18/07/2025 00:05, Thomas Monjalon:
> The main mlx5 doc (for net driver) is improved
> with better explanations, better organization, better readability,
> and will be a better skeleton for future detailed explanations.
>
> Maayan Kashani (1):
> doc: add testpmd command exam
18/07/2025 17:36, Stephen Hemminger:
> Looks better, it would be good to look at the table of contents
> (right column in html) to see if could be better in complex document
> like this.
Yes I've paid attention to the table of contents.
Thanks for the suggestions below.
> For example the Usage, d
Add 2 style classes for tables:
- numbered-table: numbering table rows
- punchcard: colouring filled cells
They can be used by inserting the class comment before the table:
.. rst-class:: numbered-table
.. rst-class:: punchcard
Signed-off-by: Thomas Monjalon
---
doc/guides
No need to list all devices of a family.
Instead, a list of families is given with technical details.
Signed-off-by: Thomas Monjalon
---
doc/guides/nics/mlx4.rst | 5 +-
doc/guides/nics/mlx5.rst | 91 +---
doc/guides/platform/mlx5.rst | 9 ++--
doc
The main mlx5 doc (for net driver) is improved
with better explanations, better organization, better readability,
and will be a better skeleton for future detailed explanations.
Maayan Kashani (1):
doc: add testpmd command examples in mlx5 guide
Thomas Monjalon (3):
doc: simplify mlx5
From: Maayan Kashani
Adding testpmd command examples to mlx5 guide,
either inline if short enough
or using external links to a GitHub repository hosting tests.
Signed-off-by: Maayan Kashani
---
doc/guides/nics/mlx5.rst | 138 +++
1 file changed, 138 insertio
16/07/2025 12:15, Thomas Monjalon:
> Time has passed since Mellanox acquisition by NVIDIA.
> No need to explain this anymore.
>
> Signed-off-by: Thomas Monjalon
Applied
15/07/2025 14:11, Thomas Monjalon:
> When closing the primary process, an error occurs when closing ports:
>
> Error closing ports
> EAL: failed to send to (/var/run/dpdk/dpdk_X/mp_socket_Y) due to Bad file
> descriptor
> EAL: Fail to send request /var/run/dpdk/dpdk_X/mp_socke
09/07/2025 17:01, Stephen Hemminger:
> On Tue, 8 Jul 2025 10:09:54 +0300
> Maayan Kashani wrote:
>
> > +static void
> > +exit_cleanup(void)
> > +{
> > + unsigned int i;
> > +
> > + RTE_LOG(INFO, APP, "Close ports.\n");
> > + for (i = 0; i < num_ports; i++) {
> > + if (rte_eal_proc
16/07/2025 12:14, Thomas Monjalon:
> Set a background color to table header
> so that it is visually easier to read.
>
> Signed-off-by: Thomas Monjalon
Applied
16/07/2025 12:37, Bruce Richardson:
> On Wed, Jul 16, 2025 at 12:15:16PM +0200, Thomas Monjalon wrote:
> > Time has passed since Mellanox acquisition by NVIDIA.
> > No need to explain this anymore.
> >
> > Signed-off-by: Thomas Monjalon
> > ---
>
>
Time has passed since Mellanox acquisition by NVIDIA.
No need to explain this anymore.
Signed-off-by: Thomas Monjalon
---
doc/guides/compressdevs/mlx5.rst | 7 ---
doc/guides/cryptodevs/mlx5.rst| 7 ---
doc/guides/nics/mlx4.rst | 7 ---
doc/guides/nics/mlx5.rst
Set a background color to table header
so that it is visually easier to read.
