Add memory space free logic for adding and removing GTP-U before return
success status, to aviod memory leak issue.
Fixes: bed9bb3139ef ("net/ice/base: fix GTP-U inner RSS IPv4 IPv6 co-exist")
Signed-off-by: Junfeng Guo
---
drivers/net/ice/base/ice_flow.c | 12
1 file changed, 8 in
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Sunday, July 19, 2020 6:36 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Thomas Monjalon
> Subject: [PATCH v2] net/mlx5: add queue start and stop feature
>
> The mlx5 PMD did not support queue_start and queue
> -Original Message-
> From: David Marchand
> Sent: Friday, July 17, 2020 9:59 PM
> To: Phil Yang
> Cc: tho...@monjalon.net; dev ; Mcnamara, John
> ; Honnappa Nagarahalli
> ; David Christensen
> ; jer...@marvell.com; Ananyev, Konstantin
> ; Ola Liljedahl ;
> Bruce Richardson ; Ruifeng Wan
Add memory space free logic for adding and removing GTP-U before return
success status, to avoid memory leak issue.
v2:
- fix small typo in commit message.
Fixes: bed9bb3139ef ("net/ice/base: fix GTP-U inner RSS IPv4 IPv6 co-exist")
Signed-off-by: Junfeng Guo
---
drivers/net/ice/base/ice_flow.
Applied, thanks
> -Original Message-
> From: dts On Behalf Of dkiric...@iol.unh.edu
> Sent: 2020年7月7日 21:41
> To: d...@dpdk.org
> Cc: m...@smartsharesystems.com; lylav...@iol.unh.edu; tho...@monjalon.net;
> dev@dpdk.org; david.march...@redhat.com; Yigit, Ferruh
> ; arybche...@solarflare.c
Hi,
> -Original Message-
> From: dev On Behalf Of Shy Shyman
> Sent: Wednesday, July 15, 2020 1:51 PM
> To: dev@dpdk.org
> Cc: Slava Ovsiienko ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix file path location of HW counters
>
> When debugging performance of a DPDK applicat
Hi,
> -Original Message-
> From: Dekel Peled
> Sent: Wednesday, July 15, 2020 10:31 AM
> To: Matan Azrad ; Slava Ovsiienko
> ; Raslan Darawsheh
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix push VLAN action on hairpin queue
>
> Push VLAN action is allowed on Tx on
Hi,
> -Original Message-
> From: Dekel Peled
> Sent: Wednesday, July 15, 2020 10:31 AM
> To: Matan Azrad ; Slava Ovsiienko
> ; Raslan Darawsheh
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix pop VLAN with decap action validate
>
> The combination of decap action fo
Hi,
> -Original Message-
> From: Gregory Etelson
> Sent: Thursday, July 16, 2020 10:40 AM
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Matan Azrad
> ; Raslan Darawsheh ;
> sta...@dpdk.org; Shahaf Shuler ; Slava Ovsiienko
> ; Ori Kam ; Yongseok
> Koh
> Subject: [PATCH] net/mlx5: fix tunnel
On Sun, Jul 19, 2020 at 5:17 PM Raslan Darawsheh wrote:
> > @@ -15,6 +16,7 @@
> > #include
> >
> > #include "mlx5_glue.h"
> > +#include "../mlx5_malloc.h"
> >
> > static int
> > mlx5_glue_fork_init(void)
> > --
> > 2.27.0
>
>
> Patch squashed into relevant commit in master-net-mlx,
Raslan,
Hi David,
Yes I noticed it already,
but it's coming from the fact that it's trying to apply it on a tree that
doesn't have the patch which this patch is trying to fix.
../drivers/common/mlx5/linux/mlx5_glue.c:19:10: fatal error: '../mlx5_malloc.h'
file not found
#include "../mlx5_malloc.h"
On Mon, Jul 20, 2020 at 10:38 AM Raslan Darawsheh wrote:
>
> Hi David,
>
> Yes I noticed it already,
> but it's coming from the fact that it's trying to apply it on a tree that
> doesn't have the patch which this patch is trying to fix.
