Hello David, Answers inline.
Regards Sunil Kumar Kori >-----Original Message----- >From: David Marchand <david.march...@redhat.com> >Sent: Friday, April 17, 2020 2:14 PM >To: Sunil Kumar Kori <sk...@marvell.com> >Cc: Stephen Hemminger <step...@networkplumber.org>; Jerin Jacob >Kollanukkaran <jer...@marvell.com>; dev <dev@dpdk.org> >Subject: [EXT] Re: [PATCH v2 1/1] bus/pci: optimise scanning with >whitelist/blacklist > >External Email > >---------------------------------------------------------------------- >On Tue, Apr 7, 2020 at 11:29 AM Sunil Kumar Kori <sk...@marvell.com> >wrote: >> >> rte_bus_scan API scans all the available PCI devices irrespective of >> white or black listing parameters then further devices are probed >> based on white or black listing parameters. So unnecessary CPU cycles >> are wasted during rte_pci_scan. >> >> For Octeontx2 platform with core frequency 2.4 Ghz, rte_bus_scan >> consumes around 26ms to scan around 90 PCI devices but all may not be >> used by the application. So for the application which uses 2 NICs, >> rte_bus_scan consumes few microseconds and rest time is saved with this >patch. >> >> Patch restricts devices to be scanned as per below mentioned conditions: >> - All devices will be scanned if no parameters are passed. >> - Only white listed devices will be scanned if white list is available. >> - All devices, except black listed, will be scanned if black list is >> available. >> >> Signed-off-by: Sunil Kumar Kori <sk...@marvell.com> >> --- >> v2: >> - Added function to validate ignorance of device based on PCI address. > >First you objected to Stephen comment, and later announced there was no >objection. Please refer: https://patches.dpdk.org/patch/63924/. In first reply to Stephen's comment, Itself I said that I agree with that approach and why I have not taken that path is also mentioned, and requested for suggestions. But there were no further inputs after asking multiple times then I thought no one has any concern and then I asked to get it merged for 20.05. > >Now, it seems you ignored what I replied without any explanation. >So tell me, what was wrong with >https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_david- >2Dmarchand_dpdk_commit_e7860231ecdce91f9f70027d4090a7057b8fd5f7& >d=DwIFaQ&c=nKjWec2b6R0mOyPaz7xtfQ&r=dXeXaAMkP5COgn1zxHMyaF1_d >9IIuq6vHQO6NrIPjaE&m=3nE0hIIwz2cXBpYrewLujeRWz5WPE7LB9j_HvOtBd68 >&s=OjPCDnof_PNgATyzPIbjG8EtSYa5fE4EwbLD0oaIw5w&e= No, Neither I have ignored your code changes nor denied. Both submitted patches uses similar approaches having one difference only that is you modified existing functions and I have written the new without touching the existing one. I have already explained in v1 that why I have not taken that path what you have implemented. Also I thought, its not good to change pci_ignore_device and pci_devargs_lookup because in future if more parameters (part of rte_pci_device structure) are considered to ignore a device then again we have to change this function to support it. It may be a rare case but it was one thought process. >? > > >> - Marked device validation function as experimental. > >Useless, this symbol is internal and not exported. > > >-- >David Marchand
