Re: [lng-odp] memory allocation issues

Thanks, Steve. THP is not really what we want. It could create jitter among the ODP threads which we don't really want. Your answer is quite clear. I could definitively talk to you as to grab some of your knowledge, but I actually think your answer both shows that you understood my problem and

Re: [lng-odp] [PATCH v3 0/4] remove Linux specifics and dependence on test dir

For the series: Reviewed-by: Christophe Milard On 18 January 2017 at 23:01, Mike Holmes wrote: > Starting with some clean up, rename the Linux specific files and then move > them > to a platform specific directory. A new configure option

[lng-odp] [Bug 2833] dead lock in ODP-crypto on some machine

https://bugs.linaro.org/show_bug.cgi?id=2833 --- Comment #5 from Christophe Milard --- Immediately. But no clue why. Never saw it on other machines (64 bits host or VM) -- You are receiving this mail because: You are on the CC list for the bug.

[lng-odp] [API-NEXT PATCH 4/4] doc: userguide: add odp_timer_capability() section to user guide

Signed-off-by: Kevin Wang --- doc/users-guide/users-guide-timer.adoc | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/doc/users-guide/users-guide-timer.adoc b/doc/users-guide/users-guide-timer.adoc index 9cd30de..ccca7d4 100644 ---

[lng-odp] [API-NEXT PATCH 3/4] validation/example: call odp_timer_capability() before creating a timer pool

Use odp_timer_capability() to determine the max timer resolution Signed-off-by: Kevin Wang --- example/generator/odp_generator.c | 8 +++- example/timer/odp_timer_simple.c | 9 - example/timer/odp_timer_test.c| 6

[lng-odp] [API-NEXT PATCH 1/4] api: timer: add odp_timer_capability() api

Currently, user needs to decide the timer resolution before creating a timer pool. But sometimes it will cause timer overrun as the system can't support such high resolution. So a new API is required to expose the timer capability to the user. Signed-off-by: Kevin Wang ---

[lng-odp] [API-NEXT PATCH 2/4] linux-generic: timer: implement odp_timer_capability()

Implement a new internal function timer_res_init() to detect the max timer resolution without overrun at the ODP init stage. It will check timer resolution from 1ms to 100us, 10us...1ns until the timer is overrun. Signed-off-by: Kevin Wang ---

Re: [lng-odp] [API-NEXT PATCHv10 1/5] drv: adding driver registration interface (stub)

For this series, I've compared with v9 and the changes look good to me, and make check and doxygen-run. Reviewed-and-tested-by: Yi He On 20 January 2017 at 00:54, Christophe Milard wrote: > The enumerator class, enumerator instance, devio and

Re: [lng-odp] [PATCH 1/2] api: New API to support timer capacity

This looks good, however it should be against api-next. Use git format-patch origin/api-next --subject-prefix="API-NEXT PATCH" Also, part 2 should not have the same commit short log. Part 1 is fine, though by convention ODP uses all lower case in short logs so it should be "api: timer: add

Re: [lng-odp] [PATCH] linux-gen: align: round up power of two as macro

On Thu, Jan 19, 2017 at 9:28 AM, Petri Savolainen wrote: > Implement round up to power of two as a macro. Macro > enables preprocessor to calculate the constant value and > avoid code generation. Also dependency to __builtin_clz() > is not needed anymore. > >

[lng-odp] [Bug 2833] dead lock in ODP-crypto on some machine

https://bugs.linaro.org/show_bug.cgi?id=2833 Bill Fischofer changed: What|Removed |Added Assignee|nikhil.agar...@linaro.org

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

This series represents a significant structural change and as such should go against api-next, not master. Patches aimed at master should be bug fixes, not something that introduces new structure development. While the goals here seem good, I'm concerned that at this stage applying this removes

Re: [lng-odp] 32-bit support in examples

On Thu, Jan 19, 2017 at 7:23 AM, Joe Savage wrote: > Hey, > > I'm just finalising a patch to add a lock-free IPv4 fragmentation and > reassembly example to ODP, and it has occurred to me that as the whole > examples directory is compiled with odp-linux by default, I ought to

Re: [lng-odp] [PATCH v3 4/4] helper: remove dependence on test dir

On 19 January 2017 at 12:19, Maxim Uvarov wrote: > On 01/19/17 19:01, Mike Holmes wrote: >> On 19 January 2017 at 09:45, Maxim Uvarov wrote: >>> On 01/19/17 01:01, Mike Holmes wrote: There is no reason that the helpers need to depend on the

Re: [lng-odp] [PATCH v3 4/4] helper: remove dependence on test dir

On 01/19/17 19:01, Mike Holmes wrote: > On 19 January 2017 at 09:45, Maxim Uvarov wrote: >> On 01/19/17 01:01, Mike Holmes wrote: >>> There is no reason that the helpers need to depend on the test directory >>> so remove the offending links >>> >>> Signed-off-by: Mike

Re: [lng-odp] Scheduling packets from control threads

On Thu, Jan 19, 2017 at 10:03 AM, Stanislaw Kardach wrote: > > > Best Regards, > Stanislaw Kardach > > > On 01/19/2017 04:57 PM, Bill Fischofer wrote: >> >> On Thu, Jan 19, 2017 at 7:17 AM, Stanislaw Kardach >> wrote: >>> >>> Hi all, >>> >>> While going

Re: [lng-odp] ODP installation issues on Cavium ThunderX

Hi, ODP Cavium implementation has not been publicly released. Regards, Bala On 19 January 2017 at 22:23, Mike Holmes wrote: > > > On 19 January 2017 at 11:43, Gyanesh Patra > wrote: > >> There is no link available for the "Cavium

Re: [lng-odp] ODP installation issues on Cavium ThunderX

On 19 January 2017 at 11:43, Gyanesh Patra wrote: > There is no link available for the "Cavium implementation" by Support > Account on the ODP download page. How can i have access to the code and > also corresponding toolchain if needed? > You need to talk to your

Re: [lng-odp] ODP installation issues on Cavium ThunderX

There is no link available for the "Cavium implementation" by Support Account on the ODP download page. How can i have access to the code and also corresponding toolchain if needed? P Gyanesh Patra On Thu, 19 Jan 2017 at 14:33 Mike Holmes < mailto:Mike Holmes > wrote:

Re: [lng-odp] ODP installation issues on Cavium ThunderX

On 19 January 2017 at 11:17, Gyanesh Patra wrote: > Hi, > > I tried to follow the instruction from OpenFastPath readme file as below: > >>> ./bootstrap > > > >>> ./configure --host=aarch64-thunderx-linux-gnu \ > > --with-platform=linux-thunder \ > >

Re: [lng-odp] memory allocation issues

Maybe the LNG Kernel team need to pick this up as a topic ? On 19 January 2017 at 11:18, Steve Capper wrote: > On 19 January 2017 at 13:04, Christophe Milard > wrote: >> Hi Steve, > > Hey Christophe, > >> >> Maybe you remember me as we have

Re: [lng-odp] memory allocation issues

On 19 January 2017 at 13:04, Christophe Milard wrote: > Hi Steve, Hey Christophe, > > Maybe you remember me as we have had contact before. Christophe. from > the LNG ODP team (mikes Holmes team). > > I have written the ODP memory allocator and I am having an issue

[lng-odp] [PATCHv2] travis: better comments to generate token in the travis file

Signed-off-by: Christophe Milard --- .travis.yml | 12 1 file changed, 12 insertions(+) diff --git a/.travis.yml b/.travis.yml index 03e61b1..cfa6c3d 100644 --- a/.travis.yml +++ b/.travis.yml @@ -11,6 +11,18 @@ env: global: #

[lng-odp] ODP installation issues on Cavium ThunderX

Hi, I tried to follow the instruction from OpenFastPath readme file as below: >>  ./bootstrap   >> ./configure --host=aarch64-thunderx-linux-gnu \   --with-platform=linux-thunder \   --with-openssl-path=${OPENSSL_DIR} \   --enable-debug-print \   --enable-debug \   --prefix=${ODP_DIR} \

Re: [lng-odp] 32-bit support in examples

On 19 January 2017 at 09:37, Joe Savage wrote: >> Is it a true very direct example of the concept, or more of a mini >> application ? >> >> We are trying to lift out of examples those things that are more >> complex mini apps to a new apps directory. >> One distinction is the

Re: [lng-odp] Scheduling packets from control threads

Best Regards, Stanislaw Kardach On 01/19/2017 04:57 PM, Bill Fischofer wrote: On Thu, Jan 19, 2017 at 7:17 AM, Stanislaw Kardach wrote: Hi all, While going through thread and scheduler APIs I've stumbled on one uncertainty in ODP API that I could not find straight

Re: [lng-odp] [PATCH v3 4/4] helper: remove dependence on test dir

On 19 January 2017 at 09:45, Maxim Uvarov wrote: > On 01/19/17 01:01, Mike Holmes wrote: >> There is no reason that the helpers need to depend on the test directory >> so remove the offending links >> >> Signed-off-by: Mike Holmes >> --- >>

Re: [lng-odp] Scheduling packets from control threads

On Thu, Jan 19, 2017 at 7:17 AM, Stanislaw Kardach wrote: > Hi all, > > While going through thread and scheduler APIs I've stumbled on one > uncertainty in ODP API that I could not find straight solution to. > > Does ODP allow scheduling packets from an ODP_THREAD_CONTROL

[lng-odp] [API-NEXT PATCHv10 5/5] linux-gen: modules: adding initial file to load modules

The shared objects listed in the ODP configuration files are loaded at init time. The odp configuration file lists the shared objects to be loaded as shown in the following example: module = { modules = ["enumerator1.so", "driver1.so"]; }; Signed-off-by: Christophe Milard

[lng-odp] [API-NEXT PATCHv10 4/5] test: preventing odp.conf loading for tests

The tests should not be affected by any system or user ODP configuration file. The ODP_SYSCONFIG_FILE environment variables is therefore set to "none" in TESTS_ENVIRONMENT. Tests which need specific a configuration file will have to overwrite this setting. Note that tests ran manually (not using

[lng-odp] [API-NEXT PATCHv10 3/5] linux-gen: init: adding configuration file parsing

The parsing of the odp.conf configuration file is added. The file is searched first in filename specified in the environment variable $ODP_SYSCONFIG_FILE (where the special string "none" prevent any file loading) The file is then searched in the user home directory (~) and then is the $prefix/etc

[lng-odp] [API-NEXT PATCHv10 2/5] linux-gen: adding enum, devio and driver registration interface (stub)

The linux implementation for the enumerator class registration function, enumerator instance registration function, devio and driver registration functions (stub) Signed-off-by: Christophe Milard --- include/odp_drv.h | 1 +

[lng-odp] [API-NEXT PATCHv10 1/5] drv: adding driver registration interface (stub)

The enumerator class, enumerator instance, devio and driver registration functions prototypes (and a draft of their parameters) are defined, the goal being to define the registration framework only. Signed-off-by: Christophe Milard --- include/odp/drv/spec/driver.h

[lng-odp] [API-NEXT PATCHv10 0/5] driver initialisation framework

Since V9: -driver interface reworked to be more consistent with the mem allocator which is now merged. (more handle based) -rebased Since V8: -fixed corrupt V8 -copyright updates: 2017 (BTW: Happy new year) Since V7: -changed include order in drv_driver.c (Anders) -correction of package

Re: [lng-odp] [PATCH] test: perf: add new packet function microbenchmark application

On 01/14/17 19:20, Bill Fischofer wrote: > --- a/test/common_plat/performance/Makefile.am >> +++ b/test/common_plat/performance/Makefile.am >> @@ -2,9 +2,12 @@ include $(top_srcdir)/test/Makefile.inc >> >> TESTS_ENVIRONMENT += TEST_DIR=${builddir} >> >> -EXECUTABLES = odp_crypto$(EXEEXT)

Re: [lng-odp] [PATCH] linux-gen: align: round up power of two as macro

 /**   * @internal - * When 'x' is not already a power of two, round it up to the next - * power of two value. Zero is not supported as an input value. - */ -#define ODP_ROUNDUP_POWER_2(x)\ -       (1 << (((int)(8 * sizeof(x))) - __builtin_clz((x) - 1))) + * Round up a uint32_t value 'x' to the

Re: [lng-odp] [API-NEXT PATCH] linux-gen: align: fix round up power of two

Hi, OK, didn't notice those other clz builtins. Anyway, I decided to write a macro instead since it was not too convenient to combine 'unsigned int' and 'long long' builtins. Also macro allows more optimal code since preprocessor calculate the constant value only once (instead of generating

[lng-odp] [PATCH] linux-gen: align: round up power of two as macro

Implement round up to power of two as a macro. Macro enables preprocessor to calculate the constant value and avoid code generation. Also dependency to __builtin_clz() is not needed anymore. Signed-off-by: Petri Savolainen ---

[lng-odp] [Bug 2428] validation timer_main fails process mode

https://bugs.linaro.org/show_bug.cgi?id=2428 Mike Holmes changed: What|Removed |Added Assignee|rizwan.ans...@linaro.org|lng-odp@lists.linaro.org

[lng-odp] [Bug 2798] ODP random and other crypto functions (possibly) not thread safe?

https://bugs.linaro.org/show_bug.cgi?id=2798 Mike Holmes changed: What|Removed |Added Status|IN_PROGRESS |RESOLVED

Re: [lng-odp] [PATCH] travis: better comments to generate token in the travis file

Easier way exists. This patch should be dropped. On 18 January 2017 at 13:34, Christophe Milard wrote: > On 18 January 2017 at 13:26, Maxim Uvarov wrote: >> On 01/18/17 16:14, Christophe Milard wrote: >>> Signed-off-by: Christophe Milard

[lng-odp] [Bug 2829] CID 168965: Unused value in helper iptablelookup

https://bugs.linaro.org/show_bug.cgi?id=2829 Mike Holmes changed: What|Removed |Added Assignee|maxim.uva...@linaro.org |lng-odp@lists.linaro.org

Re: [lng-odp] [PATCH v3 4/4] helper: remove dependence on test dir

On 01/19/17 01:01, Mike Holmes wrote: > There is no reason that the helpers need to depend on the test directory > so remove the offending links > > Signed-off-by: Mike Holmes > --- > helper/test/Makefile.am | 26 --- > helper/test/chksum.c

[lng-odp] [Bug 2830] CID 168956: Storage leak in cuckoo.c

https://bugs.linaro.org/show_bug.cgi?id=2830 Mike Holmes changed: What|Removed |Added Component|General ODP |Helpers

[lng-odp] [Bug 2833] dead lock in ODP-crypto on some machine

https://bugs.linaro.org/show_bug.cgi?id=2833 Mike Holmes changed: What|Removed |Added CC||mike.hol...@linaro.org

[lng-odp] [Bug 2834] race condition in _ishm_reserve

https://bugs.linaro.org/show_bug.cgi?id=2834 Mike Holmes changed: What|Removed |Added CC||mike.hol...@linaro.org

Re: [lng-odp] [PATCH v3 1/4] configure: use helper configure.m4

On 01/19/17 01:01, Mike Holmes wrote: > Don't keep helper data in the main configure, split it to an m4 just > like the other sub dirs > > Signed-off-by: Mike Holmes > --- > configure.ac | 2 -- > helper/m4/configure.m4 | 3 +++ > 2 files changed, 3

Re: [lng-odp] 32-bit support in examples

> Is it a true very direct example of the concept, or more of a mini > application ? > > We are trying to lift out of examples those things that are more > complex mini apps to a new apps directory. > One distinction is the requirement to use external traffic generation > for example would likely

[lng-odp] [PATCH] example: hello: ask odp for available core

Core 0 might be not available and app should ask for available core before pinning to it. https://bugs.linaro.org/show_bug.cgi?id=2806 Signed-off-by: Maxim Uvarov --- example/hello/odp_hello.c | 15 ++- 1 file changed, 10 insertions(+), 5 deletions(-) diff

[lng-odp] [Bug 2833] dead lock in ODP-crypto on some machine

https://bugs.linaro.org/show_bug.cgi?id=2833 Bill Fischofer changed: What|Removed |Added CC|

Re: [lng-odp] 32-bit support in examples

Joe, Is it a true very direct example of the concept, or more of a mini application ? We are trying to lift out of examples those things that are more complex mini apps to a new apps directory. One distinction is the requirement to use external traffic generation for example would likely make it

[lng-odp] v1.13.0.0 was tagged

v1.13.0.0 was tagged. Changes were updated in corresponding commit. Best regards, Maxim. Forwarded Message Subject: [lng-odp] [NEXT PATCHv2] changelog: summary of changes for odp v1.13.0.0 Date: Fri, 13 Jan 2017 10:14:04 -0600 From: Bill Fischofer

[lng-odp] [API-NEXT PATCH] linux-gen: _ishm: fix normal page fallback

Fixing failure due to lack of huge pages. Signed-off-by: Christophe Milard --- platform/linux-generic/_ishm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/platform/linux-generic/_ishm.c b/platform/linux-generic/_ishm.c index

Re: [lng-odp] 32-bit support in examples

On 01/19/17 16:23, Joe Savage wrote: > Hey, > > I'm just finalising a patch to add a lock-free IPv4 fragmentation and > reassembly example to ODP, and it has occurred to me that as the whole > examples directory is compiled with odp-linux by default, I ought to be > careful about supporting a

[lng-odp] [Bug 2833] dead lock in ODP-crypto on some machine

https://bugs.linaro.org/show_bug.cgi?id=2833 --- Comment #2 from Christophe Milard --- b7da911 -- You are receiving this mail because: You are on the CC list for the bug.

[lng-odp] 32-bit support in examples

Hey, I'm just finalising a patch to add a lock-free IPv4 fragmentation and reassembly example to ODP, and it has occurred to me that as the whole examples directory is compiled with odp-linux by default, I ought to be careful about supporting a wide variety of platforms (ensuring that my change

[lng-odp] [Bug 2834] New: race condition in _ishm_reserve

https://bugs.linaro.org/show_bug.cgi?id=2834 Bug ID: 2834 Summary: race condition in _ishm_reserve Product: OpenDataPlane - linux- generic reference Version: unspecified Hardware: Other OS: Linux Status:

[lng-odp] Scheduling packets from control threads

Hi all, While going through thread and scheduler APIs I've stumbled on one uncertainty in ODP API that I could not find straight solution to. Does ODP allow scheduling packets from an ODP_THREAD_CONTROL thread? If yes then what would be the difference between ODP_THREAD_CONTROL and

[lng-odp] [Bug 2833] dead lock in ODP-crypto on some machine

https://bugs.linaro.org/show_bug.cgi?id=2833 Maxim Uvarov changed: What|Removed |Added CC|

[lng-odp] [Bug 2833] New: dead lock in ODP-crypto on some machine

https://bugs.linaro.org/show_bug.cgi?id=2833 Bug ID: 2833 Summary: dead lock in ODP-crypto on some machine Product: OpenDataPlane - linux- generic reference Version: unspecified Hardware: Other OS: Linux Status:

[lng-odp] memory allocation issues

Hi Steve, Maybe you remember me as we have had contact before. Christophe. from the LNG ODP team (mikes Holmes team). I have written the ODP memory allocator and I am having an issue with it: It has a requirement that linux processes (we call them ODP threads) have to be able to share memory

Re: [lng-odp] Platform parameters in odp_init_global

Thank you. I was asking to get a grip on how a platform should behave. I'll prepare an RFC with code examples and meanwhile I'll just stick to getenv(). Best Regards, Stanislaw Kardach On 01/17/2017 04:25 PM, Maxim Uvarov wrote: We discussed that question on yesterday meeting call. And

Re: [lng-odp] [API-NEXT PATCH] linux-gen: align: fix round up power of two

Hi, Petri As replied in bug tracking, just worried uint64_t need to use __builtin_clzl() or __builtin_clzll() the __builtin_clz()'s parameter is unsigned int, if mixed uint64_t with __builtin_clz() it may result quite large value. But tested on my development machine (Intel i7) did not show

[lng-odp] [Bug 2828] CID 174662: Bad sizeof() in odp_schedule_sp.c

https://bugs.linaro.org/show_bug.cgi?id=2828 --- Comment #5 from Yi He --- Hi, Petri Since the algorithm is: 1 << total bits - leading zero bits(x - 1) __builtin_clz's parameter is (unsigned int), so the total bit number need to be calculated as 4 * sizeof(unsigned int)

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

Thanks, I resent all of them and can see those on the list now. I don't know what happened. Sometimes a mail server has replied on some patches that "cannot be delivered". But this is the first time that a patch was silently dropped. -Petri > -Original Message- > From: Mike Holmes

[lng-odp] [PATCH 7/8] abi: queue: added initial definitions

Initially, use the same default ABI file for all architectures. Default values match those defined in odp-linux implementation to minimize changes in this phase. Removed an unused type definition, documentation of that need to be still removed for API spec. Moved a TM specific define into TM

[lng-odp] [PATCH 1/8] abi: event: added the first ABI spec file

Used event API as the first example of an ABI spec file. Used the same default architecture file initially for all architectures. Default ABI files avoid multiple copies of the same definition. Signed-off-by: Petri Savolainen --- configure.ac

[lng-odp] [PATCH 3/8] abi: classifier: added initial definitions

Initially, use the same default ABI file for all architectures. Default values match those defined in odp-linux implementation to minimize changes in this phase. Removed unused type definitions, documentation of those need to be still removed for API spec. Signed-off-by: Petri Savolainen

[lng-odp] [PATCH 6/8] abi: pool: added initial definitions

Initially, use the same default ABI file for all architectures. Default values match those defined in odp-linux implementation to minimize changes in this phase. Signed-off-by: Petri Savolainen --- example/timer/odp_timer_test.c | 2 +-

[lng-odp] [PATCH 5/8] abi: packet: added initial definitions

Initially, use the same default ABI file for all architectures. Default values match those defined in odp-linux implementation to minimize changes in this phase. Signed-off-by: Petri Savolainen --- include/odp/arch/arm32-linux/odp/api/abi/packet.h | 7

[lng-odp] [PATCH 8/8] abi: shm: added initial definitions

Initially, use the same default ABI file for all architectures. Default values match those defined in odp-linux implementation to minimize changes in this phase. Signed-off-by: Petri Savolainen --- .../arch/arm32-linux/odp/api/abi/shared_memory.h | 7 +

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

Added initial version of couple of ABI specification files. These files define types/values that are implementation specific in the API spec. For ABI compatibility, application and implementation need to use these definitions (based on the target architecture). ABI is defined by CPU ISA

[lng-odp] [PATCH 4/8] abi: crypto: added initial definitions

Initially, use the same default ABI file for all architectures. Default values match those defined in odp-linux implementation to minimize changes in this phase. Signed-off-by: Petri Savolainen --- include/odp/arch/arm32-linux/odp/api/abi/crypto.h | 7 +

[lng-odp] [PATCH 2/8] abi: buffer: added initial definitions

Initially, use the same default ABI file for all architectures. Default values match those defined in odp-linux implementation to minimize changes in this phase. Signed-off-by: Petri Savolainen --- include/odp/arch/arm32-linux/odp/api/abi/buffer.h | 7 +

Re: [lng-odp] [API-NEXT PATCH] linux-gen: align: fix round up power of two

This is not correct. With e.g. uint64_t x = 1; __builtin_clz(x) == 63 and 8*sizeof(unsigned int) == 32, the shift value would negative. Sizeof is there to calculate bits of the variable that deliver x. You cannot fix it to 'unsigned int' without fixing the variable size seen by

[lng-odp] [Bug 2828] CID 174662: Bad sizeof() in odp_schedule_sp.c

https://bugs.linaro.org/show_bug.cgi?id=2828 Petri Savolainen changed: What|Removed |Added CC|