> > From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com]
> > Sent: Monday, 8 April 2024 17.27
> >
> > For next technboard meeting.
> >
> > On Sun, Apr 07, 2024 at 10:03:06AM -0700, Stephen Hemminger wrote:
> > > On Sun, 7 Apr 2024 13:07:06 +0200
> > > Morten Brørup wrote:
> > >
> > > > >
This series aims at improving the Vhost FD manager.
The fdset internals is hidden from its callers, the
notification/synchronization is made systematic for
every FD add/del operations and finally the code is
reworked to make use of epoll insteal of poll which
reduces the complexity (less locks in
This trivial patch fixes a typo in fd's manager polling
mutex name.
Reviewed-by: David Marchand
Signed-off-by: Maxime Coquelin
---
lib/vhost/fd_man.c | 8
lib/vhost/fd_man.h | 2 +-
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/lib/vhost/fd_man.c b/lib/vhost/fd_man.c
i
Instead of statically initialize the fdset, this patch
converts VDUSE and Vhost-user to use fdset_init() function,
which now also initialize the mutexes.
This is preliminary rework to hide FDs manager pipe from
its users.
Signed-off-by: Maxime Coquelin
---
lib/vhost/fd_man.c | 11 +--
l
This patch forces synchronization for all FDs additions
or deletions in the FD set. With that, it is no more
necessary for the user to know about the FD set pipe, so
hide its initialization in the FD manager.
Signed-off-by: Maxime Coquelin
---
lib/vhost/fd_man.c | 180 ---
This patch heavily reworks fdset initialization:
- fdsets are now dynamically allocated by the FD manager
- the event dispatcher is now created by the FD manager
- struct fdset is now opaque to VDUSE and Vhost
Signed-off-by: Maxime Coquelin
---
lib/vhost/fd_man.c | 177 +++
From: David Marchand
Switch to epoll so that the concern over the poll() fd array
is removed.
Add a simple list of used entries and track the next free entry.
epoll() is thread safe, we no more need a synchronization
mechanism and so can remove the notification pipe.
Signed-off-by: David Marcha
On Tue, Mar 26, 2024 at 8:04 PM Luca Vizzarro wrote:
>
> This commit introduces a new "params" module, which adds a new way
> to manage command line parameters. The provided Params dataclass
> is able to read the fields of its child class and produce a string
> representation to supply to the comm
> > From: David Marchand [mailto:david.march...@redhat.com]
> > Sent: Friday, 5 April 2024 16.46
> >
> > Mandate use of rte_eth_tx_prepare() in the mbuf Tx checksum offload
> > examples.
>
> I strongly disagree with this change!
>
> It will cause a huge performance degradation for shaping appl
> From: Konstantin Ananyev [mailto:konstantin.anan...@huawei.com]
> Sent: Tuesday, 9 April 2024 15.39
>
> > > From: David Marchand [mailto:david.march...@redhat.com]
> > > Sent: Friday, 5 April 2024 16.46
> > >
> > > Mandate use of rte_eth_tx_prepare() in the mbuf Tx checksum offload
> > > example
On Thu, Mar 28, 2024 at 5:48 PM Jeremy Spewock wrote:
>
> On Tue, Mar 26, 2024 at 3:04 PM Luca Vizzarro wrote:
> >
> > Make it so that interactive shells accept an implementation of `Params`
> > for app arguments. Convert EalParameters to use `Params` instead.
> >
> > String command line paramete
On Tue, Apr 09, 2024 at 08:28:48AM +, Konstantin Ananyev wrote:
>
>
> > > From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com]
> > > Sent: Monday, 8 April 2024 17.27
> > >
> > > For next technboard meeting.
> > >
> > > On Sun, Apr 07, 2024 at 10:03:06AM -0700, Stephen Hemminger wrote:
>
On 04/04/2024 10:25, Juraj Linkeš wrote:
Judging from the code, this patch seems like a convoluted way to implement:
1. An association between an Argument and the corresponding
environment variable,
2. A better way to add the env vars names to the help message of each
argument as well as adding t
Thank you for your review Jeremy!
On 28/03/2024 16:48, Jeremy Spewock wrote:
I might add some kind of block comment here as a separator that
delimits that metadata modifiers start here. Something like what is
written in scapy.py which creates sections for XML-RPC method vs ones
that are run by t
Thank you so much for your review Juraj!
On 09/04/2024 13:10, Juraj Linkeš wrote:
We shouldn't list what the patch does, but rather explain the choices
made within. It seems to me the patch is here to give devs an API
instead of them having to construct strings - explaining why this
approach imp
As Jeremy pointed out, going forward, this is likely to become bloated
and moving it to params.py (for example) may be better.
There's a lot of testpmd args here. I commented on the implementation
of some of them. I didn't verify that the actual values match the docs
or, god forbid, tested all of
I will change the default hugepage total back to 256. Much of the
justification for changing the default amount was based on guidelines
in the DPDK documentation. In the system requirements section, an
example is provided demonstrating how to allocate 2GB of 2MB
hugepages. We used this reasoning wh
While looking at using uuid's in some logging cases, discovered
that the existing uuid support in EAL was missing some functions
add in later versions of libuuid.
Add functions to generate Uuid values, and add missing functional
tests for uuid's.
v4 - review comments and use stdatomic
Stephen He
Useful to be able to generate uuid values for tests or
for interaction with other subsystems as magic cookie.
Naming and overall algorithm come from libuuid which is used
by permission of original author.
Signed-off-by: Stephen Hemminger
---
lib/eal/common/eal_common_uuid.c | 56
The uuid functions in EAL were not covered by existing functional
tests.
Signed-off-by: Stephen Hemminger
---
app/test/meson.build | 1 +
app/test/test_uuid.c | 138 +++
2 files changed, 139 insertions(+)
create mode 100644 app/test/test_uuid.c
diff --
The previous implementation configures and allocates hugepage sizes
based on a system default. This can lead to two problems: overallocation of
hugepages (which may crash the remote host), and configuration of hugepage
sizes that are not recommended during runtime. This new implementation
allows on
On Tue, Mar 26, 2024 at 8:04 PM Luca Vizzarro wrote:
>
> Update the buffer scatter test suite to use TestPmdParameters
> instead of the StrParams implementation.
>
> Signed-off-by: Luca Vizzarro
> Reviewed-by: Jack Bond-Preston
> Reviewed-by: Honnappa Nagarahalli
> ---
> dts/tests/TestSuite_pm
>+uint32_t *credit_pool[DLB2_NUM_QUEUE_TYPES]; /* use __atomic builtins */
Spell check complains here you can add a space after the '*' if you don’t want
that complaint. (e.g. uint32_t * credit_pool).
> case nb_events_limit:
> return dlb2->new_event_limit;
> case infl
On 4/9/24 18:38, Stephen Hemminger wrote:
On Tue, 9 Apr 2024 13:48:42 +0200
Maxime Coquelin wrote:
-void
+int
fdset_init(struct fdset *pfdset)
{
int i;
if (pfdset == NULL)
- return;
+ return -1;
This test is unnecessary. The function is not
I have a general question. What are these changes for? Do you
anticipate us needing this in the future? Wouldn't it be better to add
it only when we need it?
On Thu, Mar 28, 2024 at 5:48 PM Jeremy Spewock wrote:
>
> On Tue, Mar 26, 2024 at 3:04 PM Luca Vizzarro wrote:
>
> > diff --git a/dts/fra
25 matches
Mail list logo
