Thanks for the suggestions! I'll try them and I will report back the results in the next days. Regards Ivan
On 6 February 2017 at 02:04, Zhang, Qi Z <qi.z.zh...@intel.com> wrote: > Hi Ivan: > > I'm looking at this issue, but I can't repeat it on my environment > both with X710x4 and XL710x1 > Not sure if you could try below things to help narrow down this issue. > > 1) move i40e_dev_sync_phy_type call after i40e_set_fc call, to see if > the problem still exist, since without i40e_dev_sync_phy_type, i40e_set_fc is > the first place i40e_aq_get_phy_capabilities get called and we didn't see > this issue before 16.11. > > 2) if above change works, at least we have a work around, if above > still fail, please modify the parameter of i40e_aq_get_phy_capabilities in > i40e_dev_sync_phy_type as below and check result. > - status = i40e_aq_get_phy_capabilities(hw, false, true, &phy_ab, > - NULL); > + status = i40e_aq_get_phy_capabilities(hw, false, false, &phy_ab, > + NULL); > > Thank you! > > Regards > Qi > >> -----Original Message----- >> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ivan Nardi >> Sent: Monday, February 6, 2017 4:19 AM >> To: dev@dpdk.org >> Cc: Olivier MATZ <olivier.m...@6wind.com>; Christos Ricudis >> <ricudis.chris...@gmail.com>; Rowden, Aaron F >> <aaron.f.row...@intel.com>; Zhang, Helin <helin.zh...@intel.com>; Wu, >> Jingjing <jingjing...@intel.com> >> Subject: Re: [dpdk-dev] i40e_aq_get_phy_capabilities() fails when using SFP+ >> with no link >> >> HI >> same issue with 17.02-rc2 >> It seems to me the problem I am facing is similar to the ones reported in >> these mails; if not, I apologize to have used this thread >> >> Ivan >> >> On 5 February 2017 at 16:30, Ivan Nardi <nardi.i...@gmail.com> wrote: >> >> > Hi guys >> > any updates on this issue? > >> > We are facing a very similar problem. >> > We have a server with 4 nics X710 4*10Gbit and the dpdk randomly >> > failed to start with the error: >> > >> > PMD: eth_i40e_dev_init(): FW 4.40 API 1.4 NVM 04.05.03 eetrack >> > 80001cd8 >> > PMD: eth_i40e_dev_init(): Failed to sync phy type: -95 >> > >> > It happens randomly (sometimes it works properly, sometimes not), the >> > "failed" port index is random too and it happens whether the fibers >> > have been connected or not. >> > >> > We are using dpdk 16.11. >> > >> > Any help would be appreciated >> > Thanks in advance >> > >> > Ivan >> > >> > On 18 January 2017 at 11:15, Christos Ricudis >> > <ricudis.chris...@gmail.com> >> > wrote: >> > >> >> Hi, >> >> >> >> > On 12 Jan 2017, at 21:55, Olivier MATZ <olivier.m...@6wind.com> >> wrote: >> >> > >> >> > Hi, >> >> > >> >> > On Wed, 11 Jan 2017 20:51:58 +0000, "Rowden, Aaron F" >> >> > <aaron.f.row...@intel.com> wrote: >> >> >> Hi Helin, >> >> >> >> >> >> I'm checking on this to see why it could be failing but I don’t >> >> >> think this is one part of formal validation. Intel modules are >> >> >> always what is recommended. >> >> >> >> >> >> Aaron >> >> >> >> >> >>> Hi Helin, >> >> >>> >> >> >>>> On 11 Jan 2017, at 09:08, Zhang, Helin <helin.zh...@intel.com> >> >> >>>> wrote: >> >> >>>> >> >> >>>> Hi Aaron >> >> >>>> >> >> >>>> Is the SFP+ (Finisar FTLX8571D3BCL) supported and validated by >> >> >>>> Intel? It seems there is some PHY issue in this case. >> >> >>> >> >> >>> As the original reporter of this issue, I will test with >> >> >>> validated >> >> >>> SFP+s and will report on my testing. >> >> >>> >> >> >>> Shouldn’t unsupported SFP+s be blacklisted in the I40E driver? >> >> >>> >> >> > >> >> > Just to let you know that in my case the SFP are Intel ones. >> >> > Maybe it's a different issue. >> >> > >> >> > I see there are some i40e fixes in the net-next repo, I'll give a >> >> > try with this version. >> >> > >> >> > Regards, >> >> > Olivier >> >> >> >> After further testing, I can confirm that this issue persists with >> >> supported Intel SFPs (Intel FTLX8571D3BCV-IT). >> >> >> >> As for the changeset introducing this issue - we had failure reports >> >> with previous DPDK versions, probably related to LSE handling, but >> >> these weren’t properly investigated. The change in 16.11 which calls >> >> get_phy_capability too early in initialization stage might have >> >> alleviated the issue making it easier for us to detect and confirm. >> >> >> >> Best regards, >> >> Christos Ricudis. >> >> >> >> >> >