>
> ../drivers/common/mlx5/linux/mlx5_glue.c:19:10: fatal er
On 7/20/2020 7:42 AM, Ruifeng Wang wrote:
-Original Message-
From: Radu Nicolau
Sent: Friday, July 17, 2020 6:50 PM
To: dev@dpdk.org
Cc: beilei.x...@intel.com; jia@intel.com; bruce.richard...@intel.com;
konstantin.anan...@intel.com; jerinjac...@gmail.com;
david.march...@redhat.com;
On 7/20/2020 7:46 AM, Ruifeng Wang wrote:
-Original Message-
From: Radu Nicolau
Sent: Friday, July 17, 2020 6:50 PM
To: dev@dpdk.org
Cc: beilei.x...@intel.com; jia@intel.com; bruce.richard...@intel.com;
konstantin.anan...@intel.com; jerinjac...@gmail.com;
david.march...@redhat.com;
hi, zhihong
On 7/20/2020 10:42 AM, zhihongx.p...@intel.com wrote:
From: Peng Zhihong
The rte_eth_dev_set_vlan_offload function will check whether the NIC has
the set vlan feature. If it has not, it will return failure. So need
"...has the set vlan feature..." , that need to refine.
to a
On 19/07/20 14:17 +0530, Jerin Jacob wrote:
> On Sun, Jul 19, 2020 at 1:12 AM Manish Chopra wrote:
> >
> > > -Original Message-
> > > From: dev On Behalf Of Manish Chopra
> > > Sent: Friday, July 17, 2020 2:19 AM
> > > To: Gaëtan Rivet ; Thomas Monjalon
> > >
> > > Cc: Jerin Jacob ; Ferr
> -Original Message-
> From: David Marchand
> Sent: Monday, July 20, 2020 11:52 AM
> To: Raslan Darawsheh
> Cc: Ali Alnubani ; dev@dpdk.org; Suanming Mou
> ; Yigit, Ferruh ;
> Thomas Monjalon
> Subject: Re: [dpdk-dev] [PATCH] common/mlx5: fix mlx5 build
>
> On Mon, Jul 20, 2020 at 10:38
When eCPRI offloading is introduced, the support for misc parameters
4 of flow table entry (FTE) match set is needed. The structure of
"mlx5_ifc_fte_match_param_bits" is extended with
"mlx5_ifc_fte_match_set_misc4_bits" at the end of it. The total size
of the FTE match set will be changed into 384
Performance improvement: use a write combining store
instead of a regular mmio write to update queue tail
registers.
Signed-off-by: Radu Nicolau
Acked-by: Bruce Richardson
---
drivers/net/i40e/base/i40e_osdep.h| 5 +
drivers/net/i40e/i40e_rxtx.c | 8
drivers/net/i40e/i
Implement 2 new functions that will enable write combining
stores depending on architecture. The functions are provided
as a generic stub and a x86 specific implementation.
The reason to implement these functions is to improve performance
by reducing the overhead associated with regular mmio write
Performance improvement: use a write combining store
instead of a regular mmio write to update queue tail
registers.
Signed-off-by: Radu Nicolau
Acked-by: Fiona Trahe
---
drivers/common/qat/qat_adf/adf_transport_access_macros.h | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff -
Add rte_write32_wc and rte_write32_wc_relaxed functions
that implement 32bit stores using write combining memory protocol.
Provided generic stubs and x86 implementation.
Signed-off-by: Radu Nicolau
Acked-by: Bruce Richardson
---
lib/librte_eal/arm/include/rte_io_64.h | 12 +++
lib/librte_e
Performance improvement: use a write combining store
instead of a regular mmio write to update queue tail
registers.
Signed-off-by: Radu Nicolau
Acked-by: Konstantin Ananyev
---
drivers/net/ixgbe/base/ixgbe_osdep.h | 6 ++
drivers/net/ixgbe/ixgbe_rxtx.c | 15 ---
driv
> From: Anoob Joseph
>
> RTE_FLOW API allows hardware parsing and steering of packets to specific
> queues which helps in distributing ingress traffic across various cores.
> Adding 'flow' rules allows user to specify the distribution required.
>
> Signed-off-by: Anoob Joseph
> Acked-by: Akhil
Some protocol don't support symmetric hash, need to handle these cases.
When set an invalid symmetric hash rule, just return failed.
