On 21/04/17 19:19, Jonas Pfefferle1 wrote:
> Alexey Kardashevskiy wrote on 21/04/2017 10:43:53:
>
>> From: Alexey Kardashevskiy
>> To: gowrishankar muthukrishnan
>> Cc: Jonas Pfefferle1 , Gowrishankar
>> Muthukrishnan , Adrian Schuepbach
>> , "dev@dpdk.org"
>> Date: 21/04/2017 10:44
>> Subject
From: Matt Peters
When an mbuf alloc fails during the mempool get operation for the
i40e bulk alloc receive function, the rx_mbuf_alloc_failed counter
is not incremented to record the error.
This fix ensures consistency with the other i40e receive procedures and
other net drivers.
Signed-off-by
Hi Jerin,
Thanks for getting this ball rolling, and I agree that we need a solution that
covers the three cases you described. We've also been thinking about an
environment where devices (NIC Rx (or even Tx), crypto, or a timer "device"
that uses librte_timer to inject events) can plug in event
Hi All,
We are using dpdk version 16.04 and have a requirement to verify the MLX4
based adapter card. Mellanox dpdk driver depends on the external libraries
and kernel modules from mellanox OFED release.
The following link has support for DPDK 16.11 and DPDK 2.2.
http://www.mellanox.com/pag
On 18 April 2017 at 12:01, Wiles, Keith wrote:
>
> > On Apr 17, 2017, at 11:35 AM, Safiyat Reza wrote:
> >
> > On 17 April 2017 at 21:25, Wiles, Keith wrote:
> > Comments below:
> >
> > > On Apr 17, 2017, at 8:07 AM, Safiyat Reza
> wrote:
> > >
> > > Hi,
> > >
> > > I am trying to ping a remot
On Fri, 21 Apr 2017 17:23:13 +0530
Anupam Kapoor wrote:
> On Fri, Apr 21, 2017 at 5:18 PM, Gal Sagie wrote:
>
> > I have a feeling you are talking about P4
>
>
> well, not p4, but more specifically 'protocol-oblivious-forwarding' (POF).
> ebpf can describe both match+action rules on dp
Hi Nidhia,
What command should be used to add existing flow.txt file to the flow table.
What command should be used if we want to add new entry through CLI and not
through file?
I tried as shown below. and its giving error:
pipeline> p 1 flow add qinq bulk ./config/flow.txt
Command "flow add q
Coverity issue: 143252
Fixes: 2deb6b5246d7706448d070335b329d1acb754cee ("app/procinfo: add collectd
format and host id")
Cc: sta...@dpdk.org
Signed-off-by: Roman Korynkevych
---
app/proc_info/main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/proc_info/main.c b/app/p
On 4/18/2017 1:17 PM, Gaetan Rivet wrote:
> This new API allows reacting to a device removal.
> A device removal is the sudden disappearance of a device from its
> bus.
>
> PMDs implementing support for this notification guarantee that the removal
> of the underlying device does not incur a risk t
On 4/18/2017 1:17 PM, Gaetan Rivet wrote:
> For drivers supporting the LSC event, enable it.
> This allows to test LSC event support.
>
> Add the --no-lsc-interrupt parameter to explicitly disable the link status
> change interrupt.
>
> Signed-off-by: Gaetan Rivet
> ---
> app/test-pmd/parameter
21/04/2017 15:50, Bruce Richardson:
> Fixes a number of issues with compiling on BSD, and a general fix to
> clean up the compilation of the performance-thread app.
>
> V2 changes:
> * adjust fix for perf thread compilation to use rte_lcore.h
> instead of extra #ifdefs.
