On Tue, 2021-08-03 at 13:49 -0700, Jakub Kicinski wrote: > On Tue, 3 Aug 2021 18:36:23 +0200 Alexander Lobakin wrote: > > Most of the driver-side XDP enabled drivers provide some statistics > > on XDP programs runs and different actions taken (number of passes, > > drops, redirects etc.). > > Could you please share the statistics to back that statement up? > Having uAPI for XDP stats is pretty much making the recommendation > that drivers should implement such stats. The recommendation from > Alexei and others back in the day (IIRC) was that XDP programs should > implement stats, not the drivers, to avoid duplication. > There are stats "mainly errors*" that are not even visible or reported to the user prog, for that i had an idea in the past to attach an exception_bpf_prog provided by the user, where driver/stack will report errors to this special exception_prog. > > Regarding that it's almost pretty the same across all the drivers > > (which is obvious), we can implement some sort of "standardized" > > statistics using Ethtool standard stats infra to eliminate a lot > > of code and stringsets duplication, different approaches to count > > these stats and so on. > > I'm not 100% sold on the fact that these should be ethtool stats. > Why not rtnl_fill_statsinfo() stats? Current ethtool std stats are > all pretty Ethernet specific, and all HW stats. Mixing HW and SW > stats > is what we're trying to get away from. > XDP is going to always be eBPF based ! why not just report such stats to a special BPF_MAP ? BPF stack can collect the stats from the driver and report them to this special MAP upon user request. > > These new 12 fields provided by the standard XDP stats should cover > > most, if not all, stats that might be interesting for collecting > > and > > tracking. > > Note that most NIC drivers keep XDP statistics on a per-channel > > basis, so this also introduces a new callback for getting a number > > of channels which a driver will provide stats for. If it's not > > implemented or returns 0, it means stats are global/device-wide. > > Per-channel stats via std ethtool stats are not a good idea. Per > queue > stats must be via the queue netlink interface we keep talking about > for > ever but which doesn't seem to materialize. When stats are reported > via > a different interface than objects they pertain to matching stats, > objects and their lifetime becomes very murky.
