [4]. DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN) processing to estimate the fraction of bytes that encounter congestion, rather than simply detecting that some congestion has occurred. DCTCP then scales the TCP congestion window based on this estimate [4], thus it can derive multibit feedback from the information present in the single-bit sequence of marks in its control law. And thus act in *proportion* to the extent of congestion, not its *presence*. Switches therefore set the Congestion Experienced (CE) codepoint in packets when internal queue lengths exceed threshold K. Resulting, DCTCP delivers the same or better throughput than normal TCP, while using 90% less buffer space. It was found in [2] that DCTCP enables the applications to handle 10x the current background traffic, without impacting foreground traffic. Moreover, a 10x increase in foreground traffic did not cause any timeouts, and thus largely eliminates TCP incast collapse problems. The algorithm itself has already seen deployments in large production data centers since then. We did a long-term stress-test and analysis in a data center, short summary of our TCP incast tests with iperf compared to cubic: This test measured DCTCP throughput and latency and compared it with CUBIC throughput and latency for an incast scenario. In this test, 19 senders sent at maximum rate to a single receiver. The receiver simply ran iperf -s. The senders ran iperf -c <receiver> -t 30. All senders started simultaneously (using local clocks synchronized by ntp). This test was repeated multiple times. Below shows the results from a single test. Other tests are similar. (DCTCP results were extremely consistent, CUBIC results show some variance induced by the TCP timeouts that CUBIC encountered.) For this test, we report statistics on the number of TCP timeouts, flow throughput, and traffic latency. 1) Timeouts (total over all flows, and per flow summaries): CUBIC DCTCP Total 3227 25 Mean 169.842 1.316 Median 183 1 Max 207 5 Min 123 0 Stddev 28.991 1.600 Timeout data is taken by measuring the net change in netstat -s "other TCP timeouts" reported. As a result, the timeout measurements above are not restricted to the test traffic, and we believe that it is likely that all of the "DCTCP timeouts" are actually timeouts for non-test traffic. We report them nevertheless. CUBIC will also include some non-test timeouts, but they are drawfed by bona fide test traffic timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing TCP timeouts. DCTCP reduces timeouts by at least two orders of magnitude and may well have eliminated them in this scenario. 2) Throughput (per flow in Mbps): CUBIC DCTCP Mean 521.684 521.895 Median 464 523 Max 776 527 Min 403 519 Stddev 105.891 2.601 Fairness 0.962 0.999 Throughput data was simply the average throughput for each flow reported by iperf. By avoiding TCP timeouts, DCTCP is able to achieve much better per-flow results. In CUBIC, many flows experience TCP timeouts which makes flow throughput unpredictable and unfair. DCTCP, on the other hand, provides very clean predictable throughput without incurring TCP timeouts. Thus, the standard deviation of CUBIC throughput is dramatically higher than the standard deviation of DCTCP throughput. Mean throughput is nearly identical because even though cubic flows suffer TCP timeouts, other flows will step in and fill the unused bandwidth. Note that this test is something of a best case scenario for incast under CUBIC: it allows other flows to fill in for flows experiencing a timeout. Under situations where the receiver is issuing requests and then waiting for all flows to complete, flows cannot fill in for timed out flows and throughput will drop dramatically. 3) Latency (in ms): CUBIC DCTCP Mean 4.0088 0.04219 Median 4.055 0.0395 Max 4.2 0.085 Min 3.32 0.028 Stddev 0.1666 0.01064 Latency for each protocol was computed by running "ping -i 0.2 <receiver>" from a single sender to the receiver during the incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure that traffic traversed the DCTCP queue and was not dropped when the queue size was greater than the marking threshold. The summary statistics above are over all ping metrics measured between the single sender, receiver pair. The latency results for this test show a dramatic difference between CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer which incurs the maximum queue latency (more buffer memory will lead to high latency.) DCTCP, on the other hand, deliberately attempts to keep queue occupancy low. The result is a two orders of magnitude reduction of latency with DCTCP - even with a switch with relatively little RAM. Switches with larger amounts of RAM will incur increasing amounts of latency for CUBIC, but not for DCTCP. 4) Convergence and stability test: This test measured the time that DCTCP took to fairly redistribute bandwidth when a new flow commences. It also measured DCTCP's ability to remain stable at a fair bandwidth distribution. DCTCP is compared with CUBIC for this test. At the commencement of this test, a single flow is sending at maximum rate (near 10 Gbps) to a single receiver. One second after that first flow commences, a new flow from a distinct server begins sending to the same receiver as the first flow. After the second flow has sent data for 10 seconds, the second flow is terminated. The first flow sends for an additional second. Ideally, the bandwidth would be evenly shared as soon as the second flow starts, and recover as soon as it stops. The results of this test are shown below. Note that the flow bandwidth for the two flows was measured near the same time, but not simultaneously. DCTCP performs nearly perfectly within the measurement limitations of this test: bandwidth is quickly distributed fairly between the two flows, remains stable throughout the duration of the test, and recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth fairly, and has trouble remaining stable. CUBIC DCTCP Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2 0 9.93 0 0 9.92 0 0.5 9.87 0 0.5 9.86 0 1 8.73 2.25 1 6.46 4.88 1.5 7.29 2.8 1.5 4.9 4.99 2 6.96 3.1 2 4.92 4.94 2.5 6.67 3.34 2.5 4.93 5 3 6.39 3.57 3 4.92 4.99 3.5 6.24 3.75 3.5 4.94 4.74 4 6 3.94 4 5.34 4.71 4.5 5.88 4.09 4.5 4.99 4.97 5 5.27 4.98 5 4.83 5.01 5.5 4.93 5.04 5.5 4.89 4.99 6 4.9 4.99 6 4.92 5.04 6.5 4.93 5.1 6.5 4.91 4.97 7 4.28 5.8 7 4.97 4.97 7.5 4.62 4.91 7.5 4.99 4.82 8 5.05 4.45 8 5.16 4.76 8.5 5.93 4.09 8.5 4.94 4.98 9 5.73 4.2 9 4.92 5.02 9.5 5.62 4.32 9.5 4.87 5.03 10 6.12 3.2 10 4.91 5.01 10.5 6.91 3.11 10.5 4.87 5.04 11 8.48 0 11 8.49 4.94 11.5 9.87 0 11.5 9.9 0 SYN/ACK ECT test: This test demonstrates the importance of ECT on SYN and SYN-ACK packets by measuring the connection probability in the presence of competing flows for a DCTCP connection attempt *without* ECT in the SYN packet. The test was repeated five times for each number of competing flows. Competing Flows 1 | 2 | 4 | 8 | 16 ------------------------------ Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0 Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0 As the number of competing flows moves beyond 1, the connection probability drops rapidly. Enabling DCTCP with this patch requires the following steps: DCTCP must be running both on the sender and receiver side in your data center, i.e.: sysctl -w net.ipv4.tcp_congestion_control=dctcp Also, ECN functionality must be enabled on all switches in your data center for DCTCP to work. The default ECN marking threshold (K) heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]). In above tests, for each switch port, traffic was segregated into two queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of 0x04 - the packet was placed into the DCTCP queue. All other packets were placed into the default drop-tail queue. For the DCTCP queue, RED/ECN marking was enabled, here, with a marking threshold of 75 KB. More details however, we refer you to the paper [2] under section 3). There are no code changes required to applications running in user space. DCTCP has been implemented in full *isolation* of the rest of the TCP code as its own congestion control module, so that it can run without a need to expose code to the core of the TCP stack, and thus nothing changes for non-DCTCP users. Changes in the CA framework code are minimal, and DCTCP algorithm operates on mechanisms that are already available in most Silicon. The gain (dctcp_shift_g) is currently a fixed constant (1/16) from the paper, but we leave the option that it can be chosen carefully to a different value by the user. In case DCTCP is being used and ECN support on peer site is off, DCTCP falls back after 3WHS to operate in normal TCP Reno mode. ss {-4,-6} -t -i diag interface: ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054 ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584 send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15 reordering:101 rcv_space:29200 ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448 cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate 325.5Mbps rcv_rtt:1.5 rcv_space:29200 More information about DCTCP can be found in [1-4]. [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00 Joint work with Florian Westphal and Glenn Judd. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-27 04:37:36 +08:00
- High burst tolerance (incast due to partition/aggregate),
- Low latency (short flows, queries),
- High throughput (continuous data updates, large file transfers) with
commodity, shallow-buffered switches.
