On Sun, Mar 10, 2024 at 8:35 PM Honnappa Nagarahalli
wrote:
> > We mentionned during the weekly release meeting, it seemed too late
> > for merging this work in the 24.03 release.
> >
> > Looking at v8, I have comments on this series:
> > - rather than put a Depends-on: tag, take the lib: patch as
Hello,
Commit 9a9eb104ed ("ethdev: parse multiple representor devargs") removes
the following variable initialization in rte_eth_devargs_parse():
memset(eth_da, 0, sizeof(*eth_da));
This in turn causes a failure in ixgbe PCI probe on Arm server:
eth_ixgbe_pci_probe(): unsupport
Hi All,
I want to use the dpdk application with RSS and flow director.
is possible to use both at a time in application.
In RSS, I am using
action_rss_tcp.types = ETH_RSS_NONFRAG_IPV4_TCP | ETH_RSS_L3_SRC_ONLY |
ETH_RSS_L3_DST_ONLY;
to receive the similar traffic to same core.
One specific cas
On 3/7/24 11:34, David Marchand wrote:
For vDPA devices, vq are not locked once the device has been configured
at runtime.
On the other hand, we need to hold the vq lock to evaluate vq->access_ok,
invalidate vring addresses and translate them.
Move vring address update earlier and, when vDPA
On 3/9/2024 4:03 AM, Stephen Hemminger wrote:
Testpmd is misusing EAL logtype for some errors.
Since the code directly has a macro for logging, use that.
Also, replace fprintf(stderr, ...) with TESTPMD_LOG where
appropriate.
Signed-off-by: Stephen Hemminger
Acked-by: Huisong Li
Acked-by:
Hi Team,
We are validating the fdir with test-pmd tool. We are getting below error
while trying to add the flow create rule for the same.
Syntax:
testpmd> flow create 0 ingress pattern eth / ipv4 src is ipv4 dst is
/ tcp src is dst is / end actions rss
queues 2 3 end / end
rule:
flow cre
On 3/7/24 11:36, David Marchand wrote:
As the vhost library may receive a request for an unsupported request,
it is necessary to check msg_handler before checking if locking queue
pairs is requested.
Coverity issue: 415049
Fixes: 5e8fcc60b59d ("vhost: enhance virtqueue access lock asserts")
On 3/11/2024 9:07 AM, Thierry Herbelot wrote:
> Hello,
>
> Commit 9a9eb104ed ("ethdev: parse multiple representor devargs") removes
> the following variable initialization in rte_eth_devargs_parse():
>
> memset(eth_da, 0, sizeof(*eth_da));
>
> This in turn causes a failure in ixgbe PCI probe
On 3/11/2024 10:32 AM, Vajith Raghman wrote:
> Hi Team,
>
> We are validating the fdir with test-pmd tool. We are getting below
> error while trying to add the flow create rule for the same.
>
> Syntax:
>
> testpmd>flow create 0ingress pattern eth / ipv4 src *is*ipv4
> dst *is*/tcp src *is* dst
Commit 9a9eb104ed ("ethdev: parse multiple representor devargs") removes
the following variable initialization in rte_eth_devargs_parse():
memset(eth_da, 0, sizeof(*eth_da));
Restore the memset, as this causes regression in ixgbe PCI probe.
Fixes: 9a9eb104ed ("ethdev: parse multiple represen
Commit 9a9eb104edf6 ("ethdev: parse multiple representor devargs") removes
the following variable initialization in rte_eth_devargs_parse():
memset(eth_da, 0, sizeof(*eth_da));
Restore the memset, as this causes regression in ixgbe PCI probe.
Fixes: 9a9eb104edf6 ("ethdev: parse multiple repr
Commit 9a9eb104edf6 ("ethdev: parse multiple representor devargs") removes
the following variable initialization in rte_eth_devargs_parse():
memset(eth_da, 0, sizeof(*eth_da));
Restore the memset, as this causes regression in ixgbe PCI probe.
Fixes: 9a9eb104edf6 ("ethdev: parse multiple repr
Commit 9a9eb104edf6 ("ethdev: parse multiple representor devargs") removes
the following variable initialization in rte_eth_devargs_parse():
memset(eth_da, 0, sizeof(*eth_da));
Restore the memset, as this causes regression in ixgbe PCI probe.