Signed-off-by: Thomas Monjalon
---
doc/guides/custom.css | 5 +
1 file changed, 5 insertions(+)
diff --git a/doc/guides/custom.css b/doc/guides/custom.css
index b662abb34e..7db37ffc68 100644
--- a/doc/guides
Song Jiale
Signed-off-by: Thomas Monjalon
---
examples/multi_process/symmetric_mp/main.c | 27 --
1 file changed, 5 insertions(+), 22 deletions(-)
diff --git a/examples/multi_process/symmetric_mp/main.c
b/examples/multi_process/symmetric_mp/main.c
index de16608a0f..f7d8439cd4 10
Ferruh Yigit has no time this year for ethdev maintenance.
Signed-off-by: Thomas Monjalon
---
MAINTAINERS | 1 -
1 file changed, 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 0e9357f3a3..b96496adb7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -435,7 +435,6 @@ F: app/test
10/07/2025 16:37, Andre Muezerie:
> On Tue, Jul 01, 2025 at 04:17:20PM +0200, Thomas Monjalon wrote:
> > 23/05/2025 01:37, Andre Muezerie:
> > > The functions rte_rcu_qsbr_dq_create and rte_rcu_qsbr_dq_reclaim establish
> > > no limit on the size of each element in the
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v25.07-rc3
There are 86 new patches in this snapshot.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_25_07.html
Please test and report new issues on https://bugs.dpdk.org
Only docu
11/04/2025 18:15, Nandini Persad:
> I have uploaded all these known issues into Bugzilla,
> so they are not needed here anymore.
>
> Signed-off-by: Nandini Persad
Applied, thanks.
25/06/2025 06:07, Patrick Robb:
> Applied to next-dts, thanks Dean.
I'm almost sure it has overriden some doc added recently by Nicholas Pratte.
Anyway it is too difficult to understand what is changed in this series,
because there are too many unrelated changes.
I prefer not pulling this series
09/07/2025 10:23, Volodymyr Fialko:
> Fix a mismatch between the signature of the cryptodevs_init() function
> and the arguments passed to it during the call. This caused incorrect
> initialization of queue pairs in ipsec-secgw example.
>
> Fixes: 253265f8fb97 ("examples/ipsec-secgw: reduce queues
21/05/2025 09:27, Shani Peretz:
> The snippet enables direct packet re-routing to kernel by using
> the new RTE_FLOW_ACTION_TYPE_SEND_TO_KERNEL action.
>
> Added support for snippet-specific configurations:
> * port configuration: set promiscuous mode / flow isolation mode
> * Flow configurati
> > make clean is unable to delete build directory because *.o files are not
> > removed.
> >
> > The other way to fix this would be to add all the c files into SRCS-y.
> >
> > Signed-off-by: Tanzeel Ahmed
>
> I checked and looks good on my side
Applied with fixes line, thanks.
21/05/2025 19:23, Bing Zhao:
> In some rare case, the libc memory heap allocation may fail and
> return NULL pointer. Before accessing the memory via the pointer,
> the NULL pointer check should be done to ensure the code locates
> in the safe side and no crash.
>
> Some newer GCC version will che
09/07/2025 15:30, Burakov, Anatoly:
> On 7/8/2025 9:09 AM, Maayan Kashani wrote:
> > Device was started but not stopped on exit signal.
> > Added port stop and close on exit.
> >
> > Fixes: af75078fece3 ("first public release")
> > Cc: sta...@dpdk.org
> >
> > Signed-off-by: Maayan Kashani
> > --
20/05/2025 20:37, mamcg...@microsoft.com:
> From: Matthew G McGovern
>
> The example apps have a few different failure modes when enabling promiscuous
> mode:
>
> - testpmd will warn about the failure and continue.
>
> - l3fwd has a flag '-P' to explicitly require promiscuous mode.
>
> - symm
09/07/2025 15:28, Bruce Richardson:
> On Wed, Jul 09, 2025 at 02:06:29PM +0100, Anatoly Burakov wrote:
> > IAVF driver does not support 16-byte descriptors (because there is no PF
> > that can support a VF using 16-byte descriptor), but if IAVF is built with
> > a flag that enables 16-byte descript
07/07/2025 12:06, Gregory Etelson:
> DPDK auxiliary bus first creates a list of known devices in the
> `auxiliary_bus.device_list` and then tries to attach a driver to each
> device on that list.