net: tcp: add DCTCP congestion control algorithm This work adds the DataCenter TCP (DCTCP) congestion control algorithm [1], which has been first published at SIGCOMM 2010 [2], resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more recently as an informational IETF draft available at [4]). DCTCP is an enhancement to the TCP congestion control algorithm for data center networks. Typical data center workloads are i.e. i) partition/aggregate (queries; bursty, delay sensitive), ii) short messages e.g. 50KB-1MB (for coordination and control state; delay sensitive), and iii) large flows e.g. 1MB-100MB (data update; throughput sensitive). DCTCP has therefore been designed for such environments to provide/achieve the following three requirements: * High burst tolerance (incast due to partition/aggregate) * Low latency (short flows, queries) * High throughput (continuous data updates, large file transfers) with commodity, shallow buffered switches The basic idea of its design consists of two fundamentals: i) on the switch side, packets are being marked when its internal queue length > threshold K (K is chosen so that a large enough headroom for marked traffic is still available in the switch queue); ii) the sender/host side maintains a moving average of the fraction of marked packets, so each RTT, F is being updated as follows: F := X / Y, where X is # of marked ACKs, Y is total # of ACKs alpha := (1 - g) * alpha + g * F, where g is a smoothing constant The resulting alpha (iow: probability that switch queue is congested) is then being used in order to adaptively decrease the congestion window W: W := (1 - (alpha / 2)) * W The means for receiving marked packets resp. marking them on switch side in DCTCP is the use of ECN. RFC3168 describes a mechanism for using Explicit Congestion Notification from the switch for early detection of congestion, rather than waiting for segment loss to occur. However, this method only detects the presence of congestion, not the *extent*. In the presence of mild congestion, it reduces the TCP congestion window too aggressively and unnecessarily affects the throughput of long flows [4]. DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN) processing to estimate the fraction of bytes that encounter congestion, rather than simply detecting that some congestion has occurred. DCTCP then scales the TCP congestion window based on this estimate [4], thus it can derive multibit feedback from the information present in the single-bit sequence of marks in its control law. And thus act in *proportion* to the extent of congestion, not its *presence*. Switches therefore set the Congestion Experienced (CE) codepoint in packets when internal queue lengths exceed threshold K. Resulting, DCTCP delivers the same or better throughput than normal TCP, while using 90% less buffer space. It was found in [2] that DCTCP enables the applications to handle 10x the current background traffic, without impacting foreground traffic. Moreover, a 10x increase in foreground traffic did not cause any timeouts, and thus largely eliminates TCP incast collapse problems. The algorithm itself has already seen deployments in large production data centers since then. We did a long-term stress-test and analysis in a data center, short summary of our TCP incast tests with iperf compared to cubic: This test measured DCTCP throughput and latency and compared it with CUBIC throughput and latency for an incast scenario. In this test, 19 senders sent at maximum rate to a single receiver. The receiver simply ran iperf -s. The senders ran iperf -c <receiver> -t 30. All senders started simultaneously (using local clocks synchronized by ntp). This test was repeated multiple times. Below shows the results from a single test. Other tests are similar. (DCTCP results were extremely consistent, CUBIC results show some variance induced by the TCP timeouts that CUBIC encountered.) For this test, we report statistics on the number of TCP timeouts, flow throughput, and traffic latency. 1) Timeouts (total over all flows, and per flow summaries): CUBIC DCTCP Total 3227 25 Mean 169.842 1.316 Median 183 1 Max 207 5 Min 123 0 Stddev 28.991 1.600 Timeout data is taken by measuring the net change in netstat -s "other TCP timeouts" reported. As a result, the timeout measurements above are not restricted to the test traffic, and we believe that it is likely that all of the "DCTCP timeouts" are actually timeouts for non-test traffic. We report them nevertheless. CUBIC will also include some non-test timeouts, but they are drawfed by bona fide test traffic timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing TCP timeouts. DCTCP reduces timeouts by at least two orders of magnitude and may well have eliminated them in this scenario. 2) Throughput (per flow in Mbps): CUBIC DCTCP Mean 521.684 521.895 Median 464 523 Max 776 527 Min 403 519 Stddev 105.891 2.601 Fairness 0.962 0.999 Throughput data was simply the average throughput for each flow reported by iperf. By avoiding TCP timeouts, DCTCP is able to achieve much better per-flow results. In CUBIC, many flows experience TCP timeouts which makes flow throughput unpredictable and unfair. DCTCP, on the other hand, provides very clean predictable throughput without incurring TCP timeouts. Thus, the standard deviation of CUBIC throughput is dramatically higher than the standard deviation of DCTCP throughput. Mean throughput is nearly identical because even though cubic flows suffer TCP timeouts, other flows will step in and fill the unused bandwidth. Note that this test is something of a best case scenario for incast under CUBIC: it allows other flows to fill in for flows experiencing a timeout. Under situations where the receiver is issuing requests and then waiting for all flows to complete, flows cannot fill in for timed out flows and throughput will drop dramatically. 3) Latency (in ms): CUBIC DCTCP Mean 4.0088 0.04219 Median 4.055 0.0395 Max 4.2 0.085 Min 3.32 0.028 Stddev 0.1666 0.01064 Latency for each protocol was computed by running "ping -i 0.2 <receiver>" from a single sender to the receiver during the incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure that traffic traversed the DCTCP queue and was not dropped when the queue size was greater than the marking threshold. The summary statistics above are over all ping metrics measured between the single sender, receiver pair. The latency results for this test show a dramatic difference between CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer which incurs the maximum queue latency (more buffer memory will lead to high latency.) DCTCP, on the other hand, deliberately attempts to keep queue occupancy low. The result is a two orders of magnitude reduction of latency with DCTCP - even with a switch with relatively little RAM. Switches with larger amounts of RAM will incur increasing amounts of latency for CUBIC, but not for DCTCP. 4) Convergence and stability test: This test measured the time that DCTCP took to fairly redistribute bandwidth when a new flow commences. It also measured DCTCP's ability to remain stable at a fair bandwidth distribution. DCTCP is compared with CUBIC for this test. At the commencement of this test, a single flow is sending at maximum rate (near 10 Gbps) to a single receiver. One second after that first flow commences, a new flow from a distinct server begins sending to the same receiver as the first flow. After the second flow has sent data for 10 seconds, the second flow is terminated. The first flow sends for an additional second. Ideally, the bandwidth would be evenly shared as soon as the second flow starts, and recover as soon as it stops. The results of this test are shown below. Note that the flow bandwidth for the two flows was measured near the same time, but not simultaneously. DCTCP performs nearly perfectly within the measurement limitations of this test: bandwidth is quickly distributed fairly between the two flows, remains stable throughout the duration of the test, and recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth fairly, and has trouble remaining stable. CUBIC DCTCP Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2 0 9.93 0 0 9.92 0 0.5 9.87 0 0.5 9.86 0 1 8.73 2.25 1 6.46 4.88 1.5 7.29 2.8 1.5 4.9 4.99 2 6.96 3.1 2 4.92 4.94 2.5 6.67 3.34 2.5 4.93 5 3 6.39 3.57 3 4.92 4.99 3.5 6.24 3.75 3.5 4.94 4.74 4 6 3.94 4 5.34 4.71 4.5 5.88 4.09 4.5 4.99 4.97 5 5.27 4.98 5 4.83 5.01 5.5 4.93 5.04 5.5 4.89 4.99 6 4.9 4.99 6 4.92 5.04 6.5 4.93 5.1 6.5 4.91 4.97 7 4.28 5.8 7 4.97 4.97 7.5 4.62 4.91 7.5 4.99 4.82 8 5.05 4.45 8 5.16 4.76 8.5 5.93 4.09 8.5 4.94 4.98 9 5.73 4.2 9 4.92 5.02 9.5 5.62 4.32 9.5 4.87 5.03 10 6.12 3.2 10 4.91 5.01 10.5 6.91 3.11 10.5 4.87 5.04 11 8.48 0 11 8.49 4.94 11.5 9.87 0 11.5 9.9 0 SYN/ACK ECT test: This test demonstrates the importance of ECT on SYN and SYN-ACK packets by measuring the connection probability in the presence of competing flows for a DCTCP connection attempt *without* ECT in the SYN packet. The test was repeated five times for each number of competing flows. Competing Flows 1 | 2 | 4 | 8 | 16 ------------------------------ Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0 Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0 As the number of competing flows moves beyond 1, the connection probability drops rapidly. Enabling DCTCP with this patch requires the following steps: DCTCP must be running both on the sender and receiver side in your data center, i.e.: sysctl -w net.ipv4.tcp_congestion_control=dctcp Also, ECN functionality must be enabled on all switches in your data center for DCTCP to work. The default ECN marking threshold (K) heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]). In above tests, for each switch port, traffic was segregated into two queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of 0x04 - the packet was placed into the DCTCP queue. All other packets were placed into the default drop-tail queue. For the DCTCP queue, RED/ECN marking was enabled, here, with a marking threshold of 75 KB. More details however, we refer you to the paper [2] under section 3). There are no code changes required to applications running in user space. DCTCP has been implemented in full *isolation* of the rest of the TCP code as its own congestion control module, so that it can run without a need to expose code to the core of the TCP stack, and thus nothing changes for non-DCTCP users. Changes in the CA framework code are minimal, and DCTCP algorithm operates on mechanisms that are already available in most Silicon. The gain (dctcp_shift_g) is currently a fixed constant (1/16) from the paper, but we leave the option that it can be chosen carefully to a different value by the user. In case DCTCP is being used and ECN support on peer site is off, DCTCP falls back after 3WHS to operate in normal TCP Reno mode. ss {-4,-6} -t -i diag interface: ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054 ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584 send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15 reordering:101 rcv_space:29200 ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448 cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate 325.5Mbps rcv_rtt:1.5 rcv_space:29200 More information about DCTCP can be found in [1-4]. [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00 Joint work with Florian Westphal and Glenn Judd. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-27 04:37:36 +08:00
All switches in the data center network running DCTCP must support
ECN marking and be configured for marking when reaching defined switch
buffer thresholds. The default ECN marking threshold heuristic for
DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
(~100KB) at 10Gbps, but might need further careful tweaking.
