> From: Patrick Robb
> Sent: Wednesday, April 24, 2024 8:21 PM
> To: Ali Alnubani
> Cc: Aditya Ambadipudi ; dev@dpdk.org; Jack
> Min ; step...@networkplumber.org; Matan Azrad
> ; Slava Ovsiienko ;
> roret...@linux.microsoft.com; konstantin.anan...@huawei.com;
> hof...@lysator.liu.se; wathsala.vit
Just a few minor points, otherwise this looks good.
> diff --git a/doc/guides/tools/dts.rst b/doc/guides/tools/dts.rst
> index 47b218b2c6..71473dbb3d 100644
> --- a/doc/guides/tools/dts.rst
> +++ b/doc/guides/tools/dts.rst
> @@ -131,7 +131,11 @@ There are two areas that need to be set up on a Syst
Hello, Stephen,
Good day
The issue is not caused by DPDK itself, but arises when the DPDK worker process
attempts to set affinity to a cpuset that exceeds the limits set by the cgroup
cpuset settings.
Original error prints are:
PANIC in rte_eal_init():
Cannot set affinity
# Call
After reviewing the code, I believe that the combination of the __linux__ and
_GNU_SOURCE macros effectively confirms whether the pthread_getname_np() API
can be utilized. I will proceed with adding them. Thank you~
#if defined(__linux__) && defined(_GNU_SOURCE)
在 2024-04-25 09:08:59,"吴剑跃" 写道:
Release status meeting minutes 2024-04-25
=
Agenda:
* Release Dates
* Subtrees
* Roadmaps
* LTS
* Defects
* Opens
Participants:
* AMD
* ARM
* Debian/Microsoft
* Intel
* Marvell
* Nvidia
Release Dates
-
The following are the current/updated wor
This patch set represent an attempt to improve and extend the RTE
bitops API, in particular for functions that operate on individual
bits.
All new functionality is exposed to the user as generic selection
macros, delegating the actual work to private (__-marked) static
inline functions. Public fun
Extend bitops tests to cover the
rte_bit_once_[set|clear|assign|test]() family of functions.
Signed-off-by: Mattias Rönnblom
---
app/test/test_bitops.c | 14 --
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/app/test/test_bitops.c b/app/test/test_bitops.c
index f788b5
Extend bitops tests to cover the rte_bit_[set|clear|assign|test]()
family of functions.
The tests are converted to use the test suite runner framework.
Signed-off-by: Mattias Rönnblom
---
app/test/test_bitops.c | 76 +-
1 file changed, 61 insertions(+), 1
Add bit test/set/clear/assign functions which prevents certain
compiler optimizations and guarantees that program-level memory loads
and/or stores will actually occur.
These functions are useful when interacting with memory-mapped
hardware devices.
The "once" family of functions does not promise
Add atomic bit test/set/clear/assign and test-and-set/clear functions.
All atomic bit functions allow (and indeed, require) the caller to
specify a memory order.
RFC v2:
o Add rte_bit_atomic_test_and_assign() (for consistency).
o Fix bugs in rte_bit_atomic_test_and_[set|clear]().
o Use to sup
Add functionality to test, set, clear, and assign the value to
individual bits in 32-bit or 64-bit words.
These functions have no implications on memory ordering, atomicity and
does not use volatile and thus does not prevent any compiler
optimizations.
Signed-off-by: Mattias Rönnblom
---
lib/ea
Extend bitops tests to cover the
rte_bit_atomic_[set|clear|assign|test|test_and_[set|clear|assign]]()
family of functions.
