On Tue, Mar 21, 2017 at 08:38:25PM +, Eads, Gage wrote:
>
>
> > -Original Message-
> > From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com]
> > Sent: Tuesday, March 21, 2017 6:06 AM
> > To: Eads, Gage
> > Cc: dev@dpdk.org; Richardson, Bruce ;
> > hemant.agra...@nxp.com; Va
On Mon, Mar 20, 2017 at 07:32:45AM +, Liu, Changpeng wrote:
> > diff --git a/lib/librte_vhost/rte_virtio_net.h
> > b/lib/librte_vhost/rte_virtio_net.h
> > index fa98d29..e19ebad 100644
> > --- a/lib/librte_vhost/rte_virtio_net.h
> > +++ b/lib/librte_vhost/rte_virtio_net.h
> > @@ -42,14 +42,10
Hi Hemant,
The 03/17/2017 18:17, Hemant Agrawal wrote:
> DPAA2 Hardware Mempool handlers allow enqueue/dequeue from NXP's
> QBMAN hardware block.
> CONFIG_RTE_MBUF_DEFAULT_MEMPOOL_OPS is set to 'dpaa2', if the pool
> is enabled.
>
> This memory pool currently supports packet mbuf type blocks only.
Also Yuanhuan, your suggestion about the hugepage mapping / clearing memory
was great .. I tried a test where I just wrote random values into the
entire hugepage area and that succesfully crashed the ovs on the host :).
So thats a good test to generally ensure that the guest doesnt mess up the
host
Super trivial comment inline:
On Tuesday 21 March 2017 09:38 PM, Anatoly Burakov wrote:
From: "Burakov, Anatoly"
Fixing compile failures for kernels without sPAPR IOMMU support.
Fixes: 0fe9830b5345 ("eal/ppc: support sPAPR IOMMU for vfio-pci")
Signed-off-by: Burakov, Anatoly
---
lib/librte_
Lthread is awesome but it doesn't support C++.
So I write patch to support lthread to support C++.
Added "extern C {}" to lthread-headers
Signed-off-by: Hiroki SHIROKURA
Acked-by: Keith Wiles
---
examples/performance-thread/common/arch/x86/ctx.h | 8
examples/performance-thread/com
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, March 21, 2017 11:54 PM
> To: Zhang, Qi Z ; Wu, Jingjing ;
> Zhang, Helin
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 3/3] app/testpmd: add CL for ptype mapping
> configure
>
> On 3/17/2017 10:45 AM, Qi Zhang wrote:
On Tue, 21 Mar 2017 20:13:48 -0400
Ed Czeck wrote:
> Hi Stephen,
>
> Yes I understand the paranoid issue of volatile modifier, which is the
> reason it was coded in this manner.
>
> The struct with volatile are memory mapped IO structures. These structure
> are not instantiated in memory and h
From: Alex Zelezniak
---
drivers/net/ixgbe/ixgbe_ethdev.c | 33 +
drivers/net/ixgbe/rte_pmd_ixgbe.h | 16
2 files changed, 49 insertions(+)
diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/ixgbe_ethdev.c
index 7169007..c78e5da 1
Hi Stephen,
Yes I understand the paranoid issue of volatile modifier, which is the
reason it was coded in this manner.
The struct with volatile are memory mapped IO structures. These structure
are not instantiated in memory and hence do not incur concurrent (host)
software access. The a vast ma
On Tue, 21 Mar 2017 17:43:36 -0400
Ed Czeck wrote:
> + volatile uint32_t ctrl;
> + volatile uint32_t stats_clear;
> + volatile uint32_t cplh_max;
You are using a lot of 'volatile' in this driver.