net: tcp: add DCTCP congestion control algorithm This work adds the DataCenter TCP (DCTCP) congestion control algorithm [1], which has been first published at SIGCOMM 2010 [2], resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more recently as an informational IETF draft available at [4]). DCTCP is an enhancement to the TCP congestion control algorithm for data center networks. Typical data center workloads are i.e. i) partition/aggregate (queries; bursty, delay sensitive), ii) short messages e.g. 50KB-1MB (for coordination and control state; delay sensitive), and iii) large flows e.g. 1MB-100MB (data update; throughput sensitive). DCTCP has therefore been designed for such environments to provide/achieve the following three requirements: * High burst tolerance (incast due to partition/aggregate) * Low latency (short flows, queries) * High throughput (continuous data updates, large file transfers) with commodity, shallow buffered switches The basic idea of its design consists of two fundamentals: i) on the switch side, packets are being marked when its internal queue length > threshold K (K is chosen so that a large enough headroom for marked traffic is still available in the switch queue); ii) the sender/host side maintains a moving average of the fraction of marked packets, so each RTT, F is being updated as follows: F := X / Y, where X is # of marked ACKs, Y is total # of ACKs alpha := (1 - g) * alpha + g * F, where g is a smoothing constant The resulting alpha (iow: probability that switch queue is congested) is then being used in order to adaptively decrease the congestion window W: W := (1 - (alpha / 2)) * W The means for receiving marked packets resp. marking them on switch side in DCTCP is the use of ECN. RFC3168 describes a mechanism for using Explicit Congestion Notification from the switch for early detection of congestion, rather than waiting for segment loss to occur. However, this method only detects the presence of congestion, not the *extent*. In the presence of mild congestion, it reduces the TCP congestion window too aggressively and unnecessarily affects the throughput of long flows [4]. DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN) processing to estimate the fraction of bytes that encounter congestion, rather than simply detecting that some congestion has occurred. DCTCP then scales the TCP congestion window based on this estimate [4], thus it can derive multibit feedback from the information present in the single-bit sequence of marks in its control law. And thus act in *proportion* to the extent of congestion, not its *presence*. Switches therefore set the Congestion Experienced (CE) codepoint in packets when internal queue lengths exceed threshold K. Resulting, DCTCP delivers the same or better throughput than normal TCP, while using 90% less buffer space. It was found in [2] that DCTCP enables the applications to handle 10x the current background traffic, without impacting foreground traffic. Moreover, a 10x increase in foreground traffic did not cause any timeouts, and thus largely eliminates TCP incast collapse problems. The algorithm itself has already seen deployments in large production data centers since then. We did a long-term stress-test and analysis in a data center, short summary of our TCP incast tests with iperf compared to cubic: This test measured DCTCP throughput and latency and compared it with CUBIC throughput and latency for an incast scenario. In this test, 19 senders sent at maximum rate to a single receiver. The receiver simply ran iperf -s. The senders ran iperf -c <receiver> -t 30. All senders started simultaneously (using local clocks synchronized by ntp). This test was repeated multiple times. Below shows the results from a single test. Other tests are similar. (DCTCP results were extremely consistent, CUBIC results show some variance induced by the TCP timeouts that CUBIC encountered.) For this test, we report statistics on the number of TCP timeouts, flow throughput, and traffic latency. 1) Timeouts (total over all flows, and per flow summaries): CUBIC DCTCP Total 3227 25 Mean 169.842 1.316 Median 183 1 Max 207 5 Min 123 0 Stddev 28.991 1.600 Timeout data is taken by measuring the net change in netstat -s "other TCP timeouts" reported. As a result, the timeout measurements above are not restricted to the test traffic, and we believe that it is likely that all of the "DCTCP timeouts" are actually timeouts for non-test traffic. We report them nevertheless. CUBIC will also include some non-test timeouts, but they are drawfed by bona fide test traffic timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing TCP timeouts. DCTCP reduces timeouts by at least two orders of magnitude and may well have eliminated them in this scenario. 2) Throughput (per flow in Mbps): CUBIC DCTCP Mean 521.684 521.895 Median 464 523 Max 776 527 Min 403 519 Stddev 105.891 2.601 Fairness 0.962 0.999 Throughput data was simply the average throughput for each flow reported by iperf. By avoiding TCP timeouts, DCTCP is able to achieve much better per-flow results. In CUBIC, many flows experience TCP timeouts which makes flow throughput unpredictable and unfair. DCTCP, on the other hand, provides very clean predictable throughput without incurring TCP timeouts. Thus, the standard deviation of CUBIC throughput is dramatically higher than the standard deviation of DCTCP throughput. Mean throughput is nearly identical because even though cubic flows suffer TCP timeouts, other flows will step in and fill the unused bandwidth. Note that this test is something of a best case scenario for incast under CUBIC: it allows other flows to fill in for flows experiencing a timeout. Under situations where the receiver is issuing requests and then waiting for all flows to complete, flows cannot fill in for timed out flows and throughput will drop dramatically. 3) Latency (in ms): CUBIC DCTCP Mean 4.0088 0.04219 Median 4.055 0.0395 Max 4.2 0.085 Min 3.32 0.028 Stddev 0.1666 0.01064 Latency for each protocol was computed by running "ping -i 0.2 <receiver>" from a single sender to the receiver during the incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure that traffic traversed the DCTCP queue and was not dropped when the queue size was greater than the marking threshold. The summary statistics above are over all ping metrics measured between the single sender, receiver pair. The latency results for this test show a dramatic difference between CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer which incurs the maximum queue latency (more buffer memory will lead to high latency.) DCTCP, on the other hand, deliberately attempts to keep queue occupancy low. The result is a two orders of magnitude reduction of latency with DCTCP - even with a switch with relatively little RAM. Switches with larger amounts of RAM will incur increasing amounts of latency for CUBIC, but not for DCTCP. 4) Convergence and stability test: This test measured the time that DCTCP took to fairly redistribute bandwidth when a new flow commences. It also measured DCTCP's ability to remain stable at a fair bandwidth distribution. DCTCP is compared with CUBIC for this test. At the commencement of this test, a single flow is sending at maximum rate (near 10 Gbps) to a single receiver. One second after that first flow commences, a new flow from a distinct server begins sending to the same receiver as the first flow. After the second flow has sent data for 10 seconds, the second flow is terminated. The first flow sends for an additional second. Ideally, the bandwidth would be evenly shared as soon as the second flow starts, and recover as soon as it stops. The results of this test are shown below. Note that the flow bandwidth for the two flows was measured near the same time, but not simultaneously. DCTCP performs nearly perfectly within the measurement limitations of this test: bandwidth is quickly distributed fairly between the two flows, remains stable throughout the duration of the test, and recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth fairly, and has trouble remaining stable. CUBIC DCTCP Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2 0 9.93 0 0 9.92 0 0.5 9.87 0 0.5 9.86 0 1 8.73 2.25 1 6.46 4.88 1.5 7.29 2.8 1.5 4.9 4.99 2 6.96 3.1 2 4.92 4.94 2.5 6.67 3.34 2.5 4.93 5 3 6.39 3.57 3 4.92 4.99 3.5 6.24 3.75 3.5 4.94 4.74 4 6 3.94 4 5.34 4.71 4.5 5.88 4.09 4.5 4.99 4.97 5 5.27 4.98 5 4.83 5.01 5.5 4.93 5.04 5.5 4.89 4.99 6 4.9 4.99 6 4.92 5.04 6.5 4.93 5.1 6.5 4.91 4.97 7 4.28 5.8 7 4.97 4.97 7.5 4.62 4.91 7.5 4.99 4.82 8 5.05 4.45 8 5.16 4.76 8.5 5.93 4.09 8.5 4.94 4.98 9 5.73 4.2 9 4.92 5.02 9.5 5.62 4.32 9.5 4.87 5.03 10 6.12 3.2 10 4.91 5.01 10.5 6.91 3.11 10.5 4.87 5.04 11 8.48 0 11 8.49 4.94 11.5 9.87 0 11.5 9.9 0 SYN/ACK ECT test: This test demonstrates the importance of ECT on SYN and SYN-ACK packets by measuring the connection probability in the presence of competing flows for a DCTCP connection attempt *without* ECT in the SYN packet. The test was repeated five times for each number of competing flows. Competing Flows 1 | 2 | 4 | 8 | 16 ------------------------------ Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0 Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0 As the number of competing flows moves beyond 1, the connection probability drops rapidly. Enabling DCTCP with this patch requires the following steps: DCTCP must be running both on the sender and receiver side in your data center, i.e.: sysctl -w net.ipv4.tcp_congestion_control=dctcp Also, ECN functionality must be enabled on all switches in your data center for DCTCP to work. The default ECN marking threshold (K) heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]). In above tests, for each switch port, traffic was segregated into two queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of 0x04 - the packet was placed into the DCTCP queue. All other packets were placed into the default drop-tail queue. For the DCTCP queue, RED/ECN marking was enabled, here, with a marking threshold of 75 KB. More details however, we refer you to the paper [2] under section 3). There are no code changes required to applications running in user space. DCTCP has been implemented in full *isolation* of the rest of the TCP code as its own congestion control module, so that it can run without a need to expose code to the core of the TCP stack, and thus nothing changes for non-DCTCP users. Changes in the CA framework code are minimal, and DCTCP algorithm operates on mechanisms that are already available in most Silicon. The gain (dctcp_shift_g) is currently a fixed constant (1/16) from the paper, but we leave the option that it can be chosen carefully to a different value by the user. In case DCTCP is being used and ECN support on peer site is off, DCTCP falls back after 3WHS to operate in normal TCP Reno mode. ss {-4,-6} -t -i diag interface: ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054 ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584 send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15 reordering:101 rcv_space:29200 ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448 cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate 325.5Mbps rcv_rtt:1.5 rcv_space:29200 More information about DCTCP can be found in [1-4]. [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00 Joint work with Florian Westphal and Glenn Judd. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-27 04:37:36 +08:00
For further details see:
http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