As the listed commit introduces a new argument: n
On Thu, Mar 7, 2024 at 10:00 AM Thomas Monjalon wrote:
>
> 10/01/2024 15:42, jspew...@iol.unh.edu:
> > dts/framework/config/conf_yaml_schema.json| 3 +-
> > dts/framework/exception.py| 7 +
> > dts/framework/remote_session/testpmd_shell.py | 149 +-
> >
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, March 8, 2024 8:25 AM
> To: dev@dpdk.org
> Cc: gak...@marvell.com; Power, Ciara ; Kusztal,
> ArkadiuszX ; sta...@dpdk.org
> Subject: [PATCH] crypto/qat: fix ccm null aad pointer segfault
>
> This commit fixes a segfault,
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, March 8, 2024 9:44 AM
> To: dev@dpdk.org
> Cc: gak...@marvell.com; Power, Ciara ; Kusztal,
> ArkadiuszX
> Subject: [PATCH] common/qat: fix null dereference in release function
>
> This commit fixes NULL dereference in th
This patchset is proposing adding a new header only library
with utility functions that allow compression of arrays of pointers.
Since this is a header only library a patch needed to be added to amend
the build system to allow adding libraries without source files.
When passing caches full of poi
Allow header only libraries.
Signed-off-by: Paul Szczepanek
Reviewed-by: Honnappa Nagarahalli
---
lib/meson.build | 14 ++
1 file changed, 14 insertions(+)
diff --git a/lib/meson.build b/lib/meson.build
index 179a272932..e4e31f7ecf 100644
--- a/lib/meson.build
+++ b/lib/meson.build
Add a new utility header for compressing pointers. The provided
functions can store pointers in 32-bit or 16-bit offsets.
The compression takes advantage of the fact that pointers are
usually located in a limited memory region (like a mempool).
We can compress them by converting them to offsets fr
Add a test that runs a zero copy burst enqueue and dequeue on a ring
of raw pointers and compressed pointers at different burst sizes to
showcase performance benefits of newly added pointer compression APIs.
Refactored threading code to pass more parameters to threads to
reuse existing code. Added
Documentation added in the prog guide for the new
utility functions for pointer compression
showing example code and potential usecases.
Signed-off-by: Paul Szczepanek
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Nathan Brown
---
MAINTAINERS| 1 +
doc/guides
Test compresses and decompresses pointers with various combinations
of memory regions and alignments and verify the pointers are
recovered correctly.
Signed-off-by: Paul Szczepanek
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Nathan Brown
---
MAINTAINERS | 1 +
app/test/me
On 3/11/2024 12:55 PM, Thierry Herbelot wrote:
> Commit 9a9eb104edf6 ("ethdev: parse multiple representor devargs") removes
> the following variable initialization in rte_eth_devargs_parse():
>
> memset(eth_da, 0, sizeof(*eth_da));
>
> Restore the memset, as this causes regression in ixgbe PC
On Mon, Mar 11, 2024 at 02:47:02PM +, Paul Szczepanek wrote:
> Allow header only libraries.
>
> Signed-off-by: Paul Szczepanek
> Reviewed-by: Honnappa Nagarahalli
> ---
> lib/meson.build | 14 ++
> 1 file changed, 14 insertions(+)
>
> diff --git a/lib/meson.build b/lib/meson.bu
The API testsuite previously only used the dmadev skeleton. Now that real
devices are being used for the API tests, the DMA stats need to be reset
during testsuite teardown to ensure a known, clean state before continuing.
Fixes: 14b477ed1740 ("test/dma: use unit test framework")
Signed-off-by: K
From: Jeremy Spewock
v9:
* rebase series on main
* add "Test" to the name of the test suite class so that it gets properly
recognized as a suite according to changes from patch on main.
Note that changing the name of a test suite class funtionally doesn't
change anything about the suite. The f
From: Jeremy Spewock
Added commonly used methods in testpmd such as starting and stopping
packet forwarding, changing forward modes, and verifying link status of
ports so that developers can configure testpmd and start forwarding
through the provided class rather than sending commands to the test
From: Jeremy Spewock
Changed the factory method for creating interactive apps in the SUT Node
so that EAL parameters would only be passed into DPDK apps since
non-DPDK apps wouldn't be able to process them. Also modified
interactive apps to allow for the ability to pass parameters into the
app on
From: Jeremy Spewock
Added the options to filter out LLDP and ARP packets when
sniffing for packets with scapy. This was done using BPF filters to
ensure that the noise these packets provide does not interfere with test
cases.
Signed-off-by: Jeremy Spewock
---
dts/framework/test_suite.py
From: Jeremy Spewock
Added allow list to the EAL parameters created in DTS to ensure that
only the relevant PCI devices are considered when launching DPDK
applications.
Signed-off-by: Jeremy Spewock
---
dts/framework/testbed_model/sut_node.py | 12
1 file changed, 12 insertions(+)
From: Jeremy Spewock
Adds methods in both os_session and linux session to allow for setting
MTU of port interfaces so that suites that require the sending and
receiving of packets of a specific size, or the rejection of packets
over a certain size, can configure this maximum as needed.
Signed-of
From: Jeremy Spewock
Allow for scatter to be specified in the configuration file.