>
> If the driver attachment has failed, a device will remain on the list.
>
> The device destruction
The best is to have only rte_pcapng to depend on libpcap, as you did.
If the problem is only in ABI check, this is what we need to fix.
I'm not sure how to fix this.
> From: Thomas Monjalon
> Sent: Thursday, July 3, 2025 7:27 AM
> To: Dylan Schneider
> Cc: dev@dpdk.org ; Res
kip these libraries if they are not built?
> Or better question: How does the abi-check even know about these libraries if
> they are never built?
>
> Thanks!
> Dylan
>
>
>
> From: Thomas Monjalon
> Sent: Monday, June 30, 2025 8:28
03/07/2025 12:21, Bruce Richardson:
> Some older compilers e.g. gcc 8.5, do not support overriding
> -march=native with another architecture, leading to build warnings such
> as reported in Bugzilla (link below). Add a check for that case, and
> explicitly add the avx512 flags if necessary.
>
> No
01/07/2025 16:48, Nitin Saxena:
> On Mon, Jun 30, 2025 at 4:27 PM Bruce Richardson
> wrote:
> >
> > C++ does not allow zero-sized unions - they end up being of size 1-byte,
> > which leads to C/C++ compatibility issues, flagged by the compiler.
> >
> > lib/node/rte_node_mbuf_dynfield.h:78:2: err
01/07/2025 15:44, Bruce Richardson:
> On Tue, Jul 01, 2025 at 03:15:24PM +0200, Thomas Monjalon wrote:
> > This test triggers failures in the CI:
> >
> > event_vector_adapter_autotest FAIL
> > 3.39s (exit status 255 or signal 127 SIGinvalid)
> >
&
23/05/2025 01:37, Andre Muezerie:
> The functions rte_rcu_qsbr_dq_create and rte_rcu_qsbr_dq_reclaim establish
> no limit on the size of each element in the defer queue.
Very good, we need more unlimited API in DPDK.
> With DPDK 25.11 a hard limit will be set (``RTE_QSBR_ESIZE_MAX``).
I think it
01/07/2025 13:42, Vanshika Shukla:
> From: Stephen Hemminger
> > On Wed, 11 Jun 2025 12:40:36 +0530
> > vanshika.shu...@nxp.com wrote:
> >
> > > From: Vinod Pullabhatla
> > >
> > > Add support to set Tx rate on DPAA platform through PMD APIs
> > >
> > > Signed-off-by: Vinod Pullabhatla
> > > Si
This test triggers failures in the CI:
event_vector_adapter_autotest FAIL
3.39s (exit status 255 or signal 127 SIGinvalid)
Disable it until we have a fix.
Bugzilla ID: 1720
Fixes: 2eca0f4cd5da ("test/event: fix event vector adapter timeouts")
Signed-off-by: Thoma
30/06/2025 12:50, Bruce Richardson:
> C++ does not allow zero-sized unions - they end up being of size 1-byte,
> which leads to C/C++ compatibility issues, flagged by the compiler.
>
> lib/node/rte_node_mbuf_dynfield.h:78:2: error: union has size 0 in C,
> size 1 in C++ [-Werror,-Wextern-c-compa
15:50, Dylan Schneider:
> Hey Thomas, just wanted to confirm, I see the ARM build passing in CI. Is
> there a reason it would pass there but not on your dev machine?
>
>
>
> From: Dylan Schneider
> Sent: Friday, June 27, 2025 11:46 AM
> T
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v25.07-rc2
There are 141 new patches in this snapshot.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_25_07.html
Most significant changes are in multiple drivers.
