Hello,
Following are the work items planned for 21.02 from NTT TechnoCross:
I will try to post patch set after 20.11 is released.
---
1) Introduce API stats function
In general, DPDK application consumes CPU usage because it polls
incoming packets using rx_burst API in infinite loop.
This makes d
> Subject: [dpdk-dev] [PATCH 1/1] net/mlx5: fix flow shared action destroy
> error code
>
> External email: Use caution opening links or attachments
>
>
> In the function rte_flow_shared_action_destroy(), the errno
> ETOOMANYREFS has been replaced with EBUSY in the commit dc328d1c555a
> ("ethdev
> >
> > >
> > > The initialization me->locked=1 in lock() must happen before
> > > next->locked=0 in unlock(), otherwise a thread may hang forever,
> > > waiting me->locked become 0. On weak memory systems (such as
> ARMv8),
> > > the current implementation allows me->locked=1 to
Hi ferruh,
I hope that these two patches can be applied.
Because in that way, the version can be stable.
Thanks,
Guoyang zhou
在 2020/11/24 17:31, Ferruh Yigit 写道:
On 11/23/2020 4:09 PM, Ferruh Yigit wrote:
On 11/23/2020 1:12 PM, Guoyang Zhou wrote:
The maximum number of queues on the chip ca
Thomas and all,
20.11-RC5 is finished from Intel part. Except known issues, no new critical
issue blocked the release is found.
* Intel(R) Testing
# Basic Intel(R) NIC testing
* PF(i40e):Passed. One minor issue related to devbind tool is found. Patch is
provided. Should be merged into 21.02.
https://bugs.dpdk.org/show_bug.cgi?id=582
jiang,yu (yux.ji...@intel.com) changed:
What|Removed |Added
Resolution|--- |FIXED
Status|UNCONFIR
Tested-by: Jiang, YuX
Best Regards
Jiang yu
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen
> Hemminger
> Sent: Wednesday, November 25, 2020 1:53 AM
> To: Richardson, Bruce
> Cc: dev@dpdk.org; Ling, WeiX
> Subject: Re: [dpdk-dev] [PATCH] user
On 2020/11/24 下午8:45, Maxime Coquelin wrote:
This patch fixes an overhead met with mlx5-vdpa Kernel
driver, where for every page in the mapped area, all the
memory tables gets updated. For example, with 2MB hugepages,
a single IOTLB_UPDATE for a 1GB region causes 512 memory
updates on mlx5-vdpa
> > + if (rte_pktmbuf_alloc_bulk(umem->mb_pool, fq_bufs, nb_pkts)) {
> > + AF_XDP_LOG(DEBUG,
> > + "Failed to get enough buffers for fq.\n");
> > + /* rollback cached_cons which is added by
> > +* xsk_ring_prod__needs_wakeup
> > +*/
>
In the function rte_flow_shared_action_destroy(),
the errno ETOOMANYREFS has been replaced with EBUSY in the
commit dc328d1c555a ("ethdev: rename a flow shared action error code").
Another occurrence of ETOOMANYREFS, added later by mistake,
is replaced with EBUSY errno.
Fixes: fa7ad49e96b5 ("net/
> > In mlx5 internal hash list tool, there is a log print when an entry
> > allocation is
> > failed: Can't allocate hash list entry.
> >
> > Some initialization checks triggers hash list registration in order to
> > check some
> > capabilities. Here, the failure in registration doesn't lead to
> > Invalid memory release order of DevX resources caused PMD crash.
> >
> > 1. SQ and CQ memory must be unregistered with DevX before it is freed.
> > 2. SQ objects reference to a CQ ones. Hence, SQ should be destroyed in
> >advance of CQ it references to.
