| Age | Commit message (Collapse) | Author |
|---|
|
|
|
added without an expilict priority. This allows to specify less prefered
interfaces that will only take over if the primary interface loses link.
OK deraadt@
|
|
inside if_data, so that netstat(1) and systat(1) can see them
ok dlg
|
|
Use a 1 tick timeout() to determine if the kernel even manages to get
below softclock (from an old diff by mpf). If our timeout comes late,
reduce the high water marks (to half) for all network interfaces, thus
starving them of future packet allocations for their RX rings. For a
few ticks longer, also block the high water marks from rising even if
RX ring empty conditions would prod us to do so.
Cards may start dropping some packets off the end of their smaller RX
rings, but we were not able to do the work required in any case. With
less interrupt time and mbuf movement, the system finds time to make
progress at the network queues. Userland even gets to run.
A x40 tuned to 600MHz shows no real reduction in performance. But a
soekris has a working console now.
ok dlg claudio, and art liked it too
|
|
watermark for mbuf cluster allocations.
this is necessary for things like bge which cannot cope with less than a
certain number of pkts on the ring.
ok deraadt@
|
|
the per ifp cluster allocator. should prevent the hwm being raised
innapropriately when a driver fills its rx ring for the first time.
|
|
allocators again.
|
|
ok dlg
|
|
but don't do that in m_free() as that will cause a double loop behaviour when
called via m_freem().
OK dlg@, deraadt@
|
|
of. currently limited to MCLBYTES (2048 bytes) and 4096 bytes until pools
can allocate objects of sizes greater than PAGESIZE.
this allows drivers to ask for "jumbo" packets to fill rx rings with.
the second half of this change is per interface mbuf cluster allocator
statistics. drivers can use the new interface (MCLGETI), which will use
these stats to selectively fail allocations based on demand for mbufs. if
the driver isnt rapidly consuming rx mbufs, we dont allow it to allocate
many to put on its rx ring.
drivers require modifications to take advantage of both the new allocation
semantic and large clusters.
this was written and developed with deraadt@ over the last two days
ok deraadt@ claudio@
|
|
which are considered down will no be marked ~RTF_UP and so multipath routing
will start to work as expected and not pump 50% of the traffic to nirvana.
Most of the magic happens in rn_mpath_reprio() which fiddles with the
routing table internals. The rest is more straight forward.
get it in deraadt@
|
|
not only over routes of the same prio. This makes it possible to modify
rt_mpath_matchgate() so that if only gateway is specified without a specific
priority it will scan the full list and not only the first routes.
This is also needed for upcoming link state tracking.
|
|
addressing in IPv6 likes to do ifp = ifindex2ifnet[ifindex] without properly
checking if the ifindex is valid. As a side-effect this solves parts of
PR 5981. Debugged by jsing@. OK jsing@, deraadt@
|
|
network mask. For some reasons some parts set sa->sa_len to 0 to specify
a /0 netmask so check fot that too. tested by david@ OK henning@
|
|
OK henning@
|
|
get hung in nfs_reconnect() because they do not have the proper
privilages to bind to a socket, by adding a struct proc * argument
to sobind() (and the *_usrreq() routines, and finally in{6}_pcbbind)
and do the sobind() with proc0 in nfs_connect.
OK markus@, blambert@.
"go ahead" deraadt@.
Fixes an issue reported by bernd@ (Tested by bernd@).
Fixes PR5135 too.
|
|
Also move the sampling into ether_input() where it can happen
at the interrupt and not within splnet() processing, which might
be less random. Discussed with mickey.
OK markus@, mcbride@
|
|
decent drivers prefer to have a lot of packets on the send queue so they
can queue a lot of them up on the tx ring and then post them all in one
big chunk. unfortunately our stack queues one packet onto the send queue
and then calls the start handler immediately.
this mitigates against that queue, send, queue, send behaviour by trying to
call the start routine only once per softnet. now its queue, queue, queue,
send.
this is the result of a lot of discussion with claudio@
tested by many.
|
|
all the original ones did, the recently added ones for labels per interface
didn't. no cookie for reyk ;(
ok deraadt
|
|
from chris@nmedia.net
|
|
-remove useless casts
-MALLOC/FREE -> malloc/free
-use M_ZERO where appropriate instead of seperate bzero
feedback & ok krw, hshoexer
|
|
Makes bluetooth build again. ok uwe@
|
|
before it is removed from the multicast group in_delmulti() will try to
access the no longer available ifp.
