- netmap pipes, providing bidirectional blocking I/O while moving
100+ Mpps between processes using shared memory channels
(no mistake: over one hundred million. But mind you, i said
*moving* not *processing*);
- kqueue support (BHyVe needs it);
- improved user library. Just the interface name lets you select a NIC,
host port, VALE switch port, netmap pipe, and individual queues.
The upcoming netmap-enabled libpcap will use this feature.
- optional extra buffers associated to netmap ports, for applications
that need to buffer data yet don't want to make copies.
- segmentation offloading for the VALE switch, useful between VMs.
and a number of bug fixes and performance improvements.
My colleagues Giuseppe Lettieri and Vincenzo Maffione did a substantial
amount of work on these features so we owe them a big thanks.
There are some external repositories that can be of interest:
https://code.google.com/p/netmap
our public repository for netmap/VALE code, including
linux versions and other stuff that does not belong here,
such as python bindings.
https://code.google.com/p/netmap-libpcap
a clone of the libpcap repository with netmap support.
With this any libpcap client has access to most netmap
feature with no recompilation. E.g. tcpdump can filter
packets at 10-15 Mpps.
https://code.google.com/p/netmap-ipfw
a userspace version of ipfw+dummynet which uses netmap
to send/receive packets. Speed is up in the 7-10 Mpps
range per core for simple rulesets.
Both netmap-libpcap and netmap-ipfw will be merged upstream at some
point, but while this happens it is useful to have access to them.
And yes, this code will be merged soon. It is infinitely better
than the version currently in 10 and 9.
MFC after: 3 days
insert flow entry. During the route lookup the critical section is
exited. It may happen, that after route lookup we will be executed
on an other CPU that already has such flowentry. Before this change
we simply freed the flowentry and returned to ip_output() with
failure.
Actually there is nothing wrong with using previously allocated
flow entry, updating it properly. Thus, make flowentry_insert()
return the new either old fle, and make use of it.
Count reuses as "collisions" and real inserts as "inserts".
Reviewed by: adrian
Sponsored by: Netflix
Sponsored by: Nginx, Inc.
race prone. Some just gather statistics, but some are later used in
different calculations.
A real problem was the race provoked underflow of the states_cur counter
on a rule. Once it goes below zero, it wraps to UINT32_MAX. Later this
value is used in pf_state_expires() and any state created by this rule
is immediately expired.
Thus, make fields states_cur, states_tot and src_nodes of struct
pf_rule be counter(9)s.
Thanks to Dennis for providing me shell access to problematic box and
his help with reproducing, debugging and investigating the problem.
Thanks to: Dennis Yusupoff <dyr smartspb.net>
Also reported by: dumbbell, pgj, Rambler
Sponsored by: Nginx, Inc.
Some of the collisions that are occuring are due to flowtable lookups
that succeed but have an invalid lle - typically because the L2 adjacency
lookup hasn't completed. This would lead to a follow-up insert which
would then fail (ie, collision) and the code would fall through to doing
a slow-path L2/L3 lookup in the netinet/netinet6 code.
This patch simply aborts storing a new flowtable entry if the lle isn't
yet valid.
Whilst I'm here, add a new pcpu counter for the item so the number of
failures can be tracked separately from generic "collisions."
Reviewed by: glebius
MFC after: 10 days
Sponsored by: Netflix, Inc.
and probably is a leftover from first prototyping by Kip. The
non-pcpu implementation used mutexes, so it doubtfully worked
better than simple routing lookup.
o Use UMA_ZONE_PCPU zone for pointers instead of [MAXCPU] arrays,
use zpcpu_get() to access data in there.
o Substitute own single list implementation with SLIST(). This
has two functional side effects:
- new flows go into head of a list, before they went to tail.
- a bug when incorrect flow was deleted in flow cleaner is
fixed.
o Due to cache line alignment, there is no reason to keep
different zones for IPv4 and IPv6 flows. Both consume one
cache line, real size of allocation is equal.
o Rely on that f_hash, f_rt, f_lle are stable during fle
lifetime, remove useless volatile quilifiers.
o More INET/INET6 splitting.
Reviewed by: adrian
Sponsored by: Netflix
Sponsored by: Nginx, Inc.