Please test and r
27/06/2025 17:27, Bruce Richardson:
> In the case where we use the meson python "find_installation()" function
> to get our python binary, we can fail the configure/setup step if the
> elftools module is missing. This avoids later errors on build when the
> module is missed.
>
> Old output (error
18/06/2025 14:39, Marat Khalili:
> Test list is currently generated by scanning all files for macros
> starting with `REGISTER_` and ending with `_TEST`. Unfortunately, this
> was done line-by-line, and macros split into several lines were silently
> ignored resulting in tests being excluded from t
16/06/2025 17:05, Jerin Jacob:
> On Mon, Jun 16, 2025 at 2:02 PM wrote:
> >
> > From: Pavan Nikhilesh
> >
> > Fix missing feature matrix addition for event device DMA and
> > vector adapters.
> >
> > Fixes: 66a30a29387a ("eventdev/dma: introduce DMA adapter")
> > Fixes: e12c3754da7a ("eventdev/ve
12/06/2025 05:08, Stephen Hemminger:
> Prefer using simple structure assignment instead of memcpy.
> Using a structure assignment preserves type information and
> compiler checks types already.
>
> Signed-off-by: Stephen Hemminger
Applied, thanks.
24/06/2025 10:03, Morten Brørup:
> Coverity reports some defects, where the root cause seems to be negative
> return value from sysconf(_SC_PAGESIZE) not being handled.
> This series addresses those defects in the DPDK libraries.
>
> PS: "_SC_PAGESIZE" has the alias "_SC_PAGE_SIZE". Both are cover
> Bing Zhao (5):
> net/mlx5: add new devarg for Tx queue consecutive memory
> net/mlx5: calculate the memory length for all Tx queues
> net/mlx5: allocate and release unique resources for Tx queues
> net/mlx5: pass the information in Tx queue start
> net/mlx5: use consecutive memory for T
26/06/2025 17:13, Thomas Monjalon:
> 26/06/2025 16:26, Stephen Hemminger:
> > On Wed, 25 Jun 2025 15:42:02 +0200
> > Thomas Monjalon wrote:
> >
> > > diff --git a/lib/ethdev/ethdev_linux_ethtool.c
> > > b/lib/ethdev/ethdev_linux_ethtool.c
> > >
29/06/2025 00:49, Stephen Hemminger:
> On Sat, 28 Jun 2025 18:45:44 +0200
> Morten Brørup wrote:
>
> > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > Sent: Friday, 27 June 2025 20.30
> > >
> > > 27/06/2025 19:49, Morten Brørup:
27/06/2025 09:53, Jerin Jacob:
> On Thu, Jun 19, 2025 at 6:52 PM Pavan Nikhilesh Bhagavatula
> wrote:
> >
> > >Sent: Thursday, June 12, 2025 05:43
> > >To: Jerin Jacob; tho...@monjalon.net; david.march...@redhat.com; Pavan
> > >Nikhilesh Bhagavatula
> > >Cc: dev@dpdk.org
> > >Subject: [PATCH] tes
27/06/2025 23:07, Stephen Hemminger:
> On Thu, 26 Jun 2025 18:40:06 -0700
> "dimon.zhao" wrote:
> > Dimon Zhao (16):
> > net/nbl: add doc and minimum nbl build framework
> > net/nbl: add simple probe/remove and log module
> > net/nbl: add PHY layer definitions and implementation
> > net/nb
26/06/2025 16:14, Nitin Saxena:
> On Thu, Jun 26, 2025 at 7:29 PM Stephen Hemminger
> wrote:
> > On Thu, 19 Jun 2025 21:14:49 +0530
> > Nitin Saxena wrote:
> >
> > > +#ifndef RTE_NODE_MBUF_PERSISTENT_FIELDS_SIZE
> > > +/** Size of persistent mbuf fields */
> > > +#define RTE_NODE_MBUF_PERSISTENT_
27/06/2025 21:33, Pekka Riikonen:
> On 2025-06-27 19:00, Thomas Monjalon wrote:
> > 20/06/2025 13:47, priik...@iki.fi:
> >> Check if kernel returns 0 interrupt vectors and try another interrupt
> >> type in that case. Failing to check the vector count can select an
27/06/2025 19:49, Morten Brørup:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > Sent: Friday, 27 June 2025 19.35
> >
> > 27/06/2025 18:38, Morten Brørup:
> > > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > > Sent: Friday,
27/06/2025 19:46, Dylan Schneider:
> Can you tell me the build command you're using to produce those errors? I
> have ran the builds on my test machine and cannot reproduce these. Thanks!