In general volatile should be reserved for known software shared data structures
rather
* Flesh out device configuration
* Add links dev_ops
* allow dynamic extension loading
Signed-off-by: Shepard Siegel
Signed-off-by: John Miller
Signed-off-by: Ed Czeck
---
drivers/net/ark/ark_ethdev.c | 737 ++-
drivers/net/ark/ark_ext.h| 79 +
* Core RX packet moving functions
Signed-off-by: Ed Czeck
---
drivers/net/ark/Makefile| 1 +
drivers/net/ark/ark_ethdev_rx.c | 681
drivers/net/ark/ark_ethdev_rx.h | 67
3 files changed, 749 insertions(+)
create mode 100644 drivers/net/ar
* Core TX packet moving functions
* Flesh out ark_adapter struct to support TX code
(not all fields used at this patch
Signed-off-by: Ed Czeck
---
drivers/net/ark/Makefile| 1 +
drivers/net/ark/ark_ethdev.c| 14 ++
drivers/net/ark/ark_ethdev.h| 2 +-
drivers/net/ark/ark_ethd
Provide C-level interface for Arkville's internal HW resources
pktgen and pktchk modules
Signed-off-by: Ed Czeck
---
drivers/net/ark/Makefile | 2 +
drivers/net/ark/ark_pktchkr.c | 472
drivers/net/ark/ark_pktchkr.h | 114 ++
drivers/net/ar
Provide C-level interface for Arkville's internal HW resources
ddm and udm modules
Signed-off-by: Ed Czeck
---
drivers/net/ark/Makefile | 2 +
drivers/net/ark/ark_ddm.c | 151 +++
drivers/net/ark/ark_ddm.h | 154 +++
drivers/net/ark/ark_
Provide C-level interface for Arkville's internal HW resources
mpu, pktdir, and rqp modules
Signed-off-by: Ed Czeck
---
drivers/net/ark/Makefile | 3 +
drivers/net/ark/ark_mpu.c| 181 +++
drivers/net/ark/ark_mpu.h| 143 +++
Enable Arkville on supported configurations
Add overview documentation
Minimum driver support for valid compile
Signed-off-by: Ed Czeck
---
MAINTAINERS | 8 +
config/common_base | 11 ++
config/defconfig_arm-armv7a-linuxapp-gcc|
> -Original Message-
> From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com]
> Sent: Tuesday, March 21, 2017 6:06 AM
> To: Eads, Gage
> Cc: dev@dpdk.org; Richardson, Bruce ;
> hemant.agra...@nxp.com; Van Haaren, Harry ;
> nipun.gu...@nxp.com
> Subject: Re: [PATCH v4] eventdev
> On Mar 21, 2017, at 12:03 PM, Hiroki SHIROKURA wrote:
>
> Lthread is awesome but it doesn't support C++.
> So I write patch to support lthread to support C++.
> Added "extern C {}" to lthread-headers
>
> Signed-off-by: Hiroki SHIROKURA
Acked-by: Keith Wiles
> ---
> examples/performance-th
The FreeBSD implementation wasn't registering new devices
with the device framework on start up. However, common
code attempts to unregister them on shutdown which causes
a SEGFAULT. This fix makes the FreeBSD code do the same
thing as the Linux code for registration.
Signed-off-by: Ben Walker
--
When configuring Rx/Tx queue, if queue already exists, it is reused. But if
the queue size is changed, it must be resized to not access/overwrite
invalid memory.
Fixes: 2e22920b85d9 ("mlx5: support non-scattered Tx and Rx")
CC: sta...@dpdk.org
Signed-off-by: Yongseok Koh
---
v2:
* fix typo and
> -Original Message-
> From: Doherty, Declan
> Sent: Monday, March 20, 2017 3:28 PM
> To: Zhang, Roy Fan; dev@dpdk.org
> Cc: De Lara Guarch, Pablo; Gonzalez Monroy, Sergio
> Subject: Re: [PATCH] crypto/scheduler: optimize crypto op ordering
>
> On 02/03/17 14:18, Fan Zhang wrote:
> > Thi
> -Original Message-
> From: Doherty, Declan
> Sent: Monday, March 20, 2017 2:18 PM
> To: Zhang, Roy Fan; dev@dpdk.org
> Cc: De Lara Guarch, Pablo; Gonzalez Monroy, Sergio
> Subject: Re: [PATCH] crypto/scheduler: change enqueue and dequeue
> functions
>
> On 02/03/17 11:12, Fan Zhang wro
> So, I'll send a patch soon.
I wrote a patch to suport c++ in L-thread
Patch is bellow. please review this.
http://dpdk.org/ml/archives/dev/2017-March/060809.html
thank you.
2017年3月22日(水) 0:53 Hiroki Shirokura :
> > I believe adding the C++ ifdefs is reasonable. Please send a patch for
> th
On 3/15/2017 2:54 PM, Pascal Mazon wrote:
> Supported flow rules are now mapped to TC rules on the tap netdevice.
