Hi,
On Tue, 12 Aug 2025, Junlong Wang wrote:
Hi Maintainer,
> A general question: does the implementation somehow enforce any specific order
> of actions? Say, check that ENCAP does not follow DROP? And does it need to
> enforce, for example, a check that action DECAP is only used when the pat
Reviewed-by: Patrick Robb
On Fri, Jul 25, 2025 at 11:15 AM Luca Vizzarro
wrote:
> Add a new artifact module which provides DTS with remote and local file
> management capabilities. A new Artifact class is provided which acts as
> an abstract representation of a file that is present in any node in the
> testbed model. The
On Fri, Jul 25, 2025 at 11:15 AM Luca Vizzarro
wrote:
> Make log files behave like artifacts as dictated by the Artifact class.
> Implicitly, this will automatically place all the logs in a structured
> manner.
>
> Signed-off-by: Luca Vizzarro
> Reviewed-by: Paul Szczepanek
> ---
>
> -def s
Hi Thomas Monjalon,
First, let's describe the scenario where we discovered the problem at that
time as follows:
This error can be reproduced as follows:
1. In the client ECS with an MTU of 1500, initiate traffic using the
command "iperf3 -c {dst ip} -b 1m -M 125 -t 8000". It will trigger TCP
segm
Hi Thomas, Thank you for the greetings and link to best practices. Response to
comments inline.
Internal Use - Confidential
-Original Message-
From: Thomas Monjalon
Sent: Monday, August 11, 2025 6:22 AM
To: Bathija, Pravin
Cc: pravin.m.bathija@gmail.com; Glimcher, Boris ;
sta...@d
- modify data structures and add functions to support
add and remove memory regions/slots
- define VHOST_MEMORY_MAX_NREGIONS & modify function
vhost_user_set_mem_table accordingly
- dynamically add new memory slots via vhost_user_add_mem_reg
- remove unused memory slots via vhost_user_rem_mem_r
header definition to configure memory slots/regions
Signed-off-by: Pravin M Bathija
---
lib/vhost/rte_vhost.h | 4
1 file changed, 4 insertions(+)
diff --git a/lib/vhost/rte_vhost.h b/lib/vhost/rte_vhost.h
index 2f7c4c0080..a7f9700538 100644
--- a/lib/vhost/rte_vhost.h
+++ b/lib/vhost/rte_
add new user to mailmap
Signed-off-by: Pravin M Bathija
---
.mailmap | 1 +
1 file changed, 1 insertion(+)
diff --git a/.mailmap b/.mailmap
index 34a99f93a1..6b24ee3a30 100644
--- a/.mailmap
+++ b/.mailmap
@@ -1262,6 +1262,7 @@ Prathisna Padmasanan
Praveen Kaligineedi
Praveen Shetty
Pravi
- add protocol feature support add and removal of memory
regions/slots dynamically.
- this patch set has been tested with multiple instances of fio
connected via libblkio to spdk target backed unix domain socket.
- please apply this this patch-set to dpdk mainline as well as
version 25.03.0.
v2:
-
Remove invalid or redundant fields to make code more clean.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/benchmark.c | 20 +---
app/test-dma-perf/main.c | 19 ---
app/test-dma-perf/main.h | 12 ++--
3 files changed, 19 insertions(+), 32 del
The load_configs() function has 198 lines, and hard to understand.
This commit split it to three functions.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/main.c | 212 ---
1 file changed, 109 insertions(+), 103 deletions(-)
diff --git a/app/test-dma-perf
If some entry was not provided in section, it will be segment fault
in original impl. For example:
dpdk-test-dma-perf --config ./config.ini
config file parsing...
Segmentation fault (core dumped)
This commit support specific error information, the new output (e.g.):
This commit refactor mem_copy_benchmark() function by splitting the
data verification part into an independent function.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/benchmark.c | 153 +++---
1 file changed, 84 insertions(+), 69 deletions(-)
diff --git a/app/te
This commit add 'cache_flush' and 'test_seconds' to the global
configuration.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/benchmark.c | 4 ++--
app/test-dma-perf/config.ini | 22 +++---
app/test-dma-perf/main.c | 21 +++--
app/test-dma-perf/main.h
Because the names of dmadevs are different, this commit support list
DMA devices, so that user could quickly know how to set the lcore_dma
parameters.