We invalidate the ifa_ifp back pointer in the ifa in if_detach() now and use
the ifa_ifp in in_delmulti() instead of the internal inm_ifp. By doing it
this way we know if the interface was removed.
This fixes a kernel panic triggered by ospfd and gif(4) tunnels.
looks good henning@ reyk@
|
|
spotted by Mike Belopuhov <mkb@crypt.org.ru>
|
|
which will be used for new interface routes. For example,
ifconfig em0 10.1.1.0 255.255.255.0 rtlabel RING_1
will set the new interface address and attach the route label RING_1 to
the corresponding route.
manpage bits from jmc@
ok claudio@ henning@
|
|
some I found afterwards, ok dlg
|
|
|
|
|
|
packet. If multiple packets come in on a single interrupt the times mixed into
the randomness pool will be identical or predictably close anyways, and
nanotime() is expensive.
ok toby jason miod claudio
|
|
This reduces group failover time to a few milliseconds.
Diff from Nathanael.
OK henning@
|
|
This provides a similar functionality as ARP balancing,
but also works for traffic that comes across routers.
IPv6 is supported as well.
The configuration scheme will change as soon we have sth better.
Also add support for changing the MAC address on carp(4)
interfaces. (code from mcbride)
Tested by pyr@ and reyk@
OK mcbride@
|
|
ok kettenis@ cloder@ tom@ henning@
|
|
OK tedu@
|
|
by Andrew Thompson (thompsa@freebsd.org). The local changes include
adoption to our bridge code, reduced stack usage and many other bits.
If stp is enabled, RSTP will now be used by default.
Thanks for help from Andrew.
This code has been in snaps for while now, commit encouraged by deraadt@
|
|
an interface. Fixes a double free panic.
ok claudio@, looks fine henning@
|
|
code factored out from if_addgroup(), previously a group always had to have
members. ok mpf mcbride
|
|
success, not -1 on error. fix check in 2 cases. ok mpf mcbride
|
|
as the resulting demotion counter value is in range. previously, we only
allowed +/- 1. ok mpf mcbride deraadt
|
|
|
|
As a first user, move the global carp(4) demotion counter
into the interface group. Thus we have the possibility
to define which carp interfaces are demoted together.
Put the demotion counter into the reserved field of the carp header.
With this, we can have carp act smarter if multiple errors occur.
It now always takes over other carp peers, that are advertising
with a higher demote count. As a side effect, we can also have
group failovers without the need of running in preempt mode.
The protocol change does not break compability with older
implementations.
Collaborative work with mcbride@
OK mcbride@, henning@
|
|
directly. rather provide a rt_lookup function for regular lookups,
and a rt_gettable for those that need access to the head for some reason.
the latter cases should be revisted later probably so that nothing outside
the routing core code accesses the heads at all...
tested claudio jolan me, ok claudio markus
|
|
interface that is removed. use that from if.c and if_tun.c instead of
re-implementing in the latter case. ok claudio
|
|
the remainder of the network stack from splimp to splnet.
ok miod@
|
|
fixes a possible crash if the parent interface has been destroyed
(like vlan on trunk) before destroying the vlan interface.
ok brad@
|
|
into them, if you are gonna copy it out to userland
some ok dhartmei, some ok tedu
|
|
to the driver that there is a listener. Somehow I assumed that it was
a handle, and was trying to figure out why it was becoming zero.
Corrected by and ok claudio@
|
|
router so back out the routing stuff to pre-eurobsdcon where my machine
doesn't crash immediately.
i am happy to test diffs and report success/failures but i am not happy
to have instantaneous crashes when i reboot with a new kernel that was
compiled from pristine sources.
if you are going to be an elitist asshole then you could at least make
sure your code works.
ok and "be crass towards them" deraadt@
|
|
but go through a provided wrapper.
also provide rt_lookup() instead of doing the lookup manually in many places.
ryan ok
|
|
when the interface is deleted to a function in route.c, and replace
the copies of that code by calls to that function
from basel almost-hackathon
|
|
to trigger an if_group_egress_build() call, stop looking at the mask in the
v4 case, at least until I figured out why we sometimes see masks full of
crap.
|