> The netlink message used for creating the TC rule is stored in struct
> rte_flow. That way, by simply changing a metadata in it, we can require
> for the rule deletion without further
Lthread is awesome but it doesn't support C++.
So I write patch to support lthread to support C++.
Added "extern C {}" to lthread-headers
Signed-off-by: Hiroki SHIROKURA
---
examples/performance-thread/common/arch/x86/ctx.h | 8
examples/performance-thread/common/lthread.h
On Tue, 21 Mar 2017 15:32:06 +
"Wiles, Keith" wrote:
>
> Just noticed this new header does not have the C++ ifdefs. Create a
> new patch to fix this problem, unless you need to update this patch
> series. Just starting my review of this one, sorry was traveling last
> week.
>
> Regards,
> K
Firewall ACL definition need to use same input index for source and
destination ports as these are 16 bits and would fit in one ACL
field of 32 bits. This is required as per librte_acl API. Without this
UDP/TCP source and destination ports filtering (and for that
matter ICMP type/code filtering) do
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of De Lara Guarch,
> Pablo
> Sent: Monday, March 06, 2017 2:08 PM
> To: Kulasek, TomaszX; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] app/crypto-perf: fix uninitialized values for
> null operations
>
>
>
> > --
From: "Burakov, Anatoly"
Fixing compile failures for kernels without sPAPR IOMMU support.
Fixes: 0fe9830b5345 ("eal/ppc: support sPAPR IOMMU for vfio-pci")
Signed-off-by: Burakov, Anatoly
---
lib/librte_eal/linuxapp/eal/eal_vfio.h | 13 +
1 file changed, 13 insertions(+)
diff --gi
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, March 03, 2017 7:49 PM
> To: dev@dpdk.org
> Cc: thomas.monja...@6wind.com; Doherty, Declan; De Lara Guarch, Pablo;
> Mcnamara, John; nhor...@tuxdriver.com; hemant.agra...@nxp.com;
> Akhil Goyal; Cristian
On 3/21/2017 3:12 PM, Keith Wiles wrote:
> When polling the bonded ports for RX packets the old driver would
> always start with the first slave in the list. If the requested
> number of packets is filled on the first port in a two port config
> then the second port could be starved or have larger
On 3/21/2017 10:43 AM, Alejandro Lucero wrote:
> When LSO, not doing this can led to firmware disruption. It does
> not show as error because TCP ends up sending data again later on.
>
> Fixes: 9ba3d0ae2090 (\"net/nfp: add TSO support\")
>
> Signed-off-by: Alejandro Lucero
Series applied to dpd
> I believe adding the C++ ifdefs is reasonable. Please send a patch for
the changes.
Thank you for your reply.
So, I'll send a patch soon.
2017年3月22日(水) 0:51 Wiles, Keith :
>
> > On Mar 21, 2017, at 7:11 AM, Hiroki Shirokura
> wrote:
> >
> > Hi,
> >
> > This is Hiroki SHIROKURA, japanese stude
On 3/17/2017 10:45 AM, Qi Zhang wrote:
> Add below command line to configure ptype mapping.
> ptype mapping get .
> ptype mapping replace.
> ptype mapping reset .
> ptype mapping update .
>
> Signed-off-by: Qi Zhang
<...>
> +static void
> +cmd_ptype_mapping_get_parsed(
> + void *pars
> On Mar 21, 2017, at 7:11 AM, Hiroki Shirokura wrote:
>
> Hi,
>
> This is Hiroki SHIROKURA, japanese student
> I'm researching High-Performance-Networking using DPDK
> and L-thread.
>
> L-thread is awesome, but it doesn't support C++.
> If we want use lthread with C++, we must add only
> "ex
> On Mar 15, 2017, at 9:54 AM, Pascal Mazon wrote:
>
> This series add support for the flow API in tap PMD.
>
> It enables filtering specific packets incoming on the tap netdevice, to
> process only desired ones. Under the hood, it uses kernel TC (traffic
> control), which takes place very earl
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, March 03, 2017 7:49 PM
> To: dev@dpdk.org
> Cc: thomas.monja...@6wind.com; Doherty, Declan; De Lara Guarch, Pablo;
> Mcnamara, John; nhor...@tuxdriver.com; hemant.agra...@nxp.com;
> Akhil Goyal
> Subject
> On Mar 15, 2017, at 9:54 AM, Pascal Mazon wrote:
>
> The flow API provides the ability to classify packets received by a tap
> netdevice.