net: tcp: add DCTCP congestion control algorithm This work adds the DataCenter TCP (DCTCP) congestion control algorithm [1], which has been first published at SIGCOMM 2010 [2], resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more recently as an informational IETF draft available at [4]). DCTCP is an enhancement to the TCP congestion control algorithm for data center networks. Typical data center workloads are i.e. i) partition/aggregate (queries; bursty, delay sensitive), ii) short messages e.g. 50KB-1MB (for coordination and control state; delay sensitive), and iii) large flows e.g. 1MB-100MB (data update; throughput sensitive). DCTCP has therefore been designed for such environments to provide/achieve the following three requirements: * High burst tolerance (incast due to partition/aggregate) * Low latency (short flows, queries) * High throughput (continuous data updates, large file transfers) with commodity, shallow buffered switches The basic idea of its design consists of two fundamentals: i) on the switch side, packets are being marked when its internal queue length > threshold K (K is chosen so that a large enough headroom for marked traffic is still available in the switch queue); ii) the sender/host side maintains a moving average of the fraction of marked packets, so each RTT, F is being updated as follows: F := X / Y, where X is # of marked ACKs, Y is total # of ACKs alpha := (1 - g) * alpha + g * F, where g is a smoothing constant The resulting alpha (iow: probability that switch queue is congested) is then being used in order to adaptively decrease the congestion window W: W := (1 - (alpha / 2)) * W The means for receiving marked packets resp. marking them on switch side in DCTCP is the use of ECN. RFC3168 describes a mechanism for using Explicit Congestion Notification from the switch for early detection of congestion, rather than waiting for segment loss to occur. However, this method only detects the presence of congestion, not the *extent*. In the presence of mild congestion, it reduces the TCP congestion window too aggressively and unnecessarily affects the throughput of long flows [4]. DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN) processing to estimate the fraction of bytes that encounter congestion, rather than simply detecting that some congestion has occurred. DCTCP then scales the TCP congestion window based on this estimate [4], thus it can derive multibit feedback from the information present in the single-bit sequence of marks in its control law. And thus act in *proportion* to the extent of congestion, not its *presence*. Switches therefore set the Congestion Experienced (CE) codepoint in packets when internal queue lengths exceed threshold K. Resulting, DCTCP delivers the same or better throughput than normal TCP, while using 90% less buffer space. It was found in [2] that DCTCP enables the applications to handle 10x the current background traffic, without impacting foreground traffic. Moreover, a 10x increase in foreground traffic did not cause any timeouts, and thus largely eliminates TCP incast collapse problems. The algorithm itself has already seen deployments in large production data centers since then. We did a long-term stress-test and analysis in a data center, short summary of our TCP incast tests with iperf compared to cubic: This test measured DCTCP throughput and latency and compared it with CUBIC throughput and latency for an incast scenario. In this test, 19 senders sent at maximum rate to a single receiver. The receiver simply ran iperf -s. The senders ran iperf -c <receiver> -t 30. All senders started simultaneously (using local clocks synchronized by ntp). This test was repeated multiple times. Below shows the results from a single test. Other tests are similar. (DCTCP results were extremely consistent, CUBIC results show some variance induced by the TCP timeouts that CUBIC encountered.) For this test, we report statistics on the number of TCP timeouts, flow throughput, and traffic latency. 1) Timeouts (total over all flows, and per flow summaries): CUBIC DCTCP Total 3227 25 Mean 169.842 1.316 Median 183 1 Max 207 5 Min 123 0 Stddev 28.991 1.600 Timeout data is taken by measuring the net change in netstat -s "other TCP timeouts" reported. As a result, the timeout measurements above are not restricted to the test traffic, and we believe that it is likely that all of the "DCTCP timeouts" are actually timeouts for non-test traffic. We report them nevertheless. CUBIC will also include some non-test timeouts, but they are drawfed by bona fide test traffic timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing TCP timeouts. DCTCP reduces timeouts by at least two orders of magnitude and may well have eliminated them in this scenario. 2) Throughput (per flow in Mbps): CUBIC DCTCP Mean 521.684 521.895 Median 464 523 Max 776 527 Min 403 519 Stddev 105.891 2.601 Fairness 0.962 0.999 Throughput data was simply the average throughput for each flow reported by iperf. By avoiding TCP timeouts, DCTCP is able to achieve much better per-flow results. In CUBIC, many flows experience TCP timeouts which makes flow throughput unpredictable and unfair. DCTCP, on the other hand, provides very clean predictable throughput without incurring TCP timeouts. Thus, the standard deviation of CUBIC throughput is dramatically higher than the standard deviation of DCTCP throughput. Mean throughput is nearly identical because even though cubic flows suffer TCP timeouts, other flows will step in and fill the unused bandwidth. Note that this test is something of a best case scenario for incast under CUBIC: it allows other flows to fill in for flows experiencing a timeout. Under situations where the receiver is issuing requests and then waiting for all flows to complete, flows cannot fill in for timed out flows and throughput will drop dramatically. 3) Latency (in ms): CUBIC DCTCP Mean 4.0088 0.04219 Median 4.055 0.0395 Max 4.2 0.085 Min 3.32 0.028 Stddev 0.1666 0.01064 Latency for each protocol was computed by running "ping -i 0.2 <receiver>" from a single sender to the receiver during the incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure that traffic traversed the DCTCP queue and was not dropped when the queue size was greater than the marking threshold. The summary statistics above are over all ping metrics measured between the single sender, receiver pair. The latency results for this test show a dramatic difference between CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer which incurs the maximum queue latency (more buffer memory will lead to high latency.) DCTCP, on the other hand, deliberately attempts to keep queue occupancy low. The result is a two orders of magnitude reduction of latency with DCTCP - even with a switch with relatively little RAM. Switches with larger amounts of RAM will incur increasing amounts of latency for CUBIC, but not for DCTCP. 4) Convergence and stability test: This test measured the time that DCTCP took to fairly redistribute bandwidth when a new flow commences. It also measured DCTCP's ability to remain stable at a fair bandwidth distribution. DCTCP is compared with CUBIC for this test. At the commencement of this test, a single flow is sending at maximum rate (near 10 Gbps) to a single receiver. One second after that first flow commences, a new flow from a distinct server begins sending to the same receiver as the first flow. After the second flow has sent data for 10 seconds, the second flow is terminated. The first flow sends for an additional second. Ideally, the bandwidth would be evenly shared as soon as the second flow starts, and recover as soon as it stops. The results of this test are shown below. Note that the flow bandwidth for the two flows was measured near the same time, but not simultaneously. DCTCP performs nearly perfectly within the measurement limitations of this test: bandwidth is quickly distributed fairly between the two flows, remains stable throughout the duration of the test, and recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth fairly, and has trouble remaining stable. CUBIC DCTCP Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2 0 9.93 0 0 9.92 0 0.5 9.87 0 0.5 9.86 0 1 8.73 2.25 1 6.46 4.88 1.5 7.29 2.8 1.5 4.9 4.99 2 6.96 3.1 2 4.92 4.94 2.5 6.67 3.34 2.5 4.93 5 3 6.39 3.57 3 4.92 4.99 3.5 6.24 3.75 3.5 4.94 4.74 4 6 3.94 4 5.34 4.71 4.5 5.88 4.09 4.5 4.99 4.97 5 5.27 4.98 5 4.83 5.01 5.5 4.93 5.04 5.5 4.89 4.99 6 4.9 4.99 6 4.92 5.04 6.5 4.93 5.1 6.5 4.91 4.97 7 4.28 5.8 7 4.97 4.97 7.5 4.62 4.91 7.5 4.99 4.82 8 5.05 4.45 8 5.16 4.76 8.5 5.93 4.09 8.5 4.94 4.98 9 5.73 4.2 9 4.92 5.02 9.5 5.62 4.32 9.5 4.87 5.03 10 6.12 3.2 10 4.91 5.01 10.5 6.91 3.11 10.5 4.87 5.04 11 8.48 0 11 8.49 4.94 11.5 9.87 0 11.5 9.9 0 SYN/ACK ECT test: This test demonstrates the importance of ECT on SYN and SYN-ACK packets by measuring the connection probability in the presence of competing flows for a DCTCP connection attempt *without* ECT in the SYN packet. The test was repeated five times for each number of competing flows. Competing Flows 1 | 2 | 4 | 8 | 16 ------------------------------ Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0 Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0 As the number of competing flows moves beyond 1, the connection probability drops rapidly. Enabling DCTCP with this patch requires the following steps: DCTCP must be running both on the sender and receiver side in your data center, i.e.: sysctl -w net.ipv4.tcp_congestion_control=dctcp Also, ECN functionality must be enabled on all switches in your data center for DCTCP to work. The default ECN marking threshold (K) heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]). In above tests, for each switch port, traffic was segregated into two queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of 0x04 - the packet was placed into the DCTCP queue. All other packets were placed into the default drop-tail queue. For the DCTCP queue, RED/ECN marking was enabled, here, with a marking threshold of 75 KB. More details however, we refer you to the paper [2] under section 3). There are no code changes required to applications running in user space. DCTCP has been implemented in full *isolation* of the rest of the TCP code as its own congestion control module, so that it can run without a need to expose code to the core of the TCP stack, and thus nothing changes for non-DCTCP users. Changes in the CA framework code are minimal, and DCTCP algorithm operates on mechanisms that are already available in most Silicon. The gain (dctcp_shift_g) is currently a fixed constant (1/16) from the paper, but we leave the option that it can be chosen carefully to a different value by the user. In case DCTCP is being used and ECN support on peer site is off, DCTCP falls back after 3WHS to operate in normal TCP Reno mode. ss {-4,-6} -t -i diag interface: ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054 ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584 send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15 reordering:101 rcv_space:29200 ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448 cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate 325.5Mbps rcv_rtt:1.5 rcv_space:29200 More information about DCTCP can be found in [1-4]. [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00 Joint work with Florian Westphal and Glenn Judd. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-27 04:37:36 +08:00
tcp: add CDG congestion control CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies the TCP sender in order to [1]: o Use the delay gradient as a congestion signal. o Back off with an average probability that is independent of the RTT. o Coexist with flows that use loss-based congestion control, i.e., flows that are unresponsive to the delay signal. o Tolerate packet loss unrelated to congestion. (Disabled by default.) Its FreeBSD implementation was presented for the ICCRG in July 2012; slides are available at http://www.ietf.org/proceedings/84/iccrg.html Running the experiment scenarios in [1] suggests that our implementation achieves more goodput compared with FreeBSD 10.0 senders, although it also causes more queueing delay for a given backoff factor. The loss tolerance heuristic is disabled by default due to safety concerns for its use in the Internet [2, p. 45-46]. We use a variant of the Hybrid Slow start algorithm in tcp_cubic to reduce the probability of slow start overshoot. [1] D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011, pages 328-341. Springer, 2011. [2] K.K. Jonassen. "Implementing CAIA Delay-Gradient in Linux." MSc thesis. Department of Informatics, University of Oslo, 2015. Cc: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Neal Cardwell <ncardwell@google.com> Cc: David Hayes <davihay@ifi.uio.no> Cc: Andreas Petlund <apetlund@simula.no> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Nicolas Kuhn <nicolas.kuhn@telecom-bretagne.eu> Signed-off-by: Kenneth Klette Jonassen <kennetkl@ifi.uio.no> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 01:08:17 +08:00
config TCP_CONG_CDG
tristate "CAIA Delay-Gradient (CDG)"
default n
---help---
CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies
the TCP sender in order to:
tcp: add CDG congestion control CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies the TCP sender in order to [1]: o Use the delay gradient as a congestion signal. o Back off with an average probability that is independent of the RTT. o Coexist with flows that use loss-based congestion control, i.e., flows that are unresponsive to the delay signal. o Tolerate packet loss unrelated to congestion. (Disabled by default.) Its FreeBSD implementation was presented for the ICCRG in July 2012; slides are available at http://www.ietf.org/proceedings/84/iccrg.html Running the experiment scenarios in [1] suggests that our implementation achieves more goodput compared with FreeBSD 10.0 senders, although it also causes more queueing delay for a given backoff factor. The loss tolerance heuristic is disabled by default due to safety concerns for its use in the Internet [2, p. 45-46]. We use a variant of the Hybrid Slow start algorithm in tcp_cubic to reduce the probability of slow start overshoot. [1] D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011, pages 328-341. Springer, 2011. [2] K.K. Jonassen. "Implementing CAIA Delay-Gradient in Linux." MSc thesis. Department of Informatics, University of Oslo, 2015. Cc: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Neal Cardwell <ncardwell@google.com> Cc: David Hayes <davihay@ifi.uio.no> Cc: Andreas Petlund <apetlund@simula.no> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Nicolas Kuhn <nicolas.kuhn@telecom-bretagne.eu> Signed-off-by: Kenneth Klette Jonassen <kennetkl@ifi.uio.no> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 01:08:17 +08:00
o Use the delay gradient as a congestion signal.
o Back off with an average probability that is independent of the RTT.
o Coexist with flows that use loss-based congestion control.
o Tolerate packet loss unrelated to congestion.
