CC main odp list. Email was sent to wrong list. Maxim.
On 27 June 2017 at 21:26, Liron Himi <lir...@marvell.com> wrote: > Hi, > > Yes, I use HW counters. > I think that the attached patch will clarify the problem. > The patch is on top of ODP version 1.15.0 > > Regards, > Liron > > > -----Original Message----- > From: lng-check-odp [mailto:lng-check-odp-boun...@lists.linaro.org] On > Behalf Of Maxim Uvarov > Sent: Tuesday, June 27, 2017 17:48 > To: lng-check-...@lists.linaro.org > Subject: [EXT] Re: [lng-check-odp] PKTIO statistics validation test > > External Email > > ---------------------------------------------------------------------- > On 06/27/17 16:42, Liron Himi wrote: > > Hi, > > > > > > > > I’m running ‘pktio_test_statistics_counters’ and it failed on > > ‘in_octets’ check. > > > > The root cause for the failure related to the FCS bytes. > > > > My counter adds those bytes whereas the validation test check for the > > original packet length. > > > > According to the API those counters should count the whole packet > > length including FCS. > > > > Maybe I’m missing something here, but either: > > > > 1. The transmit packet length is already with FCS, but I didn’t > > see in the code where the FCS is calculated. > > > > 2. The transmit packet length is without FCS and the check on > > receive should add FCS in order to compare it to in_octets. > > > > > > > > Please advise what is the correct situation here. > > > > > Hello Liron, > > when we implemented this API we tried to be as match close to RFC: > > typedef struct odp_pktio_stats_t { > /** > * The number of octets in valid MAC frames received on this > interface, > * including the MAC header and FCS. See ifHCInOctets counter > * description in RFC 3635 for details. > */ > uint64_t in_octets; > > Ideally you should use hardware counters. And and your hardware ta kes > care about FCS, which obviously should match on rx and tx. > > As I know AFPACKET does not calculated FCS and it's done on nic level. > For some synthetic pktio like loop there is no FCS. Can you please point > to place which fails for you? I think I'm not completely understand your > problem. > > Thank you, > Maxim. > > > > > > Liron > > > > > > > > > > > > > > > > _______________________________________________ > > lng-check-odp mailing list > > lng-check-...@lists.linaro.org > > https://lists.linaro.org/mailman/listinfo/lng-check-odp > > > > _______________________________________________ > lng-check-odp mailing list > lng-check-...@lists.linaro.org > https://lists.linaro.org/mailman/listinfo/lng-check-odp >