> >
> > Fixes: 6deb19e1b2d2 ("net/m
On Mon, Nov 2, 2020 at 8:01 AM Ferruh Yigit wrote:
>
> On 11/1/2020 10:45 AM, Andrew Rybchenko wrote:
> > On 10/30/20 7:12 PM, Xueming(Steven) Li wrote:
> >> Hi Andrew,
> >>
> >>> -Original Message-
> >>> From: dev On Behalf Of Andrew Rybchenko
> >>> Sent: Thursday, October 29, 2020 4:53
23/11/2020 11:49, Ferruh Yigit:
> On 11/16/2020 7:55 AM, Xiaoyu Min wrote:
> > From: Xiaoyu Min
> >
> > The rte_flow_item_vlan items are refined.
> > The structs do not exactly represent the packet bits captured on the
> > wire anymore so should only copy real header instead of the whole struct.
With the recent changes in terms of free access to the Travis CI, let's
offer an alternative with Github Actions.
Running jobs on ARM is not supported unless using external runners, so
this commit only adds builds for x86_64 and cross compiling for i386 and
aarch64.
Differences with the Travis CI
On Tue, Nov 24, 2020 at 9:36 AM Ferruh Yigit wrote:
>
> Signed-off-by: Ferruh Yigit
> Acked-by: Konstantin Ananyev
Acked-by: Ajit Khaparde
> ---
> Cc: Thomas Monjalon
> Cc: Andrew Rybchenko
> Cc: Konstantin Ananyev
> Cc: Matan Azrad
> Cc: Olivier Matz
> Cc: Jerin Jacob
>
> v2:
> * ``uin
24/11/2020 18:45, Stephen Hemminger:
> Could we kill the old dpdk-setup.sh script?
> Or add for 20.11 a notice "this script will go away, learn to use other
> ones..."
Yes we should add a deprecation warning in the script,
and plan its removal for DPDK 21.11.
> It is out of date, and a terrible
> -Original Message-
> From: Mcnamara, John
> Sent: Tuesday, November 24, 2020 8:41 PM
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; Mcnamara, John
> Subject: [PATCH v1] doc: update release notes for 20.11
>
> Fix grammar, spelling and formatting of DPDK 20.11 release notes.
Note, the "
Fix grammar, spelling and formatting of DPDK 20.11 release notes.
Signed-off-by: John McNamara
---
doc/guides/rel_notes/release_20_11.rst | 178 +
1 file changed, 94 insertions(+), 84 deletions(-)
diff --git a/doc/guides/rel_notes/release_20_11.rst
b/doc/guides/rel_note
Hi Lijuan,
Thank you for the suggestions.
After that is resolved we encounter another issue.
Currently, the kernel version we have is 5.4.0-53 and has a vfio-pci built
in. But we can not use the module from the nic_devbind.py.
Because we have vfio-pci drivers on the other machine's nic and trex
r
On Mon, Aug 10, 2020 at 11:15 PM Gregory Etelson wrote:
>
> According to current RTE API, port flow rules must not be kept
> after port stop.
>
> Testpmd did not flush port flow rules after `port stop' command was
> called. As the result, after the port was restarted, it showed bogus
> flow rules.
On Wed, Nov 18, 2020 at 8:15 AM Gregory Etelson wrote:
>
> There is a discrepancy between RTE ETHDEV API and flow rules guide
> regarding flow rules maintenance after port stop. RTE ETHDEV API in
> librte_ethdev.h declares that flow rules will not be stored in PMD
> after port stop:
> > Quit
On Tue, Nov 24, 2020 at 5:15 AM Ferruh Yigit wrote:
>
> Proposing to replace protocol header fields in the ``rte_flow_item_*``
> structures with the protocol structs.
>
> This is both for documenting the intention and to be sure
> ``rte_flow_item_*`` always starts with complete protocol header.
>
On Tue, Nov 24, 2020 at 5:26 AM Anatoly Burakov
wrote:
>
> Currently, compilation instructions for igb_uio are missing. Add them,
> as well as a top-level INSTALL file referring users to per-OS
> subdirectories.
>
> Signed-off-by: Anatoly Burakov
> Reviewed-by: Ferruh Yigit
Reviewed-by: Ajit Kh
Remove list of supported OS in PMD specific doc.
