> > When building without AVX2 support using an older compiler e.g. gcc 4.8 on
> > Centos/RHEL 7, we get build errors due to the use of AVX2 intrinsics.
> > This is because the compiler does not support
> > "__attribute__((target(AVX2)))" function attribute. Disable build of this
> > driver such ed
15/06/2022 19:10, Bruce Richardson:
> The header files "l3fwd_em.h" and "l3fwd_em_sequential.h" use the
> "__rte_always_inline" macro but don't directly include "rte_common.h" to
> get the definition of it. This inclusion is not necessary for
> compilation, but the lack of it can confuse some index
> > The comments in rte_rib6 were cut-and-pasted from rte_rib
> > and because of that some references to rte_rib_node were
> > not updated.
> >
> > Signed-off-by: Stephen Hemminger
> Acked-by: Vladimir Medvedkin
Applied, thanks.
> > Expression "tx_chunks * ctx->dma_buf_size" in dma_fpga_to_fpga() is
> > evaluated
> > using 32-bit arithmetic, which would overflow potentially. Change
> > tx_chunks to
> > type "uint64_t" to avoid such issue.
> >
> > Coverity issue: 379203
> > Fixes: 7d63899a5c19 ("raw/ifpga: add N3000 AFU
> > Do null-checking on hw->adapter in fme_pmci_init() before dereference it.
> >
> > Coverity issue: 379202
> > Fixes: ca6eb0f7c836 ("raw/ifpga/base: add PMCI base driver")
> >
> > Signed-off-by: Wei Huang
>
> It looks good for me.
>
> Acked-by: Tianfei Zhang
Applied, thanks.
Hi,
Packets seem to be silently discarded in the RX NIC while waiting in the
buffer, and it does not happen when I use only one worker core.
I think multiple worker cores packet processing would have this problem to
handle heavy traffic in parallel.
I want to increase buffer size to solve this
21/04/2022 10:59, Gagandeep Singh:
> API 'netif_rx_ni()' has been removed in kernel with commit:
> baebdf48c3600 ("net: dev: Makes sure netif_rx() can be invoked in any
> context.")
>
> The API netif_rx() can be used for any context to receive packets
> from device drivers.
>
> This patch replac
04/06/2022 10:37, Heinrich Schuchardt:
> rwc_non_lf_results->multi_rw, rwc_lf_results->multi_rw, and
> rwc_perf_results->multi_rw are accessed at indexes
> [0..NUM_TEST-1][0..1][0..NUMTEST-1]. Currently the first index
> overflows the array size in struct rwc_perf.
>
> Fixes: c7eb0972e74b ("test/t
11/05/2022 18:33, Heinrich Schuchardt:
> When running DPDK in QEMU it cannot determine the connection speed.
> pmd_perf_autotest treats this as if the connection speed where
> UNIT32_MAX Mbps:
>
> RTE>>pmd_perf_autotest
> Start PMD RXTX cycles cost test.
> Allocated mbuf pool on socket
25/05/2022 09:14, Morten Brørup:
> > From: Stephen Hemminger [mailto:step...@networkplumber.org]
> > Sent: Wednesday, 25 May 2022 08.04
> >
> > On Tue, 24 May 2022 22:46:05 -0700
> > Subendu Santra wrote:
> >
> > > Show all non-owned ports when no port mask is specified
> > >
> > > show-port opt
16/02/2022 20:39, Stephen Hemminger:
> These are all functions that have been in DPDK for two
> years or more and should no longer be experimental.
>
> Stephen Hemminger (4):
> rte_log: take of some experimental tags
> lcore: change rte_lcore_to_cpu_id and rte_lcore_cpuset as not
> experim
06/06/2022 16:39, Dongdong Liu:
> From: "Min Hu (Connor)"
>
> This patch adds support for dump the device private info from a running
> application. It can help developers locate the problem.
>
> Signed-off-by: Min Hu (Connor)
> Signed-off-by: Dongdong Liu
> Acked-by: Reshma Pattan
Applied,
Hi Reshma, please could you have a look at these patches?
