sent using roundrobin protocol and set a better granularity and distribution
among the interfaces. Tuning the number of packages sent by interface can
increase throughput and reduce unordered packets as well as reduce SACK.
Example of usage:
# ifconfig bge0 up
# ifconfig bge1 up
# ifconfig lagg0 create
# ifconfig lagg0 laggproto roundrobin laggport bge0 laggport bge1 \
192.168.1.1 netmask 255.255.255.0
# ifconfig lagg0 rr_limit 500
Reviewed by: thompsa, glebius, adrian (old patch)
Approved by: bapt (mentor)
Relnotes: Yes
Differential Revision: https://reviews.freebsd.org/D540
When using lagg failover mode neither Gratuitous ARP (IPv4) or Unsolicited
Neighbour Advertisements (IPv6) are sent to notify other nodes that the
address may have moved.
This results is slow failover, dropped packets and network outages for the
lagg interface when the primary link goes down.
We now use the new if_link_state_change_cond with the force param set to
allow lagg to force through link state changes and hence fire a
ifnet_link_event which are now monitored by rip and nd6.
Upon receiving these events each protocol trigger the relevant
notifications:
* inet4 => Gratuitous ARP
* inet6 => Unsolicited Neighbour Announce
This also fixes the carp IPv6 NA's that stopped working after r251584 which
added the ipv6_route__llma route.
The new behavour can be controlled using the sysctls:
* net.link.ether.inet.arp_on_link
* net.inet6.icmp6.nd6_on_link
Also removed unused param from lagg_port_state and added descriptions for the
sysctls while here.
PR: 156226
MFC after: 1 month
Sponsored by: Multiplay
Differential Revision: https://reviews.freebsd.org/D4111
The remove began with revision r271733.
NOTE: This patch must never be merge to 10-Stable
Reviewed by: glebius
Approved by: bapt (mentor)
Relnotes: Yes
Sponsored by: EuroBSDCon Sweden.
Differential Revision: D3786
drivers can use it. This avoids some code duplication. Add missing
default case to all switch statements while at it. Also move the
hashing of the IPv6 flow field to layer 4 because the IPv6 flow field
is constant on a per L4 connection basis and not on a per L3 network.
Differential Revision: https://reviews.freebsd.org/D1987
Sponsored by: Mellanox Technologies
MFC after: 1 month
I edited the original change to retain the use of arc4random() as a seed for
the hashing as a very basic defense against intentional lagg port selection.
The author's original commit message (edited slightly):
sys/net/ieee8023ad_lacp.c
sys/net/if_lagg.c
In lagg_hashmbuf, use the FNV hash instead of the old
hash32_buf. The hash32 family of functions operate one octet
at a time, and when run on a string s of length n, their output
is equivalent to :
----- i=n-1
\
n \ (n-i-1) 32
( seed^ + / 33^ * s[i] ) % 2^
/
----- i=0
The problem is that the last five bytes of input don't get
multiplied by sufficiently many powers of 33 to rollover 2^32.
That means that changing the last few bytes (but obviously not
the very last) of input will always change the value of the
hash by a multiple of 33. In the case of lagg_hashmbuf() with
ipv4 input, the last four bytes are the TCP or UDP port
numbers. Since the output of lagg_hashmbuf is always taken
modulo the port count, and 3 is a common port count for a lagg,
that's bad. It means that the UDP or TCP source port will
never affect which lagg member is selected on a 3-port lagg.
At 10Gbps, I was not able to measure any difference in CPU
consumption between the old and new hash.
Submitted by: asomers (original commit)
Reviewed by: emaste, glebius
MFC after: 1 week
Sponsored by: Spectra Logic
MFSpectraBSD: 1001723 on 2013/08/28 (original)
1114258 on 2015/01/22 (edit)
from the FreeBSD network code. The flag is still kept around in the
"sys/mbuf.h" header file, but does no longer have any users. Instead
the "m_pkthdr.rsstype" field in the mbuf structure is now used to
decide the meaning of the "m_pkthdr.flowid" field. To modify the
"m_pkthdr.rsstype" field please use the existing "M_HASHTYPE_XXX"
macros as defined in the "sys/mbuf.h" header file.
This patch introduces new behaviour in the transmit direction.