The command: dpdk-test-dma-perf --config ./config.ini --list-dma
The output like:
DMA device: :7b:00.0-ch0
transfer-capa: m
This commit add global section which contains 'eal_args' entry
which specifies the EAL arguments for all testcases currently.
With this commit, users no longer need to enter EAL arguments on the
command line.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/config.ini | 17 ---
app/test-d
The original implement involved many functions and global variables,
This commit refactor it.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/benchmark.c | 7 ++-
app/test-dma-perf/main.c | 92 +--
app/test-dma-perf/main.h | 4 +-
3 files changed, 3
This commit uses argparse API to parse arguments.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/main.c | 96 ++-
app/test-dma-perf/meson.build | 2 +-
2 files changed, 63 insertions(+), 35 deletions(-)
diff --git a/app/test-dma-perf/main.c b/app/test-d
This patchset contain one bugfix and eight refactor commit for
test-dma-perf application.
Chengwen Feng (10):
app/dma-perf: fix use-after-free
app/dma-perf: add global section for config file
app/dma-perf: use argparse lib to parse argument
app/dma-perf: refactor output csv
app/dma-perf:
The test_case->eal_args was pointer the entry of cfgfile, it will be
used later, but the cfgfile was closed in load_configs(). This commit
fix it by using strdup.
Fixes: 623dc9364dc6 ("app/dma-perf: introduce DMA performance test")
Cc: sta...@dpdk.org
Signed-off-by: Chengwen Feng
---
app/test-d
Acked-by: Chengwen Feng
On 7/23/2025 9:31 PM, David Marchand wrote:
> Passing a NULL to strncmp is incorrect.
>
> + --- +
> + Test Suite : Test Cfgfile Unit Test Suite
> + --- +
> ../lib/cf
Hi Maintainer,
> A general question: does the implementation somehow enforce any specific order
> of actions? Say, check that ENCAP does not follow DROP? And does it need to
> enforce, for example, a check that action DECAP is only used when the pattern
> has matched on the very presence of an enc
On Fri, Jul 25, 2025 at 11:15 AM Luca Vizzarro
wrote:
>
> +
> +@overload
> +def make_file_path(node: Node, file_name: str, custom_path: PurePath |
> None = None) -> PurePath: ...
> +
> +
> +@overload
> +def make_file_path(node: None, file_name: str, custom_path: PurePath |
> None = None) -> Path:
From: Long Li
In most cases, netvsc is used with a VF device. The application generally
runs with better performance when all the device memory is allocated on
VF's NUMA node, as the VF device carries most of the data packets.
But sometimes netvsc may run on a different NUMA node than that of th
When packet capture is enabled, need to also notify
secondary processes to force them to do the callbacks.
Requires that all secondary processes also call rte_pdump_init()
or there will be warning about not responding secondary.
Signed-off-by: Stephen Hemminger
---
lib/pdump/rte_pdump.c | 213 +
The primary process will start to notify all secondary processes
about pdump changes. The pdump secondary process can just call
rte_pdump_init() and it take care of that.
Signed-off-by: Stephen Hemminger
---
app/pdump/main.c | 4
1 file changed, 4 insertions(+)
diff --git a/app/pdump/main.
The primary process will start to notify all secondary processes
about pdump changes. The dumpcap secondary process can just call
rte_pdump_init() and it take care of that.
Signed-off-by: Stephen Hemminger
---
app/dumpcap/main.c | 10 ++
1 file changed, 10 insertions(+)
diff --git a/app
The pdump callback can race with other cpu's in the datapath.
Handle this by using reference counts and LSB in manner
similar to seqcount and bpf code.
Signed-off-by: Stephen Hemminger
---
lib/pdump/rte_pdump.c | 48 +--
1 file changed, 46 insertions(+), 2
If primary process exits, then it is not possible (or needed)
to cleanup resources. Instead just exit after closing the
capture file.