For further details see:
D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
tcp: add CDG congestion control CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies the TCP sender in order to [1]: o Use the delay gradient as a congestion signal. o Back off with an average probability that is independent of the RTT. o Coexist with flows that use loss-based congestion control, i.e., flows that are unresponsive to the delay signal. o Tolerate packet loss unrelated to congestion. (Disabled by default.) Its FreeBSD implementation was presented for the ICCRG in July 2012; slides are available at http://www.ietf.org/proceedings/84/iccrg.html Running the experiment scenarios in [1] suggests that our implementation achieves more goodput compared with FreeBSD 10.0 senders, although it also causes more queueing delay for a given backoff factor. The loss tolerance heuristic is disabled by default due to safety concerns for its use in the Internet [2, p. 45-46]. We use a variant of the Hybrid Slow start algorithm in tcp_cubic to reduce the probability of slow start overshoot. [1] D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011, pages 328-341. Springer, 2011. [2] K.K. Jonassen. "Implementing CAIA Delay-Gradient in Linux." MSc thesis. Department of Informatics, University of Oslo, 2015. Cc: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Neal Cardwell <ncardwell@google.com> Cc: David Hayes <davihay@ifi.uio.no> Cc: Andreas Petlund <apetlund@simula.no> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Nicolas Kuhn <nicolas.kuhn@telecom-bretagne.eu> Signed-off-by: Kenneth Klette Jonassen <kennetkl@ifi.uio.no> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 01:08:17 +08:00
tcp_bbr: add BBR congestion control This commit implements a new TCP congestion control algorithm: BBR (Bottleneck Bandwidth and RTT). A detailed description of BBR will be published in ACM Queue, Vol. 14 No. 5, September-October 2016, as "BBR: Congestion-Based Congestion Control". BBR has significantly increased throughput and reduced latency for connections on Google's internal backbone networks and google.com and YouTube Web servers. BBR requires only changes on the sender side, not in the network or the receiver side. Thus it can be incrementally deployed on today's Internet, or in datacenters. The Internet has predominantly used loss-based congestion control (largely Reno or CUBIC) since the 1980s, relying on packet loss as the signal to slow down. While this worked well for many years, loss-based congestion control is unfortunately out-dated in today's networks. On today's Internet, loss-based congestion control causes the infamous bufferbloat problem, often causing seconds of needless queuing delay, since it fills the bloated buffers in many last-mile links. On today's high-speed long-haul links using commodity switches with shallow buffers, loss-based congestion control has abysmal throughput because it over-reacts to losses caused by transient traffic bursts. In 1981 Kleinrock and Gale showed that the optimal operating point for a network maximizes delivered bandwidth while minimizing delay and loss, not only for single connections but for the network as a whole. Finding that optimal operating point has been elusive, since any single network measurement is ambiguous: network measurements are the result of both bandwidth and propagation delay, and those two cannot be measured simultaneously. While it is impossible to disambiguate any single bandwidth or RTT measurement, a connection's behavior over time tells a clearer story. BBR uses a measurement strategy designed to resolve this ambiguity. It combines these measurements with a robust servo loop using recent control systems advances to implement a distributed congestion control algorithm that reacts to actual congestion, not packet loss or transient queue delay, and is designed to converge with high probability to a point near the optimal operating point. In a nutshell, BBR creates an explicit model of the network pipe by sequentially probing the bottleneck bandwidth and RTT. On the arrival of each ACK, BBR derives the current delivery rate of the last round trip, and feeds it through a windowed max-filter to estimate the bottleneck bandwidth. Conversely it uses a windowed min-filter to estimate the round trip propagation delay. The max-filtered bandwidth and min-filtered RTT estimates form BBR's model of the network pipe. Using its model, BBR sets control parameters to govern sending behavior. The primary control is the pacing rate: BBR applies a gain multiplier to transmit faster or slower than the observed bottleneck bandwidth. The conventional congestion window (cwnd) is now the secondary control; the cwnd is set to a small multiple of the estimated BDP (bandwidth-delay product) in order to allow full utilization and bandwidth probing while bounding the potential amount of queue at the bottleneck. When a BBR connection starts, it enters STARTUP mode and applies a high gain to perform an exponential search to quickly probe the bottleneck bandwidth (doubling its sending rate each round trip, like slow start). However, instead of continuing until it fills up the buffer (i.e. a loss), or until delay or ACK spacing reaches some threshold (like Hystart), it uses its model of the pipe to estimate when that pipe is full: it estimates the pipe is full when it notices the estimated bandwidth has stopped growing. At that point it exits STARTUP and enters DRAIN mode, where it reduces its pacing rate to drain the queue it estimates it has created. Then BBR enters steady state. In steady state, PROBE_BW mode cycles between first pacing faster to probe for more bandwidth, then pacing slower to drain any queue that created if no more bandwidth was available, and then cruising at the estimated bandwidth to utilize the pipe without creating excess queue. Occasionally, on an as-needed basis, it sends significantly slower to probe for RTT (PROBE_RTT mode). BBR has been fully deployed on Google's wide-area backbone networks and we're experimenting with BBR on Google.com and YouTube on a global scale. Replacing CUBIC with BBR has resulted in significant improvements in network latency and application (RPC, browser, and video) metrics. For more details please refer to our upcoming ACM Queue publication. Example performance results, to illustrate the difference between BBR and CUBIC: Resilience to random loss (e.g. from shallow buffers): Consider a netperf TCP_STREAM test lasting 30 secs on an emulated path with a 10Gbps bottleneck, 100ms RTT, and 1% packet loss rate. CUBIC gets 3.27 Mbps, and BBR gets 9150 Mbps (2798x higher). Low latency with the bloated buffers common in today's last-mile links: Consider a netperf TCP_STREAM test lasting 120 secs on an emulated path with a 10Mbps bottleneck, 40ms RTT, and 1000-packet bottleneck buffer. Both fully utilize the bottleneck bandwidth, but BBR achieves this with a median RTT 25x lower (43 ms instead of 1.09 secs). Our long-term goal is to improve the congestion control algorithms used on the Internet. We are hopeful that BBR can help advance the efforts toward this goal, and motivate the community to do further research. Test results, performance evaluations, feedback, and BBR-related discussions are very welcome in the public e-mail list for BBR: https://groups.google.com/forum/#!forum/bbr-dev NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, since pacing is integral to the BBR design and implementation. BBR without pacing would not function properly, and may incur unnecessary high packet loss rates. Signed-off-by: Van Jacobson <vanj@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Nandita Dukkipati <nanditad@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-20 11:39:23 +08:00
config TCP_CONG_BBR
tristate "BBR TCP"
default n
---help---
BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to
maximize network utilization and minimize queues. It builds an explicit
model of the the bottleneck delivery rate and path round-trip
propagation delay. It tolerates packet loss and delay unrelated to
congestion. It can operate over LAN, WAN, cellular, wifi, or cable
modem links. It can coexist with flows that use loss-based congestion
control, and can operate with shallow buffers, deep buffers,
bufferbloat, policers, or AQM schemes that do not provide a delay
signal. It requires the fq ("Fair Queue") pacing packet scheduler.
tcp_bbr: add BBR congestion control This commit implements a new TCP congestion control algorithm: BBR (Bottleneck Bandwidth and RTT). A detailed description of BBR will be published in ACM Queue, Vol. 14 No. 5, September-October 2016, as "BBR: Congestion-Based Congestion Control". BBR has significantly increased throughput and reduced latency for connections on Google's internal backbone networks and google.com and YouTube Web servers. BBR requires only changes on the sender side, not in the network or the receiver side. Thus it can be incrementally deployed on today's Internet, or in datacenters. The Internet has predominantly used loss-based congestion control (largely Reno or CUBIC) since the 1980s, relying on packet loss as the signal to slow down. While this worked well for many years, loss-based congestion control is unfortunately out-dated in today's networks. On today's Internet, loss-based congestion control causes the infamous bufferbloat problem, often causing seconds of needless queuing delay, since it fills the bloated buffers in many last-mile links. On today's high-speed long-haul links using commodity switches with shallow buffers, loss-based congestion control has abysmal throughput because it over-reacts to losses caused by transient traffic bursts. In 1981 Kleinrock and Gale showed that the optimal operating point for a network maximizes delivered bandwidth while minimizing delay and loss, not only for single connections but for the network as a whole. Finding that optimal operating point has been elusive, since any single network measurement is ambiguous: network measurements are the result of both bandwidth and propagation delay, and those two cannot be measured simultaneously. While it is impossible to disambiguate any single bandwidth or RTT measurement, a connection's behavior over time tells a clearer story. BBR uses a measurement strategy designed to resolve this ambiguity. It combines these measurements with a robust servo loop using recent control systems advances to implement a distributed congestion control algorithm that reacts to actual congestion, not packet loss or transient queue delay, and is designed to converge with high probability to a point near the optimal operating point. In a nutshell, BBR creates an explicit model of the network pipe by sequentially probing the bottleneck bandwidth and RTT. On the arrival of each ACK, BBR derives the current delivery rate of the last round trip, and feeds it through a windowed max-filter to estimate the bottleneck bandwidth. Conversely it uses a windowed min-filter to estimate the round trip propagation delay. The max-filtered bandwidth and min-filtered RTT estimates form BBR's model of the network pipe. Using its model, BBR sets control parameters to govern sending behavior. The primary control is the pacing rate: BBR applies a gain multiplier to transmit faster or slower than the observed bottleneck bandwidth. The conventional congestion window (cwnd) is now the secondary control; the cwnd is set to a small multiple of the estimated BDP (bandwidth-delay product) in order to allow full utilization and bandwidth probing while bounding the potential amount of queue at the bottleneck. When a BBR connection starts, it enters STARTUP mode and applies a high gain to perform an exponential search to quickly probe the bottleneck bandwidth (doubling its sending rate each round trip, like slow start). However, instead of continuing until it fills up the buffer (i.e. a loss), or until delay or ACK spacing reaches some threshold (like Hystart), it uses its model of the pipe to estimate when that pipe is full: it estimates the pipe is full when it notices the estimated bandwidth has stopped growing. At that point it exits STARTUP and enters DRAIN mode, where it reduces its pacing rate to drain the queue it estimates it has created. Then BBR enters steady state. In steady state, PROBE_BW mode cycles between first pacing faster to probe for more bandwidth, then pacing slower to drain any queue that created if no more bandwidth was available, and then cruising at the estimated bandwidth to utilize the pipe without creating excess queue. Occasionally, on an as-needed basis, it sends significantly slower to probe for RTT (PROBE_RTT mode). BBR has been fully deployed on Google's wide-area backbone networks and we're experimenting with BBR on Google.com and YouTube on a global scale. Replacing CUBIC with BBR has resulted in significant improvements in network latency and application (RPC, browser, and video) metrics. For more details please refer to our upcoming ACM Queue publication. Example performance results, to illustrate the difference between BBR and CUBIC: Resilience to random loss (e.g. from shallow buffers): Consider a netperf TCP_STREAM test lasting 30 secs on an emulated path with a 10Gbps bottleneck, 100ms RTT, and 1% packet loss rate. CUBIC gets 3.27 Mbps, and BBR gets 9150 Mbps (2798x higher). Low latency with the bloated buffers common in today's last-mile links: Consider a netperf TCP_STREAM test lasting 120 secs on an emulated path with a 10Mbps bottleneck, 40ms RTT, and 1000-packet bottleneck buffer. Both fully utilize the bottleneck bandwidth, but BBR achieves this with a median RTT 25x lower (43 ms instead of 1.09 secs). Our long-term goal is to improve the congestion control algorithms used on the Internet. We are hopeful that BBR can help advance the efforts toward this goal, and motivate the community to do further research. Test results, performance evaluations, feedback, and BBR-related discussions are very welcome in the public e-mail list for BBR: https://groups.google.com/forum/#!forum/bbr-dev NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, since pacing is integral to the BBR design and implementation. BBR without pacing would not function properly, and may incur unnecessary high packet loss rates. Signed-off-by: Van Jacobson <vanj@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Nandita Dukkipati <nanditad@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-20 11:39:23 +08:00
choice
prompt "Default TCP congestion control"
default DEFAULT_CUBIC
help
Select the TCP congestion control that will be used by default
for all connections.