Fixes: 7d0824387e63 ("net/ice: fix invalid RSS type")
Signed-off-by: Jeff Guo
---
drivers/net/ice/ice_hash.c | 13 -
1 file changed, 12 insertions(+),
Hi All,
> blockcipher cases are either returning TEST_SUCCESS
> or TEST_FAILED as status, but the test may not be
> supported by the PMD which is also a success case
> for the PMD. Hence checking for status == TEST_FAILED
> for setting the overall status as failed.
>
> Signed-off-by: Akhil Goyal
On 13/07/20 08:13 -0700, Manish Chopra wrote:
> By adding generic API, this patch removes individual
> functions/defines implemented by drivers to find PCI
> extended capability.
>
> Signed-off-by: Manish Chopra
> Signed-off-by: Igor Russkikh
> ---
> drivers/bus/pci/pci_common.c |
On Mon, Jul 20, 2020 at 09:27:57AM +, Akhil Goyal wrote:
> Hi All,
>
> > blockcipher cases are either returning TEST_SUCCESS
> > or TEST_FAILED as status, but the test may not be
> > supported by the PMD which is also a success case
> > for the PMD. Hence checking for status == TEST_FAILED
> >
> -Original Message-
> From: Jiang, JunyuX
> Sent: Friday, July 17, 2020 10:18 AM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
> ; Jiang, JunyuX ;
> sta...@dpdk.org
> Subject: [PATCH v2] net/ice: fix incorrect Rx/Tx bytes statistics
>
> This patch fixed the issue that rx/tx byte
> -Original Message-
> From: Xing, Beilei
> Sent: Friday, July 17, 2020 10:48 PM
> To: Sun, Chenmin ; Zhang, Qi Z
>
> Cc: dev@dpdk.org
> Subject: RE: [PATCH v3] net/i40e: fix fdir cannot receive rx writeback issue
>
>
>
> > -Original Message-
> > From: Sun, Chenmin
> > Sent
On 7/19/2020 9:10 PM, Thomas Monjalon wrote:
> 17/07/2020 13:36, Ferruh Yigit:
>> On 7/11/2020 9:17 AM, Hemant Agrawal wrote:
>>> DPAA platorm MAC interface is known as FMAN i.e. Frame Manager.
>>> There are two ways to control it.
>>> 1. Statically configure the queues and classification rules bef
Reviewed-by: Wei Zhao
> -Original Message-
> From: Sun, GuinanX
> Sent: Saturday, May 23, 2020 1:23 PM
> To: dev@dpdk.org
> Cc: Zhao1, Wei ; Yang, Qiming
> ; Sun, GuinanX
> Subject: [PATCH v2 0/2] fix MAC ctrl frame fwd get
>
> Fix incorrect MAC control frame forward.
> Fix flow contr
> -Original Message-
> From: Guo, Junfeng
> Sent: Monday, July 20, 2020 3:10 PM
> To: Zhang, Qi Z ; Xing, Beilei
> Cc: dev@dpdk.org; Guo, Jia ; Guo, Junfeng
> ; Su, Simei
> Subject: [PATCH] net/ice/base: free memory for GTP-U before return status
>
> Add memory space free logic for a
> -Original Message-
> From: dev On Behalf Of Zhao1, Wei
> Sent: Friday, July 17, 2020 3:30 PM
> To: Wang, ShougangX ; dev@dpdk.org
> Cc: Xing, Beilei ; Guo, Jia ; Wang,
> ShougangX ; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: fix missed i40e filter pctype
>
> Reviewed
When using --lcores option, there is a limit of CPU_SETSIZE.
Currently that allows 0..1023 on Linux.
Check it is caught when this limit is exceeded.
Signed-off-by: Kevin Traynor
---
app/test/test_eal_flags.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/app/test/test_e
>-Original Message-
>From: Akhil Goyal
>Sent: Monday, July 20, 2020 2:58 PM
>To: asoma...@amd.com; Anoob Joseph ;
>roy.fan.zh...@intel.com; fiona.tr...@intel.com; Nagadheeraj Rottela
>; Ankur Dwivedi ;
>jianjay.z...@huawei.com; pablo.de.lara.gua...@intel.com;
>adamx.dybkow...@intel.com;
When using --lcores option, there is a limit of CPU_SETSIZE.
