[dpdk-dev] olflags in SRIOV VF environment

2013-11-12 Thread Prashant Upadhyaya
Hi guys, I am facing a peculiar issue with the usage of struct rte_mbuf-> ol_flags field in the rte_mbuf when I receive the packets with the rte_eth_rx_burst function. I use the ol_flags field to identify whether is an IPv4 or IPv6 packet or not thus - if ((pkts_burst->ol_flags & PKT_RX_IPV4_HD

[dpdk-dev] Fwd: dpdk-iokit: Turn dpdk into the IO field.

2013-11-12 Thread March Jane
Hi, dpdk folks, I am working on a project which is offering a complete IO stack for dpdk, particularly a SCSI target stack in dpdk ? dpdk-iokit, once I finished my initial code, will upload to github. I would like to know if there is any other people is working on that purpose? - m

[dpdk-dev] olflags in SRIOV VF environment

2013-11-12 Thread Vladimir Medvedkin
Hi Prashant, May be it doesn't work due to Known Issues and Limitations (see Release Notes) quote: 6.1 In packets provided by the PMD, some flags are missing In packets provided by the PMD, some flags are missing. The application does not have access to information provided by the hardware (packe

[dpdk-dev] [PATCH] ixgbe: Fix offloading bits when RX bulk alloc is used.

2013-11-12 Thread Thomas Monjalon
12/11/2013 16:49, Ivan Boule : > On 11/08/2013 08:47 PM, Bryan Benson wrote: > > This is a fix for the ixgbe hardware offload flags not being set when > > bulk alloc RX is used. The issue was caused by masking off the bits that > > store the hardware offload values in the status_error field to retr

[dpdk-dev] raw frame to rte_mbuf

2013-11-12 Thread Jose Gavine Cueto
I see thanks for the tip. Cheers, Pepe On Tue, Nov 12, 2013 at 6:08 PM, Etai Lev-Ran wrote: > Hi Pepe, > > In addition, you may want to consider the frame's lifetime, to ensure > memory > is used and released > in a valid way. > When sending, it may be de-referenced by DPDK and consequently a

[dpdk-dev] [PATCH] ixgbe: Fix offloading bits when RX bulk alloc is used.

2013-11-12 Thread Ivan Boule
On 11/08/2013 08:47 PM, Bryan Benson wrote: > This is a fix for the ixgbe hardware offload flags not being set when bulk > alloc RX is used. The issue was caused by masking off the bits that store the > hardware offload values in the status_error field to retrieve the done bit > for the descript

[dpdk-dev] raw frame to rte_mbuf

2013-11-12 Thread Jose Gavine Cueto
Hi, In DPDK how should a raw ethernet frame converted to rte_mbuf * ? For example if I have an ARP packet: void * arp_pkt how should this be converted to an rte_mbuf * for transmission, does a simple cast suffice ? Cheers, Pepe -- To stop learning is like to stop loving.

[dpdk-dev] DPDK failed to handle intialize VF

2013-11-12 Thread cheng.luo...@hitachi.com
Hi, I am using DPDK for SRIOV. I have one Intel X520 with two PFs. After binding the two PFs to igb_uio, I create two VFs and assign them to a virtual machine. I found that to wake up VF, the VF will send some message to PF such as IXGBE_VF_SET_MACVLAN(0x06) and IXGBE_VF_API_NEGOTIATE(0x08) for t

[dpdk-dev] raw frame to rte_mbuf

2013-11-12 Thread Prashant Upadhyaya
Hi Pepe, Ofcourse a simple cast will not suffice. Please look the rte_mbuf structure in the header files and let me know if you still have the confusion. There is a header and payload. Your raw frame will go in the payload. Regards -Prashant -Original Message- From: dev [mailto:dev-bou

[dpdk-dev] raw frame to rte_mbuf

2013-11-12 Thread Etai Lev-Ran
Hi Pepe, In addition, you may want to consider the frame's lifetime, to ensure memory is used and released in a valid way. When sending, it may be de-referenced by DPDK and consequently a memory free may be tried. Hence, it is important that the raw buffer used for the ARP packet is allocated wit

[dpdk-dev] i210 performance ?

2013-11-12 Thread Armin Steinhoff
Hi All, after porting Intel's Data Plan to QNX 6.5 I'm doing some performance test with "testpmd". I'm using a single i210 board installed on a dual core QNX 6.5 machine and using "testpmd" as a packet generator (UDP packets). The test are done with: start: testpmd -c 3 -n -> interactive mo