config DEFAULT_BIC
bool "Bic" if TCP_CONG_BIC=y
config DEFAULT_CUBIC
bool "Cubic" if TCP_CONG_CUBIC=y
config DEFAULT_HTCP
bool "Htcp" if TCP_CONG_HTCP=y
config DEFAULT_HYBLA
bool "Hybla" if TCP_CONG_HYBLA=y
config DEFAULT_VEGAS
bool "Vegas" if TCP_CONG_VEGAS=y
config DEFAULT_VENO
bool "Veno" if TCP_CONG_VENO=y
config DEFAULT_WESTWOOD
bool "Westwood" if TCP_CONG_WESTWOOD=y
net: tcp: add DCTCP congestion control algorithm This work adds the DataCenter TCP (DCTCP) congestion control algorithm [1], which has been first published at SIGCOMM 2010 [2], resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more recently as an informational IETF draft available at [4]). DCTCP is an enhancement to the TCP congestion control algorithm for data center networks. Typical data center workloads are i.e. i) partition/aggregate (queries; bursty, delay sensitive), ii) short messages e.g. 50KB-1MB (for coordination and control state; delay sensitive), and iii) large flows e.g. 1MB-100MB (data update; throughput sensitive). DCTCP has therefore been designed for such environments to provide/achieve the following three requirements: * High burst tolerance (incast due to partition/aggregate) * Low latency (short flows, queries) * High throughput (continuous data updates, large file transfers) with commodity, shallow buffered switches The basic idea of its design consists of two fundamentals: i) on the switch side, packets are being marked when its internal queue length > threshold K (K is chosen so that a large enough headroom for marked traffic is still available in the switch queue); ii) the sender/host side maintains a moving average of the fraction of marked packets, so each RTT, F is being updated as follows: F := X / Y, where X is # of marked ACKs, Y is total # of ACKs alpha := (1 - g) * alpha + g * F, where g is a smoothing constant The resulting alpha (iow: probability that switch queue is congested) is then being used in order to adaptively decrease the congestion window W: W := (1 - (alpha / 2)) * W The means for receiving marked packets resp. marking them on switch side in DCTCP is the use of ECN. RFC3168 describes a mechanism for using Explicit Congestion Notification from the switch for early detection of congestion, rather than waiting for segment loss to occur. However, this method only detects the presence of congestion, not the *extent*. In the presence of mild congestion, it reduces the TCP congestion window too aggressively and unnecessarily affects the throughput of long flows [4]. DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN) processing to estimate the fraction of bytes that encounter congestion, rather than simply detecting that some congestion has occurred. DCTCP then scales the TCP congestion window based on this estimate [4], thus it can derive multibit feedback from the information present in the single-bit sequence of marks in its control law. And thus act in *proportion* to the extent of congestion, not its *presence*. Switches therefore set the Congestion Experienced (CE) codepoint in packets when internal queue lengths exceed threshold K. Resulting, DCTCP delivers the same or better throughput than normal TCP, while using 90% less buffer space. It was found in [2] that DCTCP enables the applications to handle 10x the current background traffic, without impacting foreground traffic. Moreover, a 10x increase in foreground traffic did not cause any timeouts, and thus largely eliminates TCP incast collapse problems. The algorithm itself has already seen deployments in large production data centers since then. We did a long-term stress-test and analysis in a data center, short summary of our TCP incast tests with iperf compared to cubic: This test measured DCTCP throughput and latency and compared it with CUBIC throughput and latency for an incast scenario. In this test, 19 senders sent at maximum rate to a single receiver. The receiver simply ran iperf -s. The senders ran iperf -c <receiver> -t 30. All senders started simultaneously (using local clocks synchronized by ntp). This test was repeated multiple times. Below shows the results from a single test. Other tests are similar. (DCTCP results were extremely consistent, CUBIC results show some variance induced by the TCP timeouts that CUBIC encountered.) For this test, we report statistics on the number of TCP timeouts, flow throughput, and traffic latency. 1) Timeouts (total over all flows, and per flow summaries): CUBIC DCTCP Total 3227 25 Mean 169.842 1.316 Median 183 1 Max 207 5 Min 123 0 Stddev 28.991 1.600 Timeout data is taken by measuring the net change in netstat -s "other TCP timeouts" reported. As a result, the timeout measurements above are not restricted to the test traffic, and we believe that it is likely that all of the "DCTCP timeouts" are actually timeouts for non-test traffic. We report them nevertheless. CUBIC will also include some non-test timeouts, but they are drawfed by bona fide test traffic timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing TCP timeouts. DCTCP reduces timeouts by at least two orders of magnitude and may well have eliminated them in this scenario. 2) Throughput (per flow in Mbps): CUBIC DCTCP Mean 521.684 521.895 Median 464 523 Max 776 527 Min 403 519 Stddev 105.891 2.601 Fairness 0.962 0.999 Throughput data was simply the average throughput for each flow reported by iperf. By avoiding TCP timeouts, DCTCP is able to achieve much better per-flow results. In CUBIC, many flows experience TCP timeouts which makes flow throughput unpredictable and unfair. DCTCP, on the other hand, provides very clean predictable throughput without incurring TCP timeouts. Thus, the standard deviation of CUBIC throughput is dramatically higher than the standard deviation of DCTCP throughput. Mean throughput is nearly identical because even though cubic flows suffer TCP timeouts, other flows will step in and fill the unused bandwidth. Note that this test is something of a best case scenario for incast under CUBIC: it allows other flows to fill in for flows experiencing a timeout. Under situations where the receiver is issuing requests and then waiting for all flows to complete, flows cannot fill in for timed out flows and throughput will drop dramatically. 3) Latency (in ms): CUBIC DCTCP Mean 4.0088 0.04219 Median 4.055 0.0395 Max 4.2 0.085 Min 3.32 0.028 Stddev 0.1666 0.01064 Latency for each protocol was computed by running "ping -i 0.2 <receiver>" from a single sender to the receiver during the incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure that traffic traversed the DCTCP queue and was not dropped when the queue size was greater than the marking threshold. The summary statistics above are over all ping metrics measured between the single sender, receiver pair. The latency results for this test show a dramatic difference between CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer which incurs the maximum queue latency (more buffer memory will lead to high latency.) DCTCP, on the other hand, deliberately attempts to keep queue occupancy low. The result is a two orders of magnitude reduction of latency with DCTCP - even with a switch with relatively little RAM. Switches with larger amounts of RAM will incur increasing amounts of latency for CUBIC, but not for DCTCP. 4) Convergence and stability test: This test measured the time that DCTCP took to fairly redistribute bandwidth when a new flow commences. It also measured DCTCP's ability to remain stable at a fair bandwidth distribution. DCTCP is compared with CUBIC for this test. At the commencement of this test, a single flow is sending at maximum rate (near 10 Gbps) to a single receiver. One second after that first flow commences, a new flow from a distinct server begins sending to the same receiver as the first flow. After the second flow has sent data for 10 seconds, the second flow is terminated. The first flow sends for an additional second. Ideally, the bandwidth would be evenly shared as soon as the second flow starts, and recover as soon as it stops. The results of this test are shown below. Note that the flow bandwidth for the two flows was measured near the same time, but not simultaneously. DCTCP performs nearly perfectly within the measurement limitations of this test: bandwidth is quickly distributed fairly between the two flows, remains stable throughout the duration of the test, and recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth fairly, and has trouble remaining stable. CUBIC DCTCP Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2 0 9.93 0 0 9.92 0 0.5 9.87 0 0.5 9.86 0 1 8.73 2.25 1 6.46 4.88 1.5 7.29 2.8 1.5 4.9 4.99 2 6.96 3.1 2 4.92 4.94 2.5 6.67 3.34 2.5 4.93 5 3 6.39 3.57 3 4.92 4.99 3.5 6.24 3.75 3.5 4.94 4.74 4 6 3.94 4 5.34 4.71 4.5 5.88 4.09 4.5 4.99 4.97 5 5.27 4.98 5 4.83 5.01 5.5 4.93 5.04 5.5 4.89 4.99 6 4.9 4.99 6 4.92 5.04 6.5 4.93 5.1 6.5 4.91 4.97 7 4.28 5.8 7 4.97 4.97 7.5 4.62 4.91 7.5 4.99 4.82 8 5.05 4.45 8 5.16 4.76 8.5 5.93 4.09 8.5 4.94 4.98 9 5.73 4.2 9 4.92 5.02 9.5 5.62 4.32 9.5 4.87 5.03 10 6.12 3.2 10 4.91 5.01 10.5 6.91 3.11 10.5 4.87 5.04 11 8.48 0 11 8.49 4.94 11.5 9.87 0 11.5 9.9 0 SYN/ACK ECT test: This test demonstrates the importance of ECT on SYN and SYN-ACK packets by measuring the connection probability in the presence of competing flows for a DCTCP connection attempt *without* ECT in the SYN packet. The test was repeated five times for each number of competing flows. Competing Flows 1 | 2 | 4 | 8 | 16 ------------------------------ Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0 Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0 As the number of competing flows moves beyond 1, the connection probability drops rapidly. Enabling DCTCP with this patch requires the following steps: DCTCP must be running both on the sender and receiver side in your data center, i.e.: sysctl -w net.ipv4.tcp_congestion_control=dctcp Also, ECN functionality must be enabled on all switches in your data center for DCTCP to work. The default ECN marking threshold (K) heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]). In above tests, for each switch port, traffic was segregated into two queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of 0x04 - the packet was placed into the DCTCP queue. All other packets were placed into the default drop-tail queue. For the DCTCP queue, RED/ECN marking was enabled, here, with a marking threshold of 75 KB. More details however, we refer you to the paper [2] under section 3). There are no code changes required to applications running in user space. DCTCP has been implemented in full *isolation* of the rest of the TCP code as its own congestion control module, so that it can run without a need to expose code to the core of the TCP stack, and thus nothing changes for non-DCTCP users. Changes in the CA framework code are minimal, and DCTCP algorithm operates on mechanisms that are already available in most Silicon. The gain (dctcp_shift_g) is currently a fixed constant (1/16) from the paper, but we leave the option that it can be chosen carefully to a different value by the user. In case DCTCP is being used and ECN support on peer site is off, DCTCP falls back after 3WHS to operate in normal TCP Reno mode. ss {-4,-6} -t -i diag interface: ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054 ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584 send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15 reordering:101 rcv_space:29200 ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448 cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate 325.5Mbps rcv_rtt:1.5 rcv_space:29200 More information about DCTCP can be found in [1-4]. [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00 Joint work with Florian Westphal and Glenn Judd. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-27 04:37:36 +08:00