I run devtools/test-meson-builds.sh with an Arm toolchain installed.
Message:
=
Libraries E
09/06/2025 23:19, Schneide:
> From: Dylan Schneider
>
> Allow the user to specify protocol link type when creating pcapng files.
> This change is needed to specify the protocol type in the pcapng file,
> DLT_EN10MB specifies ethernet packets only. This will allow dissectors
> for other protocols
27/06/2025 18:38, Morten Brørup:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > Sent: Friday, 27 June 2025 17.58
> >
> > 24/06/2025 10:03, Morten Brørup:
> > > + if ((ssize_t)page_size < 0)
> > > +
27/06/2025 18:47, Morten Brørup:
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > Sent: Friday, 27 June 2025 17.56
> >
> > 24/06/2025 10:03, Morten Brørup:
> > > In eal_mem_set_dump(), when madvise() failed, an incorrect reason was
> > > logged
09/06/2025 23:19, Schneide:
> From: Dylan Schneider
>
> Allow the user to specify protocol link type when creating pcapng files.
> This change is needed to specify the protocol type in the pcapng file,
> DLT_EN10MB specifies ethernet packets only. This will allow dissectors
> for other protocols
20/06/2025 13:47, priik...@iki.fi:
> Check if kernel returns 0 interrupt vectors and try another interrupt
> type in that case. Failing to check the vector count can select an
> interrupt type that's unusable.
>
> Signed-off-by: Pekka Riikonen
Please could you be explicit about the use case you
24/06/2025 10:03, Morten Brørup:
> + if ((ssize_t)page_size < 0)
> + rte_panic("sysconf(_SC_PAGESIZE) failed: %s",
> + errno == 0 ? "Indeterminate" :
> strerror(errno));
We don't want more rte_panic().
You could log the problem a
24/06/2025 10:03, Morten Brørup:
> In eal_mem_set_dump(), when madvise() failed, an incorrect reason was
> logged.
>
> Signed-off-by: Morten Brørup
> Acked-by: Anatoly Burakov
We need to track the root cause with Fixes: please.
24/06/2025 21:58, Edvard Fagerholm:
> RTE_FORCE_INTRINSICS with a C++ compiler causes rte_atomic.h and
> rte_byteorder.h to emit on x86 an extern "C" without a closing
> brace.