Signed-off-by: Jeremy Spewock
---
dts/framework/config/conf_yaml_schema.json | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/dts/framework/config/conf_yaml_schema.json
b/dts/framework/confi
From: Jeremy Spewock
This test suite provides testing of the support of scattered packets by
Poll Mode Drivers using testpmd, verifying the ability to receive and
transmit scattered multi-segment packets made up of multiple
non-contiguous memory buffers. This is tested through 5 different cases
i
Hi Zhicha,
It would be good to reflect FEC feature here:
https://doc.dpdk.org/guides/nics/overview.html
in "/Table 1.1 //Features availability in networking drivers/"
please find the rest comments inline
On 06/03/2024 10:41, Zhichao Zeng wrote:
This patch enabled querying Forward Error Corre
The DPDK style of indentation uses tabs not spaces.
This file had mix of both. Convert it.
Signed-off-by: Stephen Hemminger
---
drivers/net/bnx2x/bnx2x_stats.c | 174
1 file changed, 87 insertions(+), 87 deletions(-)
diff --git a/drivers/net/bnx2x/bnx2x_stats.c
On 11/28/2023 12:40 PM, Huisong Li wrote:
> The traffic management API has been introduced for a long time, please see
> commit 5d109deffa87 ("ethdev: add traffic management API").
> And many PMD also support this feature. So this series add this feature to
> features.rst, default.ini and driver.in
On 3/8/2024 10:50 AM, Chaoyong He wrote:
> From: Peng Zhang
>
> When the beat value of all ports are 0, which represent all
> ports are unused. But the current port starts beat before
> the check process, so it needs to sleep 1 second waiting
> the beat value change and to ignore the current port
The TAP device can use same file descriptopr for both rx and tx queues.
This allows up to 8 queues (versus 4).
Signed-off-by: Stephen Hemminger
---
v4 - fix typos reported by check patch
drivers/net/tap/meson.build | 2 +-
drivers/net/tap/rte_eth_tap.c | 197 +++-
On 3/7/2024 10:27 AM, Gregory Etelson wrote:
> Testpmd calls the same function to create legacy indirect action and
> indirect list action.
> The function did not identify required action correctly.
>
> The patch adds the `indirect_list` boolean function parameter that is
> derived from the action
This patchset is proposing adding a new header only library
with utility functions that allow compression of arrays of pointers.
Since this is a header only library a patch needed to be added to amend
the build system to allow adding libraries without source files.
When passing caches full of poi
Allow header only libraries.
Signed-off-by: Paul Szczepanek
Reviewed-by: Honnappa Nagarahalli
---
lib/meson.build | 16
1 file changed, 16 insertions(+)
diff --git a/lib/meson.build b/lib/meson.build
index 179a272932..7c90602bf5 100644
--- a/lib/meson.build
+++ b/lib/meson.bui
Add a new utility header for compressing pointers. The provided
functions can store pointers in 32-bit or 16-bit offsets.
The compression takes advantage of the fact that pointers are
usually located in a limited memory region (like a mempool).
We can compress them by converting them to offsets fr
Add a test that runs a zero copy burst enqueue and dequeue on a ring
of raw pointers and compressed pointers at different burst sizes to
showcase performance benefits of newly added pointer compression APIs.
Refactored threading code to pass more parameters to threads to
reuse existing code. Added
Documentation added in the prog guide for the new
utility functions for pointer compression
showing example code and potential usecases.
Signed-off-by: Paul Szczepanek
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Nathan Brown
---
MAINTAINERS| 1 +
doc/guides
Test compresses and decompresses pointers with various combinations
of memory regions and alignments and verify the pointers are
recovered correctly.
Signed-off-by: Paul Szczepanek
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Nathan Brown
---
MAINTAINERS | 1 +
app/test/me
On 11/28/2023 1:00 PM, Huisong Li wrote:
> The link speed configuration feature which is from dev_conf.link_speeds
> has been introduced for a long time. This setting interface is used to
> set fixed speed and link autonegotiation with speed capabilities feature.
> It is very important for NIC. For
On 3/8/2024 6:09 PM, Alan Elder wrote:
> The previous code allowed the number of Tx queues to be set higher than
> the number of Rx queues. If a packet was sent on a Tx queue with index
>> = number Rx queues there was a segfault.
>
> This commit fixes the issue by creating an Rx queue for every T
Sorry, I forgot to send these last week.
March 7, 2024
#
Attendees
1. Patrick Robb
2. Ali Alnubani
3. Paul Szczepanek
4. David Marchand
5. Aaron Conole
#
Minute
This patchset adds SVE support for the signature comparison in the cuckoo
hash lookup and improves the existing NEON implementation. These
optimizations required changes to the data format and signature of the
relevant functions to support dense hitmasks (no padding) and having the
primary and seco
Current hitmask includes padding due to Intel's SIMD
implementation detail. This patch allows non Intel SIMD
implementations to benefit from a dense hitmask.