Bugzilla ID: 1760
Fixes: a99a311ba101 ("app/pdump: exit with primary process")
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
---
app/pdump/main.c | 12 +++
If primary process exits, then it is not possible (or needed)
to cleanup resources. Instead just exit after closing the
capture file.
Bugzilla ID: 1760
Fixes: cbb44143be74 ("app/dumpcap: add new packet capture application")
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
---
app/dumpcap/ma
This patch series addresses the problem of packet capture when
the secondary process is sending/receiving by using the same
mechanism as hot plug. It also fixes some bugs on shutdown
of dumpcap (and pdump).
In draft form at this point, works but needs more testing.
Stephen Hemminger (6):
dumpc
https://bugs.dpdk.org/show_bug.cgi?id=1768
Bug ID: 1768
Summary: net/mlx5: get_mtu returns 1500 on startup instead of
kernel driver MTU
Product: DPDK
Version: 24.11
Hardware: All
OS: All
Status:
https://bugs.dpdk.org/show_bug.cgi?id=382
Stephen Hemminger (step...@networkplumber.org) changed:
What|Removed |Added
Status|UNCONFIRMED |RESOLVED
https://bugs.dpdk.org/show_bug.cgi?id=1695
Stephen Hemminger (step...@networkplumber.org) changed:
What|Removed |Added
Resolution|--- |FIXED
On Mon, Aug 11, 2025 at 09:27:06PM +0500, Khadem Ullah wrote:
> Thank you for providing these details. Sure, I will go through it (will
> performed the experiment) and come back to you.
> I totally agree that the documentation about connection tracking should be
> improved.
>
>
> On Mon, Aug 11,
Hi Vipin,
Thank you for understanding!
As Stephen mentioned:
"There is no easy way to handle the case where primary crashes; leaving
secondary process with invalid data (dangling pointers)."
Best regards,
Khadem
On Thu, Aug 07, 2025 at 12:39:47PM +, Ciara Loftus wrote:
> Replace the existing complicated logic with the use of the common
> function.
>
> Signed-off-by: Ciara Loftus
> ---
> v2:
> * use the new names for the renamed structs and functions
> ---
> drivers/net/intel/ice/ice_ethdev.h
Thank you for providing these details. Sure, I will go through it (will
performed the experiment) and come back to you.
I totally agree that the documentation about connection tracking should be
improved.
On Mon, Aug 11, 2025 at 8:17 PM Dariusz Sosnowski
wrote:
>
> > Are these the only testpmd
On Mon, Aug 11, 2025 at 01:42:59PM +, Vladimir Medvedkin wrote:
> This patch adds support for Data Center Bridging (DCB)
>
> Signed-off-by: Vladimir Medvedkin
> ---
> drivers/net/intel/ice/ice_ethdev.c | 182 +
> drivers/net/intel/ice/ice_rxtx.c | 21
> 2
On Mon, 11 Aug 2025 12:06:44 +0200
Morten Brørup wrote:
> PING for review.
>
> I think it would be good to get this patch merged early on.
>
> We should also consider upgrading the status of the
> rte_mbuf_raw_alloc/free_bulk() inline functions from experimental to stable,
> so they can be us
On Fri, 8 Aug 2025 09:55:38 -0700
Stephen Hemminger wrote:
> This is a rework of how packet capture is done in DPDK.
> The existing mechanism using callbacks has a number of problems:
> - can't work when packets are sent and received in secondary process
> because callbacks only function i
On Mon, 11 Aug 2025 11:55:31 +0200
Morten Brørup wrote:
> > From: Stephen Hemminger [mailto:step...@networkplumber.org]
> > Sent: Thursday, 3 April 2025 01.23
> >
> > Replace rte_mbuf_sanity_check() with rte_mbuf_verify()
> > to match the similar macro RTE_VERIFY() in rte_debug.h
> >
> > The te
On Mon, Aug 11, 2025 at 02:21:49AM -0400, Khadem Ullah wrote:
> Hi Dariusz Sosnowski,
>
> According to documentation, conntrack item matches a conntrack
> state after conntrack action. Your statement is also correct
> "match valid TCP packets which change TCP connection state",
> it means in t
[Public]
Hi Khadem,
Please do not use `sorry for any confusion`. Very clearly, I shared what works
and why your case is different.
