Re: [lng-odp] [PATCH v3 0/8] First ABI files

Hi, Petri and Brian Can I understand this patch series are giving various platforms a chance to define their own data structures (like odp_event_t etc) in arch directory, instead of sharing the same definitions as previously? Best Regards, Yi On 27 January 2017 at 16:26, Savolainen, Petri (Nokia

Re: [lng-odp] [RFC] ODP classification matching rules extensions

While we can extend the current ODP classifier by adding additional PMR terms, I think a better long-term strategy is to adopt P4 as a generalized parser adjunct to better map to future flexible HW platforms (FPGA or SoC) that will be implementing native P4 capabilities as P4 continues to gain indu

[lng-odp] [PATCH] doc: userguide: add portability and usage info for odp time apis

Clarify and expand on portability and performance considerations regarding the use of the ODP time APIs in fulfillment of JIRA issue https://projects.linaro.org/browse/ODP-575 Signed-off-by: Bill Fischofer --- doc/users-guide/users-guide.adoc | 32 +--- 1 file changed

[lng-odp] [RFC] ODP classification matching rules extensions

Hi, as I was checking ODP Classification rules, I spotted a few possible extensions: - global options: . apply the defined rule on the last IP header - additional rules . rule on SCTP port . rule on IPsec SPI . rule on GTP TEID Can those extensions be implemented by current hardware

Re: [lng-odp] [PATCH] configure: libatomic check

patch fixes build on my machine but not in CI. In CI gcc compiles ok, but clang-3.4 and clang-3.7 not. I have locally clang-3.8 and maybe somehow CI needs to go with 3.8. Looking into this... Maxim. On 02/10/17 17:26, Maxim Uvarov wrote: > upcoming patch ip fragmentation example fails to with >

Re: [lng-odp] merge window for next tag (1.14 or 1.13.1) ends 20 Feb 2017

All Here is a comparison on api-next and master to prompt merge suggestions http://people.linaro.org/~mike.holmes/diff-abi/libodp-compat_report.html

Re: [lng-odp] [PATCH 1/5] test: generator: compose sending packets from reference packet plus differences

On Mon, Feb 13, 2017 at 6:49 AM, Bogdan Pricope wrote: > Signed-off-by: Bogdan Pricope > --- > example/generator/odp_generator.c | 131 > +- > 1 file changed, 114 insertions(+), 17 deletions(-) > > diff --git a/example/generator/odp_generator.c > b/example/g

Re: [lng-odp] [PATCH 1/2] helper: linux: renamed threads_extn to linux helpers

This is getting very confusing now: why helper/? do we have odp/?: shouldn't these be symetric? My view is getting clearer and clearer: On the test side, was have made tests for {OS, HW}= {linux/PC} and given the possibility to diverge from these (for any reason, e.g. difference of HW or OS) wi

Re: [lng-odp] [PATCH 1/2] helper: linux: renamed threads_extn to linux helpers

From: Mike Holmes [mailto:mike.hol...@linaro.org] Sent: Monday, February 13, 2017 5:02 PM To: Savolainen, Petri (Nokia - FI/Espoo) Cc: lng-odp Subject: Re: [lng-odp] [PATCH 1/2] helper: linux: renamed threads_extn to linux helpers On 13 February 2017 at 09:41, Savolainen, Petri (Nokia - FI

Re: [lng-odp] [API-NEXT PATCH 3/4] Revert "linux-generic: packet: implement reference apis"

This is a pretty big step backwards and without substantial justification I'm not sure why we would consider doing this. The performance characteristics of this base code has already been improved by both patch http://patches.opendataplane.org/patch/7879/ as well as patch series http://patches.open

Re: [lng-odp] [PATCH 1/2] helper: linux: renamed threads_extn to linux helpers

On 13 February 2017 at 09:41, Savolainen, Petri (Nokia - FI/Espoo) < petri.savolai...@nokia-bell-labs.com> wrote: > > > From: Mike Holmes [mailto:mike.hol...@linaro.org] > Sent: Friday, February 10, 2017 5:02 PM > To: Petri Savolainen > Cc: lng-odp > Subject: Re: [lng-odp] [PATCH 1/2] helper: li

Re: [lng-odp] [API-NEXT PATCH 1/4] api: packet: references may be implemented as copy

On Mon, Feb 13, 2017 at 6:53 AM, Petri Savolainen wrote: > Some implementations may implement new references as packet copy. > odp_packet_has_ref() will return 0 for copies, since those are > unique packets. > > Signed-off-by: Petri Savolainen > --- > include/odp/api/spec/packet.h | 20 +

Re: [lng-odp] [PATCH 1/2] helper: linux: renamed threads_extn to linux helpers

From: Mike Holmes [mailto:mike.hol...@linaro.org] Sent: Friday, February 10, 2017 5:02 PM To: Petri Savolainen Cc: lng-odp Subject: Re: [lng-odp] [PATCH 1/2] helper: linux: renamed threads_extn to linux helpers On 3 February 2017 at 06:23, Petri Savolainen

Re: [lng-odp] [API-NEXT PATCH 4/4] linux-gen: packet: implement references as copy