Documenting an unsupported version of OS makes more sense in
PMD specific docs.
Platforms tested with this device is documented in release notes anyway.
Signed-off-by: Ajit Khaparde
---
doc/guides/nics/bnxt.rst | 24
1 fil
Add tested platforms for Broadcom NICs to the 20.11 release notes.
Signed-off-by: Ajit Khaparde
---
doc/guides/rel_notes/release_20_11.rst | 66 ++
1 file changed, 66 insertions(+)
diff --git a/doc/guides/rel_notes/release_20_11.rst
b/doc/guides/rel_notes/release_20_11.
On Tue, 24 Nov 2020 09:46:56 +
Bruce Richardson wrote:
> The "misc" and "regex" device classes were missing from the list used to
> check arguments, preventing them from being used with "--status-dev"
> flag to list only devices of those types.
>
> When adding them to the list, the list is a
On 11/12/2020 1:21 PM, Ferruh Yigit wrote:
On 11/3/2020 2:26 PM, Andrew Rybchenko wrote:
A new generic shared actions API may be used to create shared
counter. There is no point to keep duplicate COUNT action specific
capability to create shared counters.
Signed-off-by: Andrew Rybchenko
Review
On 11/3/2020 9:07 AM, Yang, SteveX wrote:
-Original Message-
From: Ananyev, Konstantin
Sent: Tuesday, November 3, 2020 12:05 AM
To: Yigit, Ferruh ; Andrew Rybchenko
; Yang, SteveX ;
dev@dpdk.org
Cc: Xing, Beilei ; Lu, Wenzhuo
; Iremonger, Bernard
; Yang, Qiming ;
m...@ashroe.eu; nhor.
Could we kill the old dpdk-setup.sh script?
Or add for 20.11 a notice "this script will go away, learn to use other ones..."
It is out of date, and a terrible user API.
Of course, there are lots of old pieces of documentation that still refer to it?
Signed-off-by: Ferruh Yigit
Acked-by: Konstantin Ananyev
---
Cc: Thomas Monjalon
Cc: Andrew Rybchenko
Cc: Konstantin Ananyev
Cc: Matan Azrad
Cc: Olivier Matz
Cc: Jerin Jacob
v2:
* ``uint32_t mtu`` moved to ``struct rte_eth_conf``
* The "Driver is responsible from updating ``(struct
rte_e
On 11/24/2020 1:56 PM, Lijun Ou wrote:
Since the hns3 NIC hardware features are not counted
and it is supported in fact. Besides, the flow director
is not supported and need to delete it.
Fixes: fa29fe45a7b4 ("net/hns3: support queue start and stop")
Fixes: 521ab3e93361 ("net/hns3: add simple Rx
On 11/24/2020 2:25 PM, Ajit Khaparde wrote:
Remove list of supported OS in PMD specific doc.
Documenting an unsupported version of OS makes more sense in
PMD specific docs.
Platforms tested with this device is documented in release notes anyway.
Signed-off-by: Ajit Khaparde
Reviewed-by: Ferru
On 10/26/2020 9:46 PM, Ajit Khaparde wrote:
Devices belonging to BCM573xx and BCM5740x family will not be supported
from the 21.02 release.