>
> This patch only implements skeleton functions for flow API support, no
> patterns are supported yet.
>
> Signed-off-by: Pascal Mazon
> Acked-by: Olga
> On Mar 15, 2017, at 9:54 AM, Pascal Mazon wrote:
>
> In the next patch, access to struct pmd_internals will be necessary in
> tap_flow.c to store the flows.
>
> Signed-off-by: Pascal Mazon
> Acked-by: Olga Shern
> ---
> drivers/net/tap/Makefile | 1 +
> drivers/net/tap/rte_eth_tap.c |
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, March 03, 2017 7:50 PM
> To: dev@dpdk.org
> Cc: thomas.monja...@6wind.com; Doherty, Declan; De Lara Guarch, Pablo;
> Mcnamara, John; nhor...@tuxdriver.com; hemant.agra...@nxp.com;
> Akhil Goyal
> Subject
On 3/20/2017 1:18 PM, Shepard Siegel wrote:
Hi Shepard,
> We feel it would complicate things to pull the net/ark PMD into still-smaller
> pieces.
Why do you think smaller patches would complicate things?
I agree that will require some effort, but I believe that can help
others to understand, re
When polling the bonded ports for RX packets the old driver would
always start with the first slave in the list. If the requested
number of packets is filled on the first port in a two port config
then the second port could be starved or have larger number of
missed packet errors.
The code attempt
Hi Akhil,
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, March 03, 2017 7:49 PM
> To: dev@dpdk.org
> Cc: thomas.monja...@6wind.com; Doherty, Declan; De Lara Guarch, Pablo;
> Mcnamara, John; nhor...@tuxdriver.com; hemant.agra...@nxp.com;
> Akhil Goyal
On 3/21/2017 2:38 PM, Jerin Jacob wrote:
> On Tue, Mar 21, 2017 at 02:31:41PM +, Ferruh Yigit wrote:
>> On 3/20/2017 2:10 PM, Jerin Jacob wrote:
>>> - bgx_link_status mbox definition was changed in Linux
>>> commit 1cc702591bae ("net: thunderx: Add ethtool support")
>>> - NIC_MBOX_MSG_RES_BIT r
> On Mar 21, 2017, at 4:54 AM, Julien Castets wrote:
>
> From: Julien Castets
>
> Signed-off-by: Julien Castets
> ---
> app/pktgen.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/app/pktgen.c b/app/pktgen.c
> index e315bff..9a304c0 100644
> --- a/app/pktgen.c
> +++
> On Mar 21, 2017, at 1:25 AM, Shreyansh Jain wrote:
>
> Hello Keith,
>
> On Tuesday 21 March 2017 11:32 AM, Wiles, Keith wrote:
>>
>>> On Mar 20, 2017, at 11:55 PM, Shreyansh Jain wrote:
>>>
>>> Hello David,
>>>
>>> On Monday 20 March 2017 08:20 PM, Hunt, David wrote:
On 20/3/20
The DPDK will still try to allocate contiguous hugepages.
Since DPDK v16.07 the mempool library is able to create a mempool with
multiple chunks of memory.
You would still have the contig memory restriction for any other DPDK
library or app.
Are you pre-allocating hugepages on boot (kernel cmd
On Tue, Mar 21, 2017 at 02:31:41PM +, Ferruh Yigit wrote:
> On 3/20/2017 2:10 PM, Jerin Jacob wrote:
> > - bgx_link_status mbox definition was changed in Linux
> > commit 1cc702591bae ("net: thunderx: Add ethtool support")
> > - NIC_MBOX_MSG_RES_BIT related changes were never part of Linux PF d
This patch provides a set of tests for verifying the functional
correctness of 16-bit and 32-bit CRC APIs.
Signed-off-by: Jasvinder Singh
---
test/test/Makefile | 2 +
test/test/test_crc.c | 223 +++
2 files changed, 225 insertions(+)
create m
APIs for selecting the architecure specific implementation and computing
the crc (16-bit and 32-bit CRCs) are added. For CRCs calculation, scalar
as well as x86 intrinsic(sse4.2) versions are implemented.
