Hi,
This is a policy coded in: *platform/linux-generic/odp_cpumask.c*
*init_default_worker_cpumask()*
*init_default_control_cpumask():*
*...default mask initialization if not specified by odp_init_global()*
*/**
* * If three or more CPUs, reserve CPU 0 for kernel, * reserve CPU 1 for
control,
Merged as trivial patch.
Maxim.
On 05/23/16 19:55, Mike Holmes wrote:
This must be in RC3, it breaks packaging
On 23 May 2016 at 10:44, Anders Roxell wrote:
Signed-off-by: Anders Roxell
---
helper/test/Makefile.am | 1 +
1 file
This must be in RC3, it breaks packaging
On 23 May 2016 at 10:44, Anders Roxell wrote:
> Signed-off-by: Anders Roxell
> ---
> helper/test/Makefile.am | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/helper/test/Makefile.am
And on the top of this , I intend to write a patch to simplify this
interface, so hopefully this will become obsolete soon :-)
On 23 May 2016 at 18:31, Christophe Milard
wrote:
> OK. if everyone now agrees, maybe this can be marked as reviewed :-). 3
> extra
OK. if everyone now agrees, maybe this can be marked as reviewed :-). 3
extra comments should not generate a storm, should it? It fixes a doxygen
warning on the helper...
Christophe.
On 23 May 2016 at 18:00, Mike Holmes wrote:
> I was looking for some definitions that
I was looking for some definitions that would save us having to
perpetuate this topic into its 5/6th week. I hoped to find a model.
I agree, we dont want to work on helper support for anything new
unless it brought a robust proven model.
On 23 May 2016 at 11:58, Christophe Milard
I don't think we should implement this by our own. If we do somthing about
it, it would just be awrapper for some functions, I guess...
On 23 May 2016 at 17:47, Mike Holmes wrote:
> Did a quick google on possibilities for how to implement an odp_thread,
> 99% of which we
Did a quick google on possibilities for how to implement an odp_thread, 99%
of which we dont support , but might make an interesting project.
https://software.intel.com/en-us/articles/choosing-the-right-threading-framework
On 23 May 2016 at 11:34, Christophe Milard
On 23 May 2016 at 17:34, Christophe Milard
wrote:
>
>
> On 23 May 2016 at 17:31, Ola Liljedahl wrote:
>
>>
>>
>> On 23 May 2016 at 17:28, Christophe Milard
>> wrote:
>>
>>> This is for linux helpers: in odp
Bill mentioned something in an email recently and I see the same.
On a four core x86-64 machine, I see only two ODP worker threads. Assuming
one CPU is allocated for the control thread, what is the fourth CPU doing
(not much I guess).
-- Ola
___
lng-odp
Merged,
Maxim.
On 05/22/16 19:02, Bill Fischofer wrote:
On Fri, May 20, 2016 at 4:45 PM, Ola Liljedahl
wrote:
Make architecture-specific code path selection generic, controlled
directly by compiler feature predefines.
Replace macro PREFETCH with intrinsic
On 23 May 2016 at 17:31, Ola Liljedahl wrote:
>
>
> On 23 May 2016 at 17:28, Christophe Milard
> wrote:
>
>> This is for linux helpers: in odp linux, just pthreads and processes are
>> supported as odpthreads.(well actually processes are
On 23 May 2016 at 17:28, Christophe Milard
wrote:
> This is for linux helpers: in odp linux, just pthreads and processes are
> supported as odpthreads.(well actually processes are not supported yet, but
> we head to it).
>
You can use C and C++ threads in Linux as
This is for linux helpers: in odp linux, just pthreads and processes are
supported as odpthreads.(well actually processes are not supported yet, but
we head to it).
If we support something else in some future, we'll update the comment then.
Christophe
On 23 May 2016 at 17:23, Ola Liljedahl
On 23 May 2016 at 17:04, Christophe Milard
wrote:
> Signed-off-by: Christophe Milard
> ---
> helper/include/odp/helper/linux.h | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git
On 23 May 2016 at 10:16, Yi He wrote:
> Hi, Christophe
>
> Here I met a difficulty, if I unified the API into
> odph_odpthread_set_affinity(),
> inside the function how can I determine whether the current context is a
> pthread or process? So I cannot decide to call
Signed-off-by: Christophe Milard
---
helper/include/odp/helper/linux.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/helper/include/odp/helper/linux.h
b/helper/include/odp/helper/linux.h
index 01c348d..2e89833 100644
---
Reported-by: Mike Holmes
Signed-off-by: Anders Roxell
---
platform/linux-generic/include/odp/drv/std_types.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/platform/linux-generic/include/odp/drv/std_types.h
Signed-off-by: Anders Roxell
---
helper/test/Makefile.am | 1 +
1 file changed, 1 insertion(+)
diff --git a/helper/test/Makefile.am b/helper/test/Makefile.am
index 8e65948..e9e8785 100644
--- a/helper/test/Makefile.am
+++ b/helper/test/Makefile.am
@@ -24,6 +24,7 @@
thanks,
Merged.