> * added in two extra pa
-Original Message-
> Date: Fri, 21 Apr 2017 12:14:41 +0100
> From: Bruce Richardson
> To: Harry van Haaren
> CC: dev@dpdk.org, jerin.ja...@caviumnetworks.com
> Subject: Re: [dpdk-dev] [PATCH 3/3] doc: add eventdev library to
> programmers guide
> User-Agent: Mutt/1.8.0 (2017-02-23)
>
>
When building any of the perf-thread examples, the output .o files were
placed in two separate directories for each app: the regular build dir and
a "common" build directory. This was due to the way the files to be built
were specified, using a relative path. Switching to use VPATH to find the
file
This set of sample apps did not compile on FreeBSD due to use of a number
of Linux/glibc-specific APIs, or APIs which existed in different headers
on FreeBSD. Specifically, the following APIs has problems:
* sched_getcpu() is a glibc extension, so use rte_lcore_id() on BSD
* pthread_yield() ret
The "examples_clean" top-level build target calls "make clean" for each
individual example. However, for a number of those which were linux-only
examples, the "if" condition only had a dummy "all" target i.e. no "clean"
target, causing an error with examples_clean.
Fixes: 3417cd687e5e ("examples:
On FreeBSD it's not necessary to use -ldl to link apps which use
dlopen. This error only showed up with a shared library gcc build,
not standard build using static libs.
Fixes: 1131cbf0fb2b ("net/ark: stub PMD for Atomic Rules Arkville")
Signed-off-by: Bruce Richardson
Acked-by: John Miller
---
Fixes a number of issues with compiling on BSD, and a general fix to
clean up the compilation of the performance-thread app.
V2 changes:
* adjust fix for perf thread compilation to use rte_lcore.h
instead of extra #ifdefs.
* added in two extra patches, enabling examples_clean to run
on BSD, a
21/04/2017 14:04, Van Haaren, Harry:
> From: Jastrzebski, MichalX K
> > fix proc-info xstats-name description string
> >
> > Fixes: 1223608adb9b ("app/proc-info: support xstats by ID")
> >
> > Signed-off-by: Michal Jastrzebski
>
> Acked-by: Harry van Haaren
Applied, thanks
On 4/21/2017 1:16 PM, Andrew Rybchenko wrote:
> Recently link status change interrupt was enabled by default in testpmd,
> it has opened the driver bug with not working LSC interrupt if either
> igb_uio or uio_pci_generic kernel driver is used.
>
> Fixes: 06bc197796e2 ("net/sfc: interrupts support
On 4/21/2017 12:02 PM, Andrew Rybchenko wrote:
> Previous too pessimistic estimation made completely impossible to send
> packets with many segments (more than 100 with minimum Tx ring size).
>
> Fixes: 8b00f426eb66 ("net/sfc: implement EF10 native Tx datapath")
>
> Signed-off-by: Andrew Rybchenk
if this flag is advertised by a PMD, Multiple threads can
invoke rte_eth_tx_burst() concurrently on the same tx queue
without SW lock. This is an HW feature found in some NICs
and useful in the following use cases if HW supports it.
1) Remove explicit spinlock in some application where cores
to tx
On 4/21/2017 3:21 AM, Lu, Wenzhuo wrote:
> Hi,
>
>
>> -Original Message-
>> From: Dai, Wei
>> Sent: Thursday, April 20, 2017 11:06 AM
>> To: Zhang, Helin; Ananyev, Konstantin; Lu, Wenzhuo; Dai, Wei
>> Cc: dev@dpdk.org
>> Subject: [PATCH] net/ixgbe: align register setting when RSC is disab
Recently link status change interrupt was enabled by default in testpmd,
it has opened the driver bug with not working LSC interrupt if either
igb_uio or uio_pci_generic kernel driver is used.
Fixes: 06bc197796e2 ("net/sfc: interrupts support sufficient for event queue
init")
Cc: sta...@dpdk.org
> From: Jastrzebski, MichalX K
> Sent: Friday, April 21, 2017 12:22 PM
> To: dev@dpdk.org
> Cc: Van Haaren, Harry ; Jain, Deepak K
> ;
> Kozak, KubaX ; Jastrzebski, MichalX K
>
> Subject: [PATCH] app/proc-info: fix proc-info xstats-name description string
>
> fix proc-info xstats-name descripti
On Fri, Apr 21, 2017 at 5:18 PM, Gal Sagie wrote:
> I have a feeling you are talking about P4
well, not p4, but more specifically 'protocol-oblivious-forwarding' (POF).
ebpf can describe both match+action rules on dpdk...
--
kind regards
anupam
In the beginning was the lambda, and the la
I have a feeling you are talking about P4
On Fri, Apr 21, 2017 at 1:32 PM, Anupam Kapoor
wrote:
> hi all,
>
> i was just wondering if there are plans on adding ebpf support in dpdk ?