Currently that allows 0..1023 on Linux.
Check it is caught when this limit is exceeded.
Signed-off-by: Kevin Traynor
---
app/test/test_eal_flags.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/app/test/test_e
> >Hi All,
> >
> >> blockcipher cases are either returning TEST_SUCCESS or TEST_FAILED as
> >> status, but the test may not be supported by the PMD which is also a
> >> success case for the PMD. Hence checking for status == TEST_FAILED for
> >> setting the overall status as failed.
> >>
> >> Signed
On 09/07/2020 00:04, Lukasz Wojciechowski wrote:
>
> W dniu 12.06.2020 o 14:09, Kevin Traynor pisze:
>> When using --lcores option, CPU_SETSIZE allows a range of
>> 0-1023. Check it is not being exceeded.
>>
>> Signed-off-by: Kevin Traynor
>> ---
>> app/test/test_eal_flags.c | 6 +-
>> 1 f
Thanks for merge and thanks for feedback for next contribution.
>
> Series applied with minor changes and doc squashed.
>
> 2 more comments for next contributions:
> - use a cover letter if there are multiple patches
> - please use --in-reply-to to thread all versions with the first one
> -Original Message-
> From: dev On Behalf Of Jiang Mao
> Sent: Thursday, July 9, 2020 3:53 AM
> To: Ye, Xiaolong
> Cc: dev@dpdk.org; sta...@dpdk.org; Jiang, MaoX
> Subject: [dpdk-dev] [PATCH 2/2] net/i40e: fix fdir allocating msix resource
> error
>
> Fdir allocating msix resource
> -Original Message-
> From: dev On Behalf Of Guinan Sun
> Sent: Saturday, May 23, 2020 1:23 PM
> To: dev@dpdk.org
> Cc: Zhao1, Wei ; Yang, Qiming
> ; Sun, GuinanX
> Subject: [dpdk-dev] [PATCH v2 0/2] fix MAC ctrl frame fwd get
>
> Fix incorrect MAC control frame forward.
> Fix flow c
W dniu 20.07.2020 o 12:19, Kevin Traynor pisze:
> When using --lcores option, there is a limit of CPU_SETSIZE.
> Currently that allows 0..1023 on Linux.
>
> Check it is caught when this limit is exceeded.
>
> Signed-off-by: Kevin Traynor
> ---
> app/test/test_eal_flags.c | 5 -
> 1 file c
> -Original Message-
> From: dev On Behalf Of Savinay Dharmappa
> Sent: Wednesday, July 15, 2020 7:28 PM
> To: Dharmappa, Savinay ; Singh, Jasvinder
> ; dev@dpdk.org
> Subject: [dpdk-dev] [RFC PATCH 1/2] sched: add dynamic config of subport
> bandwidth profile
>
> This patch modifies t
> -Original Message-
> From: Dumitrescu, Cristian
> Sent: Monday, July 20, 2020 12:21 PM
> To: Savinay Dharmappa ; Dharmappa,
> Savinay ; Singh, Jasvinder
> ; dev@dpdk.org
> Subject: RE: [dpdk-dev] [RFC PATCH 1/2] sched: add dynamic config of
> subport bandwidth profile
>
>
>
> >
Arrays of type uint64_t/int/string can now be included within an array
or dict. One level of embedded containers is supported. This is
necessary to allow for instances such as the ethdev queue stats to be
reported as a list of uint64_t values, rather than having multiple dict
entries with one uint6
From: Louise Kilheeney
This patch adds tests for verifying telemetry data structures are
converted to JSON as expected. Both flat and recursive data structures
are tested, for all possible value types.
The app connects to the telemetry socket as a client, and registers one
command with a corresp
v6:
- Fixed FreeBSD build failure for unit tests.
- Added comments and expanded commit log.
- Add loop to call test cases stored in a list.
v5: Added unit tests for telemetry data to JSON conversion.
v4: Added missing param description to Doxygen comment.
v3:
- Modified commit logs.
- Cha
The ethdev library now registers a telemetry command for common ethdev
statistics.
An example usage is shown below:
Connecting to /var/run/dpdk/rte/dpdk_telemetry.v2
{"version": "DPDK 20.08.0-rc1", "pid": 14119, "max_output_len": 16384}
--> /ethdev/stats,0
{"/ethdev/stats": {"ipackets": 0, "opack
> Add to the documentation for 20.08 a notice about the changes of rawdev
> APIs proposed by patchset [1].