>
> Signed-off-by: Edvard Fagerholm
> Acked-by: Bruce Richardson
Added root cause tracking:
Fixes: 719834a6849e ("use
27/06/2025 12:44, Thomas Monjalon:
> 20/06/2025 15:37, Bruce Richardson:
> > On Fri, Jun 20, 2025 at 02:30:23PM +0100, Anatoly Burakov wrote:
> > > This issue was reported by static analysis. It is a false positive,
> > > because both `rte_socket_count` and `rte_so
16/06/2025 11:55, Anatoly Burakov:
> This issue was reported by static analysis. It is a false positive,
> because both `rte_socket_count` and `rte_socket_id_by_idx` only report
> information about physical sockets (so return value of -1 cannot happen,
> as we only get into this function when socke
20/06/2025 15:37, Bruce Richardson:
> On Fri, Jun 20, 2025 at 02:30:23PM +0100, Anatoly Burakov wrote:
> > This issue was reported by static analysis. It is a false positive,
> > because both `rte_socket_count` and `rte_socket_id_by_idx` only report
> > information about physical sockets, and these
27/06/2025 11:53, Bruce Richardson:
> On Fri, Jun 20, 2025 at 09:44:15AM +0100, Bruce Richardson wrote:
> > On Mon, Jun 16, 2025 at 11:49:40AM +0100, Bruce Richardson wrote:
> > > Coverity (correctly) identified an issue[1] where, after the recent
> > > rework[2], the internal flag, used by argpars
12/06/2025 16:46, Andre Muezerie:
> On Thu, Jun 12, 2025 at 02:41:05AM +0200, Thomas Monjalon wrote:
> > 06/05/2025 03:43, Andre Muezerie:
> > > The asprintf function is not part of the C standard library but is a
> > > GNU extension commonly available in Unix-l
> > When doing a build for a target that already has the instruction sets for
> > AVX2/AVX512 enabled, skip emitting the AVX compiler flags, or the
> > x86-64-v4 '-march' flags, as they are unnecessary. Instead, when the
> > default flags
> > produce the desired output, just use them unmodified, a
10/06/2025 11:33, Bruce Richardson:
> Rather than specifying a minimum compiler version, update the docs to
> recommend a particular compiler version. In other words, earlier
> versions may work, but are not officially supported, or may give reduced
> functionality.
>
> Since we don't require that
20/06/2025 12:42, Junfeng Guo:
> This patchset support IPIP Tunnel in NT2HWS and HWS, including the
> following {IPv4 x IPv6} combinations:
> - IPv4 over IPv4
> - IPv4 over IPv6
> - IPv6 over IPv4
> - IPv6 over IPv6
>
> This feature cover both basic IPIP and IPIP over VXLAN Tunnel types.
>
>
27/06/2025 10:25, Bing Zhao:
> The txq_calc_wqebb_cnt() should be consistent with the calculation in
> the function mlx5_txq_devx_obj_new(). Or when the input descriptor
> number is 512, the WQE size will be wrongly considered to be 30 when
> no max_inline_data is zero in some cases. The total numb
26/06/2025 15:32, Dariusz Sosnowski:
> Thank you very much for changes and detailed descriptions.
> It helped a lot during review.
>
> Acked-by: Dariusz Sosnowski
>
> On Thu, Jun 26, 2025 at 09:07:02AM -0400, Khadem Ullah wrote:
> > v2:
> > - Added missing check for AGE + CT conflict in flow_dv
26/06/2025 09:59, Gregory Etelson:
> Support SAMPLE flow action in the non-template API.
>
> Bing Zhao (1):
> net/mlx5: fix the table flags of mirror action
>
> Gregory Etelson (3):
> net/mlx5: add a stand alone function for mirror creation
> net/mlx5: add functions for non template sample
26/06/2025 16:29, Stephen Hemminger:
> On Thu, 26 Jun 2025 13:18:18 +
> Bing Zhao wrote:
>
> > Hi Stephen,
> >
> > Thanks for your review and comments. I will add the description about the
> > new devarg in our mlx5.rst file to have a detailed description.
> > Indeed, after some review and
26/06/2025 14:53, Stephen Hemminger:
> On Wed, 18 Jun 2025 12:01:45 +0200
> Thomas Monjalon wrote:
>
> > 18/06/2025 09:39, Morten Brørup:
> > > > Why are we still building one .so file per DPDK library, instead of just
> > > > building one big dpdk.so for a
26/06/2025 16:26, Stephen Hemminger:
> On Wed, 25 Jun 2025 15:42:02 +0200
> Thomas Monjalon wrote:
>
> > diff --git a/lib/ethdev/ethdev_linux_ethtool.c
> > b/lib/ethdev/ethdev_linux_ethtool.c
> > index ec42d3054a..f508cdba6c 100644
> > --- a/lib/ethdev/eth
15/06/2025 09:41, Gregory Etelson:
> The PMD reads auxiliary network device name from the Linux SYSFS.
