For the SKB function change I had to change the ifdef in the kcompat.h file
around line 3848 (I think) to:
/* Changed the next line to use (3,13,8) instead of (3,14,0) KeithW */
#if ( LINUX_VERSION_CODE < KERNEL_VERSION(3,13,8) )
#if (!(RHEL_RELEASE_CODE && RHEL_RELEASE_CODE >= RHEL_RELEASE_
On Thu, Aug 14, 2014 at 06:15:24PM -0400, Aws Ismail wrote:
>
> On 08/14/2014 05:44 PM, Qiaobing Xie wrote:
> >Hi,
> >
> >I got the following error when I tried to compile 1.7.0 release tarball on
> >a Linux box (Ubuntu 12.04/kernel=3.13.0-32-generic, gcc=4.6.3):
> >
> >
> >In file inc
Nail,
Thanks for the info... I got v1.7.0 tarball compile after configuring
out both IXGBE_INC_VECTOR and ACL. I will take a look at the head.
-Q
On 8/14/14 7:16 PM, Neil Horman wrote:
> On Thu, Aug 14, 2014 at 06:15:24PM -0400, Aws Ismail wrote:
>> On 08/14/2014 05:44 PM, Qiaobing Xie wrote:
>
OK, I made the following 3 changes and the v1.7.0 release tarball got
built cleanly on my older machine (Ubuntu 12.04/kernel
3.13.0-32-generic, Intel C2D E6550 without SSE4.x, gcc 4.6.3):
1) kcompat.h change version check from 3.14.0 -> 3.13.8, as Roger suggested.
2) disable RTE_IXGBE_INC_VECTO
On 08/14/2014 05:55 PM, Wiles, Roger Keith wrote:
> For the SKB function change I had to change the ifdef in the kcompat.h file
> around line 3848 (I think) to:
>
> /* Changed the next line to use (3,13,8) instead of (3,14,0) KeithW */
> #if ( LINUX_VERSION_CODE < KERNEL_VERSION(3,13,8) )
>
On 08/14/2014 05:44 PM, Qiaobing Xie wrote:
> Hi,
>
> I got the following error when I tried to compile 1.7.0 release
> tarball on a Linux box (Ubuntu 12.04/kernel=3.13.0-32-generic,
> gcc=4.6.3):
>
>
> In file included from
> /home/qxie/dpdk-1.7.0/lib/librte_eal/linuxapp/kni/ethto
Aws,
Thanks, I will move to v1.7.0-rc4 and get it a try...
-Q
On 8/14/14 5:24 PM, Aws Ismail wrote:
>
>
> On 08/14/2014 05:55 PM, Wiles, Roger Keith wrote:
>> For the SKB function change I had to change the ifdef in the
>> kcompat.h file around line 3848 (I think) to:
>>
>> /* Changed the
v3 change:
- Investigate the comments from Huawei and fix one potential issue of wrong
offset to
the number of descriptor in buffer; also fix other tiny comments.
v2 change:
- Resolve conflicts with the tip code;
- And resolve 2 issues:
-- fix mbuf leak when discard an uncompleted packet.
Hi,
I got the following error when I tried to compile 1.7.0 release tarball
on a Linux box (Ubuntu 12.04/kernel=3.13.0-32-generic, gcc=4.6.3):
In file included from
/home/qxie/dpdk-1.7.0/lib/librte_eal/linuxapp/kni/ethtool/igb/e1000_osdep.h:41:0,
from
/home/qxie/dpdk-1.7.0/lib/lib
From: "Chen Jing D(Mark)"
VF driver to add per-queue RX/TX start/stop function. Support
field start_rx_per_q in rx_queue_setup and start_tx_per_q in
tx_queue_setup. In the meanwhile, Change dev_start/stop function
to call per-queue RX/TX function.
Signed-off-by: Chen Jing D(Mark)
Reviewed-by: K
From: "Chen Jing D(Mark)"
PF driver to support field start_rx_per_q in i40e_dev_rx_queue_setup
and start_tx_per_q in i40e_dev_tx_queue_setup. In the meanwhile,
Change dev_start/stop function to call per-queue RX/TX function.
Signed-off-by: Chen Jing D(Mark)
Reviewed-by: Konstantin Ananyev
Revi
From: "Chen Jing D(Mark)"
I40E driver add function pointer to start/stop specific RX/TX queue.
Signed-off-by: Chen Jing D(Mark)
Reviewed-by: Konstantin Ananyev
Reviewed-by: Changchun Ouyang
Reviewed-by: Huawei Xie
---
lib/librte_pmd_i40e/i40e_ethdev.c |4 +
lib/librte_pmd_i40e/i40e_rxtx
From: "Chen Jing D(Mark)"
rte_ether library provide function pointer to start/stop specific
RX/TX queue, NIC driver also implemented functions. This change
adds command in testpmd to start/stop specific RX/TX queue.
Signed-off-by: Chen Jing D(Mark)
Reviewed-by: Konstantin Ananyev
Reviewed-by:
From: "Chen Jing D(Mark)"
This patch mainly includes 2 changes. One is in testpmd to add command
testing specific RX/TX queue start/stop in Port X. Another change is in
i40e, which implemented rx/tx_queue_start/stop in both PF and VF driver.
In the meanwhile, support field start_rx_per_q in i40e_
i40e was failing to run in XEN domain0, as the physical
memory for adminq DMA should be allocated and translated
in a different way for XEN domain0. So
rte_memzone_reserve_bounded() should be used for DMA
memory allocation, and rte_mem_phy2mch() should be used
for DMA memory address translation to
Hello,
I'm trying to configure the flow director of VF 82599 port using
rte_eth_dev_fdir_add_signature_filter ().
The function returns with ENOTSUP.
Doe's flow director supported for VF ?
What can be the reason for ENOTSUP ?
Thanks,
Ilan B
I will verified this next week. :)
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Chen Jing D(Mark)
Sent: Thursday, August 14, 2014 3:35 PM
To: dev at dpdk.org
Subject: [dpdk-dev] [PATCH 2/4] i40e: PF Add support for per-queue start/stop
From: "Chen Jing D(Mark)"
> i40e was failing to run in XEN domain0, as the physical
> memory for adminq DMA should be allocated and translated
> in a different way for XEN domain0. So
> rte_memzone_reserve_bounded() should be used for DMA
> memory allocation, and rte_mem_phy2mch() should be used
> for DMA memory address tr
18 matches
Mail list logo