The scalar version is based on generic Look-Up Table(LUT) algorithm,
while x86 intrinsic vers
In some applications, CRC (Cyclic Redundancy Check) needs to be computed
or updated during packet processing operations. This patchset adds
software implementation of some common standard CRCs (32-bit Ethernet
CRC as per Ethernet/[ISO/IEC 8802-3] and 16-bit CCITT-CRC [ITU-T X.25]).
Two versions of
Hi Fan,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Fan Zhang
> Sent: Tuesday, February 21, 2017 2:30 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo
> Subject: [dpdk-dev] [PATCH] crypto/scheduler: add mode specific option
> support
>
> Some scheduling mo
On 3/20/2017 2:10 PM, Jerin Jacob wrote:
> - bgx_link_status mbox definition was changed in Linux
> commit 1cc702591bae ("net: thunderx: Add ethtool support")
> - NIC_MBOX_MSG_RES_BIT related changes were never part of Linux PF driver
>
> Signed-off-by: Jerin Jacob
<...>
> @@ -157,6 +151,7 @@ s
Yes. That is right Srinivas.
Ferruh, thanks for pointing to the supported device list.
Thanks
-Ajit
On Tue, Mar 21, 2017 at 6:36 AM, Srinivasreddy R <
srinivasreddy4...@gmail.com> wrote:
> Thank you so much for your quick reply .
>
>
> On Tue, Mar 21, 2017 at 4:40 PM, Ferruh Yigit
> wrote:
>
>
Hi,
Recently after moving to 4.4 Linux kernel we found that DPDK v16.07
can't find physically contiguous chunk of hugepages memory.
I've tracked this down to kernel commits
81c0a2bb515f ("mm: page_alloc: fair zone allocator policy")
fff4068cba48 ("mm: page_alloc: revert NUMA aspect of fair all
On 3/21/2017 1:56 PM, Shijith Thotton wrote:
> On Tue, Mar 21, 2017 at 01:01:58PM +, Ferruh Yigit wrote:
>> On 3/21/2017 12:53 PM, Shijith Thotton wrote:
>>> On Tue, Mar 21, 2017 at 12:24:49PM +, Ferruh Yigit wrote:
On 3/2/2017 11:32 AM, Shijith Thotton wrote:
> Signed-off-by: Shij
On Tue, Mar 21, 2017 at 01:01:58PM +, Ferruh Yigit wrote:
> On 3/21/2017 12:53 PM, Shijith Thotton wrote:
> > On Tue, Mar 21, 2017 at 12:24:49PM +, Ferruh Yigit wrote:
> >> On 3/2/2017 11:32 AM, Shijith Thotton wrote:
> >>> Signed-off-by: Shijith Thotton
> >>> Signed-off-by: Jerin Jacob
>
On 3/7/2017 10:39 PM, Keith Wiles wrote:
> When polling the bonded ports for RX packets the old driver would
> always start with the first slave in the list. If the requested
> number of packets is filled on the first port in a two port config
> then the second port could be starved or have larger
On 3/21/2017 12:53 PM, Shijith Thotton wrote:
> On Tue, Mar 21, 2017 at 12:24:49PM +, Ferruh Yigit wrote:
>> On 3/2/2017 11:32 AM, Shijith Thotton wrote:
>>> Signed-off-by: Shijith Thotton
>>> Signed-off-by: Jerin Jacob
>>> Signed-off-by: Derek Chickles
>>> Signed-off-by: Venkat Koppula
>>>
On Tue, Mar 21, 2017 at 12:24:49PM +, Ferruh Yigit wrote:
> On 3/2/2017 11:32 AM, Shijith Thotton wrote:
> > Signed-off-by: Shijith Thotton
> > Signed-off-by: Jerin Jacob
> > Signed-off-by: Derek Chickles
> > Signed-off-by: Venkat Koppula
> > Signed-off-by: Srisivasubramanian S
> > Signed-
On 3/2/2017 11:32 AM, Shijith Thotton wrote:
> The patch series provides initial version of virtual function poll mode
> driver for Cavium LiquidIO II server adapters. This version adds support
> for LiquidIO II CN23XX 210SV adapters.
