[lng-odp] [Bug 1752] New: timer test: Number of timeouts delivered/received too late: 0

https://bugs.linaro.org/show_bug.cgi?id=1752 Bug ID: 1752 Summary: timer test: Number of timeouts delivered/received too late: 0 Product: OpenDataPlane Version: unspecified Hardware: Other OS: Linux

[lng-odp] [API-NEXT PATCHv2 0/7] implementation of odp_pktio_start and _stop

v2: return -1 and set odp_errno on send/receive on stopped pktio. Adjust test accordingly. -- odp_pktio_start() and odp_pktio_stop() API function uses to control pktio inside worker or to start/stop pktio from control thread. Patch set includes: - linux-generic implementation - validation t

[lng-odp] [API-NEXT PATCHv2 2/7] linux-generic: schedule pktin_poll: account pktio stop state

If pktio in state stop return 0, which means no packets was received but that pktio is good to be sheduled next time. Signed-off-by: Maxim Uvarov --- platform/linux-generic/odp_packet_io.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/platform/linux-generic/odp_packet_io.c b/platform/l

[lng-odp] [API-NEXT PATCHv2 1/7] linux-generic: add pktio_start and pktio_stop

Signed-off-by: Maxim Uvarov --- .../linux-generic/include/odp_packet_io_internal.h | 6 platform/linux-generic/odp_packet_io.c | 34 ++ 2 files changed, 40 insertions(+) diff --git a/platform/linux-generic/include/odp_packet_io_internal.h b/platform/linux-g

[lng-odp] [API-NEXT PATCHv2 3/7] linux-generic: loop: implement pktio_start and pktio_stop

Signed-off-by: Maxim Uvarov --- platform/linux-generic/pktio/loop.c | 27 +++ 1 file changed, 27 insertions(+) diff --git a/platform/linux-generic/pktio/loop.c b/platform/linux-generic/pktio/loop.c index 188a9ee..f61ccd5 100644 --- a/platform/linux-generic/pktio/loop.c +

[lng-odp] [API-NEXT PATCHv2 4/7] linux-generic: socket mmap: implement pktio_start and pktio_stop

Signed-off-by: Maxim Uvarov --- platform/linux-generic/pktio/socket_mmap.c | 27 +++ 1 file changed, 27 insertions(+) diff --git a/platform/linux-generic/pktio/socket_mmap.c b/platform/linux-generic/pktio/socket_mmap.c index 7d42678..2e55672 100644 --- a/platform/linux-g

[lng-odp] [API-NEXT PATCHv2 5/7] linux-generic: socket: implement pktio_start and pktio_stop

Signed-off-by: Maxim Uvarov --- platform/linux-generic/pktio/socket.c | 37 +++ 1 file changed, 37 insertions(+) diff --git a/platform/linux-generic/pktio/socket.c b/platform/linux-generic/pktio/socket.c index 55c3594..7db9747 100644 --- a/platform/linux-generic/

[lng-odp] [API-NEXT PATCHv2 6/7] validation: test odp_pktio_start and odp_pktio_stop

Signed-off-by: Maxim Uvarov --- test/validation/pktio/pktio.c | 114 ++ 1 file changed, 114 insertions(+) diff --git a/test/validation/pktio/pktio.c b/test/validation/pktio/pktio.c index ebe34fa..4222463 100644 --- a/test/validation/pktio/pktio.c +++ b/tes

[lng-odp] [API-NEXT PATCHv2 7/7] linux-generic: default state for pktio is STOP

After open pktio remains stopped. Inside worker thread (after all configuration done it should be started.) In that patch I just start it everywhere to keep original logic and be easy for review. Putting it inside worker threads will require thread arguments change and understanding logic of curren

[lng-odp] [PATCHv2 0/4] make it possible to build from tarball source

Hi, This is the last patches that is needed to be able to build from the tarball source. And a patch that makes it possible for a platform to add its own custom string. v2: fix according to Maxims comments; shortlog on patch "scripts/git_hash: change repo to CUSTOM_STR" and added a comment in p

