https://bugs.dpdk.org/show_bug.cgi?id=920
Bug ID: 920
Summary: [19.11.11] drivers/event/skeleton meson build failure
with gcc 10.3.0 + debug on FreeBSD13.0/64
Product: DPDK
Version: 19.11
Hardware: All
OS: A
>From 85c4e32996fc262dd6f69d0ce272ae8e8350 Mon Sep 17 00:00:00 2001
From: Yu Wenjun
Date: Wed, 12 Jan 2022 15:01:10 +0800
Subject: [PATCH] net/bonding: fix RSS not work for bonding
RSS don39t work when upgrade to DPDK21.11.
e.g.:
examples/bond/main.c:
conf:
static struct rte_eth_co
Hi All
I use igb_uio or uio_pci_generic to bind X710 VF:
:00:07.0 'XL710/X710 Virtual Function 154c' drv=igb_uio
unused=iavf,uio_pci_generic
The problem is that the device is not probed anymore by DPDK!
It works perfectly with 20.11.
Any advice?
Thank-you
Jean-Philippe Longeray
Senior
On 1/12/2022 6:18 AM, Ruifeng Wang wrote:
-Original Message-
From: Ruifeng Wang
Sent: Wednesday, January 12, 2022 11:01 AM
To: Ferruh Yigit ; Ashwin Sekhar Thalakalath
Kottilveetil ; dev@dpdk.org; Honnappa Nagarahalli
Cc: Nithin Kumar Dabilpuram ;
jer...@marvell.com; Sunil Kumar Kori ;
On 1/12/2022 3:01 AM, Ruifeng Wang wrote:
-Original Message-
From: Ferruh Yigit
Sent: Tuesday, January 11, 2022 9:46 PM
To: Ashwin Sekhar Thalakalath Kottilveetil ;
dev@dpdk.org; Honnappa Nagarahalli ;
Ruifeng Wang
Cc: Nithin Kumar Dabilpuram ;
jer...@marvell.com; Sunil Kumar Kori ; Sat
On 1/12/2022 9:07 AM, Jean-Philippe Longeray wrote:
Hi All
I use igb_uio or uio_pci_generic to bind X710 VF:
:00:07.0 'XL710/X710 Virtual Function 154c' drv=igb_uio
unused=iavf,uio_pci_generic
The problem is that the device is not probed anymore by DPDK!
It works perfectly with 20.11.
A
Thanks a lot!
Adding library librte_net_iavf.so solves the problem!
Nice!
JPL.
-Message d'origine-
De : Ferruh Yigit
Envoyé : mercredi 12 janvier 2022 10:28
À : Jean-Philippe Longeray
Cc : Qi Zhang ; Beilei Xing ;
dev@dpdk.org
Objet : Re: X710 VF not working anymore on DPDK 21.11
EX
Hi Xueming,
Happy new year!
Sorry for the late reply - could you help revert the commit
2f2c2b5b7e7ae4942b4b3686bce2eb856fee447d
Author: Przemyslaw Zegan
Date: Wed Nov 3 15:08:23 2021
common/qat: fix queue pairs number
As this patch relates to new feature introduce in 2021 and is not meant for
12/01/2022 03:44, Min Hu (Connor):
> Hi, Thomas,
>
> 在 2022/1/11 20:48, Thomas Monjalon 写道:
> > Please use --cc-cmd devtools/get-maintainer.sh so all maintainers are
> > Cc'edlike this ?
> git send-email -to dev@dpdk.org -cc ferruh.yi...@intel.com -cc
> tho...@monjalon.net --cc-cmd devtools/ge
> > > diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
> > > index d9a03f12f9..ecc6c1fe37 100644
> > > --- a/lib/ethdev/rte_ethdev.c
> > > +++ b/lib/ethdev/rte_ethdev.c
> > > @@ -6473,6 +6473,36 @@ rte_eth_rx_metadata_negotiate(uint16_t port_id,
> > uint64_t *features)
> > >
> >
> > > Hardware IP reassembly may be incomplete for multiple reasons like
> > > reassembly timeout reached, duplicate fragments, etc.
> > > To save application cycles to process these packets again, a new
> > > mbuf ol_flag (RTE_MBUF_F_RX_IPREASSEMBLY_INCOMPLETE) is added to
> > > show that th
> > > Another question - if we have reassembly_conf_set() would it make sense to
> > > have also reassembly_conf_get?
> > > So user can retrieve current ip_reassembly config values?
> > >
> > The set/supported values can be retrieved using rte_eth_dev_info ::
> reass_capa
>
> Hmm, I thought rte_et
> > > > Another question - if we have reassembly_conf_set() would it make sense
> > > > to
> > > > have also reassembly_conf_get?
> > > > So user can retrieve current ip_reassembly config values?