config DEFAULT_DCTCP
bool "DCTCP" if TCP_CONG_DCTCP=y
tcp: add CDG congestion control CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies the TCP sender in order to [1]: o Use the delay gradient as a congestion signal. o Back off with an average probability that is independent of the RTT. o Coexist with flows that use loss-based congestion control, i.e., flows that are unresponsive to the delay signal. o Tolerate packet loss unrelated to congestion. (Disabled by default.) Its FreeBSD implementation was presented for the ICCRG in July 2012; slides are available at http://www.ietf.org/proceedings/84/iccrg.html Running the experiment scenarios in [1] suggests that our implementation achieves more goodput compared with FreeBSD 10.0 senders, although it also causes more queueing delay for a given backoff factor. The loss tolerance heuristic is disabled by default due to safety concerns for its use in the Internet [2, p. 45-46]. We use a variant of the Hybrid Slow start algorithm in tcp_cubic to reduce the probability of slow start overshoot. [1] D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011, pages 328-341. Springer, 2011. [2] K.K. Jonassen. "Implementing CAIA Delay-Gradient in Linux." MSc thesis. Department of Informatics, University of Oslo, 2015. Cc: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Neal Cardwell <ncardwell@google.com> Cc: David Hayes <davihay@ifi.uio.no> Cc: Andreas Petlund <apetlund@simula.no> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Nicolas Kuhn <nicolas.kuhn@telecom-bretagne.eu> Signed-off-by: Kenneth Klette Jonassen <kennetkl@ifi.uio.no> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 01:08:17 +08:00
config DEFAULT_CDG
bool "CDG" if TCP_CONG_CDG=y
tcp_bbr: add BBR congestion control This commit implements a new TCP congestion control algorithm: BBR (Bottleneck Bandwidth and RTT). A detailed description of BBR will be published in ACM Queue, Vol. 14 No. 5, September-October 2016, as "BBR: Congestion-Based Congestion Control". BBR has significantly increased throughput and reduced latency for connections on Google's internal backbone networks and google.com and YouTube Web servers. BBR requires only changes on the sender side, not in the network or the receiver side. Thus it can be incrementally deployed on today's Internet, or in datacenters. The Internet has predominantly used loss-based congestion control (largely Reno or CUBIC) since the 1980s, relying on packet loss as the signal to slow down. While this worked well for many years, loss-based congestion control is unfortunately out-dated in today's networks. On today's Internet, loss-based congestion control causes the infamous bufferbloat problem, often causing seconds of needless queuing delay, since it fills the bloated buffers in many last-mile links. On today's high-speed long-haul links using commodity switches with shallow buffers, loss-based congestion control has abysmal throughput because it over-reacts to losses caused by transient traffic bursts. In 1981 Kleinrock and Gale showed that the optimal operating point for a network maximizes delivered bandwidth while minimizing delay and loss, not only for single connections but for the network as a whole. Finding that optimal operating point has been elusive, since any single network measurement is ambiguous: network measurements are the result of both bandwidth and propagation delay, and those two cannot be measured simultaneously. While it is impossible to disambiguate any single bandwidth or RTT measurement, a connection's behavior over time tells a clearer story. BBR uses a measurement strategy designed to resolve this ambiguity. It combines these measurements with a robust servo loop using recent control systems advances to implement a distributed congestion control algorithm that reacts to actual congestion, not packet loss or transient queue delay, and is designed to converge with high probability to a point near the optimal operating point. In a nutshell, BBR creates an explicit model of the network pipe by sequentially probing the bottleneck bandwidth and RTT. On the arrival of each ACK, BBR derives the current delivery rate of the last round trip, and feeds it through a windowed max-filter to estimate the bottleneck bandwidth. Conversely it uses a windowed min-filter to estimate the round trip propagation delay. The max-filtered bandwidth and min-filtered RTT estimates form BBR's model of the network pipe. Using its model, BBR sets control parameters to govern sending behavior. The primary control is the pacing rate: BBR applies a gain multiplier to transmit faster or slower than the observed bottleneck bandwidth. The conventional congestion window (cwnd) is now the secondary control; the cwnd is set to a small multiple of the estimated BDP (bandwidth-delay product) in order to allow full utilization and bandwidth probing while bounding the potential amount of queue at the bottleneck. When a BBR connection starts, it enters STARTUP mode and applies a high gain to perform an exponential search to quickly probe the bottleneck bandwidth (doubling its sending rate each round trip, like slow start). However, instead of continuing until it fills up the buffer (i.e. a loss), or until delay or ACK spacing reaches some threshold (like Hystart), it uses its model of the pipe to estimate when that pipe is full: it estimates the pipe is full when it notices the estimated bandwidth has stopped growing. At that point it exits STARTUP and enters DRAIN mode, where it reduces its pacing rate to drain the queue it estimates it has created. Then BBR enters steady state. In steady state, PROBE_BW mode cycles between first pacing faster to probe for more bandwidth, then pacing slower to drain any queue that created if no more bandwidth was available, and then cruising at the estimated bandwidth to utilize the pipe without creating excess queue. Occasionally, on an as-needed basis, it sends significantly slower to probe for RTT (PROBE_RTT mode). BBR has been fully deployed on Google's wide-area backbone networks and we're experimenting with BBR on Google.com and YouTube on a global scale. Replacing CUBIC with BBR has resulted in significant improvements in network latency and application (RPC, browser, and video) metrics. For more details please refer to our upcoming ACM Queue publication. Example performance results, to illustrate the difference between BBR and CUBIC: Resilience to random loss (e.g. from shallow buffers): Consider a netperf TCP_STREAM test lasting 30 secs on an emulated path with a 10Gbps bottleneck, 100ms RTT, and 1% packet loss rate. CUBIC gets 3.27 Mbps, and BBR gets 9150 Mbps (2798x higher). Low latency with the bloated buffers common in today's last-mile links: Consider a netperf TCP_STREAM test lasting 120 secs on an emulated path with a 10Mbps bottleneck, 40ms RTT, and 1000-packet bottleneck buffer. Both fully utilize the bottleneck bandwidth, but BBR achieves this with a median RTT 25x lower (43 ms instead of 1.09 secs). Our long-term goal is to improve the congestion control algorithms used on the Internet. We are hopeful that BBR can help advance the efforts toward this goal, and motivate the community to do further research. Test results, performance evaluations, feedback, and BBR-related discussions are very welcome in the public e-mail list for BBR: https://groups.google.com/forum/#!forum/bbr-dev NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, since pacing is integral to the BBR design and implementation. BBR without pacing would not function properly, and may incur unnecessary high packet loss rates. Signed-off-by: Van Jacobson <vanj@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Nandita Dukkipati <nanditad@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-20 11:39:23 +08:00
config DEFAULT_BBR
bool "BBR" if TCP_CONG_BBR=y
config DEFAULT_RENO
bool "Reno"
endchoice
endif
config TCP_CONG_CUBIC
tristate
depends on !TCP_CONG_ADVANCED
default y
config DEFAULT_TCP_CONG
string
default "bic" if DEFAULT_BIC
default "cubic" if DEFAULT_CUBIC
default "htcp" if DEFAULT_HTCP
default "hybla" if DEFAULT_HYBLA
default "vegas" if DEFAULT_VEGAS
default "westwood" if DEFAULT_WESTWOOD
default "veno" if DEFAULT_VENO
default "reno" if DEFAULT_RENO
net: tcp: add DCTCP congestion control algorithm This work adds the DataCenter TCP (DCTCP) congestion control algorithm [1], which has been first published at SIGCOMM 2010 [2], resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more recently as an informational IETF draft available at [4]). DCTCP is an enhancement to the TCP congestion control algorithm for data center networks. Typical data center workloads are i.e. i) partition/aggregate (queries; bursty, delay sensitive), ii) short messages e.g. 50KB-1MB (for coordination and control state; delay sensitive), and iii) large flows e.g. 1MB-100MB (data update; throughput sensitive). DCTCP has therefore been designed for such environments to provide/achieve the following three requirements: * High burst tolerance (incast due to partition/aggregate) * Low latency (short flows, queries) * High throughput (continuous data updates, large file transfers) with commodity, shallow buffered switches The basic idea of its design consists of two fundamentals: i) on the switch side, packets are being marked when its internal queue length > threshold K (K is chosen so that a large enough headroom for marked traffic is still available in the switch queue); ii) the sender/host side maintains a moving average of the fraction of marked packets, so each RTT, F is being updated as follows: F := X / Y, where X is # of marked ACKs, Y is total # of ACKs alpha := (1 - g) * alpha + g * F, where g is a smoothing constant The resulting alpha (iow: probability that switch queue is congested) is then being used in order to adaptively decrease the congestion window W: W := (1 - (alpha / 2)) * W The means for receiving marked packets resp. marking them on switch side in DCTCP is the use of ECN. RFC3168 describes a mechanism for using Explicit Congestion Notification from the switch for early detection of congestion, rather than waiting for segment loss to occur. However, this method only detects the presence of congestion, not the *extent*. In the presence of mild congestion, it reduces the TCP congestion window too aggressively and unnecessarily affects the throughput of long flows [4]. DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN) processing to estimate the fraction of bytes that encounter congestion, rather than simply