Snipped
Hi Vipin,
sorry for any confusion. I am only trying to explain that these patches are in
its final state (waiting to upstream).
[VV] it is not about the s
Hello,
04/08/2025 05:54, Su Sai:
> The rte_raw_cksum_mbuf function is used to compute
> the raw checksum of a packet.
> If the packet payload stored in multi mbuf, the function
> will goto the hard case. In hard case,
> the variable 'tmp' is a type of uint32_t,
> so rte_bswap16 will drop high 16 b
Added the option to jump to a specific group.
snippets that are not supported on the root table can now call
create_jump_flow to jump to other group.
Added three new snippets that uses the jump flow:
- match Network Service Header (NSH) snippet
- match RoCE IB BTH opcode/dest_qp snippet
- Switch G
This snippet demonstrates port affinity matching in bonded ports,
ensuring packets are sent back through their ingress port.
The NR_QUEUES constant was moved to common.h to support mapping
four TX queues (0-3) to two port affinities (0,1→1 and 2,3→2).
Signed-off-by: Shani Peretz
---
examples/fl
v2:
sent mistakely as RFC - remove RFC tag, no functional changes
v1:
This patch series adds port affinity matching for bonded ports and
refactors queue management to support the new port affinity snippets.
This refactoring also enables other snippets that require access to
the queue number to uti
On Mon, Aug 11, 2025 at 01:42:56PM +, Vladimir Medvedkin wrote:
> Add the following function related to DCB:
>
> * Get number of Congestion Domains per port
> * Resolve Traffic Class(TC) by 802.1p VLAN User Priority(UP)
> * Get absolute index of the Congestion Domain by the TC
>
> Signed-off-
Hi all,
Here is a list of patches targeted for stable release 23.11.5.
The planned date for the final release is 15th August.
Please help with testing and validation of your use cases and report
any issues/results with reply-all to this mail. For the final release
the fixes and reported validati
Expose PFC statistics in xstats.
Signed-off-by: Vladimir Medvedkin
---
drivers/net/intel/ice/ice_ethdev.c | 63 ++
1 file changed, 63 insertions(+)
diff --git a/drivers/net/intel/ice/ice_ethdev.c
b/drivers/net/intel/ice/ice_ethdev.c
index 43fdbc7bc9..cdb729ee55 1006
This patch add support for Priority Flow Control (PFC)
Signed-off-by: Vladimir Medvedkin
---
drivers/net/intel/ice/ice_ethdev.c | 125 -
1 file changed, 124 insertions(+), 1 deletion(-)
diff --git a/drivers/net/intel/ice/ice_ethdev.c
b/drivers/net/intel/ice/ice_ethd
This patch adds support for Data Center Bridging (DCB)
Signed-off-by: Vladimir Medvedkin
---
drivers/net/intel/ice/ice_ethdev.c | 182 +
drivers/net/intel/ice/ice_rxtx.c | 21
2 files changed, 203 insertions(+)
diff --git a/drivers/net/intel/ice/ice_ethdev.c
Current implementation supports only symmetric PFC configuration.
In this patch two bitmasks for asymmetric PFC were added to the
struct ice_dcb_pfc_cfg.
Signed-off-by: Vladimir Medvedkin
---
drivers/net/intel/ice/base/ice_dcb.c | 96 ++-
drivers/net/intel/ice/base/ice_d
Current implementation of the ice_aq_set_mac_cfg() sets Flow Control (FC)
settings such as quanta and threshold only for LFC. This patch makes this
function Traffic Class (TC) aware, so it can configure FC for each TC
individually.
Signed-off-by: Vladimir Medvedkin
---
drivers/net/intel/ice/base
Add the following function related to DCB:
* Get number of Congestion Domains per port
* Resolve Traffic Class(TC) by 802.1p VLAN User Priority(UP)
* Get absolute index of the Congestion Domain by the TC
Signed-off-by: Vladimir Medvedkin
---
drivers/net/intel/ice/base/ice_common.c | 28
This series introduces an initial implementation of DCB and PFC to the ICE PMD.
