Re: [lng-odp] [PATCH v4] linux-gen: system: correctly set CPU frequency

Ilias Apalodimas(apalos) replied on github web page: platform/linux-generic/odp_system_info.c line 22 @@ -326,6 +327,23 @@ int odp_system_info_init(void) fclose(file); + for (i = 0; i < MAX_CPU_NUMBER; i++) { + char temp[256], *endptr = NULL; +

Re: [lng-odp] [PATCH v4] linux-gen: system: correctly set CPU frequency

Ilias Apalodimas(apalos) replied on github web page: platform/linux-generic/odp_system_info.c line 18 @@ -326,6 +327,23 @@ int odp_system_info_init(void) fclose(file); + for (i = 0; i < MAX_CPU_NUMBER; i++) { + char temp[256], *endptr = NULL; +

Re: [lng-odp] [PATCH v4] linux-gen: system: correctly set CPU frequency

Ilias Apalodimas(apalos) replied on github web page: platform/linux-generic/odp_system_info.c line 12 @@ -326,6 +327,23 @@ int odp_system_info_init(void) fclose(file); + for (i = 0; i < MAX_CPU_NUMBER; i++) { Comment: This might be better to be converted to a function, since

[lng-odp] [PATCH API-NEXT v1 9/19] test: rework build system

From: Dmitry Eremin-Solenikov - Stop using extra libraries just to create a test executable - Stop using EXTRA_DIST to distribute headers, include them into _SOURCES - Stop using unnecessary dist_ prefixes, sources are distributed automatically

[lng-odp] [PATCH API-NEXT v1 18/19] configure: call PKG_PROG_PKG_CONFIG explicitly

From: Dmitry Eremin-Solenikov Since it well might be that first PKG_CHECK_* call ends up under if, it is required (by pkg-config docs) to call PKG_PROG_PKG_CONFIG explicitly. Signed-off-by: Dmitry Eremin-Solenikov

[lng-odp] [PATCH API-NEXT v1 19/19] test: drv: remove -Wno-deprecated-declarations set

From: Maxim Uvarov cflags are set from top level directory, drv should not modify them internaly. Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173 (muvarov:api-next) ** https://github.com/Linaro/odp/pull/173 ** Patch:

[lng-odp] [PATCH API-NEXT v1 15/19] travis: skip install stage for doxygen and checkpatch tests

From: Dmitry Eremin-Solenikov Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173

[lng-odp] [PATCH API-NEXT v1 14/19] travis: don't error out if there are no patches to check

From: Dmitry Eremin-Solenikov Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173

[lng-odp] [PATCH API-NEXT v1 13/19] test: misc rewrites in Makefile.am files

From: Dmitry Eremin-Solenikov Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173

[lng-odp] [PATCH API-NEXT v1 11/19] test: pktio_ipc: switch to test_debug rather than example_debug

From: Dmitry Eremin-Solenikov Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173

[lng-odp] [PATCH API-NEXT v1 12/19] test: build all tests with -static

From: Dmitry Eremin-Solenikov Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173

[lng-odp] [PATCH API-NEXT v1 6/19] build: drop platorm/linux-generic/Makefile.inc

From: Dmitry Eremin-Solenikov Mandate that platform provides platform/$(with_platform)/arch/$(ARCH_DIR) directory and reference it directly from all Makefile.am/.inc files. Main reason for this change is to allow automake to process all includes at the time of

[lng-odp] [PATCH API-NEXT v1 8/19] configure: stop setting AM_* variables

From: Dmitry Eremin-Solenikov AM_* variables by design should be set by Makefile.am, not by configure.ac. Use CFLAGS/CXXFLAGS instead. Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer

[lng-odp] [PATCH API-NEXT v1 2/19] travis: drop ubuntu-toolchain-r-test PPA

From: Dmitry Eremin-Solenikov Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173

[lng-odp] [PATCH API-NEXT v1 10/19] helper: test: rework build system

From: Dmitry Eremin-Solenikov - Stop using extra libraries just to create a test executable - Stop using EXTRA_DIST to distribute headers, include them into _SOURCES - Stop using unnecessary dist_ prefixes, sources are distributed automatically

[lng-odp] [PATCH API-NEXT v1 7/19] build: use AM_CPPFLAGS to set include paths, rather than AM_CFLAGS

From: Dmitry Eremin-Solenikov Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov --- /** Email created from pull request 173

[lng-odp] [PATCH API-NEXT v1 4/19] linux-gen: crypto: stop using RAND_pseudo_bytes()

From: Dmitry Eremin-Solenikov RAND_pseudo_bytes() was deprecated in OpenSSL 1.1.0. It is recommended to use RAND_bytes() instead. Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer

[lng-odp] [PATCH API-NEXT v1 5/19] build: drop -Wno-deprecated-declaration

From: Dmitry Eremin-Solenikov We do not use deprecated attribute anymore, thus let's drop the -Wno-deprecated-declaration flag from compiler options. Signed-off-by: Dmitry Eremin-Solenikov Reviewed-by: Bill Fischofer

[lng-odp] [PATCH API-NEXT v1 0/19] merge master to api-next

Almost plain merge + one commit on top. github /** Email created from pull request 173 (muvarov:api-next) ** https://github.com/Linaro/odp/pull/173 ** Patch: https://github.com/Linaro/odp/pull/173.patch ** Base sha:

[lng-odp] [PATCH API-NEXT v1 1/19] linux-gen: socket: don't use odp_packet_l2_offset() in _tx_pkt_to_iovec()

From: Matias Elo A packet may not have valid L2 offset set, so odp_packet_l2_offset() cannot be used when transmitting packets. Signed-off-by: Matias Elo Reviewed-by: Bill Fischofer Signed-off-by: Maxim Uvarov

Re: [lng-odp] Supporting ODP_PKTIO_OP_MT_SAFE

On Mon, Sep 11, 2017 at 12:27 PM, Honnappa Nagarahalli wrote: > On 10 September 2017 at 22:26, Brian Brooks wrote: >> Honnappa, >> >> Could your proposal be simplified to: MT-safe pktio should be >> deprecated because it is not a common

Re: [lng-odp] Supporting ODP_PKTIO_OP_MT_SAFE

On 10 September 2017 at 22:26, Brian Brooks wrote: > Honnappa, > > Could your proposal be simplified to: MT-safe pktio should be > deprecated because it is not a common use case. Applications will > either use MT-unsafe pktio or the MT-safe scheduler. Not sure about

Re: [lng-odp] Supporting ODP_PKTIO_OP_MT_SAFE

On Mon, Sep 11, 2017 at 12:22 PM, Honnappa Nagarahalli wrote: > We can come up with use cases. My question is what do we expect to get > deployed? What is required for quick development might be different > from what is required for deployment. > > With NICs

Re: [lng-odp] Supporting ODP_PKTIO_OP_MT_SAFE

We can come up with use cases. My question is what do we expect to get deployed? What is required for quick development might be different from what is required for deployment. With NICs supporting multiple queues, will we have a case of lesser pkt ins than the number of cores? Thanks, Honnappa

[lng-odp] [PATCH CLOUD-DEV v4 3/3] linux-gen: cleanup internal schedule interface

From: Brian Brooks Signed-off-by: Brian Brooks Reviewed-by: Ola Liljedahl --- /** Email created from pull request 166 (brbrooks:cloud-dev) ** https://github.com/Linaro/odp/pull/166 ** Patch:

[lng-odp] [PATCH CLOUD-DEV v4 2/3] linux-gen: schedule: move schedulers into modules

From: Brian Brooks Signed-off-by: Brian Brooks Reviewed-by: Honnappa Nagarahalli Reviewed-by: Kevin Wang --- /** Email created from pull request 166 (brbrooks:cloud-dev) **

[lng-odp] [PATCH CLOUD-DEV v4 1/3] linux-gen: schedule: add subsystem

From: Brian Brooks Signed-off-by: Brian Brooks Reviewed-by: Honnappa Nagarahalli Reviewed-by: Yi He --- /** Email created from pull request 166 (brbrooks:cloud-dev) **

[lng-odp] [PATCH CLOUD-DEV v4 0/3] Modular Framework: schedulers

github /** Email created from pull request 166 (brbrooks:cloud-dev) ** https://github.com/Linaro/odp/pull/166 ** Patch: https://github.com/Linaro/odp/pull/166.patch ** Base sha: 344fe21a06ef4273f34c4441edd0caef876517d9 ** Merge commit sha:

Re: [lng-odp] [COMPRESSION,RFCv1]

Thanks Barry. Will go through these. Thanks Shally -Original Message- From: Barry Spinney [mailto:spin...@mellanox.com] Sent: 09 September 2017 03:37 To: lng-odp@lists.linaro.org Cc: Bill Fischofer ; Verma, Shally ; Barry Spinney

[lng-odp] [Linaro/odp] 2cb0ed: DEPENDENCIES: document changes in CUnit localizati...

Branch: refs/heads/master Home: https://github.com/Linaro/odp Commit: 2cb0edd5820fc7fc14d6f4018a605873fdf47033 https://github.com/Linaro/odp/commit/2cb0edd5820fc7fc14d6f4018a605873fdf47033 Author: Dmitry Eremin-Solenikov Date: 2017-09-11

Re: [lng-odp] [PATCH API-NEXT v1] RFC api: classification: add random early discard

Bill Fischofer(Bill-Fischofer-Linaro) replied on github web page: include/odp/api/spec/classification.h line 6 @@ -135,6 +135,13 @@ typedef struct odp_cls_capability_t { /** A Boolean to denote support of PMR range */ odp_bool_t pmr_range_supported; + + /** Support for

Re: [lng-odp] [PATCH API-NEXT v1] RFC api: classification: add random early discard

Bill Fischofer(Bill-Fischofer-Linaro) replied on github web page: include/odp/api/spec/classification.h line 22 @@ -206,6 +213,43 @@ typedef struct odp_cls_cos_param { /** Drop policy associated with CoS */ odp_cls_drop_t drop_policy; + + /* Random Early Discard (RED) +

[lng-odp] [PATCH API-NEXT v1 1/1] api: classification: add random early discard

From: Balasubramanian Manoharan Signed-off-by: Balasubramanian Manoharan --- /** Email created from pull request 172 (bala-manoharan:random_early_discard) ** https://github.com/Linaro/odp/pull/172 ** Patch:

[lng-odp] [PATCH API-NEXT v1 0/1] RFC api: classification: add random early discard

Adds random early discard and back pressure feature configurable per CoS Signed-off-by: Balasubramanian Manoharan bala.manoha...@linaro.org github /** Email created from pull request 172 (bala-manoharan:random_early_discard) **

[lng-odp] [PATCH v4 1/1] linux-gen: system: correctly set CPU frequency

From: Kelvin Cheung When CPU frequency info under /sys is available, use the real value instead of default value. Signed-off-by: Kelvin Cheung Signed-off-by: Keguang Zhang --- /** Email created from pull request

[lng-odp] [PATCH v4 0/1] linux-gen: system: correctly set CPU frequency

When CPU frequency info under /sys is available, use the real value instead of default value. Signed-off-by: Kelvin Cheung keguang.zh...@gmail.com Signed-off-by: Keguang Zhang keguang.zh...@spreadtrum.com github /** Email created from pull request 171

Re: [lng-odp] IPsec API finialization

On Mon, Sep 11, 2017 at 1:30 AM, Peltonen, Janne (Nokia - FI/Espoo) wrote: > > Bill Fischofer [mailto:bill.fischo...@linaro.org] wrote: >> On Fri, Sep 8, 2017 at 6:10 AM, Janne Peltonen >> wrote: >> > >> > >> > On Fri, 8 Sep 2017, Nikhil

Re: [lng-odp] Supporting ODP_PKTIO_OP_MT_SAFE

On 11 September 2017 at 12:11, Bogdan Pricope wrote: > Hi, > > There is the case where a a pktio has less pktins than available > cores. It is a valid case? We want to support it? > For example: 4 pktins and 8 cores... or default (socket) pktio with > one pktin/one

Re: [lng-odp] Supporting ODP_PKTIO_OP_MT_SAFE

Hi, There is the case where a a pktio has less pktins than available cores. It is a valid case? We want to support it? For example: 4 pktins and 8 cores... or default (socket) pktio with one pktin/one pktout? Best regards, Bogdan On 11 September 2017 at 11:33, Maxim Uvarov

Re: [lng-odp] Supporting ODP_PKTIO_OP_MT_SAFE

On 11 September 2017 at 06:26, Brian Brooks wrote: > Honnappa, > > Could your proposal be simplified to: MT-safe pktio should be > deprecated because it is not a common use case. Applications will > either use MT-unsafe pktio or the MT-safe scheduler. > > > 1) Polling

[lng-odp] [PATCH API-NEXT v5 2/2] linux-generic: api schedule unlock lock

From: Balasubramanian Manoharan Signed-off-by: Balasubramanian Manoharan --- /** Email created from pull request 160 (bala-manoharan:api_sched_order_lock) ** https://github.com/Linaro/odp/pull/160 ** Patch:

[lng-odp] [PATCH API-NEXT v5 1/2] api: schedule: add schedule order unlock lock api

From: Balasubramanian Manoharan Adds odp_schedule_order_unlock_lock() api. This API combines schedule order unlock and lock into a single api for performance optimization in HW. Signed-off-by: Balasubramanian Manoharan --- /** Email created

[lng-odp] [PATCH API-NEXT v5 0/2] api: add schedule order unlock lock

Adds odp_schedule_order_unlock_lock() api. This API combines schedule order unlock and lock into a single api for HW performance optimisation. github /** Email created from pull request 160 (bala-manoharan:api_sched_order_lock) **

Re: [lng-odp] IPsec API finialization

Bill Fischofer [mailto:bill.fischo...@linaro.org] wrote: > On Fri, Sep 8, 2017 at 6:10 AM, Janne Peltonen > wrote: > > > > > > On Fri, 8 Sep 2017, Nikhil Agarwal wrote: > >> On 7 September 2017 at 14:09, Peltonen, Janne (Nokia - FI/Espoo) > >>

Re: [lng-odp] Compiler Barrier API

On Sun, Sep 10, 2017 at 10:33 PM, Bill Fischofer wrote: > Before we consider adding new synchronization APIs, we need a clearly > defined use case for why a portable application would need this. ODP > implementations may make use of such things based on their knowledge