> > > >
> > > The set/supported values can be retrieved using rte_eth_dev_info ::
> > reass_capa
>
On 1/11/2022 2:29 PM, Satheesh Paul wrote:
Hi,
Please find reply inline.
Thanks,
Satheesh.
-Original Message-
From: Ferruh Yigit
Sent: 11 January 2022 05:26 PM
To: Satheesh Paul ; Nithin Kumar Dabilpuram ;
Kiran Kumar Kokkilagadda ; Sunil Kumar Kori ; Satha
Koteswara Rao Kottidi
Cc
> > > >
> > > > +/**
> > > > + * In case of IP reassembly offload failure, ol_flags in mbuf will be
> > > > set
> > > > + * with RTE_MBUF_F_RX_IPREASSEMBLY_INCOMPLETE and packets will
> be
> > > returned
> > > > + * without alteration. The application can retrieve the attached
> > > > fragments
>
On Wed, 2022-01-12 at 09:53 +, Zhang, Roy Fan wrote:
> Hi Xueming,
>
> Happy new year!
> Sorry for the late reply - could you help revert the commit
>
> 2f2c2b5b7e7ae4942b4b3686bce2eb856fee447d
> Author: Przemyslaw Zegan
> Date: Wed Nov 3 15:08:23 2021
> common/qat: fix queue pairs number
>
> > > > > Another question - if we have reassembly_conf_set() would it make
> > > > > sense
> to
> > > > > have also reassembly_conf_get?
> > > > > So user can retrieve current ip_reassembly config values?
> > > > >
> > > > The set/supported values can be retrieved using rte_eth_dev_info ::
> > >
> -Original Message-
> From: Xueming(Steven) Li
> Sent: Wednesday, January 12, 2022 7:02 PM
> To: Lin, Xueqin ; sta...@dpdk.org; Zhang, Roy Fan
> ; Jiang, YuX
> Cc: Stokes, Ian ; dev@dpdk.org;
> abhishek.mara...@microsoft.com; ktray...@redhat.com;
> d...@linux.vnet.ibm.com; NBU-Contact-Th
12/01/2022 08:28, Josh Soref:
> Some additional comment fixes...
They are not only comments, some are functions or struct fields.
> The tool comes from https://github.com/jsoref
It requires some reviews. I started to review below.
> -cpt_lfs_alloc(struct dev *dev, uint8_t eng_grpmsk, uint8_t bl
12/01/2022 08:28, Josh Soref:
> fixed spellings:
>
> * accelerator
> * acceptable
> * account
> * accounting
> * acknowledge
> * acknowledgement
> * across
> * action
> * actually
> * adapter
> * adaptive
> * added
> * addition
> * address
> * addresses
> * adds
> * adjustment
> * affinity
...
It
Min Hu (Connor) writes:
> Added the ethdev dump API which provides functions for query private info
> from device. There exists many private properties in different PMD drivers,
> such as adapter state, Rx/Tx func algorithm in hns3 PMD. The information of
> these properties is important for deb
On Wed, Jan 12, 2022, 6:50 AM Thomas Monjalon wrote:
> 12/01/2022 08:28, Josh Soref:
> > fixed spellings:
> >
> > * accelerator
> > * acceptable
> > * account
> > * accounting
> > * acknowledge
> > * acknowledgement
> > * across
> > * action
> > * actually
> > * adapter
> > * adaptive
> > * added
On Wed, 2022-01-12 at 11:29 +, Jiang, YuX wrote:
> > -Original Message-
> > From: Xueming(Steven) Li
> > Sent: Wednesday, January 12, 2022 7:02 PM
> > To: Lin, Xueqin ; sta...@dpdk.org; Zhang, Roy
> > Fan
> > ; Jiang, YuX
> > Cc: Stokes, Ian ; dev@dpdk.org;
> > abhishek.mara...@micros
AF_XDP support is deprecated in libbpf since v0.7.0 [1]. The
libxdp library now provides the functionality which once was in
libbpf and which the AF_XDP PMD relies on. This commit updates the
AF_XDP meson build to use the libxdp library if a version >= v1.3.0 is
available. If it is not available, o
Old macros kept for backward compatibility, but this cause old macro
usage to sneak in silently.
Marking old macros as deprecated. Downside is this will cause some noise
for applications that are using old macros.
Fixes: 295968d17407 ("ethdev: add namespace")
Signed-off-by: Ferruh Yigit
Acked-b
> Jerin Jacob (1):
> drivers: remove octeontx2 drivers
>
> Liron Himi (4):
> common/cnxk: add REE HW definitions
> common/cnxk: add REE mbox definitions
> common/cnxk: add REE support
> regex/cn9k: use cnxk infrastructure
Applied, thanks.