>
> [1]
> http://inbox.dpdk.org/dev/20200709152047.167730-1-bruce.richard...@intel.com/
>
> Cc: Nipun Gupta
> Cc: Hemant Agrawal
>
> Signed-off-by: Bruce Richardson
> ---
> doc/guide
On 20-Jul-20 3:00 AM, wangyunjian wrote:
-Original Message-
From: Burakov, Anatoly [mailto:anatoly.bura...@intel.com]
Sent: Friday, July 17, 2020 10:24 PM
To: wangyunjian ; dev@dpdk.org;
david.march...@redhat.com
Cc: Lilijun (Jerry) ; xudingke
; sta...@dpdk.org
Subject: Re: [dpdk-dev] [PA
On 7/16/2020 9:39 AM, Tejasree Kondoj wrote:
> From: Vamsi Attunuru
>
> This patch adds lookaside IPsec enqueue and dequeue routines.
>
> Signed-off-by: Vamsi Attunuru
> Signed-off-by: Tejasree Kondoj
<...>
> @@ -33,6 +34,13 @@ struct otx2_cpt_vf {
> /**< CPT device capabilities */
>
This commit improves the service_lcore_stop() implementation,
waiting for the service core in question to return. The service
thread itself now has a variable to indicate if its thread is
active. When zero the service thread has completed its service,
and has returned from the service_runner_func()
> -Original Message-
> From: Phil Yang
> Sent: Saturday, July 18, 2020 9:34 AM
> To: Aaron Conole ; Lukasz Wojciechowski
>
> Cc: David Marchand ; Van Haaren, Harry
> ; Igor Romanov ;
> Honnappa Nagarahalli ; dev
> ; Yigit, Ferruh ; nd ; nd
>
> Subject: RE: [dpdk-dev] Random failure in se
Hi,
> -Original Message-
> From: Bing Zhao
> Sent: Monday, July 20, 2020 12:04 PM
> To: Ori Kam ; Slava Ovsiienko
>
> Cc: Raslan Darawsheh ; Matan Azrad
> ; dev@dpdk.org
> Subject: [PATCH] net/mlx5: fix the compatibility with MISC4
>
> When eCPRI offloading is introduced, the support fo
On Mon, Jul 20, 2020 at 11:12 AM Radu Nicolau wrote:
>
> Add rte_write32_wc and rte_write32_wc_relaxed functions
> that implement 32bit stores using write combining memory protocol.
> Provided generic stubs and x86 implementation.
What is the difference of using this new API when compared to the
On Mon, Jul 20, 2020 at 10:59 AM Raslan Darawsheh wrote:
> > > Yes I noticed it already,
> > > but it's coming from the fact that it's trying to apply it on a tree that
> > > doesn't
> > have the patch which this patch is trying to fix.
> > >
> > > ../drivers/common/mlx5/linux/mlx5_glue.c:19:10:
On 18-Jul-20 3:22 AM, Stephen Hemminger wrote:
On Fri, 17 Jul 2020 16:21:37 +0100
"Burakov, Anatoly" wrote:
On 16-Jul-20 11:04 PM, Stephen Hemminger wrote:
On Thu, 16 Jul 2020 14:41:41 +0100
"Burakov, Anatoly" wrote:
On 15-Jul-20 9:29 PM, Stephen Hemminger wrote:
On Wed, 15 Jul 2020 14
Hi Pablo
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Friday, July 17, 2020 8:29 PM
> >
> > #ifdef AESNI_MB_DOCSIS_SEC_ENABLED
> > + struct rte_security_ctx *security_instance;
> > security_instance = rte_malloc("aesni_mb_sec",
> > sizeof(s
Hi Akhil,
> -Original Message-
> From: Akhil Goyal
> Sent: Saturday, July 18, 2020 10:41 PM
> > > > This patch makes some minor improvements to the security instance
> > > > setup for the QAT SYM PMD. All of this setup code is now in one
> > > > '#ifdef RTE_LIBRTE_SECURITY' block. Enablin
These patches make some improvements to the security instance setup for
the QAT SYM and AESNI-MB PMDs.