detecting that some congestion has occurred. DCTCP then scales the TCP congestion window based on this estimate [4], thus it can derive multibit feedback from the information present in the single-bit sequence of marks in its control law. And thus act in *proportion* to the extent of congestion, not its *presence*. Switches therefore set the Congestion Experienced (CE) codepoint in packets when internal queue lengths exceed threshold K. Resulting, DCTCP delivers the same or better throughput than normal TCP, while using 90% less buffer space. It was found in [2] that DCTCP enables the applications to handle 10x the current background traffic, without impacting foreground traffic. Moreover, a 10x increase in foreground traffic did not cause any timeouts, and thus largely eliminates TCP incast collapse problems. The algorithm itself has already seen deployments in large production data centers since then. We did a long-term stress-test and analysis in a data center, short summary of our TCP incast tests with iperf compared to cubic: This test measured DCTCP throughput and latency and compared it with CUBIC throughput and latency for an incast scenario. In this test, 19 senders sent at maximum rate to a single receiver. The receiver simply ran iperf -s. The senders ran iperf -c <receiver> -t 30. All senders started simultaneously (using local clocks synchronized by ntp). This test was repeated multiple times. Below shows the results from a single test. Other tests are similar. (DCTCP results were extremely consistent, CUBIC results show some variance induced by the TCP timeouts that CUBIC encountered.) For this test, we report statistics on the number of TCP timeouts, flow throughput, and traffic latency. 1) Timeouts (total over all flows, and per flow summaries): CUBIC DCTCP Total 3227 25 Mean 169.842 1.316 Median 183 1 Max 207 5 Min 123 0 Stddev 28.991 1.600 Timeout data is taken by measuring the net change in netstat -s "other TCP timeouts" reported. As a result, the timeout measurements above are not restricted to the test traffic, and we believe that it is likely that all of the "DCTCP timeouts" are actually timeouts for non-test traffic. We report them nevertheless. CUBIC will also include some non-test timeouts, but they are drawfed by bona fide test traffic timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing TCP timeouts. DCTCP reduces timeouts by at least two orders of magnitude and may well have eliminated them in this scenario. 2) Throughput (per flow in Mbps): CUBIC DCTCP Mean 521.684 521.895 Median 464 523 Max 776 527 Min 403 519 Stddev 105.891 2.601 Fairness 0.962 0.999 Throughput data was simply the average throughput for each flow reported by iperf. By avoiding TCP timeouts, DCTCP is able to achieve much better per-flow results. In CUBIC, many flows experience TCP timeouts which makes flow throughput unpredictable and unfair. DCTCP, on the other hand, provides very clean predictable throughput without incurring TCP timeouts. Thus, the standard deviation of CUBIC throughput is dramatically higher than the standard deviation of DCTCP throughput. Mean throughput is nearly identical because even though cubic flows suffer TCP timeouts, other flows will step in and fill the unused bandwidth. Note that this test is something of a best case scenario for incast under CUBIC: it allows other flows to fill in for flows experiencing a timeout. Under situations where the receiver is issuing requests and then waiting for all flows to complete, flows cannot fill in for timed out flows and throughput will drop dramatically. 3) Latency (in ms): CUBIC DCTCP Mean 4.0088 0.04219 Median 4.055 0.0395 Max 4.2 0.085 Min 3.32 0.028 Stddev 0.1666 0.01064 Latency for each protocol was computed by running "ping -i 0.2 <receiver>" from a single sender to the receiver during the incast test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure that traffic traversed the DCTCP queue and was not dropped when the queue size was greater than the marking threshold. The summary statistics above are over all ping metrics measured between the single sender, receiver pair. The latency results for this test show a dramatic difference between CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer which incurs the maximum queue latency (more buffer memory will lead to high latency.) DCTCP, on the other hand, deliberately attempts to keep queue occupancy low. The result is a two orders of magnitude reduction of latency with DCTCP - even with a switch with relatively little RAM. Switches with larger amounts of RAM will incur increasing amounts of latency for CUBIC, but not for DCTCP. 4) Convergence and stability test: This test measured the time that DCTCP took to fairly redistribute bandwidth when a new flow commences. It also measured DCTCP's ability to remain stable at a fair bandwidth distribution. DCTCP is compared with CUBIC for this test. At the commencement of this test, a single flow is sending at maximum rate (near 10 Gbps) to a single receiver. One second after that first flow commences, a new flow from a distinct server begins sending to the same receiver as the first flow. After the second flow has sent data for 10 seconds, the second flow is terminated. The first flow sends for an additional second. Ideally, the bandwidth would be evenly shared as soon as the second flow starts, and recover as soon as it stops. The results of this test are shown below. Note that the flow bandwidth for the two flows was measured near the same time, but not simultaneously. DCTCP performs nearly perfectly within the measurement limitations of this test: bandwidth is quickly distributed fairly between the two flows, remains stable throughout the duration of the test, and recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth fairly, and has trouble remaining stable. CUBIC DCTCP Seconds Flow 1 Flow 2 Seconds Flow 1 Flow 2 0 9.93 0 0 9.92 0 0.5 9.87 0 0.5 9.86 0 1 8.73 2.25 1 6.46 4.88 1.5 7.29 2.8 1.5 4.9 4.99 2 6.96 3.1 2 4.92 4.94 2.5 6.67 3.34 2.5 4.93 5 3 6.39 3.57 3 4.92 4.99 3.5 6.24 3.75 3.5 4.94 4.74 4 6 3.94 4 5.34 4.71 4.5 5.88 4.09 4.5 4.99 4.97 5 5.27 4.98 5 4.83 5.01 5.5 4.93 5.04 5.5 4.89 4.99 6 4.9 4.99 6 4.92 5.04 6.5 4.93 5.1 6.5 4.91 4.97 7 4.28 5.8 7 4.97 4.97 7.5 4.62 4.91 7.5 4.99 4.82 8 5.05 4.45 8 5.16 4.76 8.5 5.93 4.09 8.5 4.94 4.98 9 5.73 4.2 9 4.92 5.02 9.5 5.62 4.32 9.5 4.87 5.03 10 6.12 3.2 10 4.91 5.01 10.5 6.91 3.11 10.5 4.87 5.04 11 8.48 0 11 8.49 4.94 11.5 9.87 0 11.5 9.9 0 SYN/ACK ECT test: This test demonstrates the importance of ECT on SYN and SYN-ACK packets by measuring the connection probability in the presence of competing flows for a DCTCP connection attempt *without* ECT in the SYN packet. The test was repeated five times for each number of competing flows. Competing Flows 1 | 2 | 4 | 8 | 16 ------------------------------ Mean Connection Probability 1 | 0.67 | 0.45 | 0.28 | 0 Median Connection Probability 1 | 0.65 | 0.45 | 0.25 | 0 As the number of competing flows moves beyond 1, the connection probability drops rapidly. Enabling DCTCP with this patch requires the following steps: DCTCP must be running both on the sender and receiver side in your data center, i.e.: sysctl -w net.ipv4.tcp_congestion_control=dctcp Also, ECN functionality must be enabled on all switches in your data center for DCTCP to work. The default ECN marking threshold (K) heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]). In above tests, for each switch port, traffic was segregated into two queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of 0x04 - the packet was placed into the DCTCP queue. All other packets were placed into the default drop-tail queue. For the DCTCP queue, RED/ECN marking was enabled, here, with a marking threshold of 75 KB. More details however, we refer you to the paper [2] under section 3). There are no code changes required to applications running in user space. DCTCP has been implemented in full *isolation* of the rest of the TCP code as its own congestion control module, so that it can run without a need to expose code to the core of the TCP stack, and thus nothing changes for non-DCTCP users. Changes in the CA framework code are minimal, and DCTCP algorithm operates on mechanisms that are already available in most Silicon. The gain (dctcp_shift_g) is currently a fixed constant (1/16) from the paper, but we leave the option that it can be chosen carefully to a different value by the user. In case DCTCP is being used and ECN support on peer site is off, DCTCP falls back after 3WHS to operate in normal TCP Reno mode. ss {-4,-6} -t -i diag interface: ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054 ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584 send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15 reordering:101 rcv_space:29200 ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448 cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate 325.5Mbps rcv_rtt:1.5 rcv_space:29200 More information about DCTCP can be found in [1-4]. [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00 Joint work with Florian Westphal and Glenn Judd. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-27 04:37:36 +08:00
default "dctcp" if DEFAULT_DCTCP
tcp: add CDG congestion control CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies the TCP sender in order to [1]: o Use the delay gradient as a congestion signal. o Back off with an average probability that is independent of the RTT. o Coexist with flows that use loss-based congestion control, i.e., flows that are unresponsive to the delay signal. o Tolerate packet loss unrelated to congestion. (Disabled by default.) Its FreeBSD implementation was presented for the ICCRG in July 2012; slides are available at http://www.ietf.org/proceedings/84/iccrg.html Running the experiment scenarios in [1] suggests that our implementation achieves more goodput compared with FreeBSD 10.0 senders, although it also causes more queueing delay for a given backoff factor. The loss tolerance heuristic is disabled by default due to safety concerns for its use in the Internet [2, p. 45-46]. We use a variant of the Hybrid Slow start algorithm in tcp_cubic to reduce the probability of slow start overshoot. [1] D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011, pages 328-341. Springer, 2011. [2] K.K. Jonassen. "Implementing CAIA Delay-Gradient in Linux." MSc thesis. Department of Informatics, University of Oslo, 2015. Cc: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Neal Cardwell <ncardwell@google.com> Cc: David Hayes <davihay@ifi.uio.no> Cc: Andreas Petlund <apetlund@simula.no> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Nicolas Kuhn <nicolas.kuhn@telecom-bretagne.eu> Signed-off-by: Kenneth Klette Jonassen <kennetkl@ifi.uio.no> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 01:08:17 +08:00
default "cdg" if DEFAULT_CDG
default "bbr" if DEFAULT_BBR
default "cubic"
config TCP_MD5SIG
bool "TCP: MD5 Signature Option support (RFC2385)"
select CRYPTO
select CRYPTO_MD5
---help---
RFC2385 specifies a method of giving MD5 protection to TCP sessions.
Its main (only?) use is to protect BGP sessions between core routers
on the Internet.
If unsure, say N.