>
> Patch series includes driver documentation doc/guides/nics/
On 3/2/2017 11:32 AM, Shijith Thotton wrote:
> Added doc/guides/nics/liquidio.rst and
> doc/guides/nics/features/liquidio.ini. Updated release notes.
>
> Signed-off-by: Shijith Thotton
> Signed-off-by: Jerin Jacob
> Signed-off-by: Derek Chickles
> Signed-off-by: Venkat Koppula
> Signed-off-by:
On 3/2/2017 11:32 AM, Shijith Thotton wrote:
> Signed-off-by: Shijith Thotton
> Signed-off-by: Jerin Jacob
> Signed-off-by: Derek Chickles
> Signed-off-by: Venkat Koppula
> Signed-off-by: Srisivasubramanian S
> Signed-off-by: Mallesham Jatharakonda
<...>
>
> static int
> +lio_dev_change_
Acking the correct version of the patch this time.
On 07/03/2017 10:39 PM, Keith Wiles wrote:
When polling the bonded ports for RX packets the old driver would
always start with the first slave in the list. If the requested
number of packets is filled on the first port in a two port config
then
On 07/03/2017 10:27 PM, Keith Wiles wrote:
When polling the bonded ports for RX packets the old driver would
always start with the first slave in the list. If the requested
number of packets is filled on the first port in a two port config
then the second port could be starved or have larger numb
Hi,
This is Hiroki SHIROKURA, japanese student
I'm researching High-Performance-Networking using DPDK
and L-thread.
L-thread is awesome, but it doesn't support C++.
If we want use lthread with C++, we must add only
"extern C {}" like a below's commit.
https://github.com/susanow/lthread
https:/
Thank you so much for your quick reply .
On Tue, Mar 21, 2017 at 4:40 PM, Ferruh Yigit
wrote:
> On 3/21/2017 11:01 AM, Srinivasreddy R wrote:
> > Hi all,
> > I have "NetXtreme BCM5720 Gigabit Ethernet PCI" controllers .
> > I have binded to igb_uio . I have run l2fwd example .l2fwd saysno ports
Hi Thomas:
> -Original Message-
> From: Zhang, Qi Z
> Sent: Tuesday, March 21, 2017 8:10 PM
> To: Wu, Jingjing ; Zhang, Helin
>
> Cc: dev@dpdk.org; Zhang, Qi Z ; sta...@dpdk.org
> Subject: [PATCH v2] net/i40e: fix wrong handle when enable interrupt
>
> In i40e_dev_interrupt_hand
In i40e_dev_interrupt_handler, when call rte_intr_enable,
the intr_handle is the copy when we registered.
According to interrupt handle framework, if the requirement
of intr_handle is changed, we need to unregister then register
a new copy. This happens on i40e driver when bind to vfio-pci,
the rte
On 3/21/2017 11:01 AM, Srinivasreddy R wrote:
> Hi all,
> I have "NetXtreme BCM5720 Gigabit Ethernet PCI" controllers .
> I have binded to igb_uio . I have run l2fwd example .l2fwd saysno ports bye
> .
> Does BCM5720 works with dpdk .
Is your device's PCI device ID listed in the driver:
http://dpd
Yes, DPDK can be used to promote underlying commercial hardware or software,
as long as it is fair and not intrusive.
Please promote more products by becoming an Open Source contributor ;)
2017-03-20 22:30, Hobywan Kenoby:
> If AVP was an upstream device of Qemu or Linux kernel that would be very
On Fri, Mar 17, 2017 at 09:51:28AM -0500, Gage Eads wrote:
> From: "Eads, Gage"
>
> This commit adds rte_errno return values to rte_event_enqueue_burst() and
> rte_event_dequeue_burst().
>
> These return values allows user software to differentiate between an
> invalid argument (such as an inval
Hi all,
I have "NetXtreme BCM5720 Gigabit Ethernet PCI" controllers .
I have binded to igb_uio . I have run l2fwd example .l2fwd saysno ports bye
.
Does BCM5720 works with dpdk .
./dpdk-stable-16.07.2/tools/dpdk-devbind.py --status
Network devices using DPDK-compatible driver
Current code enables RX interrupts even if this it not
requested.