David Coyle (2):
crypto/qat: improve security instance setup
crypto/aesni-mb: improve security instance setup
drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c | 18 +-
drivers/crypto/qat/
This patch makes some improvements to the security instance setup for
the QAT SYM PMD, as follows:
- fix potential memory leak where the security instance was not freed if
an error occurred later in the device creation
- tidy-up security instance initialization code by moving it all,
including
This patch makes some improvements to the security instance setup for
the AESNI-MB PMD, as follows:
- fix potential memory leak where the security instance was not freed if
an error occurred later in the device creation
- tidy-up security instance initialization code by moving it all,
including
W dniu 20.07.2020 o 14:09, Van Haaren, Harry pisze:
>> -Original Message-
>> From: Phil Yang
>> Sent: Saturday, July 18, 2020 9:34 AM
>> To: Aaron Conole ; Lukasz Wojciechowski
>>
>> Cc: David Marchand ; Van Haaren, Harry
>> ; Igor Romanov ;
>> Honnappa Nagarahalli ; dev
>> ; Yigit, Fer
W dniu 20.07.2020 o 14:09, Harry van Haaren pisze:
> This commit improves the service_lcore_stop() implementation,
> waiting for the service core in question to return. The service
> thread itself now has a variable to indicate if its thread is
> active. When zero the service thread has completed
> > > Subject: Re: [PATCH v2 3/3] eal/windows: librte_net build on Windows
> > >
> > > > diff --git a/lib/librte_eal/common/meson.build
> > > > b/lib/librte_eal/common/meson.build
> > > > index e1bdaf024..05e40a26b 100644
> > > > --- a/lib/librte_eal/common/meson.build
> > > > +++ b/lib/librte_ea
Hi Pablo,
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Friday, July 17, 2020 8:04 PM
> > @@ -48,6 +48,10 @@ cperf_set_ops_security(struct rte_crypto_op **ops,
> > } else
> > buf_sz = options->test_buffer_size;
> >
> > +
Hi,
I am using DPDK 17.11 in my application. I am facing an RX issue when
running the application with an intel I350 NIC.
Details of the NIC:
driver: igb
version: 5.4.0-k*
firmware-version: 1.63, 0x8d58, 1.1099.0
Kernel - 3.10.0-957.5.1.el7.x86_64
>From the release notes, I found out that th
On Mon, Jul 20, 2020 at 12:19:06PM +0100, Ciara Power wrote:
> From: Louise Kilheeney
>
> This patch adds tests for verifying telemetry data structures are
> converted to JSON as expected. Both flat and recursive data structures
> are tested, for all possible value types.
>
> The app connects to
Hi Patrick,
Thanks for the series.
I think we miss a chapter in the Vhost lib documentation to explain what
this new API is about.
Do you think you can write something by -rc3?
Thanks in advance,
Maxime
On 7/7/20 7:07 AM, patrick...@intel.com wrote:
> From: Patrick Fu
>
> Performing large mem
On 7/13/2020 1:31 PM, Bruce Richardson wrote:
> Add in an official notice that the make build system is being removed in
> 20.11 and provide a link to instructions on how to build using meson and
> ninja instead.
>
> Cc: Thomas Monjalon
>
> Signed-off-by: Bruce Richardson
> ---
> doc/guides/re
On 7/20/20 4:28 PM, Ferruh Yigit wrote:
> On 7/13/2020 1:31 PM, Bruce Richardson wrote:
>> Add in an official notice that the make build system is being removed in
>> 20.11 and provide a link to instructions on how to build using meson and
>> ninja instead.
>>
>> Cc: Thomas Monjalon
>>
>> Signed-o
Arrays of type uint64_t/int/string can now be included within an array
or dict. One level of embedded containers is supported. This is
necessary to allow for instances such as the ethdev queue stats to be
reported as a list of uint64_t values, rather than having multiple dict
entries with one uint6
v7:
- Simplified connecting to socket by removing use of glob.
- Fixed buffer overflow issue when reading from socket.
- Split expected response strings over multiple lines.
v6:
- Fixed FreeBSD build failure for unit tests.
- Added comments and expanded commit log.
- Add loop to call te
The ethdev library now registers a telemetry command for common ethdev
statistics.