> imho, it would be pretty useful, among other things, in creating generic
> (protocol oblivious) match+actio
On 4/18/2017 7:56 AM, Wei Dai wrote:
> This patch set has following 4 patches.
> No any new device id is added.
>
> net/ixgbe/base: acquire PHY semaphore before device reset
> net/ixgbe/base: add support for 2.5G KX physical layer
> net/ixgbe/base: add MAC X550em/X557 LED on/off support
>
fix proc-info xstats-name description string
Fixes: 1223608adb9b ("app/proc-info: support xstats by ID")
Signed-off-by: Michal Jastrzebski
---
app/proc_info/main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/proc_info/main.c b/app/proc_info/main.c
index 9c9b2b5..16b2
On Fri, Apr 21, 2017 at 10:51:39AM +0100, Harry van Haaren wrote:
> This commit adds an entry in the programmers guide
> explaining the eventdev library.
>
> The rte_event struct, queues and ports are explained.
> An API walktrough of a simple two stage atomic pipeline
> provides the reader with a
Previous too pessimistic estimation made completely impossible to send
packets with many segments (more than 100 with minimum Tx ring size).
Fixes: 8b00f426eb66 ("net/sfc: implement EF10 native Tx datapath")
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andrew Lee
---
drivers/net/sfc/sfc_ef10_t
From: Akhil Goyal
license and copyright for hw and mc files are made consistent
as per the other dpaa2 dual licensed files.
Signed-off-by: Akhil Goyal
---
drivers/crypto/dpaa2_sec/hw/compat.h | 40 ++--
drivers/crypto/dpaa2_sec/hw/desc.h | 44 +
Hi Ferruh,
On Thu, Apr 20, 2017 at 07:54:47PM +0100, Ferruh Yigit wrote:
DPDK works with packets, but some network administration tools works based on
flow information.
This library is suggested to provide helper APIs to convert packet based
information to the flow records. Library header file
hi all,
i was just wondering if there are plans on adding ebpf support in dpdk ?
imho, it would be pretty useful, among other things, in creating generic
(protocol oblivious) match+action support in dpdk based forwarding elements.
--
thank you
kind regards
anupam
In the beginning was the lambda
This commit adds an entry in the programmers guide
explaining the eventdev library.
The rte_event struct, queues and ports are explained.
An API walktrough of a simple two stage atomic pipeline
provides the reader with a step by step overview of the
expected usage of the Eventdev API.
Signed-off-
This commit adds a sample app for the eventdev library.
The app has been tested with DPDK 17.05-rc2, hence this
release (or later) is recommended.
The sample app showcases a pipeline processing use-case,
with event scheduling and processing defined per stage.
The application recieves traffic as no
This patchset introduces a sample application that demonstrates
a pipeline model for packet processing. Running this sample app
with 17.05-rc2 or later is recommended.
The sample app itself allows configuration of various pipelines using
command line arguments. Parameters like number of stages, nu
Add a new entry in the sample app user-guides,
which details the working of the eventdev_pipeline.
Signed-off-by: Harry van Haaren
---
doc/guides/sample_app_ug/eventdev_pipeline.rst | 188 +
doc/guides/sample_app_ug/index.rst | 1 +
2 files changed, 189 inse
21/04/2017 10:59, Zhao1, Wei:
> Hi, thomas
>
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > 21/04/2017 04:27, Yuanhan Liu:
> > > On Thu, Apr 20, 2017 at 09:17:24AM +, Zhao1, Wei wrote:
> > > > > > > Please explain exactly the responsibility of this function,
> > > > > > > and how it
The patch is OK for me. I have run tests with that change with no problems.
But I can just run tests with devices where each one got its own IOMMU
group, so my ack is just for that case (although theoretically this patch
fixes the other case). I'm looking at doing some changes to the kernel for
bei
Could this patch be reviewed and merged for 17.05 rc3 ?. It solved
regression with i40e pmd
bring up in one of our ppc64le server models through vfio-pci pci module.
Thanks Alexey pointing out this in one of your patches.