We need to update the email address of Maryam as well.
Thanks
27/05/2022 03:42, Min Hu (Connor):
> Min Hu (Connor) (3):
> app/procinfo: add version dump
> app/procinfo: add RSS RETA dump
> app/procinfo: add module info dump
24/05/2021 14:09, Min Hu (Connor):
> Hi, Thierry,
> This bug has been fixed in my earlier patch, please refer to:
> https://patches.dpdk.org/project/dpdk/patch/1618839289-33224-5-git-send-email-humi...@huawei.com/
Your patch is doing
+ if (!nb_jobs) {
+ job_len = data_len
19/04/2021 15:34, Min Hu (Connor):
> From: HongBo Zheng
>
> The rte_zmalloc is called in test_crc_calc without null pointer
> check. This patch adds null pointer checks on return value of
> rte_zmalloc.
>
> Fixes: 9c77b848b1c1 ("test: add CRC computation")
> Cc: sta...@dpdk.org
>
> Signed-off-b
23/06/2022 10:38, Rahul Bhansali пишет:
This will make the packet grouping function common, so
that other examples can utilize as per need.
For each architecture sse/neon/altivec, port group
headers will be created under examples/common/.
Signed-off-by: Rahul Bhansali
---
Changes in v3: Create
On Sun, Jun 12, 2022 at 11:22 PM Ruifeng Wang wrote:
>
> To read descriptors in expected order, barriers are inserted after each
> descriptor read. The excessive use of barriers is unnecessary and could
> cause performance drop.
>
> Removed barriers between descriptor reads. And changed counting o
On Wed, Jun 15, 2022 at 7:57 AM Kalesh A P
wrote:
>
> From: Kalesh AP
>
> This patchset contains bug fixes in bnxt PMD.
Patchset applied to dpdk-next-net-brcm. Thanks
>
> Ajit Khaparde (1):
> net/bnxt: fix switch domain allocation
>
> Damodharam Ammepalli (3):
> net/bnxt: allow Tx only or R
Please could we have some tests on other hardware with this improvement?
25/05/2022 11:13, Rahul Bhansali:
> An additional check is added to avoid extra processing if
> receive packets are 0.
>
> Performance impact: with Marvell OCTEON TX2 platform, observed an
> improvement by ~14%.
>
> Signed
27/05/2022 08:42, Usman Tanveer:
> There is a call to rte_eth_dev_stop() in rte_ethtool_net_open()
> due to which user gets misleading message upon first open/start call.
> It says that the
> device is already stopped, which should not be the case. This patch
> removes rte_eth_dev_stop() from rte_e
30/05/2022 11:37, Raja Zidane:
> TIMER_MILLISECOND is defined as the number of cpu cycles per millisecond,
> current definition is correct for cores with frequency of 2GHZ, for cores
> with different frequency, it caused different periods between refresh,
> (i.e. the definition is about 14ms on ARM
21/06/2022 10:44, Hunt, David:
> On 20/06/2022 18:10, Ferruh Yigit wrote:
> > On 6/20/2022 5:31 PM, Abdullah Ömer Yamaç wrote:
> >> This patch fixes the syntax error when using the single-core
> >> for both rx and distributor functions.
> >>
> >> Fixes: 4a7f40c0ff9a ("examples/distributor: add dedi
14/06/2022 16:12, Mcnamara, John:
> From: Bruce Richardson
> > Both the Linux and FreeBSD GSG docs had a "Documentation Roadmap"
> > section as part of the introduction page, and this contained the same
> > information, with only the reference to the GSGs themselves being
> > different. This text
On Sun, Jun 26, 2022 at 8:15 AM Thomas Monjalon wrote:
>
> 11/05/2022 18:33, Heinrich Schuchardt:
> > When running DPDK in QEMU it cannot determine the connection speed.
