On Jul 28, 2013, at 2:42 PM, Jack Vogel <jfvo...@gmail.com> wrote: > On Sat, Jul 27, 2013 at 9:22 AM, Andre Oppermann <an...@freebsd.org> wrote: > >> On 27.07.2013 10:42, Alexander V. Chernikov wrote: >> >>> On 27.07.2013 12:15, Luigi Rizzo wrote: >>> >>>> On Sat, Jul 27, 2013 at 10:02 AM, Alexander V. Chernikov >>>> <melif...@freebsd.org> wrote: >>>> This makes me curious because i believe people have used netmap with >>>> the 82598 and achieved close to line rate even with 64-byte frames/one >>>> port, >>>> and i thought (maybe I am wrong ?) the various 2-port NICs use 4 lanes >>>> per port. >>>> So the number i remember does not match with your quote of 2.5Gt/s. >>>> Are all 82598 using 2.5GT/s (which is a gen.1 speed) instead of 5 ? >>>> >>>> >> >>> Quoting 82598EB datasheet: >>> The PCIe v2.0 (2.5 GT/s) interface is used by the 82598EB as a host >>> interface. It supports x8, x4, >>> x2 and x1 configurations at a speed of 2.5 GHz. The maximum aggregated >>> raw ban.. >>> >>> Actually I discovered this exactly with netmap and 82598*-DA2 NIC :) >>> >> >> Discussing the 82598 is moot because it has been replaced with the 82599 >> which supports x1-x8 at 5 GT/s. AFAIK you can't event buy the 82598 >> anymore. >> >> > Yes, and the new quad port adapters on PCIE Gen 3 give you 8GT/s bandwidth > for > the device. I'm not sure if you could buy the 82598 but I surely would not > recommend > it to anyone :)
FWIW, sometimes these kinds of cards are interesting if your primary interest is link failover instead of aggregate link speed. If the 82598 generated less heat and/or consumed less power, or was significantly cheaper than more modern offerings, it can still be attractive. Scott _______________________________________________ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to "freebsd-net-unsubscr...@freebsd.org"