[lng-odp] [PATCHv2 2/4] scripts/git_hash: change repo to CUSTOM_STR

other platforms should export CUSTOM_STR in their platform//Makefile.am Signed-off-by: Anders Roxell --- platform/linux-generic/Makefile.am | 3 +++ scripts/git_hash.sh| 4 ++-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/platform/linux-generic/Makefile.am b/p

[lng-odp] [PATCHv2 1/4] scripts/git_hash: fix build from tar source

Signed-off-by: Anders Roxell --- .gitignore| 1 + platform/Makefile.inc | 2 +- scripts/Makefile.am | 2 +- scripts/git_hash.sh | 18 ++ 4 files changed, 17 insertions(+), 6 deletions(-) diff --git a/.gitignore b/.gitignore index f534808..b4c146b 100644 --- a/.

[lng-odp] [PATCHv2 4/4] test/performance: Makefile: add scripts to EXTRA_DIST

Makes it possible to run make check from the tar source. Signed-off-by: Anders Roxell --- test/performance/Makefile.am | 2 ++ 1 file changed, 2 insertions(+) diff --git a/test/performance/Makefile.am b/test/performance/Makefile.am index ae2973e..721615b 100644 --- a/test/performance/Makefile.a

[lng-odp] [PATCHv2 3/4] test/validation: fix build from tar source

Signed-off-by: Anders Roxell --- test/validation/buffer/Makefile.am | 2 ++ test/validation/classification/Makefile.am | 2 ++ test/validation/common/Makefile.am | 2 ++ test/validation/cpumask/Makefile.am| 2 ++ test/validation/crypto/Makefile.am | 2 ++ test/vali

Re: [lng-odp] [PATCH 2/3] test: validation: classification: unused variable

Thanks will generate additional tests On 14 August 2015 at 02:23, Bala Manoharan wrote: > I agree with Bill. retval should be tested for success in this case. > > Regards, > Bala > > On 14 August 2015 at 01:24, Bill Fischofer > wrote: > >> >> >> On Thu, Aug 13, 2015 at 2:04 PM, Mike Holmes >>

Re: [lng-odp] [API-NEXT PATCH v2] api: packet: allow access to packet RSS hash values

No, you need the hash of a particular packet you process: "The filter used in RSS is typically a hash function over the network and/or transport layer headers-- for example, a 4-tuple hash over IP addresses and TCP ports of a packet" On 14/08/15 16:06, Maxim Uvarov wrote: Should it be per pktio

Re: [lng-odp] [API-NEXT PATCH v2] api: packet: allow access to packet RSS hash values

Should it be per pktio rss hash then per packet? I'm reading here: https://www.kernel.org/doc/Documentation/networking/scaling.txt that rss is hash per device how to split traffic. If it's per device than in odp terms it's for pktio. Maxim. On 08/13/15 22:59, Bill Fischofer wrote: On Thu,

Re: [lng-odp] [API-NEXT PATCH v2] api: packet: allow access to packet RSS hash values

On 08/14/15 18:12, Zoltan Kiss wrote: No, you need the hash of a particular packet you process: "The filter used in RSS is typically a hash function over the network and/or transport layer headers-- for example, a 4-tuple hash over IP addresses and TCP ports of a packet" ok, it's not hash func

[lng-odp] [Patch] validation: time: use timer resolution instead of TOLERANCE

The TOLERANCE hardcodes a timer resolution, so replace it on real timer resolution that can be got by odp_time_tick_to_ns(1). Signed-off-by: Ivan Khoronzhuk --- Based on "api: time: change API to use ticks instead of cycles" https://lists.linaro.org/pipermail/lng-odp/2015-August/014198.html te

Re: [lng-odp] [API-NEXT PATCHv2] validation: classification: added additional suite to test individual PMRs