This includes adding support for TCs in ice_aq_set_mac_cfg() and asymmetric
DCB/PFC configuration in base code.
Current implementation relies on current API and has a number of limitation and
assumptions such as:
-
Welcome in DPDK community,
Thank you for contributing.
Please check this quick guide about our tools and process:
https://core.dpdk.org/contribute/
There is a link to register to the dev mailing list
so your future patches and replies won't be moderated.
Note that you can disable receivin
Hi all/Maxime/Chenbox,
Hope you're doing well.
Please let me know if you need any more details on the VLAN offload issue,
or if you require steps to reproduce it. I'm happy to provide further
information to assist in resolving this.
Thanks,
Samar
On Wed, Aug 6, 2025 at 6:34 PM Samar Yadav wr
Hi all/Maxime/Chenbox,
I’m observing an issue with virtio_user (with vhost-net backend) where VLAN
offload doesn't seem to insert the VLAN tag, even though both vlan_tci and
ol_flags are set correctly in the mbuf. We are using DPDK Version: 24.11
(custom build) and virtio_user for exception path t
From: Pravin M Bathija
- modify data structures and add functions to support
add and remove memory regions/slots
- define VHOST_MEMORY_MAX_NREGIONS & modify function
vhost_user_set_mem_table accordingly
- dynamically add new memory slots via vhost_user_add_mem_reg
- remove unused memory slots
From: Pravin M Bathija
header definition to configure memory slots/regions
Signed-off-by: Pravin M Bathija
---
lib/vhost/rte_vhost.h | 4
1 file changed, 4 insertions(+)
diff --git a/lib/vhost/rte_vhost.h b/lib/vhost/rte_vhost.h
index 2f7c4c0080..a7f9700538 100644
--- a/lib/vhost/rte_vho
From: Pravin M Bathija
add new user to mailmap
Signed-off-by: Pravin M Bathija
---
.mailmap | 1 +
1 file changed, 1 insertion(+)
diff --git a/.mailmap b/.mailmap
index 34a99f93a1..6b24ee3a30 100644
--- a/.mailmap
+++ b/.mailmap
@@ -1262,6 +1262,7 @@ Prathisna Padmasanan
Praveen Kaligineedi
add protocol feature support add and removal of memory
regions/slots dynamically.
this patch set has been tested with multiple instances of fio
connected via libblkio to spdk target backed unix domain socket.
please apply this this patch-set to dpdk mainline as well as
version 25.03.0.
Pravin M Ba
modify data structures and add functions to support
add and remove memory regions/slots.
define VHOST_MEMORY_MAX_NREGIONS & modify function
vhost_user_set_mem_table accordingly.
dynamically add new memory slots via vhost_user_add_mem_reg.
remove unused memory slots via vhost_user_rem_mem_reg.
defin
header definition to configure memory slots/regions
Signed-off-by: Pravin M Bathija
---
lib/vhost/rte_vhost.h | 4
1 file changed, 4 insertions(+)
diff --git a/lib/vhost/rte_vhost.h b/lib/vhost/rte_vhost.h
index 2f7c4c0080..a7f9700538 100644
--- a/lib/vhost/rte_vhost.h
+++ b/lib/vhost/rte_
add new user to mailmap
Signed-off-by: Pravin M Bathija
---
.mailmap | 1 +
1 file changed, 1 insertion(+)
diff --git a/.mailmap b/.mailmap
index 34a99f93a1..6b24ee3a30 100644
--- a/.mailmap
+++ b/.mailmap
@@ -1262,6 +1262,7 @@ Prathisna Padmasanan
Praveen Kaligineedi
Praveen Shetty
Pravi
add protocol feature support add and removal of memory
regions/slots dynamically.
this patch set has been tested with multiple instances of fio
connected via libblkio to spdk target backed unix domain socket.
please apply this this patch-set to dpdk mainline as well as
version 25.03.0.