Signed-off-by: Mattias Rönnblom
---
app/test/test_bitops.c | 233 ++-
lib/eal/include/rte_bitops.h | 1 -
2 files changed, 232 insert
On 2024-04-25 01:55, Stephen Hemminger wrote:
On Thu, 25 Apr 2024 00:27:36 +0200
Mattias Rönnblom wrote:
On 2024-04-24 21:13, Stephen Hemminger wrote:
On Wed, 24 Apr 2024 18:50:50 +0100
Ferruh Yigit wrote:
I don't know how slow af_packet is, but if you care about performance,
you don't
> From: Mattias Rönnblom [mailto:hof...@lysator.liu.se]
> Sent: Thursday, 25 April 2024 11.26
>
> On 2024-04-25 01:55, Stephen Hemminger wrote:
> > On Thu, 25 Apr 2024 00:27:36 +0200
> > Mattias Rönnblom wrote:
> >
> >> On 2024-04-24 21:13, Stephen Hemminger wrote:
> >>> On Wed, 24 Apr 2024 18:50
> +#define rte_bit_atomic_test(addr, nr, memory_order) \
> + _Generic((addr),\
> + uint32_t *: __rte_bit_atomic_test32, \
> + uint64_t *: __rte_bit_atomic_test64)(addr, nr, memory_order)
On 3/26/2024 12:55 PM, Sivaprasad Tummala wrote:
> With modern CPUs, it is possible to have higher
> CPU count thus we can have higher RTE_MAX_LCORES.
> In DPDK sample applications, the current config
> lcore options are hard limited to 255.
>
> The patchset fixes these constraints by allowing
> a
On 4/24/2024 8:04 PM, Stephen Hemminger wrote:
> Yes, the lower limit only applies to the secondary process.
> But any application using secondary processes will have the problem;
> i.e it is not that primary gets 16 and the secondary only sees 8.
>
> Lets keep MAX_QUEUES at 16 for now, and let us
On 4/24/2024 8:04 PM, Stephen Hemminger wrote:
> On Wed, 24 Apr 2024 17:57:46 +0100
> Ferruh Yigit wrote:
>
>> OK to merge file descriptors instead of duplicating them.
>>
>> But we have this 4 queue limitation only for multi process case, right?
>> If user is planning to use only with primary, t
Hi Haoqian,
We try to avoid passing functions or variable names in the commit title.
Maybe something like this would work:
"vhost: cleanup resubmit info before inflight setup"
On 3/21/24 10:57, Haoqian He wrote:
We should cleanup vq resubmit info when set_inflight_fd
virtqueue*
before set_v
On 4/10/24 17:21, Luca Vizzarro wrote:
This patch resolves a build error with GCC 13 and arm/aarch32 as
targets:
In function ‘mbuf_to_desc’,
inlined from ‘vhost_enqueue_async_packed’ at
../lib/vhost/virtio_net.c:1828:6,
inlined from ‘virtio_dev_rx_async_packed’ at
../l
On 4/17/24 11:15, Ушков Даниил wrote:
This patch introduces a new flag RTE_VHOST_USER_ASYNC_CONNECT,
which in combination with the flag RTE_VHOST_USER_CLIENT makes
rte_vhost_driver_start connect asynchronously to the vhost server.
Signed-off-by: Ушков Даниил
---
Fixes:
1. Fix warning about t
Thanks for the comments. This is due to the tab size, and I will fix them.
On Wed, Apr 24, 2024 at 12:24 AM Stephen Hemminger <
step...@networkplumber.org> wrote:
> On Mon, 15 Apr 2024 11:26:02 +
> Abdullah Ömer Yamaç wrote:
>
> > + ret = rte_rcu_qsbr_dq_reclaim(h->dq,
> h->hash_rcu_cfg-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Thursday, 25 April 2024 15.48
>
> On 4/17/24 11:15, Ушков Даниил wrote:
> >
> > Signed-off-by: Ушков Даниил
> > ---
> > Fixes:
> > 1. Fix warning about the name in signature.
> > 2. Fix warning about coding style.
> >
> > P.S.
>
On 4/25/2024 10:26 AM, Mattias Rönnblom wrote:
> On 2024-04-25 01:55, Stephen Hemminger wrote:
>> On Thu, 25 Apr 2024 00:27:36 +0200
>> Mattias Rönnblom wrote:
>>
>>> On 2024-04-24 21:13, Stephen Hemminger wrote:
On Wed, 24 Apr 2024 18:50:50 +0100
Ferruh Yigit wrote:
>> I do
On 4/23/2024 12:15 PM, Ferruh Yigit wrote:
>> Signed-off-by: Mattias Rönnblom
>> ---
>> drivers/net/af_packet/rte_eth_af_packet.c | 5 +++--
>> 1 file changed, 3 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
>> b/drivers/net/af_packet/rte_eth_af_packe
On 2024-04-25 12:25, Morten Brørup wrote:
+#define rte_bit_atomic_test(addr, nr, memory_order)\
+ _Generic((addr),\
+uint32_t *: __rte_bit_atomic_test32, \
+uint64_t *: __rt
Add Maryam Tahhan as an additional maintainer for AF_XDP
PMD and it's documentation.