>
> The current implementation closed directory context before it copied
> a file name from that directory into internal buffer.
>
> The patch closes SYSFS directory after file name was copied.
25/06/2025 11:43, Gregory Etelson:
> The MLX5 PMD keeps non-essential flow data in an auxiliary structure
> to reduce flow L1 cache usage.
>
> The auxiliary data location differs in HWS and non-template flows.
>
> The PMD tried to fetch HWS flow table from a non-template flow object
> and accesse
19/06/2025 09:17, Rongwei Liu:
> Rdma-core exposes E-Switch Manager vport metadata
> for matching in flow rules.
> Use that metadata when available.
>
> Signed-off-by: Rongwei Liu
> Acked-by: Dariusz Sosnowski
Applied, thanks.
25/06/2025 11:32, Maayan Kashani:
> When there is not enough memory, counter pool creation fails.
> As a result, the pool is being destroyed.
> Since not all pointers were initialized during creation,
> Need to check for null pointer in destruction.
>
> Fixes: 13ea6bdcc7ee ("net/mlx5: support coun
25/06/2025 17:00, Maayan Kashani:
> Cross NUMA support means that when there is no
> memory on the local NUMA, use other available
> NUMA memory for port initialization and start.
>
> If mlx5 malloc with specified socket failed,
> malloc function would return an error.
> To support cross NUMA,
> N
igned-off-by: Thomas Monjalon
---
lib/ethdev/ethdev_linux_ethtool.c | 24 ++--
1 file changed, 22 insertions(+), 2 deletions(-)
diff --git a/lib/ethdev/ethdev_linux_ethtool.c
b/lib/ethdev/ethdev_linux_ethtool.c
index ec42d3054a..f508cdba6c 100644
--- a/lib/e
.org/archives/test-report/2025-June/886815.html
We are working to resolve the Windows errors currently.
We'll have to re-run tests on the patches when it will be resolved in the main
branch.
> -----邮件原件-----
> 发件人: Thomas Monjalon
> 发送时间: 2025年6月18日 17:25
> 收件人: 王颢
> 抄送
18/06/2025 09:39, Morten Brørup:
> > Why are we still building one .so file per DPDK library, instead of just
> > building one big dpdk.so for all DPDK libraries?
> > I think it's legacy from when DPDK libraries were versioned individually,
> > and
> > thus not relevant anymore.
I think it helps
18/06/2025 09:16, Morten Brørup:
> > diff --git a/lib/meson.build b/lib/meson.build
> > index 1934cb4a29..87b567f01b 100644
> > --- a/lib/meson.build
> > +++ b/lib/meson.build
> > @@ -13,7 +13,7 @@ libraries = [
> > 'kvargs', # eal depends on kvargs
> > 'argparse',
> > 't
16/06/2025 09:37, David Marchand:
> On Thu, Jun 12, 2025 at 4:18 PM Andre Muezerie
> wrote:
> > diff --git a/drivers/net/r8169/base/rtl8125a_mcu.c
> > b/drivers/net/r8169/base/rtl8125a_mcu.c
> > index 5a69b3e094..c9bf5fc6ad 100644
> > --- a/drivers/net/r8169/base/rtl8125a_mcu.c
> > +++ b/drivers/
This is the documentation to prepare mlx5 on Windows:
https://docs.nvidia.com/networking/display/winof2v290/devx+interface
13/06/2025 23:48, Patrick Robb:
> Good catch David on this system having a partial install of mlx5dev
> header/library.
>
> NVIDIA guys, do any of you have a link to the cur
16/06/2025 08:53, Tomasz Duszynski:
> RTE_LIB_PMU is defined by build system automatically if DPDK is build
> for Linux. Otherwise it's missing.
>
> That said all cases where conditional compilation is required
> can be handled without introducing other macros.