Regards,
Gowrishankar
On Tuesday 04 April 2017 09:36 PM, Andrew Rybchenk
Hi,
What is the use of flow id offset in flow classification pipeline?
What all changes should I make to flow classification pipeline if I have to
forward packets based on single vlan id(rather than 2 vlan id as in qinq
packets)?
Regards,
Nidhia Varghese
Hi, thomas
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Friday, April 21, 2017 4:28 PM
> To: Yuanhan Liu ; Zhao1, Wei
>
> Cc: Ananyev, Konstantin ; Mcnamara, John
> ; dev@dpdk.org; Lu, Wenzhuo
> ; Liu, Yu Y
> Subject: Re: [dpdk-dev] [PATCH v4 1/3] lib
On 21/04/17 18:35, Jonas Pfefferle1 wrote:
>
> Jonas Pfefferle
> Cloud Storage & Analytics
> IBM Zurich Research Laboratory
> Saeumerstrasse 4
> CH-8803 Rueschlikon, Switzerland
> +41 44 724 8539
>
> Alexey Kardashevskiy wrote on 21/04/2017 05:42:35:
>
>>
> -Original Message-
> From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> Sent: Friday, April 21, 2017 10:28 AM
> To: Zhao1, Wei
> Cc: Ananyev, Konstantin ; Mcnamara, John
> ; dev@dpdk.org; Lu, Wenzhuo
> ; Thomas Monjalon ; Liu,
> Yu Y
> Subject: Re: [dpdk-dev] [PATCH v4 1/3] lib/
On 04/20/2017 10:24 AM, Alexey Kardashevskiy wrote:
The existing code correctly checks if a container is set to a group and
does not try attaching a group to a container for a second/third/...
device from the same IOMMU group.
However it still tries to set IOMMU type to a container for every dev
On Friday 21 April 2017 09:12 AM, Alexey Kardashevskiy wrote:
On 21/04/17 05:16, gowrishankar muthukrishnan wrote:
On Thursday 20 April 2017 07:52 PM, Alexey Kardashevskiy wrote:
On 20/04/17 23:25, Alexey Kardashevskiy wrote:
On 20/04/17 19:04, Jonas Pfefferle1 wrote:
Alexey Kardashevskiy wr
On 21/04/17 13:42, Alexey Kardashevskiy wrote:
> On 21/04/17 05:16, gowrishankar muthukrishnan wrote:
>> On Thursday 20 April 2017 07:52 PM, Alexey Kardashevskiy wrote:
>>> On 20/04/17 23:25, Alexey Kardashevskiy wrote:
On 20/04/17 19:04, Jonas Pfefferle1 wrote:
> Alexey Kardashevskiy wro
21/04/2017 10:11, Adrien Mazarguil:
> On Thu, Apr 20, 2017 at 11:49:33AM -0700, John Daley wrote:
> > Change comments for rte_flow_validate() function to indicate that flow
> > rule collision and resource validation is optional for PMDs and
> > therefore the return codes may have different meanings
21/04/2017 04:27, Yuanhan Liu:
> On Thu, Apr 20, 2017 at 09:17:24AM +, Zhao1, Wei wrote:
> > > > > Please explain exactly the responsibility of this function, and how
> > > > > it is different from calling stop/configure/start.
> > > >
> > > > In this reset feature, reset function can do the c
On Thu, Apr 20, 2017 at 11:49:33AM -0700, John Daley wrote:
> Change comments for rte_flow_validate() function to indicate that flow
> rule collision and resource validation is optional for PMDs and
> therefore the return codes may have different meanings.
>
> Fixes: b1a4b4cbc0a8 ("ethdev: introdu
This commit fixes NULL auth problem by setting state sizes
in request descriptor
Signed-off-by: Arek Kusztal
---
drivers/crypto/qat/qat_adf/qat_algs_build_desc.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/crypto/qat/qat_adf/qat_algs_build_desc.c
b/drivers/crypto/qat/qat_a
Hi,
What command should be used to add existing flow.txt file to the flow
table.
What command should be used if we want to add new entry through CLI and not
through file?
I tried as shown below. and its giving error:
pipeline> p 1 flow add qinq bulk ./config/flow.txt
Command "flow add qinq bulk"
52 matches
Mail list logo
