Re: [lng-odp] [RFC/API-NEXT 1/1] api: classification: packet hashing per class of service

2016-12-09 Thread Bala Manoharan
Regards, Bala On 10 December 2016 at 02:06, Bill Fischofer wrote: > Is this supposed to be instead of queue groups or in addition to queue > group support? Yes. Basically the changes is that this proposal merges queue group and queue together. > > On Fri, Dec 9,

Re: [lng-odp] [RFC/API-NEXT 1/1] api: classification: packet hashing per class of service

2016-12-09 Thread Bill Fischofer
Is this supposed to be instead of queue groups or in addition to queue group support? On Fri, Dec 9, 2016 at 5:54 AM, Balasubramanian Manoharan wrote: > Adds support to spread packet from a single CoS to multiple queues by > configuring hashing at CoS level. > >

[lng-odp] [API-NEXT PATCH 4/4] linux-gen: pktio ipc: make it work again

2016-12-09 Thread Maxim Uvarov
Signed-off-by: Maxim Uvarov --- .../linux-generic/include/odp_buffer_internal.h| 10 +- platform/linux-generic/include/odp_internal.h | 1 - .../include/odp_packet_io_ipc_internal.h | 27 +- platform/linux-generic/odp_init.c | 5

[lng-odp] [API-NEXT PATCH 3/4] linux-gen: pktio ipc: update tests

2016-12-09 Thread Maxim Uvarov
Signed-off-by: Maxim Uvarov --- test/linux-generic/pktio_ipc/ipc_common.c | 41 ++ test/linux-generic/pktio_ipc/ipc_common.h | 15 +-- test/linux-generic/pktio_ipc/pktio_ipc1.c | 60 --

[lng-odp] [API-NEXT PATCH 2/4] linux-gen: pktio ipc: more accurate settings of pool flags

2016-12-09 Thread Maxim Uvarov
Clean up code for exporting packet pools. Signed-off-by: Maxim Uvarov --- platform/linux-generic/odp_pool.c | 11 +++ 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/platform/linux-generic/odp_pool.c b/platform/linux-generic/odp_pool.c index

[lng-odp] [API-NEXT PATCH 1/4] linux-gen: pktio ipc: ring changes

2016-12-09 Thread Maxim Uvarov
Make rings visible by other processes. Signed-off-by: Maxim Uvarov --- platform/linux-generic/pktio/ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/platform/linux-generic/pktio/ring.c b/platform/linux-generic/pktio/ring.c index

[lng-odp] [API-NEXT PATCH 0/4] linux-gen: pktio ipc: make it work again

2016-12-09 Thread Maxim Uvarov
Make ipc pktio functional after Petris and Chistophe changes. Maxim Uvarov (4): linux-gen: pktio ipc: ring changes linux-gen: pktio ipc: more accurate settings of pool flags linux-gen: pktio ipc: update tests linux-gen: pktio ipc: make it work again

Re: [lng-odp] [API-NEXT PATCHv2 0/4] Add iquery scheduler

2016-12-09 Thread Maxim Uvarov
Hello Yi, can you please add some documentation text about that scheduler. Might be something very close to that commit description. It will be good do have some doc to point people who ask what is propose of different scheduler. Thank you, Maxim. On 12/09/16 13:51, Yi He wrote: > v2: rebase to

Re: [lng-odp] [API-NEXT PATCH v3] api: ipsec: added IPSEC API

2016-12-09 Thread Maxim Uvarov
Merged, Maxim. On 12/09/16 12:00, Bala Manoharan wrote: > Reviewed-by: Balasubramanian Manoharan > > > On 1 December 2016 at 14:47, Petri Savolainen > wrote: >> Added definitions for a look-a-side IPSEC offload API. In addition to >>

Re: [lng-odp] contributing to the "example" directory

2016-12-09 Thread Mike Holmes
One further thought is that if it in some way benchmarks anything it is perhaps a candidate for the test performance directory instead. On 9 December 2016 at 09:47, Bill Fischofer wrote: > This sounds like an excellent example. The goal of ODP examples is to >

Re: [lng-odp] [API-NEXT PATCHv8 1/3] api: random: add explicit controls over random data

2016-12-09 Thread Bill Fischofer
On Fri, Dec 9, 2016 at 3:27 AM, Savolainen, Petri (Nokia - FI/Espoo) wrote: > > >> + >> +/** >> + * Generate repeatable random data for testing purposes >> + * >> + * For testing purposes it is often useful to generate "random" sequences >> that >> + * are

Re: [lng-odp] contributing to the "example" directory

2016-12-09 Thread Bill Fischofer
This sounds like an excellent example. The goal of ODP examples is to illustrate programming techniques and API usage that may be of interest to others in either evaluating ODP and/or writing their own applications with it. As such, examples are expected to be reasonably succinct and focused, but