Signed-off-by: Ajit Khaparde
---
doc/guides/rel_notes/deprecation.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/rel_notes/dep
On Tue, Nov 24, 2020 at 04:14:15PM +0100, Timothy Redaelli wrote:
> Commit 49b536fc3060 ("eal: load only shared libs from driver plugin
> directories")
> introduced a check that any shared library must ends with .so, but it can't
> work, at least, on Fedora/CentOS/RHEL since .so symlinks are not i
On Tue, Nov 24, 2020 at 04:14:14PM +0100, Timothy Redaelli wrote:
> Commit 06c7871dde01 ("eal: restrict default plugin path to shared lib mode")
> introduced a check that enabled shared lib mode when librte_eal.so can
> be loaded, but it can't work, at least, on Fedora/CentOS/RHEL since .so
> symli
Commit 49b536fc3060 ("eal: load only shared libs from driver plugin
directories")
introduced a check that any shared library must ends with .so, but it can't
work, at least, on Fedora/CentOS/RHEL since .so symlinks are not installed
when you install dpdk package, but only when you install dpdk-dev
Commit 06c7871dde01 ("eal: restrict default plugin path to shared lib mode")
introduced a check that enabled shared lib mode when librte_eal.so can
be loaded, but it can't work, at least, on Fedora/CentOS/RHEL since .so
symlinks are not installed when you install dpdk package, but only when
you ins
Currently eal only tries to find shared lib by looking for .so files,
but on Fedora, CentOS and RHEL the .so file is not installed by dpdk
package, but it's only installed by dpdk-devel package, since .so files
should not be necessary in order to run a program [1].
This series fix that by checking
Hi Thomas,
The testing with dpdk 20.11-rc5 from Red Hat looks good. We tested below 16
scenarios and and all got PASS on RHEL8:
(1)Guest with device assignment(PF) throughput testing(1G hugepage size): PASS
(2)Guest with device assignment(PF) throughput testing(2M hugepage size) : PASS
(3)Guest
>
> when receive packets, the max bunch number of mbuf are allocated
> if hardware does not receive the max bunch number packets, it
> will free redundancy mbuf, this is low performance
>
> so optimize rx performance, by allocating number of mbuf based on
> result of xsk_ring_cons__peek, to avoid
Since the hns3 NIC hardware features are not counted
and it is supported in fact. Besides, the flow director
is not supported and need to delete it.
Fixes: fa29fe45a7b4 ("net/hns3: support queue start and stop")
Fixes: 521ab3e93361 ("net/hns3: add simple Rx path")
Fixes: bba636698316 ("net/hns3: s
Previous patch added support of shared age action.
This feature is supported on group 1 and higher, and validation was
added accordingly.
On FDB table the group 0 is skipped to improve performance.
As a result the mentioned validation is not relevant for transfer rules.
This patch adds the required
Currently, compilation instructions for igb_uio are missing. Add them,
as well as a top-level INSTALL file referring users to per-OS
subdirectories.
Signed-off-by: Anatoly Burakov
Reviewed-by: Ferruh Yigit
---
INSTALL | 5 +
linux/README.rst | 45 ++
On 11/24/2020 11:49 AM, Viacheslav Ovsiienko wrote:
If there was no RTE_NET_I40E configured the static routine
str2flowtype() was not used causing compilation warning.
The str2flowtype() is moved under #ifdef RTE_NET_I40E block.
Fixes: 1be514fbcea9 ("ethdev: remove legacy FDIR filter type suppo
Proposing to replace protocol header fields in the ``rte_flow_item_*``
structures with the protocol structs.
This is both for documenting the intention and to be sure
``rte_flow_item_*`` always starts with complete protocol header.
Change will be done in two steps, at first step in v21.02 release
On 24/11/2020 12:23, Ferruh Yigit wrote:
> On 11/24/2020 10:27 AM, Thomas Monjalon wrote:
>> Is it OK to keep this regression?
>>
>> Ferruh, what do you suggest?
>>
>
> I confirm the '--txpkts' parameter is broken now, I suggest submitting a
> defect
> for it and continue with the regression.
