[dpdk-dev] How to know corresponding device from port number

> [BR] Firstly, to identify the ring PMD's vs the ethernet device PMDs you can > use the information in the rte_eth_dev structure. For each device x, (0 <= x > <=5), if you check rte_eth_devices[x], the ring pmd's will have a NULL driver > pointer and the pci address given in the pci_dev structu

[dpdk-dev] Regarding VM live migration with SRIOV

Hi, Let me be more specific. Does DPDK support hot plugin/plugout of PCI devices ? What typically needs to be done if this is to be achieved inside an application. Typically, the NIC PF or VF appears to the DPDK application as a PCI device which is probed at startup. Now what happens if I insert

[dpdk-dev] Regarding VM live migration with SRIOV

Hi Stephen, The rte_eal_pci_probe is typically called at the startup. Now let's say a DPDK application is running with a PCI device (doing tx and rx) and I remove that PCI device underneath (hot plugout) So how does the application now know that the device is gone ? Is it that rte_eal_pci_probe

[dpdk-dev] Cannot run l3fwd with the problem of " nb_tx_queues"

Hi, I also have the same question in l3fwd example. I guess may DPDK don't support the chip-set so that we got this error msg. In my system, I have 2 kinds of chip-set, 82580 & 82574L. If I use l3fwd -c 3 -n 1 -- -p 3 --config '(0,0,0),(1,0,1)' in 82574L, it will get the error msg. But when I cha

[dpdk-dev] Cannot run l3fwd with the problem of " nb_tx_queues"

Hello, 27/11/2013 11:58, Zachary.Jen (???) : 6305 : > I also have the same question in l3fwd example. > I guess may DPDK don't support the chip-set so that we got this error msg. > > In my system, I have 2 kinds of chip-set, 82580 & 82574L. > If I use l3fwd -c 3 -n 1 -- -p 3 --config '(0,0,0),(1,

[dpdk-dev] Cannot run l3fwd with the problem of " nb_tx_queues"

Hi yuxuan, Yes, by experience I've successfully run dpdk with a virtualbox vm using an e1000 NIC. I'm not totally sure about the capabilities of the e1000 NIC but based on the error you've mentioned, it seems that it can only support 1 TX queue. "Now, I can use only one logic core to run the app

[dpdk-dev] Cannot run l3fwd with the problem of " nb_tx_queues"

Hi, The problem is that E1000 NIC only support 1 TX queue ,the dpdk will change the max TX queue number in eth_em_infos_get() function the when you call the rte_eth_dev_configure() function .If you want to run l3fwd program on e1000 NIC correctly, you should modify the l3fwd by using only one TX

[dpdk-dev] Sporadic errors while initializing NICs in example applications, dpdk-1.5.0r1

Looks like I finally found the reason. After applying this patch I can no longer reproduce the error. diff --git a/lib/librte_pmd_ixgbe/ixgbe/ixgbe_82599.c b/lib/librte_pmd_ixgbe/ixgbe/ixgbe_82599.c index db07789..5f825fa 100644 --- a/lib/librte_pmd_ixgbe/ixgbe/ixgbe_82599.c +++ b/lib/librte_pmd

[dpdk-dev] Sporadic errors while initializing NICs in example applications, dpdk-1.5.0r1

I had exactly same problem and fixed it with same patch since release 1.4. But somehow it stopped to appear even without the patch. I have no idea what I have done since both the kernel and the driver have been updated during these days. On Wed, Nov 27, 2013 at 4:06 PM, Dmitry Vyal wrote: > Looks

[dpdk-dev] Sporadic errors while initializing NICs in example applications, dpdk-1.5.0r1

27/11/2013 15:06, Dmitry Vyal : > Looks like I finally found the reason. After applying this patch I can > no longer reproduce the error. > > --- a/lib/librte_pmd_ixgbe/ixgbe/ixgbe_82599.c > +++ b/lib/librte_pmd_ixgbe/ixgbe/ixgbe_82599.c > /* Wait for AN to leave state 0 */ > - for

[dpdk-dev] Increasing number of txd and rxd from 256 to 1024 for virtio-net-pmd-1.1

Can you share your virtio driver with me ? Do you mean to create multiple queues, each has 256 txd/rxd ? The packets could be stored into the freeslots in those queues. But how can the virtio pmd codes feed the slots down to the hardware to deliver them ? The other question is that I was using vh