You don't need to know if it is com
16/06/2025 08:53, Tomasz Duszynski:
> @@ -86,6 +86,7 @@ always_enable = [
> 'ring',
> 'stack',
> 'telemetry',
> +'pmu',
> ]
This list is alphabetically sorted.
What is the justification for always enabling PMU lib?
Is it a good idea to always enable an experime
16/06/2025 08:53, Tomasz Duszynski:
> +static inline int
> +pmu_arch_init(void)
> +{
> + if (arch_ops && arch_ops->init)
> + return arch_ops->init();
These are not boolean values, please compare explicitly with NULL.
14/04/2025 10:45, Thomas Monjalon:
> The guides having a diverse list of multiple drivers or tools
> are easier to browse with an index limited
> to the first headings (depth 1).
>
> Signed-off-by: Thomas Monjalon
Applied
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v25.07-rc1
There are 542 new patches in this snapshot.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_25_07.html
Highlights of 25.07-rc1:
- Mucse RNP driver
- ZTE St
12/06/2025 03:42, Jiawen Wu:
> From: Thomas Monjalon
> > 06/06/2025 10:01, Jiawen Wu:
> > > There were some defects in the original configuration for flow director
> > > filter. Now make the following improvements:
> > >
> > > 1) Fix incorrect parsin
05/05/2025 22:40, Andre Muezerie:
> Existing DPDK code uses getline(), which is a POSIX function and is
> not available in the Windows APIs.
>
> Instead of rewriting it or coming up with some other replacement, this
> patch makes use of the implementation provided by NetBSD to make it
> possible t
06/05/2025 03:43, Andre Muezerie:
> The asprintf function is not part of the C standard library but is a
> GNU extension commonly available in Unix-like systems. It dynamically
> allocates memory to store the formatted output string, similar to
> sprintf, but avoids buffer overflow issues by automa
06/06/2025 10:01, Jiawen Wu:
> There were some defects in the original configuration for flow director
> filter. Now make the following improvements:
>
> 1) Fix incorrect parsing to ntuple filter when set the pattern likes:
>flow create ... ipv4 / udp dst is ... / raw ... / end actions ... / e
Hello,
07/06/2025 04:30, Junlong Wang:
> modify some mac config issues,
> which were discovered during the testing process.
>
> Signed-off-by: Junlong Wang
That's not how we fix issues in general in DPDK.
We want to provide tracking history, so:
- we split the fixes per issue
- we provide the c
10/06/2025 16:50, Bruce Richardson:
> Add an entry in the release notes about the "-l" flag now being the
> same as the "--lcores" flag. Refer to the GSG for examples.
>
> Fixes: 1ea3833e9c4e ("eal: merge corelist and core mapping options")
>
> Signed-off-by: Bruce Richardson
Applied, thanks.
08/02/2025 21:21, Stephen Hemminger:
> This patch series reduces use of memcpy and rte_memcpy
> in DPDK. It changes memcpy to a simple assignment operator
> which easier to read, generates the same code, and
> keeps type safety.
>
> Historically memcpy was used in textbooks because there
> was no
> Stephen Hemminger (7):
> latencystats: handle fractional cycles per ns
> latencystats: do not use floating point
> latencystats: fix log messages
> latencystats: update include files
> latencystats: enforce that unused callback function is NULL
> latencystats: add metric for number of
10/06/2025 16:12, Stephen Hemminger:
> The cycle counts do not need to be stored as floating point.
> Instead keep track of latency in cycles, and convert to
> nanoseconds when read.
>
> Use scaled math with exponential Weighted Moving Average weight
> of .25 to avoid use of floating point for tha
> Bruce Richardson (3):
> argparse: add support for string and boolean args
> argparse: make argparse EAL-args compatible
> argparse: use enums to remove max-value defines in lists
Applied, thanks.
1 - 100 of 1730 matches
Mail list logo