Hi, Bala Just checked if you added real MAC and seems you forgot to. Or maybe you are planing to do it in separate patch. On 12.08.15 11:53, Balasubramanian Manoharan wrote: Additional test suite is added to classification validation suite to test individual PMRs. This suite will test the defin

Re: [lng-odp] [API-NEXT PATCHv2] validation: classification: added additional suite to test individual PMRs

Hi Ivan, I am planning to add MAC support in a separate patch. I believe MAC should be easier to get-in since it has been agreed. Regards, Bala On 14 August 2015 at 21:57, Ivan Khoronzhuk wrote: > Hi, Bala > > Just checked if you added real MAC and seems you forgot to. > Or maybe you are plani

Re: [lng-odp] [API-NEXT PATCHv2] validation: classification: added additional suite to test individual PMRs

On 14.08.15 19:29, Bala Manoharan wrote: Hi Ivan, I am planning to add MAC support in a separate patch. I believe MAC should be easier to get-in since it has been agreed. Ok. ___ lng-odp mailing list lng-odp@lists.linaro.org https://lists.linaro.org

[lng-odp] [API-NEXT PATCH v3 1/3] api: packet: allow access to packet RSS hash values

Applications can read the computed hash (if any) and set it if they changed the packet headers or if the platform haven't calculated the hash. Signed-off-by: Zoltan Kiss --- v2: - focus on RSS hash only - use setter/getter's v3: - do not mention pointers - add a note - add new patches for implem

[lng-odp] [API-NEXT PATCH v3 2/3] linux-generic: packet: implement RSS hash support

This platform doesn't compute it, packet_init set it to 0, which happens to be ODP_PACKET_RSS_INVALID. Signed-off-by: Zoltan Kiss --- platform/linux-generic/include/odp/plat/packet_types.h | 2 ++ platform/linux-generic/include/odp_packet_internal.h | 1 + platform/linux-generic/odp_packet.c

[lng-odp] [API-NEXT PATCH v3 3/3] validation: packet: test if the max value can be set for RSS hash

Signed-off-by: Zoltan Kiss --- test/validation/packet/packet.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/test/validation/packet/packet.c b/test/validation/packet/packet.c index 99a6745..a4eb24c 100644 --- a/test/validation/packet/packet.c +++ b/test/validation/packet/packet.c @@ -164

[lng-odp] [API-NEXT PATCH v4 1/3] api: pool: add packet user area initializer for pool creation parameters

Applications can preset certain parts of the packet user area, so when that memory will be allocated it starts from a known state. If the platform allocates the memory during pool creation, it's enough to run the constructor after that. If it's allocating memory on demand, it should call the constr

[lng-odp] [API-NEXT PATCH v4 2/3] linux-generic: pool: implement user area init support

Signed-off-by: Zoltan Kiss --- v4: - fix function pointer call - add newline after declarations platform/linux-generic/odp_pool.c | 11 +++ 1 file changed, 11 insertions(+) diff --git a/platform/linux-generic/odp_pool.c b/platform/linux-generic/odp_pool.c index 14221fd..028f0be 100644

[lng-odp] [API-NEXT PATCH v4 3/3] validation: packet: test if user area is properly set

Signed-off-by: Zoltan Kiss Reviewed-and-tested-by: Bill Fischofer --- test/validation/packet/packet.c | 18 ++ 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/test/validation/packet/packet.c b/test/validation/packet/packet.c index 99a6745..36edc12 100644 --- a/test

Re: [lng-odp] [API-NEXT PATCH v4 1/3] api: pool: add packet user area initializer for pool creation parameters

For the v4 series: Reviewed-and-tested-by: Bill Fischofer On Fri, Aug 14, 2015 at 1:55 PM, Zoltan Kiss wrote: > Applications can preset certain parts of the packet user area, so when that > memory will be allocated it starts from a known state. If the platform > allocates the memory during poo