>
On 11/24/20 4:00 PM, Andrew Rybchenko wrote:
> On 11/24/20 3:56 PM, Ferruh Yigit wrote:
>> On 11/24/2020 11:43 AM, Ori Kam wrote:
>>> Hi
>>>
-Original Message-
From: Ferruh Yigit
Sent: Monday, November 23, 2020 5:51 PM
Subject: Re: [PATCH] doc: announce flow API matchin
On 11/24/20 3:56 PM, Ferruh Yigit wrote:
> On 11/24/2020 11:43 AM, Ori Kam wrote:
>> Hi
>>
>>> -Original Message-
>>> From: Ferruh Yigit
>>> Sent: Monday, November 23, 2020 5:51 PM
>>> Subject: Re: [PATCH] doc: announce flow API matching pattern struct
>>> changes
>>>
>>> On 11/23/2020 2:2
On 11/24/2020 11:43 AM, Ori Kam wrote:
Hi
-Original Message-
From: Ferruh Yigit
Sent: Monday, November 23, 2020 5:51 PM
Subject: Re: [PATCH] doc: announce flow API matching pattern struct changes
On 11/23/2020 2:25 PM, Andrew Rybchenko wrote:
On 11/23/20 5:17 PM, Ferruh Yigit wrote:
This patch fixes an overhead met with mlx5-vdpa Kernel
driver, where for every page in the mapped area, all the
memory tables gets updated. For example, with 2MB hugepages,
a single IOTLB_UPDATE for a 1GB region causes 512 memory
updates on mlx5-vdpa side.
Using batching mode, the mlx5 driver will
This patch fixes an overhead met with mlx5-vdpa Kernel
driver, where for every page in the mapped area, all the
memory tables gets updated. For example, with 2MB hugepages,
a single IOTLB_UPDATE for a 1GB region causes 512 memory
updates on mlx5-vdpa side.
Using batching mode, the mlx5 driver will
Thank you for applying it.
On Fri, Nov 20, 2020 at 5:04 PM David Marchand
wrote:
> On Thu, Nov 5, 2020 at 9:54 AM David Marchand
> wrote:
> > On Mon, Nov 2, 2020 at 12:20 PM Ibtisam Tariq
> wrote:
> > >
> > > Add "--" and remove extra spaces in l3fwd-acl commands.
> > >
> > > Fixes: d0dff9ba4
Instead of using getopt_long return value, strcmp was used to
compare the input parameters with the struct option array. This
patch get rid of all those strcmp by directly binding each longopt
with an int enum. This is to improve readability and consistency in
all examples.
Bugzilla ID: 238
Cc: ro
Instead of using getopt_long return value, strcmp was used to
compare the input parameters with the struct option array. This
patch get rid of all those strcmp by directly binding each longopt
with an int enum. This is to improve readability and consistency in
all examples.
Bugzilla ID: 238
Cc: ji
Instead of using getopt_long return value, strcmp was used to
compare the input parameters with the struct option array. This
patch get rid of all those strcmp by directly binding each longopt
with an int enum. This is to improve readability and consistency in
all examples.
Bugzilla ID: 238
Cc: st
Instead of using getopt_long return value, strcmp was used to
compare the input parameters with the struct option array. This
patch get rid of all those strcmp by directly binding each longopt
with an int enum. This is to improve readability and consistency in
all examples.
Bugzilla ID: 238
Cc: ia
Instead of using getopt_long return value, strcmp was used to
compare the input parameters with the struct option array. This
patch get rid of all those strcmp by directly binding each longopt
with an int enum. This is to improve readability and consistency in
all examples.
Bugzilla ID: 238
Cc: se
Instead of using getopt_long return value, strcmp was used to
compare the input parameters with the struct option array. This
patch get rid of all those strcmp by directly binding each longopt
with an int enum. This is to improve readability and consistency in
all examples.
Bugzilla ID: 238
Cc: ko
Instead of using getopt_long return value, strcmp was used to
compare the input parameters with the struct option array. This
patch get rid of all those strcmp by directly binding each longopt
with an int enum. This is to improve readability and consistency in
all examples.
Bugzilla ID: 238
Cc: ma
On 11/24/2020 10:27 AM, Thomas Monjalon wrote:
Is it OK to keep this regression?
Ferruh, what do you suggest?
I confirm the '--txpkts' parameter is broken now, I suggest submitting a defect
for it and continue with the regression.