Re: [lng-odp] [PATCH v2 4/6] helper: use ODP_LIB_FLAVOR to generate libodp name

2016-12-09 Thread Nicolas Morey-Chaisemartin
Le 12/09/2016 à 02:41 PM, Mike Holmes a écrit : > > > On 9 December 2016 at 08:33, Nicolas Morey-Chaisemartin > wrote: > > > > Le 12/09/2016 à 02:18 PM, Mike Holmes a écrit : >> >> >> On 9 December 2016 at 04:41, Nicolas Morey-Chaisemartin

Re: [lng-odp] [PATCH v2 4/6] helper: use ODP_LIB_FLAVOR to generate libodp name

2016-12-09 Thread Mike Holmes
On 9 December 2016 at 08:33, Nicolas Morey-Chaisemartin wrote: > > > Le 12/09/2016 à 02:18 PM, Mike Holmes a écrit : > > > > On 9 December 2016 at 04:41, Nicolas Morey-Chaisemartin > wrote: > >> I'm OK with this. The only issue I have with this is that it

Re: [lng-odp] [PATCH v2 4/6] helper: use ODP_LIB_FLAVOR to generate libodp name

2016-12-09 Thread Nicolas Morey-Chaisemartin
Le 12/09/2016 à 02:18 PM, Mike Holmes a écrit : > > > On 9 December 2016 at 04:41, Nicolas Morey-Chaisemartin > wrote: > > I'm OK with this. The only issue I have with this is that it moves back > platform/OS selection back to configure.ac

Re: [lng-odp] [PATCH v2 4/6] helper: use ODP_LIB_FLAVOR to generate libodp name

2016-12-09 Thread Mike Holmes
On 9 December 2016 at 04:41, Nicolas Morey-Chaisemartin wrote: > I'm OK with this. The only issue I have with this is that it moves back > platform/OS selection back to configure.ac while I've been trying to move > it out

Re: [lng-odp] [PATCHv4] platform: linux-generic: reading cpu affinity from cpuset

2016-12-09 Thread Maxim Uvarov
Merged, Maxim. On 12/07/16 06:36, Yi He wrote: > Reviewed-and-tested-by: Yi He > > > On 6 December 2016 at 22:15, Balakrishna Garapati < > balakrishna.garap...@linaro.org> wrote: > >> With this new proposal cpu affinity is read correctly especially >> when using cgroups

Re: [lng-odp] [PATCH] linux-generic: only enable pktout when egress kind is pktio

2016-12-09 Thread Maxim Uvarov
Bala, please review TM patch. Thank you, Maxim. On 12/08/16 04:58, Forrest Shi wrote: > ping. > > This is a simple fix. > The original code skips the support of egress_kind as ODP_TM_EGRESS_FN > > On 2 December 2016 at 15:42, wrote: > >> From: Xuelin Shi

Re: [lng-odp] [PATCH] helper: remove unused variable

2016-12-09 Thread Maxim Uvarov
Merged, Maxim. On 12/08/16 00:05, Bill Fischofer wrote: > On Fri, Dec 2, 2016 at 9:55 AM, Mike Holmes wrote: >> Signed-off-by: Mike Holmes > > Reviewed-by: Bill Fischofer > >> --- >> helper/linux.c | 1 - >> 1 file

Re: [lng-odp] [PATCH] linux-generic: move tm system barrier to tm group

2016-12-09 Thread Maxim Uvarov
Merged, Maxim. On 12/08/16 05:21, Bala Manoharan wrote: > Reviewed-by: Balasubramanian Manoharan > > On 2 December 2016 at 13:41, wrote: >> From: Xuelin Shi >> >> since tm thread is handling tm group, move the thread

Re: [lng-odp] [PATCH] validation: packet: remove todos from packet tests

2016-12-09 Thread Maxim Uvarov
Merged, Maxim. On 12/08/16 21:24, Mike Holmes wrote: > On 12 September 2016 at 16:48, Bill Fischofer > wrote: > >> Resolve Bug https://bugs.linaro.org/show_bug.cgi?id=2405 by removing >> todos in packet validation test. Add additional tests for todos that can >> be

Re: [lng-odp] [PATCH 1/2] configure: if no ABI reset .so to 0

2016-12-09 Thread Maxim Uvarov
Merged with fix. Maxim. On 12/08/16 18:58, Mike Holmes wrote: > Thanks Petri > > Maxim can you fix typo on commit ? > > On 8 December 2016 at 02:32, Savolainen, Petri (Nokia - FI/Espoo) < > petri.savolai...@nokia-bell-labs.com> wrote: > >> >> >>> -Original Message- >>> From: lng-odp

[lng-odp] [RFC/API-NEXT 1/1] api: classification: packet hashing per class of service

2016-12-09 Thread Balasubramanian Manoharan
Adds support to spread packet from a single CoS to multiple queues by configuring hashing at CoS level. Signed-off-by: Balasubramanian Manoharan --- include/odp/api/spec/classification.h | 45 --- 1 file changed, 42 insertions(+), 3