In addition, the new dense hitmask interweave the primary
and secondary matches which allow a better cache usage and
enable future improvemen
Upon a successful comparison, NEON sets all the bits in the lane to 1
We can skip shifting by simply masking with specific masks.
Signed-off-by: Yoan Picchi
Reviewed-by: Ruifeng Wang
Reviewed-by: Nathan Brown
---
lib/hash/arch/arm/compare_signatures.h | 24 +++-
1 file chan
This patch adds unit test for rte_hash_lookup_bulk().
It also update the test_full_bucket test to the current number of entries
in a hash bucket.
Signed-off-by: Yoan Picchi
Signed-off-by: Harjot Singh
Reviewed-by: Ruifeng Wang
Reviewed-by: Nathan Brown
---
app/test/test_hash.c | 99 ++
- Implemented SVE code for comparing signatures in bulk lookup.
- Added Defines in code for SVE code support.
- Optimise NEON code
- New SVE code is ~5% slower than optimized NEON for N2 processor.
Signed-off-by: Yoan Picchi
Signed-off-by: Harjot Singh
Reviewed-by: Nathan Brown
Reviewed-by: Rui
On 3/11/2024 1:54 AM, Chaoyong He wrote:
> From: Qin Ke
>
> When getting firmware VNIC version, the logic for representor
> ports and other ports is inverse, fix it.
>
> Fixes: c4de52eca76c ("net/nfp: remove redundancy for representor port")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Qin Ke
> Re
It's not a bugfix, but a best practice for test (clean state before continuing).
The other is LGTM,
Acked-by: Chengwen Feng
On 2024/3/11 23:25, Kevin Laatz wrote:
> The API testsuite previously only used the dmadev skeleton. Now that real
> devices are being used for the API tests, the DMA stat
Acked-by: Chengwen Feng
On 2024/3/9 3:06, Vipin Varghese wrote:
> Modify the user information with total average latency per worker
> in both CSV and console logs.
>
> Signed-off-by: Vipin Varghese
>
> V3 Changes:
> - update CSV_TOTAL_LINE_FMT to change Avg Cycles / op per worker
>
> V2 Chan
Hi Vipin,
On 2024/3/11 14:00, Vipin Varghese wrote:
> In case incorrect NUMA configuration, the current commit shares
> 1) either `source or destination numa is greater`
> 2) instead of `actual NUMA` it is `acture NUMA`
>
> Current changes helps to rectify the same by using `PRINT_ERR` instead
diff --git a/app/test-dma-perf/benchmark.c b/app/test-dma-perf/benchmark.c
index 9b1f58c78c..b6d0dbe4c0 100644
--- a/app/test-dma-perf/benchmark.c
+++ b/app/test-dma-perf/benchmark.c
@@ -311,9 +311,14 @@ setup_memory_env(struct test_configure *cfg, struct
rte_mbuf ***srcs,
uint32_t nr_bu
Hi Yoan,
On 2024/3/12 7:21, Yoan Picchi wrote:
> - Implemented SVE code for comparing signatures in bulk lookup.
> - Added Defines in code for SVE code support.
> - Optimise NEON code
This commit does not include this part. Pls only describe the content in this
commit.
> - New SVE code is ~5% s
https://bugs.dpdk.org/show_bug.cgi?id=1398
Bug ID: 1398
Summary: [dpdk-24.03] ptpclient causes NIC I225/I226 port RX
missed
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONF
For configuration parameters `mem_size` and `buf_size` are represented
as megabytes and bytes respectively in application. Update the
documentation and to represent the same.
V2 Changes:
- add mem_size and buf_size in config.ini, suggested by Chengwen.
Signed-off-by: Vipin Varghese
---
---
app
Hi Stephen,
Thank you!
Will there be any conflict occur between rss and the flow pattern that I am
going to create.
RSS and flow rule having same criteria which one takes the priority
Regards,
Bala
-Original Message-
From: Stephen Hemminger
Sent: Monday, March 11, 2024 9:16 PM
To: B
Acked-by: Chengwen Feng
On 2024/3/12 12:22, Vipin Varghese wrote:
> For configuration parameters `mem_size` and `buf_size` are represented
> as megabytes and bytes respectively in application. Update the
> documentation and to represent the same.
>
> V2 Changes:
> - add mem_size and buf_size in
Sorry for same reply,
@Vipin,
the title should reflect which submodule, so pls add prefix: test/dma-perf:
Suggest: test/dma-perf: refine size parameter details in doc
Just a suggestion, you could refine it.
On 2024/3/12 14:07, fengchengwen wrote:
> Acked-by: Chengwen Feng
>
> On 2024/3/12 12:22
64 matches
Mail list logo