Previously network drivers checked if "M_FLOWID" was set in "m_flags"
before using the "m_pkthdr.flowid" field. This check has now now been
replaced by checking if "M_HASHTYPE_GET(m)" is different from
"M_HASHTYPE_NONE". In the future more hashtypes will be added, for
example hashtypes for hardware dedicated flows.
"M_HASHTYPE_OPAQUE" indicates that the "m_pkthdr.flowid" value is
valid and has no particular type. This change removes the need for an
"if" statement in TCP transmit code checking for the presence of a
valid flowid value. The "if" statement mentioned above is now a direct
variable assignment which is then later checked by the respective
network drivers like before.
Additional notes:
- The SCTP code changes will be committed as a separate patch.
- Removal of the "M_FLOWID" flag will also be done separately.
- The FreeBSD version has been bumped.
MFC after: 1 month
Sponsored by: Mellanox Technologies
LOR of softc rmlock in iflladdr_event handlers.
- Call if_delmulti_ifma() after LACP_UNLOCK(). This fixes another LOR.
- Fix a panic in lacp_transit_expire().
- Fix a panic in lagg_input() upon shutting down a port.
if_lagg(4) interfaces which were cloned in a vnet jail.
Sysctl nodes which are dynamically generated for each cloned interface
(net.link.lagg.N.*) have been removed, and use_flowid and flowid_shift
ifconfig(8) parameters have been added instead. Flags and per-interface
statistics counters are displayed in "ifconfig -v".
CR: D842
then drop lock, run the attach routines, and then set it to specific
proto. This removes tons of WITNESS warnings.
- Make lagg protocol attach handlers not failing and allocate memory
with M_WAITOK.
Sponsored by: Netflix
Sponsored by: Nginx, Inc.
The current TSO limitation feature only takes the total number of
bytes in an mbuf chain into account and does not limit by the number
of mbufs in a chain. Some kinds of hardware is limited by two
factors. One is the fragment length and the second is the fragment
count. Both of these limits need to be taken into account when doing
TSO. Else some kinds of hardware might have to drop completely valid
mbuf chains because they cannot loaded into the given hardware's DMA
engine. The new way of doing TSO limitation has been made backwards
compatible as input from other FreeBSD developers and will use
defaults for values not set.
Reviewed by: adrian, rmacklem
Sponsored by: Mellanox Technologies
MFC after: 1 week
and receives frames on any port of the lagg(4).
Phabric: D549
Reviewed by: glebius, thompsa
Approved by: glebius
Obtained from: OpenBSD
Sponsored by: QNAP Systems Inc.
The current TSO limitation feature only takes the total number of
bytes in an mbuf chain into account and does not limit by the number
of mbufs in a chain. Some kinds of hardware is limited by two
factors. One is the fragment length and the second is the fragment
count. Both of these limits need to be taken into account when doing
TSO. Else some kinds of hardware might have to drop completely valid
mbuf chains because they cannot loaded into the given hardware's DMA
engine. The new way of doing TSO limitation has been made backwards
compatible as input from other FreeBSD developers and will use
defaults for values not set.
MFC after: 1 week
Sponsored by: Mellanox Technologies
These changes prevent sysctl(8) from returning proper output,
such as:
1) no output from sysctl(8)
2) erroneously returning ENOMEM with tools like truss(1)
or uname(1)
truss: can not get etype: Cannot allocate memory
there is an environment variable which shall initialize the SYSCTL
during early boot. This works for all SYSCTL types both statically and
dynamically created ones, except for the SYSCTL NODE type and SYSCTLs
which belong to VNETs. A new flag, CTLFLAG_NOFETCH, has been added to
be used in the case a tunable sysctl has a custom initialisation
function allowing the sysctl to still be marked as a tunable. The
kernel SYSCTL API is mostly the same, with a few exceptions for some
special operations like iterating childrens of a static/extern SYSCTL
node. This operation should probably be made into a factored out
common macro, hence some device drivers use this. The reason for
changing the SYSCTL API was the need for a SYSCTL parent OID pointer
and not only the SYSCTL parent OID list pointer in order to quickly
generate the sysctl path. The motivation behind this patch is to avoid
parameter loading cludges inside the OFED driver subsystem. Instead of
adding special code to the OFED driver subsystem to post-load tunables
into dynamically created sysctls, we generalize this in the kernel.
Other changes:
- Corrected a possibly incorrect sysctl name from "hw.cbb.intr_mask"
to "hw.pcic.intr_mask".
