Hi Changchun,
Yes, we are trying add some startup parameter when we create VM. But
unfortunately our Guest OS kernel version is too low, it can't work.
# uname -r
2.6.34.13-WR4.3.fp_x86_64_standard-00027-g76285ab
Brs,
Fu Weiyi
-Original Message-
From: ext Ouyang, Changchun
Hi,
With follow changes, the link is UP and interface can receive and send traffic.
Thanks a lot:)
diff --git a/lib/librte_pmd_virtio/virtio_ethdev.c
b/lib/librte_pmd_virtio/virtio_ethdev.c
index 3344ffb..43d1c19 100644
--- a/lib/librte_pmd_virtio/virtio_ethdev.c
+++
Hi,
I have ingnored the link status. Rx and tx can't work.
I will try the methods Vijay suggested to have a try. Thanks!
Brs,
Fu Weiyi
-Original Message-
From: ext Ouyang, Changchun [mailto:changchun.ouy...@intel.com]
Sent: Friday, December 12, 2014 9:00 AM
To: Fu, Weiyi (NSN -
Hi Changchun,
I found you had done follow change to allow the virtio interface startup when
the link is down. Is there any scenario causing link down for virtio interface?
diff --git a/lib/librte_pmd_virtio/virtio_ethdev.c
b/lib/librte_pmd_virtio/virtio_ethdev.c
index 78018f9..4bff0fe 100644
Hi,
The result is still the same.
[root at EIPU-0(KVMCluster) /root]
# ./testpmd -c 3 -n 4 -- --burst=64 -i --txq=1 --rxq=1 --txqflags=0x
EAL: Cannot read numa node link for lcore 0 - using physical package id instead
EAL: Detected lcore 0 as core 0 on socket 0
EAL: Cannot read numa node
Hi,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Fu, Weiyi (NSN -
> CN/Hangzhou)
> Sent: Thursday, December 11, 2014 3:57 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] In DPDK 1.7.1, the link status of the interface using
> virtio
> driver is always
Hi,
We are using the l2fwd based on DPDK 1.7.1 and found out that the link status
of the interface using virtio driver is always down.
Is there any precondition to let the link up?
# ./pci_unbind.py --status
Network devices using IGB_UIO driver
:00:04.0
Hi,
I have seen this issue happen on older kernels like 2.6.32-220.el6.x86_64
while it works with no issues on a recent kernel like 3.10.x.
Further, I found this issue was happening due to
/sys/bus/pci/devices//msi_irqs dir not being enumerated in
older kernels resulting in
hw->use_msix=0. This
8 matches
Mail list logo