Hello Everyone,
The DTS Working Group wanted to let everyone give feedback on the proposed
DTS commit policies. Please leave a comment with any feedback you have. We
will be reviewing feedback in the DTS Working Group meeting on January
26th, at which point the comment period will close.
The purp
Hi Kevin,
On 11/01/2022 17:15, Kevin Traynor wrote:
On 23/12/2021 15:25, Vladimir Medvedkin wrote:
This patch fixes the division by 0, which occurs if the number of
routes is less than 10.
Can be triggered by passing -n argument with value < 10:
9 causing a divide by zero - another example
Hi,
My system developper friend recently ran into a problem where
l3fwd does not appear to receive balanced traffic on Intel XL710,
but it is resolved when the attached patch is applied.
-.rss_hf = ETH_RSS_IP,
+.rss_hf = ETH_RSS_IP | ETH_RSS_TCP | ETH_RSS_UDP,
IIRC I ra
> From: Bruce Richardson [mailto:bruce.richard...@intel.com]
> Sent: Tuesday, 14 December 2021 15.58
>
> On Tue, Dec 14, 2021 at 02:12:30PM +, Ronan Randles wrote:
> > This patchset introduces a Gen library for DPDK. This library
> provides an easy
> > way to generate traffic in order to test
03/01/2022 19:00, Dmitry Kozlyuk:
> 2022-01-03 12:09 (UTC-0500), Lance Richardson:
> > Python 3.5 subprocess.run() does not have a capture_output
> > parameter (it is present only in 3.7 and up). Capture output
> > by using subprocess.PIPE for stdout instead.
> >
> > Fixes: bb9cd91095b3 ("buildtoo
22/12/2021 16:18, Bruce Richardson:
> Standard "find" on BSD does not support the "-printf" so gfind from
> findutils package was used to enable full doc builds. We can remove this
> extra dependency by using "sed" and "tr" to adjust the output from
> regular find instread.
>
> Fixes: 8260f4f98cfe
Add support for the show CLI command to print table entries to a file
instead of standard output.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Harshad Narayane
---
examples/pipeline/cli.c | 34 +++---
1 file changed, 27 insertions(+), 7 deletions(-)
diff --git
Add support for the show CLI command to print table entries to a file
instead of standard output.
Signed-off-by: Cristian Dumitrescu
Signed-off-by: Harshad Narayane
---
examples/pipeline/cli.c | 34 +++---
1 file changed, 27 insertions(+), 7 deletions(-)
diff --git
Add recommended matching list for ice PMD in DPDK 21.08 and DPDK 21.11.
Signed-off-by: Qi Zhang
---
doc/guides/nics/ice.rst | 4
1 file changed, 4 insertions(+)
diff --git a/doc/guides/nics/ice.rst b/doc/guides/nics/ice.rst
index f95fef8cf0..a1780c46c3 100644
--- a/doc/guides/nics/ice.rst
On Wed, Dec 1, 2021 at 4:00 PM wrote:
>
> From: Asaf Ravid
>
> When multicast promisc was being enabled it caused the unicast promisc
> to be disabled. This fix resolves this by setting NIX_RX_MODE_PROMISC
> when eth_dev->data->promiscuous is set, regardless.
>
> ci: skip_checkpatch skip_roc_chec
Hi Konstatin,
Thank you for your comments and the test report!
> On Jan 10, 2022, at 8:26 PM, Ananyev, Konstantin
> wrote:
>
>
>
>
>> Current mempool per core cache implementation stores pointers to mbufs
>> On 64b architectures, each pointer consumes 8B
>> This patch replaces it with index
Hi,
Thank you for your valuable review comments and suggestions!
I will be sending out a v2 in which I have increased the size of the mempool to
32GB by using division by sizeof(uintptr_t).
However, I am seeing ~5% performance degradation with mempool_perf_autotest
(for bulk size of 32) with th
Current mempool per core cache implementation stores pointers to mbufs
On 64b architectures, each pointer consumes 8B
This patch replaces it with index-based implementation,
where in each buffer is addressed by (pool base address + index)
It reduces the amount of memory/cache required for per core
Current mempool per core cache implementation stores pointers to mbufs
On 64b architectures, each pointer consumes 8B
This patch replaces it with index-based implementation,
where in each buffer is addressed by (pool base address + index)
It reduces the amount of memory/cache required for per core
On Thu, Jan 13, 2022 at 3:12 AM Qi Zhang wrote:
>
> Add recommended matching list for ice PMD in DPDK 21.08 and DPDK 21.11.
Any reason why this is not marked for backport in 21.11?
>
> Signed-off-by: Qi Zhang
> ---
> doc/guides/nics/ice.rst | 4
> 1 file changed, 4 insertions(+)
>
> diff
41 matches
Mail list logo
