Date: Thu, 25 May 2017 17:24:58 +0200 From: Harry Schmalzbauer <freebsd@omnilan.de> To: Vincenzo Maffione <v.maffione@gmail.com> Cc: "freebsd-net@freebsd.org" <freebsd-net@freebsd.org> Subject: vale uplink via vlan-if [Was: Re: Are ./valte-ctl and ./bridge friends or competitors?] Message-ID: <5926F74A.1000101@omnilan.de> In-Reply-To: <CA%2B_eA9hxpevk%2BSJwJZCdnSsQu0iRBo52V5qC=225hVxQu04KyQ@mail.gmail.com> References: <58CBA727.3040108@omnilan.de> <58CBBF7A.8050604@omnilan.de> <CA%2B_eA9jYxRoi2HPcVjKbifTM43nnHeMQGDmmQvsw5UdXtLmFug@mail.gmail.com> <58CC26CF.5050708@omnilan.de> <CA%2B_eA9j30Shp1QB%2B6UY1YRqsWKRo4xqPvDRnMHT25VQL4QhQ_Q@mail.gmail.com> <58CFA606.7090306@omnilan.de> <CA%2B_eA9hso4AKpFEJCXWHYYz5tbLx4jT2o=3c-3YrWM98ovB8%2BA@mail.gmail.com> <58D02259.9010101@omnilan.de> <CA%2B_eA9hxpevk%2BSJwJZCdnSsQu0iRBo52V5qC=225hVxQu04KyQ@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Bezüglich Vincenzo Maffione's Nachricht vom 21.03.2017 19:05 (localtime):
> 2017-03-20 19:41 GMT+01:00 Harry Schmalzbauer <freebsd@omnilan.de>:
>
>> Bezüglich Vincenzo Maffione's Nachricht vom 20.03.2017 12:50 (localtime):
>> …
>>>> So to summarize for newbies exploring netmap(4) world in combination
>>>> with physical uplinks and virtual interfaces, it's important to do the
>>>> following uplink NIC configuration (ifconfig(8)):
>>>> -rxcsum -txcsum -rxcsum6 -txcsum6 -tso -lro promisc
>>>>
>>>
>>> Exactly. This is mentioned at the very end of netmap(4):
>>>
>>> "netmap does not use features such as checksum offloading, TCP
>> segmentation
>>> offloading, encryption, VLAN encapsulation/decapsulation, etc. When
>> using
>>> netmap to exchange packets with the host stack, make sure to disable
>> these
>>> features."
>>>
>>> But it is probably a good idea to add these example ifconfig instructions
>>> somewhere (man page or at least the README in the netmap repo).
>>>
>>>
>>>>
>>>> I guess vlanhwtag, vlanhwfilter and vlanhwtso don't interfere, do they?
>>>>
>>>
>>> Well, I think they interfere: if you receive a tagged packet and the NIC
>>> strips the tag and puts it in the packet descriptor, then with netmap you
>>> will see the untagged packet, and you wouldn't have a way to see the tag.
Sorry picking this up again, but I'm stuck getting vale(4) productive :-(
I took lagg(4) out of the game and configured my desired setup using
if_bridge(4) at first.
The physical uplink NIC is em0.
The bridge/vale uplink is em0.232.
hostB --switch-- em0-hostA
|
'- em0.232
|
bridge5-vmnet0
|
vtnet0-GUESTa <-tcpdump:
17:07:28.423768 00:a0:98:73:9f:42 > ff:ff:ff:ff:ff:ff, ethertype ARP
(0x0806), length 42: Request who-has 172.21.34.10 tell 172.21.35.1,
length 28
17:07:28.424208 00:0c:29:40:3a:dd > 00:a0:98:73:9f:42, ethertype ARP
(0x0806), length 60: Reply 172.21.34.10 is-at 00:0c:29:40:3a:dd, length 46
The same is visable on vmnet0 nad em0 of course.
Now if I replace bridge5 by vale, leaving everything else unchanged
besides using netmap-vtnet with bhyve, I don't get ARP is-at answer.
I can see the who-has on all interfaces involved, and also the is-at
answer up to em0.232, but not at vtnet0 (the guest, connected via vale).
To draw the same picture like with bridge:
hostB --switch-- em0-hostA
|
'- em0.232
|
vale232:em0.232-'
vale232:GUESTa--vtnet0-GUESTa <-tcpdump:
17:16:00.111868 00:a0:98:73:9f:42 > ff:ff:ff:ff:ff:ff, ethertype ARP
(0x0806), length 42: Request who-has 172.21.34.10 tell 172.21.35.1,
length 28
... no reply
While tcpdump of em0.232 shows:
17:16:01.119537 00:a0:98:73:9f:42 > ff:ff:ff:ff:ff:ff, ethertype ARP
(0x0806), length 60: Request who-has 172.21.34.10 tell 172.21.35.1,
length 46
17:16:01.119849 00:0c:29:40:3a:dd > 00:a0:98:73:9f:42, ethertype ARP
(0x0806), length 60: Reply 172.21.34.10 is-at 00:0c:29:40:3a:dd, length 46
The reply made it up to vale's uplink, but not through vale. Am I
missing something?
Tagging, checksum-disabling etc. seems to be right, since utilizing
if_bridge(4) gives the expected result, but I have no idea why I can't
get packets via vale(4).
Important note: Using em0.232 parent (vlandev em0) for vale uplink does
work!
So I guess if_em(4)'s native netmap support interferes with the vlan clone.
I'm out at this point, far too less knwoledge about the code paths...
Can anybody else help here?
Thanks,
-harry
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5926F74A.1000101>