An example usage is shown below:
Connecting to /var/run/dpdk/rte/dpdk_telemetry.v2
{"version": "DPDK 20.08.0-rc1", "pid": 14119, "max_output_len": 16384}
--> /ethdev/stats,0
{"/ethdev/stats": {"ipackets": 0, "opack
From: Louise Kilheeney
This patch adds tests for verifying telemetry data structures are
converted to JSON as expected. Both flat and recursive data structures
are tested, for all possible value types.
The app connects to the telemetry socket as a client, and registers one
command with a corresp
On 7/16/2020 9:23 AM, Viacheslav Ovsiienko wrote:
> To provide the packet send schedule on mbuf timestamp the Tx
> queue must be attached to the same UAR as Clock Queue is.
> UAR is special hardware related resource mapped to the host
> memory and provides doorbell registers, the assigning UAR
> to
> -Original Message-
> From: Lukasz Wojciechowski
> Sent: Monday, July 20, 2020 1:52 PM
> To: Van Haaren, Harry ; dev@dpdk.org
> Cc: david.march...@redhat.com; igor.roma...@oktetlabs.ru;
> honnappa.nagaraha...@arm.com; Yigit, Ferruh ;
> n...@arm.com; acon...@redhat.com
> Subject: Re: [PATC
On Mon, Jul 20, 2020 at 03:04:02PM +0100, Ciara Power wrote:
> From: Louise Kilheeney
>
> This patch adds tests for verifying telemetry data structures are
> converted to JSON as expected. Both flat and recursive data structures
> are tested, for all possible value types.
>
> The app connects to
+ igb maintainer
On Mon, Jul 20, 2020 at 6:29 PM siddarth rai wrote:
> Hi,
>
> I am using DPDK 17.11 in my application. I am facing an RX issue when
> running the application with an intel I350 NIC.
> Details of the NIC:
> driver: igb
> version: 5.4.0-k*
> firmware-version: 1.63, 0x8d58, 1.1
This commit fixes a potential race condition in the tests
where the lcore running a service would increment a counter
that was already reset by the test-suite thread. The resulting
race-condition incremented value could cause CI failures, as
indicated by DPDK's CI.
This patch fixes the race-condit
This commit adds a new experimental API which allows the user
to retrieve the active state of an lcore. Knowing when the service
lcore is completed its polling loop can be useful to applications
to avoid race conditions when e.g. finalizing statistics.
The service thread itself now has a variable
> -Original Message-
> From: Xu, Ting
> Sent: Thursday, July 9, 2020 2:48 AM
> To: dev@dpdk.org
> Cc: Dumitrescu, Cristian ; Xu, Ting
> ; sta...@dpdk.org
> Subject: [PATCH v3] lib/table: fix cache alignment issue
>
> When create softnic hash table with 16 keys, it failed on 32bit
> env
Hi Patrick,
On 7/15/20 1:15 PM, patrick...@intel.com wrote:
> From: Patrick Fu
>
> Vhost async enqueue assumes that all async copies should break at packet
> boundary. i.e. if a packet is splited into multiple copy segments, the
> async engine should always report copy completion when entire pac
On 7/20/2020 3:18 PM, Ferruh Yigit wrote:
> On 7/16/2020 9:23 AM, Viacheslav Ovsiienko wrote:
>> To provide the packet send schedule on mbuf timestamp the Tx
>> queue must be attached to the same UAR as Clock Queue is.
>> UAR is special hardware related resource mapped to the host
>> memory and pro
In the techboard of April 22, it has been decided to block patches
using rte_atomicNN_xx and rte_smp_*mb APIs, starting DPDK 20.08.