> > pmd_perf_autotest treats this as if the connection speed where
> > UNIT32_MAX Mbps:
> >
> > RTE>>pmd_perf_autotest
> >
> Dmitry Kozlyuk (5):
> usertools: add option to select hugetlbfs directory
> usertools: add options to change mount point owner
> doc: give specific instructions for running as non-root
> doc: update instructions for running as non-root for MLX5
> doc: add note about running virtio-legac
26/06/2022 22:45, Ajit Khaparde:
> On Wed, Jun 15, 2022 at 7:57 AM Kalesh A P
> wrote:
> >
> > From: Kalesh AP
> >
> > This patchset contains bug fixes in bnxt PMD.
>
> Patchset applied to dpdk-next-net-brcm. Thanks
It is very late for -rc2, but it has found its way at last minute.
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v22.07-rc2
There are 317 new patches in this snapshot.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_22_07.html
There were a lot of updates in drivers.
The driver features should b
Add release notes for asynchronous vhost dequeue data-path. Emphasize
that split virtqueue and packed virtqueue are both supported in
asynchronous vhost dequeue data-path
Signed-off-by: Cheng Jiang
---
doc/guides/rel_notes/release_22_07.rst | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
Add release notes for asynchronous vhost dequeue data-path. Emphasize
that split virtqueue and packed virtqueue are both supported in
asynchronous vhost dequeue data-path.
Signed-off-by: Cheng Jiang
---
v2: fixed a full stop missing in the commit message.
doc/guides/rel_notes/release_22_07.rst
On Sun, Jun 26, 2022 at 7:08 PM Thomas Monjalon wrote:
>
> 26/06/2022 22:45, Ajit Khaparde:
> > On Wed, Jun 15, 2022 at 7:57 AM Kalesh A P
> > wrote:
> > >
> > > From: Kalesh AP
> > >
> > > This patchset contains bug fixes in bnxt PMD.
> >
> > Patchset applied to dpdk-next-net-brcm. Thanks
>
> I
Hi Peng,
> -Original Message-
> From: Zhang, Peng1X
> Sent: Friday, June 24, 2022 2:15 AM
> To: dev@dpdk.org
> Cc: Singh, Aman Deep ; Zhang, Yuying
> ; Zhang, Peng1X ;
> sta...@dpdk.org
> Subject: [PATCH] app/testpmd: fix secondary process cannot dump packet
>
> From: Peng Zhang
>
> Th
New event subtypes need to be added for notifying expiry events
upon reaching IPsec SA soft packet expiry and hard packet/byte
expiry limits. This would be added in DPDK 22.11.
Signed-off-by: Vamsi Attunuru
Acked-by: Akhil Goyal
---
More details on new event subtype proposal discussion are in be
If vring state changes after pmd starts working, the locked vring
notifies pmd, thus calling update_queuing_status(), the latter
will wait for pmd to finish accessing vring, while pmd is also
waiting for vring to be unlocked, thus causing deadlock.
Actually, update_queuing_status() only needs to w
Acked-by: Tejasree Kondoj
> -Original Message-
> From: Ciara Power
> Sent: Thursday, June 23, 2022 8:13 PM
> To: Akhil Goyal ; Fan Zhang
>
> Cc: dev@dpdk.org; kai...@intel.com; pablo.de.lara.gua...@intel.com;
> Tejasree Kondoj ; Ciara Power
> ; arkadiuszx.kusz...@intel.com; sta...@dpdk.
Acked-by: Tejasree Kondoj
> -Original Message-
> From: Ciara Power
> Sent: Thursday, June 23, 2022 8:13 PM
> To: Akhil Goyal ; Fan Zhang
>
> Cc: dev@dpdk.org; kai...@intel.com; pablo.de.lara.gua...@intel.com;
> Tejasree Kondoj ; Ciara Power
> ; deepak.k.j...@intel.com;
> lukaszx.krakow.
Hi,
>From DPDK 21.11, the Rx adapter event buffer size is configurable through API
>during creation time. Please refer to
>rte_event_eth_rx_adapter_create_with_params() API in the below link:
https://doc.dpdk.org/api/rte__event__eth__rx__adapter_8h.html
You could refer to EAL docs on how to use
36 matches
Mail list logo