We have alternative for the parameter, "set txpkts " comman
> -Original Message-
> From: Ferruh Yigit
> Sent: 2020年11月24日 19:31
> To: Zhang, Tianfei ; Jerin Jacob
> ; Dumitrescu, Cristian ;
> Hemant Agrawal ; Sachin Saxena
> ; Ray Kinsella ; Neil Horman
> ; Xu, Rosen ; Wu, Jingjing
> ; Xing, Beilei ; Nithin
> Dabilpuram ; Ajit Khaparde
> ; Raveen
If there was no RTE_NET_I40E configured the static routine
str2flowtype() was not used causing compilation warning.
The str2flowtype() is moved under #ifdef RTE_NET_I40E block.
Fixes: 1be514fbcea9 ("ethdev: remove legacy FDIR filter type support")
Signed-off-by: Viacheslav Ovsiienko
---
app/te
Hi
> -Original Message-
> From: Ferruh Yigit
> Sent: Monday, November 23, 2020 5:51 PM
> Subject: Re: [PATCH] doc: announce flow API matching pattern struct changes
>
> On 11/23/2020 2:25 PM, Andrew Rybchenko wrote:
> > On 11/23/20 5:17 PM, Ferruh Yigit wrote:
> >> On 11/23/2020 1:50 PM,
On 11/24/2020 11:01 AM, Zhang, Tianfei wrote:
-Original Message-
From: Ferruh Yigit
Sent: 2020年11月24日 18:26
To: Zhang, Tianfei ; Jerin Jacob
; Dumitrescu, Cristian ;
Hemant Agrawal ; Sachin Saxena
; Ray Kinsella ; Neil Horman
; Xu, Rosen ; Wu, Jingjing
; Xing, Beilei ; Nithin
Dabilpur
There is also a testpmd patch pending about this behaviour:
https://patches.dpdk.org/patch/75353/
22/11/2020 17:55, Thomas Monjalon:
> Andrew, any comment on this v2?
> (disclosure: I did not read it)
>
>
> 18/11/2020 17:15, Gregory Etelson:
> > There is a discrepancy between RTE ETHDEV
> -Original Message-
> From: Ferruh Yigit
> Sent: 2020年11月24日 18:26
> To: Zhang, Tianfei ; Jerin Jacob
> ; Dumitrescu, Cristian ;
> Hemant Agrawal ; Sachin Saxena
> ; Ray Kinsella ; Neil Horman
> ; Xu, Rosen ; Wu, Jingjing
> ; Xing, Beilei ; Nithin
> Dabilpuram ; Ajit Khaparde
> ; Raveen
This adds ConnectX6 Lx and BlueFiled-2 to the list of supported
NICs by mlx5 PMD.
Signed-off-by: Raslan Darawsheh
---
doc/guides/nics/mlx5.rst | 46 +++-
1 file changed, 26 insertions(+), 20 deletions(-)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics
Is it OK to keep this regression?
Ferruh, what do you suggest?
23/11/2020 12:50, Slava Ovsiienko:
> Hi, Wei
>
> It was found this patch rejects the --txpkts command line settings.
> set_tx_pkt_segments() is called before device started and
> we have failure chain:
>
> set_tx_pkt_segments()
>
The rdma-core library uses callbacks to allocate and free memory
from DPDK. The memory allocation callback used the complicated
and incorrect way to get the NUMA socket ID from the context.
The context was wrong that might result in wrong socket ID
and allocating memory from wrong node.
The callba
On 11/24/2020 10:00 AM, Zhang, Tianfei wrote:
-Original Message-
From: Ferruh Yigit
Sent: 2020年11月23日 17:57
To: Zhang, Tianfei ; Jerin Jacob
; Dumitrescu, Cristian ;
Hemant Agrawal ; Sachin Saxena
; Ray Kinsella ; Neil Horman
; Xu, Rosen ; Wu, Jingjing
; Xing, Beilei ; Nithin
Dabilpur
From: Gregory Etelson
> Invalid memory release order of DevX resources caused PMD crash.
>
> 1. SQ and CQ memory must be unregistered with DevX before it is freed.