Meeting minutes:
http://mails.dpdk.org/archives/dev/2020-April/165143.html
Deprecation notice:
http://doc.dpdk.org/guides/rel_notes/deprecation.html
S
+Ruifeng
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, July 20, 2020 10:34 AM
> To: Honnappa Nagarahalli
> Cc: ferruh.yi...@intel.com; david.march...@redhat.com; dev@dpdk.org; Phil
> Yang ; techbo...@dpdk.org
> Subject: Using C11 atomic semantic
>
> In the techboard of Ap
Do you agree with below title?
vhost: fix double-free with zero-copy
Thanks,
Maxime
On 7/15/20 5:58 PM, patrick...@intel.com wrote:
> From: Patrick Fu
>
> zmbufs should be set to NULL when getting freed to avoid double free on
> the same buffer pointer
>
> Fixes: b0a985d1f340 ("vhost: add dequ
What about below title (we try to avoid passing variable names in commit
titles)?
vhost: fix missing device pointer validity check
On 7/16/20 5:37 PM, patrick...@intel.com wrote:
> From: Patrick Fu
>
> This patch adds the check of dev pointer in vhost async enqueue
> completion poll. If a NULL d
What about this commit title?
vhost: fix missing virtqueue status check in async path
On 7/16/20 5:30 PM, patrick...@intel.com wrote:
> From: Patrick Fu
>
> Vring should not be touched if vq is disabled. This patch adds the vq
> status check in async enqueue polling to avoid accessing to a disab
DOCSIS protocol performance in the downlink direction can be improved
significantly in the QAT SYM PMD, especially for larger packets, by
pre-processing all CRC generations in a batch before building and
enqueuing any requests to the HW. This patch adds this optimization.
Fixes: 6f0ef237404b ("cry
This patch adds support for DOCSIS and PDCP security protocols to the
pmd-cyclecount mode of the crypto performance tool. Adding this support
involves freeing the correct session type (i.e. security or cryptodev
session) when the test ends, depending on the op_type specificed.
Signed-off-by: David
On 7/17/2020 2:49 PM, Parav Pandit wrote:
> Currently mlx5_common uses CLASS priority to initialize
> common code before initializing the PMD.
> However mlx5_common is not really a class, it is the pre-initialization
> code needed for the PMDs.
>
> In subsequent patch a needed initialization seque
On Mon, 20 Jul 2020 12:54:08 +, Fady Bader wrote:
[snip]
> > Getting the same error with a setup similar to Dmitry's. My setup: SDK
> > 10.0.18362,
>
> I'm sending v4 patch that should resolve this.
>
> > clang 9.0.0. What version of clang are you using on your system?
> > You can try inst
The title could be improved, it is not very clear IMHO.
On 7/20/20 4:52 AM, patrick...@intel.com wrote:
> From: Patrick Fu
>
> Async copy fails when ring buffer cross two physical pages. This patch
> fix the failure by letting copies occur in sync mode if crossing page
> buffers are given.
Woul
20/07/2020 17:44, Honnappa Nagarahalli:
> From: Thomas Monjalon
> >
> > In the techboard of April 22, it has been decided to block patches using
> > rte_atomicNN_xx and rte_smp_*mb APIs, starting DPDK 20.08.
> > Meeting minutes:
> > http://mails.dpdk.org/archives/dev/2020-April/165143.html
>
20/07/2020 18:21, Ferruh Yigit:
> On 7/17/2020 2:49 PM, Parav Pandit wrote:
> > Currently mlx5_common uses CLASS priority to initialize
> > common code before initializing the PMD.
> > However mlx5_common is not really a class, it is the pre-initialization
> > code needed for the PMDs.
> >
> > In
On 7/20/2020 4:51 PM, Maxime Coquelin wrote:
> Do you agree with below title?
> vhost: fix double-free with zero-copy
Existing commit dropped from next-net and patchwork status updated.
>
> Thanks,
> Maxime
>
> On 7/15/20 5:58 PM, patrick...@intel.com wrote:
>> From: Patrick Fu
>>
>> zmbufs sh
On 7/20/2020 3:58 PM, Maxime Coquelin wrote:
> Hi Patrick,
>
> On 7/15/20 1:15 PM, patrick...@intel.com wrote:
>> From: Patrick Fu
>>
>> Vhost async enqueue assumes that all async copies should break at packet
>> boundary. i.e. if a packet is splited into multiple copy segments, the
>> async engi
On 7/20/2020 4:57 PM, Maxime Coquelin wrote:
> What about this commit title?
> vhost: fix missing virtqueue status check in async path
Existing commit dropped from next-net and patchwork status updated.
>
> On 7/16/20 5:30 PM, patrick...@intel.com wrote:
>> From: Patrick Fu
>>
>> Vring should n
1 - 100 of 159 matches
Mail list logo