Signed-off-by: Maryam Tahhan
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 7abb3aee49..f0d6a36abd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -647,6 +647,7
On Thu, 25 Apr 2024 13:40:21 +0800 (CST)
吴剑跃 wrote:
> After reviewing the code, I believe that the combination of the __linux__ and
> _GNU_SOURCE macros effectively confirms whether the pthread_getname_np() API
> can be utilized. I will proceed with adding them. Thank you~
> #if defined(__linux
> Subject: [v1 1/1] MAINTAINERS: add another AF_XDP maintainer
>
> Add Maryam Tahhan as an additional maintainer for AF_XDP
> PMD and it's documentation.
>
> Signed-off-by: Maryam Tahhan
Thanks Maryam.
Acked-by: Ciara Loftus
> ---
> MAINTAINERS | 1 +
> 1 file changed, 1 insertion(+)
>
> d
From: Luca Boccassi
As per Intel, this is not supported, and the librte-bpf test fails on 32bit x86
kernels, so disable the library and the pmd.
Signed-off-by: Luca Boccassi
---
drivers/net/af_xdp/meson.build | 6 ++
lib/bpf/meson.build| 6 ++
2 files changed, 12 insertions
On 2024-04-25 16:04, Ferruh Yigit wrote:
On 4/25/2024 10:26 AM, Mattias Rönnblom wrote:
On 2024-04-25 01:55, Stephen Hemminger wrote:
On Thu, 25 Apr 2024 00:27:36 +0200
Mattias Rönnblom wrote:
On 2024-04-24 21:13, Stephen Hemminger wrote:
On Wed, 24 Apr 2024 18:50:50 +0100
Ferruh Yigit wro
On 2024-04-25 16:08, Ferruh Yigit wrote:
On 4/23/2024 12:15 PM, Ferruh Yigit wrote:
Signed-off-by: Mattias Rönnblom
---
drivers/net/af_packet/rte_eth_af_packet.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
b/drivers/net/
Fixup the references to the AF_XDP Device Plugin repo.
Fixes: 66a2aca4f512 ("docs: fix AF_XDP device plugin howto")
Cc: sta...@dpdk.org
Signed-off-by: Maryam Tahhan
---
doc/guides/howto/af_xdp_cni.rst | 12 ++--
doc/guides/nics/af_xdp.rst | 2 +-
2 files changed, 7 insertions(+),
On Thu, 25 Apr 2024 16:05:58 +0100
luca.bocca...@gmail.com wrote:
> From: Luca Boccassi
>
> As per Intel, this is not supported, and the librte-bpf test fails on 32bit
> x86
> kernels, so disable the library and the pmd.
>
> Signed-off-by: Luca Boccassi
Acked-by: Stephen Hemminger
On 4/25/2024 4:08 PM, Mattias Rönnblom wrote:
> On 2024-04-25 16:08, Ferruh Yigit wrote:
>> On 4/23/2024 12:15 PM, Ferruh Yigit wrote:
Signed-off-by: Mattias Rönnblom
---
drivers/net/af_packet/rte_eth_af_packet.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
>>>
> From: Mattias Rönnblom [mailto:hof...@lysator.liu.se]
> Sent: Thursday, 25 April 2024 16.36
>
> On 2024-04-25 12:25, Morten Brørup wrote:
> >> +#define rte_bit_atomic_test(addr, nr, memory_order)
> \
> >> + _Generic((addr),\
> >> +
On 4/25/2024 4:06 PM, Mattias Rönnblom wrote:
> On 2024-04-25 16:04, Ferruh Yigit wrote:
>> On 4/25/2024 10:26 AM, Mattias Rönnblom wrote:
>>> On 2024-04-25 01:55, Stephen Hemminger wrote:
On Thu, 25 Apr 2024 00:27:36 +0200
Mattias Rönnblom wrote:
> On 2024-04-24 21:13, Stephen
Making 'rte_eth_stats_reset()' and 'rte_eth_xstats_reset()' APIs thread
safe has performance impact on datapath.