> 2. SQ objects reference to a CQ ones. Hence, SQ should be destroyed in
>advance of CQ it references to.
>
> Fixes: 6deb19e1b
This code is just ported from the Linux kernel where it is used for around
7 years, so I suppose it is pretty safe.
But of course, take your time to test it, I am fine with getting this in
the next LTS release.
Igor
On Tue, Nov 24, 2020 at 12:43 PM Zhang, Qi Z wrote:
>
>
> > -Original Messa
> -Original Message-
> From: Stephen Hemminger
> Sent: 2020年11月24日 0:07
> To: Yigit, Ferruh
> Cc: Zhang, Tianfei ; Jerin Jacob
> ; Dumitrescu, Cristian ;
> Hemant Agrawal ; Sachin Saxena
> ; Ray Kinsella ; Neil Horman
> ; Xu, Rosen ; Wu, Jingjing
> ; Xing, Beilei ; Nithin
> Dabilpuram ;
> -Original Message-
> From: Ferruh Yigit
> Sent: 2020年11月23日 17:57
> To: Zhang, Tianfei ; Jerin Jacob
> ; Dumitrescu, Cristian ;
> Hemant Agrawal ; Sachin Saxena
> ; Ray Kinsella ; Neil Horman
> ; Xu, Rosen ; Wu, Jingjing
> ; Xing, Beilei ; Nithin
> Dabilpuram ; Ajit Khaparde
> ; Raveen
Signed-off-by: Raslan Darawsheh
---
doc/guides/rel_notes/release_20_11.rst | 117 +
1 file changed, 117 insertions(+)
diff --git a/doc/guides/rel_notes/release_20_11.rst
b/doc/guides/rel_notes/release_20_11.rst
index da63707752..ff0685022e 100644
--- a/doc/guides/rel_not
The "misc" and "regex" device classes were missing from the list used to
check arguments, preventing them from being used with "--status-dev"
flag to list only devices of those types.
When adding them to the list, the list is also sorted alphabetically for
consistency.
Fixes: 81255f27c65c ("usert
> -Original Message-
> From: dev On Behalf Of Thomas Monjalon
> Sent: Tuesday, November 24, 2020 4:25 PM
> To: Igor Ryzhov ; dev ; Guo, Jia
>
> Cc: dpdk stable ; Xing, Beilei ;
> Yigit,
> Ferruh
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: fix counters
>
> I will follow the recommend
On 11/23/2020 4:09 PM, Ferruh Yigit wrote:
On 11/23/2020 1:12 PM, Guoyang Zhou wrote:
The maximum number of queues on the chip can be any value greater
than 0, it does not have to be the power of two, and remove the
operation of optical modules in the link function.
--
v1:
- remove the limit
On Tue, Nov 24, 2020 at 08:52:56AM +0100, Juraj Linkeš wrote:
> The current machine='default' build name is not descriptive. The actual
> default build is machine='native'. Add an alternative string which does
> the same build and better describes what we're building:
> machine='generic'. Leave mac
https://bugs.dpdk.org/show_bug.cgi?id=582
Bug ID: 582
Summary: [Regression Test] usertools/dpdk-devbind.py: execute
"./usertools/dpdk-devbind.py --status-dev misc"
command to get CBDMA device info failed.
Product: DPDK
I will follow the recommendation of Ferruh and i40e maintainers.
It is risky but it can be applied just before the release.
24/11/2020 04:34, Guo, Jia:
> hi, igor ryzhov and Thomas
>
> Since this remain issue is report recently and we need to reproduce the issue
> and evaluate the patch and gua
Invalid memory release order of DevX resources caused PMD crash.
1. SQ and CQ memory must be unregistered with DevX before it is freed.
2. SQ objects reference to a CQ ones. Hence, SQ should be destroyed in
advance of CQ it references to.
Fixes: 6deb19e1b2d2 ("net/mlx5: separate Rx queue objec
83 matches
Mail list logo