Re: [lng-odp] [API-NEXT PATCH] linux-gen: sched: fix SP scheduler hang in process mode

2016-12-09 Thread Savolainen, Petri (Nokia - FI/Espoo)
> -Original Message- > From: Yi He [mailto:yi...@linaro.org] > Sent: Friday, December 09, 2016 5:35 AM > To: Savolainen, Petri (Nokia - FI/Espoo) labs.com>; Elo, Matias (Nokia - FI/Espoo) labs.com>; lng-odp@lists.linaro.org > Cc: Yi

Re: [lng-odp] odp_rwlock_read_trylock

2016-12-09 Thread Savolainen, Petri (Nokia - FI/Espoo)
> -Original Message- > From: Nicolas Morey-Chaisemartin [mailto:nmo...@kalray.eu] > Sent: Friday, December 09, 2016 12:14 PM > To: Savolainen, Petri (Nokia - FI/Espoo) labs.com>; LNG ODP Mailman List > Subject: Re: [lng-odp]

[lng-odp] [API-NEXT PATCHv2 3/4] linux-gen: add generic bitmaps and iterators

2016-12-09 Thread Yi He
Add C++ template alike bitmap to allow instantiate bitmap data structure of any size, and provide iterators to help walking through the bitmap objects. Signed-off-by: Yi He --- platform/linux-generic/Makefile.am | 2 +

[lng-odp] [API-NEXT PATCHv2 4/4] linux-gen: add interests query (iquery) scheduler

2016-12-09 Thread Yi He
Add this interests query (iquery) scheduler as an alternate choice of ODP-linux scheduler component for performance optimization especially in lower queue counts use cases. It includes a new core algorithm, but adopted the ring-based pktio poll algorithm from default scheduler, and still uses the

[lng-odp] [API-NEXT PATCHv2 2/4] linux-gen: sched: add unsched_queue callback

2016-12-09 Thread Yi He
Add this unsched_queue callback to indicate queue's ineligible for scheduling. Signed-off-by: Yi He --- platform/linux-generic/include/odp_schedule_if.h | 2 ++ platform/linux-generic/odp_queue.c | 4 +++- platform/linux-generic/odp_schedule.c| 6

[lng-odp] [API-NEXT PATCHv2 1/4] linux-gen: sched: solve ordered context inversion

2016-12-09 Thread Yi He
For ordered queue, a thread consumes events (dequeue) and acquires its unique sequential context in two steps, non atomic and preemptable. This leads to potential ordered context inversion in case the thread consumes prior events acquired subsequent context, while the thread consumes subsequent

Re: [lng-odp] odp_rwlock_read_trylock

2016-12-09 Thread Nicolas Morey-Chaisemartin
Le 12/09/2016 à 10:45 AM, Savolainen, Petri (Nokia - FI/Espoo) a écrit : > >> -Original Message- >> From: Nicolas Morey-Chaisemartin [mailto:nmo...@kalray.eu] >> Sent: Thursday, December 08, 2016 5:30 PM >> To: Savolainen, Petri (Nokia - FI/Espoo) >

Re: [lng-odp] odp_rwlock_read_trylock

2016-12-09 Thread Savolainen, Petri (Nokia - FI/Espoo)
> -Original Message- > From: Nicolas Morey-Chaisemartin [mailto:nmo...@kalray.eu] > Sent: Thursday, December 08, 2016 5:30 PM > To: Savolainen, Petri (Nokia - FI/Espoo) labs.com>; LNG ODP Mailman List > Subject: Re: [lng-odp]

Re: [lng-odp] [PATCH v2 4/6] helper: use ODP_LIB_FLAVOR to generate libodp name

2016-12-09 Thread Nicolas Morey-Chaisemartin
I'm OK with this. The only issue I have with this is that it moves back platform/OS selection back to configure.ac while I've been trying to move it out (https://github.com/nmorey/odp/tree/dev/generic-platforms). Shouldn't each platform select the right OS ? I mean linux-generic will probably

Re: [lng-odp] [API-NEXT PATCHv8 1/3] api: random: add explicit controls over random data

2016-12-09 Thread Savolainen, Petri (Nokia - FI/Espoo)
> + > +/** > + * Generate repeatable random data for testing purposes > + * > + * For testing purposes it is often useful to generate "random" sequences > that > + * are repeatable. This is accomplished by supplying a seed value that is > used > + * for pseudo-random data generation. The

Re: [lng-odp] [API-NEXT PATCH v3] api: ipsec: added IPSEC API

2016-12-09 Thread Bala Manoharan
Reviewed-by: Balasubramanian Manoharan On 1 December 2016 at 14:47, Petri Savolainen wrote: > Added definitions for a look-a-side IPSEC offload API. In addition to > IPSEC packet transformations, it also supports: > * inbound SA look up >