Pravin M B
Attendees:
- Aaron Conole
- Bruce Richardson
- Honnappa Nagarahalli
- Maxime Coquelin
- Morten Brørup
- Thomas Monjalon
1. Board initiatives follow up
- Cloud, AI, security initiatives
- No discussion on this topic.
2. Gov board
- any proposals for following up (meeting on Mar. 20, Q1 sync)
Hi Bruce,
Thank you for the feedback. We will later see if anything can be done
at this point.
I think that this can be solved by the following patch, please check.
https://patches.dpdk.org/project/dpdk/patch/20250804113322.53650-1-14pwcse1...@uetpeshawar.edu.pk/
Thanks & Regards,
Khadem
Members Attending: 5/11
- Aaron Conole
- Bruce Richardson
- Jerin Jacob
- Stephen Hemminger
- Thomas Monjalon (Chair)
NOTE: The Technical Board meetings take place every second Wednesday at 3 pm UTC
on
https://zoom-lfx.platform.linuxfoundation.org/meeting/9
On Mon, Jul 21, 2025 at 06:55:22AM -0400, Khadem Ullah wrote:
> In secondary processes, accessing 'dev->data->dev_private' directly can
> cause a segmentation fault if the primary process has exited or the
> shared memory is unavailable.
>
> This patch adds a check for dev/data/dev_private and use
> From: Morten Brørup [mailto:m...@smartsharesystems.com]
> Sent: Tuesday, 24 June 2025 08.13
>
> When fast releasing mbufs, the mbufs are not accessed, so do not prefetch
> them.
> This saves a mbuf load operation for each fast released TX mbuf.
>
> When fast release of mbufs is enabled for a TX
On Fri, Jul 18, 2025 at 05:09:07PM +0800, Yuan Wang wrote:
> Modification of default values should be limited to E610,
> as 82599 handles raw IP well.
>
Hi,
I think you could do with clarifying the issue here. The patch title seems to
imply that there is an issue with the E610, but in fact the c
Hi Andrew,
I mean, tunnel offload api and vxlan-decap provides information about inner
header after decap.
So, incase of a tunnelled packet, inner information would also contain the
information about inner header.
Verified that it consists of same lines and is generally equivalent to result
of the following command, except for position of names with diacritics:
sort --ignore-case --stable --field-separator='<' --key=1,1 .mailmap
--output=.mailmap
> -Original Message-
> From: Bruce Richardson
> S
Hi Vipin,
sorry for any confusion. I am only trying to explain that these patches are
in its final state (waiting to upstream). You have provided your valuable
insights and
I am very thankful for that. There was much discussion about these patches
from start to finish.
Already mentioned that with
Acked-by: Chengwen Feng
On 8/4/2025 3:42 AM, Morten Brørup wrote:
> Enabling some offload by default may conflict with a manually configured
> offload.
> Specifically, the mbuf fast release TX offload, which conflicts with multi
> segment packet TX offload, was enabled by default.
> Therefore, mb
On Thu, Aug 07, 2025 at 12:39:46PM +, Ciara Loftus wrote:
> The code for determining which Rx path to select during initialisation
> has become complicated in many intel drivers due to the amount of
> different paths and features available within each path. This commit
> aims to simplify and ge
[Public]
HI,
Snipped
Hi,
You can create a simple setup with only running testpmd with primary and
another testpmd with secondary and then see the results.
No, the reason for the primary process termination could be close or shutdown
(ctrl + c or ctrl + q) or any other.
The reason is clear: "I
LGTM
> -Original Message-
> From: Bruce Richardson
> Sent: Friday 8 August 2025 22:09
> To: dev@dpdk.org
> Cc: Marat Khalili ; Bruce Richardson
>
> Subject: [PATCH v2 1/2] devtools/mailmap_ctl: script to work with mailmap
>
> Add a script to easily add entries to, check and sort the ma
> -Original Message-
> From: Bruce Richardson
> Sent: Friday 8 August 2025 20:59
> To: Marat Khalili
> Cc: dev@dpdk.org
> Subject: Re: [PATCH 1/2] devtools/mailmap_ctl: script to work with mailmap
> > > +def check_mailmap(mailmap_path, _):
> > > +"""Check that mailmap entries are cor
On 8/11/25 13:13, Khadem Ullah wrote:
Hi Andrew,
You are right, but I haven't found any other reference to the specific
usage of the definition i.e. in correspondence with vxlan_decap,
tunneled offload API and in mbuf packet type .
