Re: [lng-odp] [PATCHv2] linux-generic: tm: handle pktout queue check properly

On 10 August 2016 at 16:41, Bill Fischofer wrote: > Resolve bug https://bugs.linaro.org/show_bug.cgi?id=2458 by only checking > for a proper pktout_queue count if the egress_kind is ODP_TM_EGRESS_PKT_IO. > > This check is also moved before locking and allocating a tm_system struct > to avoid dead

Re: [lng-odp] [PATCHv2] linux-generic: tm: handle pktout queue check properly

Ping. This urgently needs a review for Monarch release. Testing is simple: example/traffic_mgmt/odp_traffic_mngr sefaults immediately without this patch and passes with it. Thanks. On Wed, Aug 10, 2016 at 3:41 PM, Bill Fischofer wrote: > Resolve bug https://bugs.linaro.org/show_bug.cgi?id=2458

Re: [lng-odp] [API-NEXT PATCH] test: drv: atomic renamed to drvatomic

After discussions in the ARCH calls I think this is the best way forward. On 4 August 2016 at 04:58, Christophe Milard wrote: > At installation time (make install) all tests executables are copied > into a single directory (lib/odp/tests). > Having two modules with identical names on the two int

Re: [lng-odp] [PATCH] test: performance: capture termination failures in final return code

On 08/11/16 21:43, Bill Fischofer wrote: On Thu, Aug 11, 2016 at 1:15 PM, Mike Holmes > wrote: On 11 August 2016 at 13:01, Maxim Uvarov mailto:maxim.uva...@linaro.org>> wrote: > I'm going to apply this patch to master. But test might fail on bug in

Re: [lng-odp] [PATCH] test: performance: capture termination failures in final return code

On 08/11/16 21:43, Bill Fischofer wrote: On Thu, Aug 11, 2016 at 1:15 PM, Mike Holmes > wrote: On 11 August 2016 at 13:01, Maxim Uvarov mailto:maxim.uva...@linaro.org>> wrote: > I'm going to apply this patch to master. But test might fail on bug in

Re: [lng-odp] [PATCHv2] example: odp_l2fwd place readme with symlink

Merged, Maxim. On 08/12/16 16:41, Mike Holmes wrote: On 11 August 2016 at 12:44, Maxim Uvarov > wrote: odp_l2fwd is standalone application which can be used as example or as performance test. Hiding it inside performance tests might be not new user

Re: [lng-odp] [PATCH v2 1/6] linux-generic: internal odp_cpu_pause()

Does anybody else reviewing this patchset? Maxim. On 08/04/16 22:30, Brian Brooks wrote: Signed-off-by: Brian Brooks --- platform/linux-generic/arch/default/odp/api/cpu_arch.h | 2 +- platform/linux-generic/arch/mips64/odp/api/cpu_arch.h | 2 +- platform/linux-generic/arch/powerpc/odp/api

Re: [lng-odp] [PATCHv3] linux-gen: doc: defining the ODP thread

Merged, Maxim. On 08/12/16 18:00, Bill Fischofer wrote: On Tue, Aug 9, 2016 at 3:01 AM, Christophe Milard mailto:christophe.mil...@linaro.org>> wrote: Signed-off-by: Christophe Milard mailto:christophe.mil...@linaro.org>> Signed-off-by: Mike Holmes mailto:mike.hol...@linaro.org>>

Re: [lng-odp] [API-NEXT PATCHv2] helper: cuckootable: add missing return codes

Merged, Maxim. On 08/12/16 17:30, Bill Fischofer wrote: On Thu, Aug 11, 2016 at 9:14 AM, Maxim Uvarov > wrote: add missing return codes for non void functions. Signed-off-by: Maxim Uvarov mailto:maxim.uva...@linaro.org>> Reviewed-and-tested-by: Bill

Re: [lng-odp] [PATCHv3] linux-gen: doc: defining the ODP thread

On Tue, Aug 9, 2016 at 3:01 AM, Christophe Milard < christophe.mil...@linaro.org> wrote: > Signed-off-by: Christophe Milard > Signed-off-by: Mike Holmes > Reviewed-and-tested-by: Bill Fischofer > --- > doc/platform-api-guide/Doxyfile | 1 + > doc/platform-api-guide/Makefil

Re: [lng-odp] [API-NEXT PATCHv2] helper: cuckootable: add missing return codes

On Thu, Aug 11, 2016 at 9:14 AM, Maxim Uvarov wrote: > add missing return codes for non void functions. > > Signed-off-by: Maxim Uvarov > Reviewed-and-tested-by: Bill Fischofer > --- > helper/cuckootable.c | 36 +--- > 1 file changed, 25 insertions(+), 11 del

Re: [lng-odp] [PATCH v2] doc: release-guide: add LTS details

On Fri, Aug 12, 2016 at 5:38 AM, Mike Holmes wrote: > Signed-off-by: Mike Holmes > --- > v2 >clean up to text (Bill) >Added comment on bisect ability on patch acceptance > > doc/process-guide/release-guide.adoc | 52 ++ > ++ > 1 file changed, 52 insertion

Re: [lng-odp] [PATCHv2] example: odp_l2fwd place readme with symlink

On 11 August 2016 at 12:44, Maxim Uvarov wrote: > odp_l2fwd is standalone application which can be used > as example or as performance test. Hiding it inside > performance tests might be not new users friendly way. > Create symlink with small readme file for better finding > it. > > Signed-off-by

Re: [lng-odp] odp_scheduling.c bug

Yes :) On 12 August 2016 at 09:12, Maxim Uvarov wrote: > sorry, not mine. Bill's patch which I wanted to merge. > > On 08/12/16 15:18, Mike Holmes wrote: > >> Anders confirmed he saw the same thing and it appears that make check >> does not get informed that it failed. >> >> > my yesterdays patc

Re: [lng-odp] odp_scheduling.c bug

sorry, not mine. Bill's patch which I wanted to merge. On 08/12/16 15:18, Mike Holmes wrote: Anders confirmed he saw the same thing and it appears that make check does not get informed that it failed. my yesterdays patch ;)

Re: [lng-odp] odp_scheduling.c bug

On 08/12/16 15:18, Mike Holmes wrote: Anders confirmed he saw the same thing and it appears that make check does not get informed that it failed. my yesterdays patch ;)

Re: [lng-odp] odp_scheduling.c bug

I just tried to run this in a docker container to see if valgrind thread lock checking tools could help and never got that far, I consistently get issues and I used two sandboxes. run1 odp_queue.c:328:odp_queue_destroy():queue "sched_00_47" not empty odp_schedule.c:271:schedule_term_global():Queue

[lng-odp] odp_scheduling.c bug

Looking to issue with issue with odp_scheduling.c Problem can be described with following code: Each cpu does this: 1. code allocs some events and place them to queue. 2. odp_schedule_pause(); 3. odp_schedule_multi() put them back to queue. 4. odp_schedule_resume(); 5. odp_barrier_wait(&globals

[lng-odp] [PATCH v2] doc: release-guide: add LTS details

Signed-off-by: Mike Holmes --- v2 clean up to text (Bill) Added comment on bisect ability on patch acceptance doc/process-guide/release-guide.adoc | 52 1 file changed, 52 insertions(+) diff --git a/doc/process-guide/release-guide.adoc b/doc/process-g

Re: [lng-odp] [PATCHv7 1/2] example: introducing l3fwd

I tested the application on our server and the forwarding rate doesn’t scale when core count is increased (added l2fwd and OFP results for reference). Based on some debugging this seems to be caused by using locks on the TX side. ‘perf’ shows that the application spends most of time in odp_ticke