- Removed redundant TUNABLE statements throughout the kernel.
- Some minor code rewrites in connection to removing not needed
TUNABLE statements.
- Added a missing SYSCTL_DECL().
- Wrapped two very long lines.
- Avoid malloc()/free() inside sysctl string handling, in case it is
called to initialize a sysctl from a tunable, hence malloc()/free() is
not ready when sysctls from the sysctl dataset are registered.
- Bumped FreeBSD version to indicate SYSCTL API change.
MFC after: 2 weeks
Sponsored by: Mellanox Technologies
was stacked on top of network interfaces that set if_hw_tsomax,
tcp_output() would see the default value instead of the value
set by the network interface(s). This patch modifies lagg so that
it sets if_hw_tsomax to the minimum of the value(s) for the
underlying network interfaces.
Reviewed by: glebius
MFC after: 2 weeks
callback providers. link_init_sdl() function can be used to
fill most of the parameters. Use caller stack instead of
allocation / freing memory for each request. Do not drop support
for extra-long (probably non-existing) link-layer protocols by
introducing link_alloc_sdl() (used by if_resolvemulti() callback)
and link_free_sdl() (used by caller).
Since this change breaks KBI, MFC requires slightly different approach
(link_init_sdl() auto-allocating buffer if necessary to handle cases
with unmodified if_resolvemulti() callers).
MFC after: 2 weeks
bits of the flowid as each other, resulting in a poor distribution of
packets among queues in certain cases. Work around this by adding a
set of sysctls for controlling a bit-shift on the flowid when doing
multi-port aggrigation in lagg and lacp. By default, lagg/lacp will
now use bits 16 and higher instead of 0 and higher.
Reviewed by: max
Obtained from: Netflix
MFC after: 3 days
and there are ifnets, that do that via counter(9). Provide a flag that
would skip cache line trashing '+=' operation in ether_input().
Sponsored by: Netflix
Sponsored by: Nginx, Inc.
Reviewed by: melifaro, adrian
Approved by: re (marius)
We've been seeing lots of cache line contention (but not lock contention!)
in our workloads between the various TX and RX threads going on.
The write lock is only grabbed when configuration changes are made - which
are infrequent.
With this patch, the contention and cycles spent waiting for updates
disappear.
Sponsored by: Netflix, Inc.
sysctl tree.
* Create a net.link.lagg.X.lacp node
* Add a debug node under that for tx_test and rx_test
* Add lacp_strict_mode, defaulting to 1
tx_test and rx_test are still a bitmap of unit numbers for now.
At some point it would be nice to create child nodes of the lagg bundle
for each sub-interface, and then populate those with various knobs
and statistics.
Sponsored by: Netflix
additions.
* Add some new tracing events to aid in debugging.
* Add in a debugging mode to drop transmit and received frames, specifically
to test whether seeing or hearing heartbeats correctly cause LACP to
drop the port.
* Add in (and make default) a strict LACP mode, which requires the
heartbeat on a port to be heard before it's used. Sometimes vendor ports
will hang but the link layer stays up, resulting in hung traffic.
* Add logging the number of link status flaps, again to aid in debugging
badly behaving switch ports.
* Calculate the lagg interface port speed as the multiple of the
configured ports, rather than the largest.
Obtained from: Netflix
MFC after: 2 weeks
is initialized with !ND6_IFF_AUTO_LINKLOCAL && !ND6_IFF_ACCEPT_RTADV
regardless of net.inet6.ip6.accept_rtadv and net.inet6.ip6.auto_linklocal.
To configure an autoconfigured link-local address (RFC 4862), the
following rc.conf(5) configuration can be used:
ifconfig_bridge0_ipv6="inet6 auto_linklocal"
- if_bridge(4) now removes IPv6 addresses on a member interface to be
added when the parent interface or one of the existing member
interfaces has an IPv6 address. if_bridge(4) merges each link-local
scope zone which the member interfaces form respectively, so it causes
address scope violation. Removal of the IPv6 addresses prevents it.
- if_lagg(4) now removes IPv6 addresses on a member interfaces
unconditionally.
- Set reasonable flags to non-IPv6-capable interfaces. [*]
Submitted by: rpaulo [*]
MFC after: 1 week
inactive when upper layer tries to transmit packet. This
gives better feedback and meaningful errors for applications.
MFC after: 2 weeks
Reviewed by: thompsa