- ip_output() and ip_output6() simply call flowtable_lookup(),
passing mbuf and address family. That's the only code under
#ifdef FLOWTABLE in the protocols code now.
o Revamp statistics gathering and export.
- Remove hand made pcpu stats, and utilize counter(9).
- Snapshot of statistics is available via 'netstat -rs'.
- All sysctls are moved into net.flowtable namespace, since
spreading them over net.inet isn't correct.
o Properly separate at compile time INET and INET6 parts.
o General cleanup.
- Remove chain of multiple flowtables. We simply have one for
IPv4 and one for IPv6.
- Flowtables are allocated in flowtable.c, symbols are static.
- With proper argument to SYSINIT() we no longer need flowtable_ready.
- Hash salt doesn't need to be per-VNET.
- Removed rudimentary debugging, which use quite useless in dtrace era.
The runtime behavior of flowtable shouldn't be changed by this commit.
Sponsored by: Netflix
Sponsored by: Nginx, Inc.
in the sysctl_root().
Note: SYSCTL_VNET_* macros can be removed as well. All is
needed to virtualize a sysctl oid is set CTLFLAG_VNET on it.
But for now keep macros in place to avoid large code churn.
Sponsored by: Nginx, Inc.
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
has the same prefix as some other alias on the same interface, use
newly-added rt_addrmsg() instead of hand-rolled in_addralias_rtmsg().
This eliminates the following rtsock messages:
Pinned RTM_ADD for prefix (for alias addition).
Pinned RTM_DELETE for prefix (for alias withdrawal).
Example (got 10.0.0.1/24 on vlan4, playing with 10.0.0.2/24):
before commit, addition:
got message of size 116 on Fri Jan 10 14:13:15 2014
RTM_NEWADDR: address being added to iface: len 116, metric 0, flags:
sockaddrs: <NETMASK,IFP,IFA,BRD>
255.255.255.0 vlan4:8.0.27.c5.29.d4 10.0.0.2 10.0.0.255
got message of size 192 on Fri Jan 10 14:13:15 2014
RTM_ADD: Add Route: len 192, pid: 0, seq 0, errno 0, flags:<UP,PINNED>
locks: inits:
sockaddrs: <DST,GATEWAY,NETMASK>
10.0.0.0 10.0.0.2 (255) ffff ffff ff
after commit, addition:
got message of size 116 on Fri Jan 10 13:56:26 2014
RTM_NEWADDR: address being added to iface: len 116, metric 0, flags:
sockaddrs: <NETMASK,IFP,IFA,BRD>
255.255.255.0 vlan4:8.0.27.c5.29.d4 14.0.0.2 14.0.0.255
before commit, wihdrawal:
got message of size 192 on Fri Jan 10 13:58:59 2014
RTM_DELETE: Delete Route: len 192, pid: 0, seq 0, errno 0, flags:<UP,PINNED>
locks: inits:
sockaddrs: <DST,GATEWAY,NETMASK>
10.0.0.0 10.0.0.2 (255) ffff ffff ff
got message of size 116 on Fri Jan 10 13:58:59 2014
RTM_DELADDR: address being removed from iface: len 116, metric 0, flags:
sockaddrs: <NETMASK,IFP,IFA,BRD>
255.255.255.0 vlan4:8.0.27.c5.29.d4 10.0.0.2 10.0.0.255
adter commit, withdrawal:
got message of size 116 on Fri Jan 10 14:14:11 2014
RTM_DELADDR: address being removed from iface: len 116, metric 0, flags:
sockaddrs: <NETMASK,IFP,IFA,BRD>
255.255.255.0 vlan4:8.0.27.c5.29.d4 10.0.0.2 10.0.0.255
Sending both RTM_ADD/RTM_DELETE messages to rtsock is completely wrong
(and requires some hacks to keep prefix in route table on RTM_DELETE).
I've tested this change with quagga (no change) and bird (*).
bird alias handling is already broken in *BSD sysdep code, so nothing
changes here, too.
I'm going to MFC this change if there will be no complains about behavior
change.
While here, fix some style(9) bugs introduced by r260488
(pointed by glebius and bde).
Sponsored by: Yandex LLC
MFC after: 4 weeks
Adding/deleting interface addresses involves access to 3 different subsystems,
int different parts of code. Each call can fail, so reporting successful
operation by rtsock in the middle of the process error-prone.
Further split routing notification API and actual rtsock calls via creating
public-available rt_addrmsg() / rt_routemsg() functions with "private"
rtsock_* backend.
MFC after: 2 weeks
Remove old bits of data concat for 'ascii' field.
Remove special SIOCGIFSTATUS handling from if.c (which Coverity yells at).
Reported by: Coverity
Coverity CID: 1147174
MFC after: 2 weeks
Most relevant features:
- netmap emulation on any NIC, even those without native netmap support.
On the ixgbe we have measured about 4Mpps/core/queue in this mode,
which is still a lot more than with sockets/bpf.
- seamless interconnection of VALE switch, NICs and host stack.
If you disable accelerations on your NIC (say em0)
ifconfig em0 -txcsum -txcsum
you can use the VALE switch to connect the NIC and the host stack:
vale-ctl -h valeXX:em0
allowing sharing the NIC with other netmap clients.
- THE USER API HAS SLIGHTLY CHANGED (head/cur/tail pointers
instead of pointers/count as before). This was unavoidable to support,
in the future, multiple threads operating on the same rings.
Netmap clients require very small source code changes to compile again.
On the plus side, the new API should be easier to understand
and the internals are a lot simpler.
The manual page has been updated extensively to reflect the current
features and give some examples.
This is the result of work of several people including Giuseppe Lettieri,
Vincenzo Maffione, Michio Honda and myself, and has been financially
supported by EU projects CHANGE and OPENLAB, from NetApp University
Research Fund, NEC, and of course the Universita` di Pisa.
it performs exact match search, regardless of netmask existance.
This simplifies most of rnh_lookup() consumers.
Fix panic triggered by deleting non-existent host route.
PR: kern/185092
Submitted by: Nikolay Denev <ndenev at gmail.com>
MFC after: 1 month
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
most often used with network interfaces.
The SFF-8472 standard defines the information that can be retrieved
from an optic or a copper cable plugged into a NIC, most often
referred to as SFP+. Examples of values that can be read
include the cable vendor's name, part number, date of manufacture
as well as running data such as temperature, voltage and tx
and rx power.
Copious comments on how to use these values with an I2C interface
are given in the header file itself.
MFC after: 2 weeks
In its stead use the Solaris / illumos approach of emulating '-' (dash)
in probe names with '__' (two consecutive underscores).
Reviewed by: markj
MFC after: 3 weeks
option, unbreak the lock tracing release semantic by embedding
calls to LOCKSTAT_PROFILE_RELEASE_LOCK() direclty in the inlined
version of the releasing functions for mutex, rwlock and sxlock.
Failing to do so skips the lockstat_probe_func invokation for
unlocking.
- As part of the LOCKSTAT support is inlined in mutex operation, for
kernel compiled without lock debugging options, potentially every
consumer must be compiled including opt_kdtrace.h.
Fix this by moving KDTRACE_HOOKS into opt_global.h and remove the
dependency by opt_kdtrace.h for all files, as now only KDTRACE_FRAMES
is linked there and it is only used as a compile-time stub [0].
[0] immediately shows some new bug as DTRACE-derived support for debug
in sfxge is broken and it was never really tested. As it was not
including correctly opt_kdtrace.h before it was never enabled so it
was kept broken for a while. Fix this by using a protection stub,
leaving sfxge driver authors the responsibility for fixing it
appropriately [1].
Sponsored by: EMC / Isilon storage division
Discussed with: rstone
[0] Reported by: rstone
[1] Discussed with: philip
- Removed pf_remove_src_node().
- Introduce pf_unlink_src_node() and pf_unlink_src_node_locked().
These function do not proceed with freeing of a node, just disconnect
it from storage.
- New function pf_free_src_nodes() works on a list of previously
disconnected nodes and frees them.
- Utilize new API in pf_purge_expired_src_nodes().
In collaboration with: Kajetan Staszkiewicz <kajetan.staszkiewicz innogames.de>
Sponsored by: InnoGames GmbH
Sponsored by: Nginx, Inc.
assigned by the IEEE. This file includes documentation on how developers
must carve up the space as well as an initial allocation for bhyve.
Sponsored by: The FreeBSD Foundation