Fixes: ea121b28316d (\"net/nfp: add Rx interrupts\")
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/nfp/
Chained mbufs hold data_len as the length of that particular mbuf
and pkt_len as the full packet length including all the chained
mbufs. It is not clear from the mbuf definition if pkt_len should
be set for all the mbufs in a chain, but code there for handling
mbufs suggests just the first mbuf req
When LSO, not doing this can led to firmware disruption. It does
not show as error because TCP ends up sending data again later on.
Fixes: 9ba3d0ae2090 (\"net/nfp: add TSO support\")
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 12 +---
1 file changed, 9 insertions(+)
On 3/20/2017 3:58 PM, Ed Czeck wrote:
> Hi All,
> I have a small number checkpatch.sh messages in the pattern below. The
> message is a conflict between the definition of PRIu32 in the system header
> files and the DPDK checkpatch setup.
>
> CHECK:CAMELCASE: Avoid CamelCase:
> #866: FILE: driver
compile error:
.../build/build/lib/librte_eal/linuxapp/kni/kni_net.c:124:6:
error: implicit declaration of function ‘signal_pending’
[-Werror=implicit-function-declaration]
if (signal_pending(current) || ret_val <= 0) {
^~
Linux 4.11 moves signal function declarations to its ow
From: Julien Castets
Signed-off-by: Julien Castets
---
app/pktgen.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/pktgen.c b/app/pktgen.c
index e315bff..9a304c0 100644
--- a/app/pktgen.c
+++ b/app/pktgen.c
@@ -110,7 +110,7 @@ pktgen_packet_rate(port_info_t *info)
Hi Andrew
I'm developing a kit for kernel bypass purpose.OpenOnLoad already provides
a way to do kernel bypass.
Can dpdk also be used for kernel bypassing purpose on intel/solarflare
cards?
Ankit Aggarwal
On Tue, Mar 21, 2017 at 1:48 PM, Andrew Rybchenko wrote:
> Hi Ankit,
>
> (May be us...@d
Hi, Olivier
You need to add your new API in lib/librte_ether/rte_ether_version.map and
doc/guides/rel_notes/release_17_05.rst
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
> Sent: Wednesday, March 8, 2017 12:00 AM
> To: dev@dpdk.org; thomas.monja
On Fri, Mar 10, 2017 at 03:19:15PM +, Harry van Haaren wrote:
> PMDs that only do a specific type of scheduling cannot provide
> CFG_ALL_TYPES, so the Eventdev infrastructure should not demand
> that every PMD supports CFG_ALL_TYPES.
>
> By not overriding the default configuration of the queue
Hi Ankit,
(May be us...@dpdk.org is a better place for such questions)
OpenOnload provides a user-level TCP/IP stack with POSIX interface –
transparently runs any Linux sockets binary without requiring any
changes to the application. "DPDK is a set of libraries and drivers for
fast packet pro
Yongseok,
Please see few comments below
On Mon, Mar 20, 2017 at 04:38:04PM -0700, Yongseok Koh wrote:
> When configuring Rx/Tx queue, if queue already exists, it is reused. But if
> the queue size is changed, it must be resized to not access/overwrite
> invalid memory.
>
> Fixes: 2e22920b85d9 ("
On Mon, Mar 20, 2017 at 04:04:32PM -0700, Yongseok Koh wrote:
> Currently rte_eth_dev_rss_reta_update() doesn't work properly for mlx5 PMD.
> This
> patchset fixes the issue. This also enables testing the API with testpmd.
>
> v2:
> * Minor code change by review.
>
> Yongseok Koh (3):
> lib/li
Hi Singh,
The second patch cannot be applied, since the test folder has moved to the DPDK
root directory.
[root@localhost dpdk]# git apply
dpdk-dev-v4-2-2-app-test-add-unit-test-for-CRC-computation.patch
error: app/test/Makefile: No such file or directory
Thank you.
Yuan.
-Original Messag
Hello,
>
> compile error:
> .../build/build/lib/librte_eal/linuxapp/kni/kni_net.c:124:6:
> error: implicit declaration of function ‘signal_pending’
> [-Werror=implicit-function-declaration]
> if (signal_pending(current) || ret_val <= 0) {
> ^~
>
> Linux 4.11 moves signal fun
89 matches
Mail list logo
