Re: [lng-odp] [PATCH] linux-generic: tm: init pthread attr to 0

On Mon, May 30, 2016 at 1:42 AM, Maxim Uvarov wrote: > Fix segmentation failt with not initialized attr for pthreads. > > Signed-off-by: Maxim Uvarov > --- > platform/linux-generic/odp_traffic_mngr.c | 1 + > 1 file changed, 1 insertion(+) > >

[lng-odp] [PATCHv2] linux-generic: sched: do not allocate sheduler info in shm area

Patch: 637a482 linux-generic: schedule: clean interface towards pktio Broke ipc pktio work. Restore original logic back. Idea here the following that 2 processes roll in the same name space instance and should not overlap each other shared memory files. There is no reason in putting sheduler

Re: [lng-odp] [PATCHv2] linux-generic: timer fix odp_timer_pool_create return code

Merged, Maxim. On 05/27/16 21:57, Bill Fischofer wrote: On Fri, May 27, 2016 at 11:25 AM, 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.

Re: [lng-odp] [PATCH] linux-generic: sched: do not allocate sheduler info in shm area

On 05/30/16 17:16, Maxim Uvarov wrote: On 05/30/16 16:53, Savolainen, Petri (Nokia - FI/Espoo) wrote: -Original Message- From: Maxim Uvarov [mailto:maxim.uva...@linaro.org] Sent: Monday, May 30, 2016 4:37 PM To: lng-odp@lists.linaro.org Cc: Maxim Uvarov ;

Re: [lng-odp] [PATCHv3] helper: cleaner interface to odph_odpthreads_create/join

On 30 May 2016 at 15:44, Savolainen, Petri (Nokia - FI/Espoo) < petri.savolai...@nokia.com> wrote: > > >> -Original Message- >> From: Christophe Milard [mailto:christophe.mil...@linaro.org] >> Sent: Monday, May 30, 2016 3:52 PM >> To: Savolainen, Petri (Nokia - FI/Espoo)

Re: [lng-odp] [PATCH] linux-generic: sched: do not allocate sheduler info in shm area

On 05/30/16 16:53, Savolainen, Petri (Nokia - FI/Espoo) wrote: -Original Message- From: Maxim Uvarov [mailto:maxim.uva...@linaro.org] Sent: Monday, May 30, 2016 4:37 PM To: lng-odp@lists.linaro.org Cc: Maxim Uvarov ; Savolainen, Petri (Nokia - FI/Espoo)

Re: [lng-odp] [PATCH] linux-generic: sched: do not allocate sheduler info in shm area

> -Original Message- > From: Maxim Uvarov [mailto:maxim.uva...@linaro.org] > Sent: Monday, May 30, 2016 4:37 PM > To: lng-odp@lists.linaro.org > Cc: Maxim Uvarov ; Savolainen, Petri (Nokia - > FI/Espoo) > Subject: [PATCH]

Re: [lng-odp] [PATCHv3] helper: cleaner interface to odph_odpthreads_create/join

> -Original Message- > From: Christophe Milard [mailto:christophe.mil...@linaro.org] > Sent: Monday, May 30, 2016 3:52 PM > To: Savolainen, Petri (Nokia - FI/Espoo) > Cc: yi...@linaro.org; lng-odp@lists.linaro.org > Subject: Re: [lng-odp] [PATCHv3] helper:

[lng-odp] [PATCH] linux-generic: sched: do not allocate sheduler info in shm area

Patch: 637a482 linux-generic: schedule: clean interface towards pktio Broke ipc pktio work. Restore this chunk back. Idea here the following that 2 processes roll in the same name space instance and should not overlap each other shared memory files. There is no reason in putting sheduler internal

Re: [lng-odp] [PATCHv3] helper: cleaner interface to odph_odpthreads_create/join

On 30 May 2016 at 14:12, Savolainen, Petri (Nokia - FI/Espoo) wrote: > > > > From: Christophe Milard [mailto:christophe.mil...@linaro.org] > Sent: Monday, May 30, 2016 1:34 PM > To: Savolainen, Petri (Nokia - FI/Espoo) > Cc:

Re: [lng-odp] [PATCH v2] example: introducing l3fwd

One more thing, the output binary file should be added to .gitignore. -Matias > > Checkpatch throws one error from the patch: > > ERROR: spaces required around that '==' (ctx:VxW) > #485: FILE: example/l3fwd/odp_l3fwd.c:427: > + if (args->route_str[0]== NULL) { > > You

Re: [lng-odp] [PATCH v2] example: introducing l3fwd

Hi Forrest, Checkpatch throws one error from the patch: ERROR: spaces required around that '==' (ctx:VxW) #485: FILE: example/l3fwd/odp_l3fwd.c:427: + if (args->route_str[0]== NULL) { You could add a test script for running the application during make check (for

[lng-odp] [Bug 2289] Ring test deadlocks

https://bugs.linaro.org/show_bug.cgi?id=2289 Maxim Uvarov changed: What|Removed |Added CC|

Re: [lng-odp] [PATCH] linux-generic: pktio: gracefully un-schedule pktins

The reason for this patch is the following: we noticed that for multithreaded applications that accidentally called odp_schedule() after an odp_pktio_close(), error messages were printed. The deep reason is that the schedule_fn_t struct doesn't provide a pktio_stop, which prevents the PKTIOs to

[lng-odp] [PATCH] linux-generic: pktio: gracefully un-schedule pktins

When a scheduled pktio entry is closed it will become "closed", which is neither open nor free. When it is scheduled again, the schedule command is removed and the entry is freed. Before, a pktio entry could potentially be reused between the odp_pktio_close() and odp_schedule() calls.

Re: [lng-odp] [PATCHv3] helper: cleaner interface to odph_odpthreads_create/join

On 30 May 2016 at 11:23, Savolainen, Petri (Nokia - FI/Espoo) < petri.savolai...@nokia.com> wrote: > > > From: Christophe Milard [mailto:christophe.mil...@linaro.org] > Sent: Friday, May 27, 2016 4:08 PM > To: Savolainen, Petri (Nokia - FI/Espoo) > Cc:

Re: [lng-odp] [lng-odp-dpdk] [RFC PATCH] linux-dpdk: Enable inlines if dynamic library is not used

Hi, On 30/05/16 02:46, Bill Fischofer wrote: diff --git a/configure.ac b/configure.ac index 99772a1..199a6e2 100644 --- a/configure.ac +++ b/configure.ac @@ -141,6 +141,13 @@

Re: [lng-odp] [PATCHv2] validation: sched: fix out of array reference

Merged, Maxim. On 05/27/16 23:41, Bill Fischofer wrote: v2 works much better :) On Fri, May 27, 2016 at 2:50 PM, Maxim Uvarov > wrote: If MAX_CPUS defined to less then current cpus, then odp call calculates current available

[lng-odp] [PATCH] linux-generic: tm: init pthread attr to 0

Fix segmentation failt with not initialized attr for pthreads. Signed-off-by: Maxim Uvarov --- platform/linux-generic/odp_traffic_mngr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/platform/linux-generic/odp_traffic_mngr.c

Re: [lng-odp] 2fadf47 broke tm test

On 05/27/16 23:58, Bill Fischofer wrote: Which test? The TM validation tests continue to pass for me (both 64-bit and 32-bit) with the current master. ./bootstrap; ./configure --enable-test-vald --enable-test-perf --enable-test-cpp --enable-debug CFLAGS="-O0 -g" --enable-debug

[lng-odp] Fwd: thread/shmem discussion summary

Forwarded again to the list as the address I wrote was obviously wrong (no change for those who already received a personnal copy) -- Forwarded message -- From: Christophe Milard Date: 26 May 2016 at 17:11 Subject: thread/shmem discussion summary To: