Re: [lng-odp] [PATCH] example: introducing multi-threaded traffic management case

Hi Bala, I think the example is evolved individually, especially we want the simple case in one file only. This case mainly demos how to run multiple background TM threads with traffic management. So if needed, I can only show one user scenario like speed/bandwidth limitation here. thanks,

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

Re: [lng-odp] drv API issue

Hi Christophe, Another issue may relate to driver interface. As you know, there is some soc level initialization specific to some platform before the network driver works. Where do you expect this kind of initialization? at the odp_init or driver_init? For dpaa2, the thread is also needed before

Re: [lng-odp] [PATCH v2] example: introducing multi-threaded traffic management case

Hi Maxim, Thank you. I will fix it in the next version. Forrest On 6 February 2017 at 21:10, Maxim Uvarov wrote: > Hello Xuelin, > > new example also needs 'make check' test. > > please see some comments bellow also. > > On 02/06/17 04:35, forrest@linaro.org

Re: [lng-odp] [API-NEXT PATCHv4 2/5] linux-gen: adding enum, devio and driver registration interface (stub)

I'm a bit curious why not odp_drv_enum? On 19 December 2016 at 14:04, Yi He wrote: > > > On 8 December 2016 at 17:20, Christophe Milard < > christophe.mil...@linaro.org> wrote: > >> The linux implementation for the enumerator class registration function, >> enumerator instance

Re: [lng-odp] [PATCH] example: introducing multi-threaded traffic management case

Hi, this patch is a followup of http://patches.opendataplane.org/patch/7515/ to keep the original traffic management example structure and keep it small, this multi-thread version is going to make a new example. Thanks, Forrest On 19 December 2016 at 14:01, wrote: >

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

Hi Bala, Would you please review this small fix? thanks, Forrest On 9 December 2016 at 20:31, Maxim Uvarov <maxim.uva...@linaro.org> wrote: > Bala, > > please review TM patch. > > Thank you, > Maxim. > > On 12/08/16 04:58, Forrest Shi wrote: > >

Re: [lng-odp] [RFC v2] example: traffic_mgmt: enhancement with multiple pktios

Hi, would you please review this RFC? it addresses the JIRA ticket odp-488. The due date will be the end of this month. thanks, Forrest On 8 December 2016 at 09:59, Forrest Shi <forrest@linaro.org> wrote: > ping > > On 2 December 2016 at 16:29, <forrest@linaro.org

Re: [lng-odp] [RFC v2] example: traffic_mgmt: enhancement with multiple pktios

ping On 2 December 2016 at 16:29, wrote: > From: Xuelin Shi > > This patch made the following changes: > - try to create one tm background thread for each pktio > - receiving packets from multiple pktios other than generating packets > -

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

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 > > Signed-off-by: Xuelin Shi > --- >

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

Hi Bala, I'm testing example/traffic_mgmt with 20Gbps connections, not see any issue here. Thanks, Forrest On 6 December 2016 at 21:43, Bala Manoharan <bala.manoha...@linaro.org> wrote: > On 6 December 2016 at 18:30, Forrest Shi <forrest@linaro.org> wrote: > > Hi B

Re: [lng-odp] cannot create multiple threads for traffic management

Hi Barry, Sorry to call you surname. I have changed the number to 4 cores. Please have a review for http://patches.opendataplane.org/patch/7515/ Thanks, Forrest On 30 November 2016 at 15:47, Forrest Shi <forrest@linaro.org> wrote: > Hi Spinney, > > I noticed you

[lng-odp] cannot create multiple threads for traffic management

Hi Spinney, I noticed you add a tm group to the traffic management and create thread for the group. However, I cannot create multiple tm threads with system less than 24 cores. In this case, multiple tms are attached to the same group and serviced by a single thread. Is it too big? Can I remove

Re: [lng-odp] question on traffic management

ailable a single queue > could transmit packets at the Peak Information Rate (PIR) above the > Committed Information Rate (CIR). Hence this threshold limit is of > importance simply coz this is internally handled by the > implementation. > > > Regards, > Bala > &g

Re: [lng-odp] question on traffic management

fer <bill.fischo...@linaro.org> > wrote: > > This question properly belongs on the ODP mailing list (+cc) > > > > On Wed, Nov 2, 2016 at 4:12 AM, Forrest Shi <forrest@linaro.org> > wrote: > >> > >> Hi, > >> > >> I can see some

Re: [lng-odp] [PATCH v2 3/5] example: l3fwd: make packet error check optional

Hi Matias, see comments inline. thanks, Forrest On 16 September 2016 at 15:13, Matias Elo wrote: > Make packet error check optional as it forces full packet parse. > > Signed-off-by: Matias Elo > --- > example/l3fwd/odp_l3fwd.c | 24

Re: [lng-odp] [PATCH v2 1/5] example: l3fwd: add missing gitignores

Hi Matias, On what condition, *.log and *.trs will be generated? Other examples have no this. Thanks, Forrest On 16 September 2016 at 15:13, Matias Elo wrote: > Signed-off-by: Matias Elo > --- > example/l3fwd/.gitignore | 2 ++ > 1 file changed, 2

Re: [lng-odp] [PATCH 3/3] example/l3fwd: enhance flow lookup performance in hash

The previous version does not include the "hash fixing" patch. sorry to confuse you. On 6 September 2016 at 03:04, Maxim Uvarov wrote: > uh.. some previous version had clang issue and I was sure that it's fixed. > Will send a patch due to it's very trivial. > > Maxim. >

Re: [lng-odp] [PATCH] example/l3fwd: fix clang compiling.

Hi Maxim, Do you mean all the l3fwd related patches, including pending patches waiting for review? like hash performance issue patch? thanks, Forrest On 30 August 2016 at 14:53, Maxim Uvarov wrote: > On 08/30/16 05:56, forrest@linaro.org wrote: > >> From: Xuelin

Re: [lng-odp] [PATCH v2] helper/eth: add mac address to string conversion

Hi, this is the coverage report of call the function by l3fwd. thanks, Forrest On 3 August 2016 at 09:57, Forrest Shi <forrest@linaro.org> wrote: > Hi Maxim & Bala， > > It is a reverse function of the odph_eth_addr_parse(...). > > It could be used by l2fwd-simpl

Re: [lng-odp] [PATCH v2] helper/eth: add mac address to string conversion

Hi Maxim & Bala， It is a reverse function of the odph_eth_addr_parse(...). It could be used by l2fwd-simple, ipsec or other example like l3fwd to avoid duplicate or similar code. thanks, Forrest On 2 August 2016 at 23:50, Maxim Uvarov wrote: > On 08/02/16 18:21,

[lng-odp] about adding termination path for l3fwd

Hi Mike, Why the cases under test/ are added termination path? I'm wondering if it is needed in l3fwd. Maxim is talking if l3fwd should be under test/ not example/, what's your thought? Before sending new version, I want to include this change. thanks, Forrest

Re: [lng-odp] [PATCH/API-NEXT 1/3] helper/ip: fix ip parsing endian issue

Hi Maxim, Let's see if any comments first, then I will send it to master again. Thanks, Forrest On 11 July 2016 at 21:08, Maxim Uvarov wrote: > Ping. Review is needed. > > This patch series has to be for master branch. Especially this bug fix > patch. > > Maxim. > > >