Maxim.
On 05/20/16 22:48, Bill Fischofer wrote:
For this series:
Reviewed-and-tested-by: Bill Fischofer
On Fri, May 20, 2016 at 12:31 PM, Mike Holmes
wrote:
Signed-off-by: Mike Holmes
---
v2
Hello Yi,
some more clean up is needed here.
perl ./scripts/checkpatch.pl
0001-linux-generic-test-ring-convert-to-cunit-and-improve.patch
CHECK: Alignment should match open parenthesis
#164: FILE: platform/linux-generic/test/ring/ring_basic.c:84:
+st_ring = _ring_create(st_ring_name,
Hi,
The odp-dpdk part of http://www.opendataplane.org/downloads/ needs updating:
- The patchworks links should be deleted, as nobody uses it, given that
I'm the only maintainer and the only regular commiter.
- The "latest stable release link" is also very old, and doesn't fit for
odp-dpdk: I
Merged,
Maxim.
On 05/20/16 03:03, Bill Fischofer wrote:
For this series:
Reviewed-by: Bill Fischofer
On Thu, May 19, 2016 at 3:48 AM, Matias Elo wrote:
Add new function pointer 'print' to pktio_if_ops_t. This can
be used to print pktio type
merged,
Maxim.
On 05/19/16 20:04, Mike Holmes wrote:
Ping to merge
On 16 May 2016 at 17:15, Bill Fischofer wrote:
On Mon, May 16, 2016 at 11:29 AM, Mike Holmes
wrote:
Converting to asciidoc allows a tidy page to be added to the online
Merged,
Maxim.
On 05/21/16 09:16, Christophe Milard wrote:
Yes! I get that easily on my home computer:
while (true); do ./platform/linux-generic/test/ring/ringtest ; done
just hangs after a short while.
even on origin/master
For some reason that refuses to hang at work...
I don't think
On 23 May 2016 at 11:13, Yi He wrote:
> Thanks very much Christophe
>
> This is great, I'll use this tech in
> odph_odpthread_setaffinity()/getaffinity() APIs.
>
> Do you mean you think keeping underlying Linux pthread/process concepts
> out of ODP thread concept is not good?
Thanks very much Christophe
This is great, I'll use this tech in
odph_odpthread_setaffinity()/getaffinity() APIs.
Do you mean you think keeping underlying Linux pthread/process concepts out
of ODP thread concept is not good?
From many discussions I got a Feeling that by ODP thread we are really
Hi,
I guess (not 100% sure if that civer all cases) if gettid() == getpid() you
are on the main process thread.
Having said that I do not like this solution very much: It really looks to
me that we have a larger problem trying to keep these things out of ODP
Something for ARCH call, maybe?
Am I understanding correctly if I try to rephrase your suggestion, Petri,
as follows:
1) " For simplicity all memory should be reserved from the system at global
init time.":
When calling init_global(), the application provides the total amount of
memory it will ever need, including everything
On 18 May 2016 at 16:24, Maxim Uvarov wrote:
> Accodring to API return code for fail case is ODP_TIMER_POOL_INVALID
> and errno set event if it's defined to NULL. Also add check on pool
> alloc that input parameter is not invalid.
>
Hi, Christophe
Here I met a difficulty, if I unified the API into
odph_odpthread_set_affinity(),
inside the function how can I determine whether the current context is a
pthread or process? So I cannot decide to call sched_setaffinity() or
pthread_setaffinity_np().
thanks and best regards, Yi
> >>
> >> === Addressing Scope
> >> -Unless specifically noted in the API, all ODP resources are global to
> >> the ODP
> >> -application, whether it runs as a single process or multiple
> processes.
> >> ODP
> >> -handles therefore have common meaning within an ODP application but
> have
> >>
Hi, Christophe
Yes, I'll apply your series and send a new one later.
Best Regards, Yi
On 23 May 2016 at 14:33, Christophe Milard
wrote:
>
>
> On 20 May 2016 at 10:48, Yi He wrote:
>
>> Set affinity to 1st available control cpu for all odp
>>
On 20 May 2016 at 10:48, Yi He wrote:
> Set affinity to 1st available control cpu for all odp
> validation programs in odp_cunit_common library.
>
> Signed-off-by: Yi He
> ---
> helper/include/odp/helper/linux.h | 47 +++
>
34 matches
Mail list logo