I suggest this be reposted as the initial skeleton implementation of packet references to odp-dpdk since that platform currently does not support these APIs and this would allow v1.14 functional parity with odp-linux. On Mon, Feb 13, 2017 at 6:53 AM, Petri Savolainen wrote: > Implement packet ref

[lng-odp] [PATCH 2/5] test: generator: send UDP packets in bursts

Signed-off-by: Bogdan Pricope --- example/generator/odp_generator.c | 77 +++ 1 file changed, 53 insertions(+), 24 deletions(-) diff --git a/example/generator/odp_generator.c b/example/generator/odp_generator.c index d1e3ecc..158bddf 100644 --- a/example/gene

[lng-odp] [PATCH 0/5] test:generator: improve performance

Hi, The goal of this series is to improve performance of "odp_generator" example application. [PATCH 1/5] test: generator: compose sending packets from reference packet plus differences Packets to send are basically similar with only small differences. [PATCH 2/5] test: generator: send UD

[lng-odp] [API-NEXT PATCH 3/4] Revert "linux-generic: packet: implement reference apis"

This reverts commit 22b3986fea090986625f3255d57b64de35bbc475. --- .../linux-generic/include/odp_packet_internal.h| 85 +--- platform/linux-generic/odp_packet.c| 536 - 2 files changed, 107 insertions(+), 514 deletions(-) diff --git a/platform/linux-generic

[lng-odp] [API-NEXT PATCH 2/4] validation: packet: remove non compatible tests

Tests for bad inputs are not compatible to the spec. Out-of-range values cause undefined results and must not be tested in validation suite. Remove reference checks that do not comply anymore to the new odp_packet_has_ref() specification. Signed-off-by: Petri Savolainen --- test/common_plat/val

[lng-odp] [API-NEXT PATCH 1/4] api: packet: references may be implemented as copy

Some implementations may implement new references as packet copy. odp_packet_has_ref() will return 0 for copies, since those are unique packets. Signed-off-by: Petri Savolainen --- include/odp/api/spec/packet.h | 20 +--- 1 file changed, 13 insertions(+), 7 deletions(-) diff --g

[lng-odp] [API-NEXT PATCH 0/4] Packet references as copy

Change packet references API specification to enable implementation as packet copy. Remove validation test cases which test for out-of-range inputs. Generally, results are undefined for bad or out-of-range inputs. Update validation tests with the API change. Greatly simplify packet reference im

[lng-odp] [API-NEXT PATCH 4/4] linux-gen: packet: implement references as copy

Implement packet references API as packet copy. This is the simplest way to support the API, as other packet functions are not affected at all. Signed-off-by: Petri Savolainen --- platform/linux-generic/odp_packet.c | 78 + 1 file changed, 78 insertions(+) di

[lng-odp] [PATCH 5/5] test: generator: use multiple TX queues in send UDP mode

Signed-off-by: Bogdan Pricope --- example/generator/odp_generator.c | 136 +++--- 1 file changed, 84 insertions(+), 52 deletions(-) diff --git a/example/generator/odp_generator.c b/example/generator/odp_generator.c index 8ed3b4b..922d185 100644 --- a/example/gene

[lng-odp] [PATCH 4/5] test: generator: use multiple RX queue in receiving mode

Signed-off-by: Bogdan Pricope --- example/generator/odp_generator.c | 23 +-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/example/generator/odp_generator.c b/example/generator/odp_generator.c index fbd3ec0..8ed3b4b 100644 --- a/example/generator/odp_generat

[lng-odp] [PATCH 3/5] test: generator: receive packets in bursts

Signed-off-by: Bogdan Pricope --- example/generator/odp_generator.c | 29 +++-- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/example/generator/odp_generator.c b/example/generator/odp_generator.c index 158bddf..fbd3ec0 100644 --- a/example/generator/odp_

[lng-odp] [PATCH 1/5] test: generator: compose sending packets from reference packet plus differences

Signed-off-by: Bogdan Pricope --- example/generator/odp_generator.c | 131 +- 1 file changed, 114 insertions(+), 17 deletions(-) diff --git a/example/generator/odp_generator.c b/example/generator/odp_generator.c index 8062d87..d1e3ecc 100644 --- a/example/gen

[lng-odp] [Bug 2464] strict priority schedule is not tested under CI

https://bugs.linaro.org/show_bug.cgi?id=2464 --- Comment #6 from Mike Holmes --- Commit f21b2d2 -- You are receiving this mail because: You are on the CC list for the bug.

Re: [lng-odp] [PATCH v2 2/3] linux-generic: crypto: move OpenSSL locks out of global crypto data

Hi Dmitry, Have you got the CRYPTO_set_id_callback building issue? implicit declaration, because of failing define the macro OPENSSL_USE_DEPRECATED . Looks like the function is deprecated by #ifdef in openssl/crypto.h. # ifdef OPENSSL_USE_DEPRECATED DECLARE_DEPRECATED(void CRYPTO_set_id_callback(

Re: [lng-odp] what is a platform?

> -Original Message- > From: Christophe Milard [mailto:christophe.mil...@linaro.org] > Sent: Saturday, February 11, 2017 7:56 PM > To: Mike Holmes ; Savolainen, Petri (Nokia - > FI/Espoo) ; LNG ODP Mailman List > > Subject: what is a platform? > > Hi, > > I am afraid I got very confuse