From: Nishant Verma <vnish11@gmail.com>
To: dev@dpdk.org, "Lu, Wenzhuo" <wenzhuo.lu@intel.com>,
vnish11 <vnish11@gmail.com>
Subject: [dpdk-dev] LINUX VF
Date: Mon, 30 Oct 2017 18:33:20 -0400 [thread overview]
Message-ID: <CAHhCjUGpMrZ9NQzLjWdSH4poOO4Ah9MHMXT4F7jCuQHoY1Pojg@mail.gmail.com> (raw)
Hi,
I am trying to configure SRIOV on my SUPERMICRO BLADES.
I assigned 10G NIC to igb_uio. After that created 4 VF's.
Out of 4 VF's, 3 are used by DPDK App and one I am assigning to Linux
kernel.
Now when I am assigning IP to a virtual interface on top of Linux VF after
PF is up. The first time it takes the IP but internally it just goes down
and comes up again. That basically leads to change in MAC address of the
virtual interface VF.
After this, i am not able to send or receive any packet on a virtual
interface on top of linuxVF. If I down everything on Linux side, then UP
the interface and re-create the virtual on top of Linux VF then things
works, becuase, in this case, MAC address of both the VF and virtual
interface on top of VF are same.
My Question is, Why linuxVF is going down? How can i stop it or can have
same MAC address every time?
---
This is when i assigned interface to linux VF
[root@localhost aavila]# ifconfig enp2s16f7
enp2s16f7: flags=4098<BROADCAST,MULTICAST> mtu 1500
ether 02:7f:48:b1:a7:b9 txqueuelen 1000 (Ethernet)
RX packets 0 bytes 0 (0.0 B)
RX errors 0 dropped 0 overruns 0 frame 0
TX packets 0 bytes 0 (0.0 B)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
----
After creating virtual NIC and assigning IP
7: enp2s16f7: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP
qlen 1000
link/ether f6:45:8f:03:ba:1a brd ff:ff:ff:ff:ff:ff
inet6 fe80::f445:8fff:fe03:ba1a/64 scope link
valid_lft forever preferred_lft forever
8: vlan2034@enp2s16f7: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc
noqueue state UP
link/ether f6:45:8f:03:ba:1a brd ff:ff:ff:ff:ff:ff
inet 10.31.226.6/20 scope global vlan2034
valid_lft forever preferred_lft forever
inet6 fe80::f445:8fff:fe03:ba1a/64 scope link
valid_lft forever preferred_lft forever
---------
After some seconds...
7: enp2s16f7: <BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq state UP qlen 1000
link/ether 02:7f:48:b1:a7:b9 brd ff:ff:ff:ff:ff:ff
8: vlan2034@enp2s16f7: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc
noqueue state UP
link/ether f6:45:8f:03:ba:1a brd ff:ff:ff:ff:ff:ff
inet 10.31.226.6/20 scope global vlan2034
valid_lft forever preferred_lft forever
----
Here is the dmesg output :
[ 320.341653] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 320.341686] ixgbevf 0000:02:10.7: NIC Link is Down
[ 322.338665] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 323.340775] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 324.341407] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 324.341428] ixgbevf 0000:02:10.7: NIC Link is Down
[ 326.338448] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 327.340536] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 328.341172] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 328.341194] ixgbevf 0000:02:10.7: NIC Link is Down
[ 328.341252] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 329.342992] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 330.343652] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 330.343698] ixgbevf 0000:02:10.7: NIC Link is Down
[ 330.343770] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 331.344292] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 333.344258] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 334.344630] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 334.344653] ixgbevf 0000:02:10.7: NIC Link is Down
[ 336.341439] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 380.276206] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 381.276826] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 381.276849] ixgbevf 0000:02:10.7: NIC Link is Down
[ 381.385871] IPv6: ADDRCONF(NETDEV_UP): enp2s16f7: link is not ready
[ 381.385874] 8021q: adding VLAN 0 to HW filter on device enp2s16f7
[ 381.386386] device enp2s16f7 entered promiscuous mode
[ 381.394896] IPv6: ADDRCONF(NETDEV_UP): vlan2034: link is not ready
[ 382.343248] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 382.353248] IPv6: ADDRCONF(NETDEV_CHANGE): vlan2034: link becomes ready
[ 383.353628] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 384.354004] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 385.354582] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 386.354958] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 386.355252] IPv6: ADDRCONF(NETDEV_CHANGE): enp2s16f7: link becomes ready
[ 387.355899] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 388.356533] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 389.357654] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 390.358357] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 391.359263] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 392.359965] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 393.362737] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 393.362993] ixgbevf 0000:02:10.7: NIC Link is Down
[ 394.357568] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 395.359945] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 395.360161] ixgbevf 0000:02:10.7: NIC Link is Down
[ 395.360205] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
[ 397.355218] ixgbevf 0000:02:10.7 enp2s16f7: Polling for VF0 mailbox ack
timedout
[ 397.355433] ixgbevf 0000:02:10.7: NIC Link is Down
[ 398.354374] ixgbevf 0000:02:10.7: NIC Link is Up 10 Gbps
Rgds,
Nishant
next reply other threads:[~2017-10-30 22:33 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-30 22:33 Nishant Verma [this message]
2017-11-03 13:57 ` Nishant Verma
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAHhCjUGpMrZ9NQzLjWdSH4poOO4Ah9MHMXT4F7jCuQHoY1Pojg@mail.gmail.com \
--to=vnish11@gmail.com \
--cc=dev@dpdk.org \
--cc=wenzhuo.lu@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).