According to tunnel offload API, vxlan encap/decap action, the
I am not sure where these changes stem from. From my understanding, this
enforces the creation of a DPDK environment for the TG, regardless if
it's needed or not.
The only scenario I can think of this being useful is when paired with
T-Rex. But like I've mentioned before, since the TG node is
Hi,
You can create a simple setup with only running testpmd with primary and
another testpmd with secondary and then see the results.
No, the reason for the primary process termination could be close or
shutdown (ctrl + c or ctrl + q) or any other.
The reason is clear: "In secondary processes, ac
Looks mostly fine but as noted in the earlier patch, should be * not -.
Just one small issue:
On 07/08/2025 15:50, Dean Marx wrote:
diff --git a/dts/tests/TestSuite_mtu.py b/dts/tests/TestSuite_mtu.py
index d5b3fe02af..0d36f18b00 100644
--- a/dts/tests/TestSuite_mtu.py
+++ b/dts/tests/TestSuite
[Public]
Hi Khadem
snipped
Hi Vipin,
Glad you got the reason.
I have only checked it in testpmd, any other application which provides
primary-secondary support could also follow the same model.
This patch only adds stability and robustness to primary-secondary
applications. Primary application
Looks fine but looks like an unordered list is done with asterisks, see
the rst reference[1].
[1]
https://www.sphinx-doc.org/en/master/usage/restructuredtext/basics.html#lists-and-quote-like-blocks
Because the names of dmadevs are different, this commit support list
DMA devices, so that user could quickly know how to set the lcore_dma
parameters.
The command: dpdk-test-dma-perf --config ./config.ini --list-dma
The output like:
DMA device: :7b:00.0-ch0
transfer-capa: m
On 8/8/25 19:55, Stephen Hemminger wrote:
This adds new feature port mirroring to the ethdev layer.
And standalone tests for those features.
Signed-off-by: Stephen Hemminger
[snip]
@@ -513,23 +551,25 @@ static_assert(sizeof(struct ethdev_mp_response) <=
RTE_MP_MAX_PARAM_LEN,
int
ethdev
accepted in next-dts, thanks.
Reviewed-by: Luca Vizzarro
On Thu, Aug 07, 2025 at 12:39:45PM +, Ciara Loftus wrote:
> Order the elements in the enum of Rx function types starting from
> smallest SIMD width to largest, similar to the order in the i40e and
> ice drivers.
>
> Signed-off-by: Ciara Loftus
> ---
Acked-by: Bruce Richardson
It seems that you forgot to add the Reviewed-by tags.
Reviewed-by: Luca Vizzarro
This commit refactor mem_copy_benchmark() function by splitting the
data verification part into an independent function.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/benchmark.c | 153 +++---
1 file changed, 84 insertions(+), 69 deletions(-)
diff --git a/app/te
The load_configs() function has 198 lines, and hard to understand.
This commit split it to three functions.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/main.c | 212 ---
1 file changed, 109 insertions(+), 103 deletions(-)
diff --git a/app/test-dma-perf
Remove invalid or redundant fields to make code more clean.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/benchmark.c | 20 +---
app/test-dma-perf/main.c | 24
app/test-dma-perf/main.h | 12 ++--
3 files changed, 19 insertions(+), 3
This commit add 'cache_flush' and 'test_seconds' to the global
configuration.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/benchmark.c | 4 ++--
app/test-dma-perf/config.ini | 22 +++---
app/test-dma-perf/main.c | 21 +++--
app/test-dma-perf/main.h
This commit add global section which contains 'eal_args' entry
which specifies the EAL arguments for all testcases currently.
With this commit, users no longer need to enter EAL arguments on the
command line.
Signed-off-by: Chengwen Feng
---
app/test-dma-perf/config.ini | 15 +++---
app/test-dm
1 - 100 of 135 matches
Mail list logo