Instead document APIs as not thread safe and add condition for reliable
stats reset functionality, forwarding should be stopped.
Cc: sta...@dpdk.org
Signed-off-by: Ferruh Yigit
---
C
For stats reset, use an offset instead of zeroing out actual stats values,
get_stats() displays diff between stats and offset.
This way stats only updated in datapath and offset only updated in stats
reset function. This makes stats reset function more reliable.
As stats only written by single thr
On Thu, Apr 25, 2024 at 10:58:47AM +0200, Mattias Rönnblom wrote:
> This patch set represent an attempt to improve and extend the RTE
> bitops API, in particular for functions that operate on individual
> bits.
>
> All new functionality is exposed to the user as generic selection
> macros, delegat
This part documents and provides script to replace the unused
type argument in rte_malloc. The type was intended to be a string
but never implemented, and if it hasn't been implemented in 10 years
it won't be. Too invasive to completely remove it.
Stephen Hemminger (4):
rte_malloc: document tha
The string type is left over from first version of DPDK and
was never implemented.
Signed-off-by: Stephen Hemminger
---
lib/eal/include/rte_malloc.h | 21 +++--
1 file changed, 7 insertions(+), 14 deletions(-)
diff --git a/lib/eal/include/rte_malloc.h b/lib/eal/include/rte_mallo
Better to use ret_calloc() than directly multiply up the
sizes of objects.
Signed-off-by: Stephen Hemminger
---
devtools/cocci/prefer-calloc.cocci | 19 +++
1 file changed, 19 insertions(+)
create mode 100644 devtools/cocci/prefer-calloc.cocci
diff --git a/devtools/cocci/prefer
The malloc type argument is unused and should be NULL.
This script finds and fixes those places.
Signed-off-by: Stephen Hemminger
---
devtools/cocci/malloc-type.cocci | 27 +++
1 file changed, 27 insertions(+)
create mode 100644 devtools/cocci/malloc-type.cocci
diff --g
The type argument is carried through malloc heap routines but
never used.
Signed-off-by: Stephen Hemminger
---
lib/eal/common/eal_common_memzone.c | 6 ++---
lib/eal/common/malloc_heap.c | 39
lib/eal/common/malloc_heap.h | 7 +++--
lib/eal/common/
On Thu, Apr 25, 2024 at 11:23:58AM -0700, Stephen Hemminger wrote:
> The string type is left over from first version of DPDK and
> was never implemented.
>
> Signed-off-by: Stephen Hemminger
> ---
> lib/eal/include/rte_malloc.h | 21 +++--
> 1 file changed, 7 insertions(+), 14 de
On Thu, 25 Apr 2024 11:31:31 -0700
Tyler Retzlaff wrote:
> On Thu, Apr 25, 2024 at 11:23:58AM -0700, Stephen Hemminger wrote:
> > The string type is left over from first version of DPDK and
> > was never implemented.
> >
> > Signed-off-by: Stephen Hemminger
> > ---
> > lib/eal/include/rte_mall
Microsoft DPDK 24.07 Release Roadmap
1. Update drivers to use optional stdatomic macros
Continuation of work started in 24.11 release.
Use stdatomic API
https://patchwork.dpdk.org/project/dpdk/list/?series=31797
2. MSVC Enable working Application & Nvidia mlx5 Driver
Bring MSVC built l
On Thu, Apr 25, 2024 at 01:50:16PM -0700, Tyler Retzlaff wrote:
> Microsoft DPDK 24.07 Release Roadmap
>
> 1. Update drivers to use optional stdatomic macros
>
> Continuation of work started in 24.11 release.
started in 23.11 release, oops.
The current calculation assumes that the mbufs are contiguous. However,
this assumption is incorrect when the memory spans across a huge page.
Correct to directly read the size from the mempool memory chunks.
Signed-off-by: Frank Du
---
drivers/net/af_xdp/rte_eth_af_xdp.c | 10 +-
1 file
50 matches
Mail list logo