For the record, I've just patched -current with Brad's flow control diff from
last year and now I'm getting 90Mbps with tcpbench on this card. I'm not sure
if it was that diff or some other one in the last three years, but 800Kbps ->
90Mbps is quite a nice improvement.
Pity I didn't attach ifconfig output in my original e-mail, but here it is
now:
gem0: flags=8863<UP,BROADCAST,NOTRAILERS,RUNNING,SIMPLEX,MULTICAST> mtu 1500
lladdr 00:0d:93:60:bd:36
priority: 0
media: Ethernet autoselect (100baseTX full-duplex,rxpause,txpause)
status: active
inet 192.168.0.3 netmask 0xffffff00 broadcast 192.168.0.255
inet6 fe80::20d:93ff:fe60:bd36%gem0 prefixlen 64 scopeid 0x1
To the best of my knowledge, it didn't show fxpause/txpause before.
--
bk
On Jan 11, 2007, at 9:45 PM, Brian Keefer wrote:
> Has anyone else noticed extremely poor performance with gem(4) devices,
particularly on the Mac Mini G4?
>
> dmesg is below, but the summary is that I have a gem(4), and after finally
being fed up with the poor performance I plugged in an old axe(4) that I had
lying around:
> gem0 at pci2 dev 15 function 0 "Apple Uni-N2 GMAC" rev 0x80: irq 41, address
00:0d:93:60:bd:36
> bmtphy0 at gem0 phy 0: BCM5221 100baseTX PHY, rev. 4
> axe0 at uhub5 port 2 configuration 1 interface 0
> axe0: Linksys USB 2.0 10/100 ethernet controller, rev 2.00/0.01, addr 2,
AX88172, address 00:10:60:25:d0:17
> rlphy0 at axe0 phy 3: RTL8201L 10/100 PHY, rev. 1
>
> Using scp(1) on the local network I was seeing about 100KB/s transfer rates
(according to scp(1)). I was also noticing that large images were taking a
long time to load on the websites I am serving off this machine, even for
machines directly connected to the same 100baseTX switch. I ruled out the
hard drive as the performance problem by doing several scp operations to
/dev/null. The transfer rate was exactly the same. I also noticed that if I
had a long-running scp transfer that responses to keyboard input were
sluggish, both on the directly attached keyboard & mouse, and through ssh
sessions.
>
> So I plugged in the axe(4) and repeated the tests, and I was getting 2MB/s -
4MB/s. Still terrible, but much better than the built-in gem(4). All images
on the website load *immediately* now, very, very noticeably faster than
previous. There is also no sluggishness when the network is busy.
>
> Are there any known problems with gem(4) on Macs, or is this likely a case
of bad hardware? The cable and switch are both fine. I'm using the same
connections with the axe(4) and it's working fine (although at expected USB
speeds).
>
>
> [ using 357352 bytes of bsd ELF symbol table ]
> console out [ATY,RockHopper2_A]console in [keyboard] USB found
> using parent ATY,RockHopper2Paren:: memaddr 98000000 size 8000000, :
consaddr 9c008000, : ioaddr 90020000, size 20000: memtag 8000, iotag 8000:
width 640 linebytes 768 height 480 depth 8
> Copyright (c) 1982, 1986, 1989, 1991, 1993
> The Regents of the University of California. All rights reserved.
> Copyright (c) 1995-2006 OpenBSD. All rights reserved.
http://www.OpenBSD.org
>
> OpenBSD 4.0-stable (GENERIC) #0: Fri Nov 10 15:06:55 PST 2006
> [email protected]:/usr/src/sys/arch/macppc/compile/GENERIC
> real mem = 268435456 (262144K)
> avail mem = 235343872 (229828K)
> using 1254 buffers containing 13418496 bytes (13104K) of memory
> mainbus0 (root): model PowerMac10,1
> cpu0 at mainbus0: 7447A (Revision 0x102): 1416 MHz: 512KB L2 cache
> memc0 at mainbus0: uni-n
> "hw-clock" at memc0 not configured
> ki2c0 at memc0 offset 0xf8001000
> iic0 at ki2c0
> mpcpcibr0 at mainbus0 pci: uni-north, Revision 0xff
> pci0 at mpcpcibr0 bus 0
> pchb0 at pci0 dev 11 function 0 "Apple UniNorth AGP" rev 0x00
> vgafb0 at pci0 dev 16 function 0 "ATI Radeon 9200" rev 0x01, mmio
> wsdisplay0 at vgafb0 mux 1: console (std, vt100 emulation)
> mpcpcibr1 at mainbus0 pci: uni-north, Revision 0x5
> pci1 at mpcpcibr1 bus 0
> pchb1 at pci1 dev 11 function 0 "Apple UniNorth PCI" rev 0x00
> macobio0 at pci1 dev 23 function 0 "Apple Intrepid" rev 0x00
> openpic0 at macobio0 offset 0x40000: version 0x4614
> macgpio0 at macobio0 offset 0x50
> "modem-reset" at macgpio0 offset 0x1d not configured
> "modem-power" at macgpio0 offset 0x1c not configured
> macgpio1 at macgpio0 offset 0x9 irq 47
> "programmer-switch" at macgpio0 offset 0x11 not configured
> "gpio5" at macgpio0 offset 0x6f not configured
> "gpio6" at macgpio0 offset 0x70 not configured
> "extint-gpio15" at macgpio0 offset 0x67 not configured
> "escc-legacy" at macobio0 offset 0x12000 not configured
> zsc0 at macobio0 offset 0x13000: irq 22,23
> zstty0 at zsc0 channel 0
> zstty1 at zsc0 channel 1
> aoa0 at macobio0 offset 0x10000: irq 30,1,2
> audio0 at aoa0
> "timer" at macobio0 offset 0x15000 not configured
> adb0 at macobio0 offset 0x16000 irq 25: via-pmu, 0 targets
> apm0 at adb0: battery flags 0x0, 0% charged
> pi2c0 at adb0
> iic1 at pi2c0
> maxtmp0 at iic1 addr 0xc8: max6642
> ki2c1 at macobio0 offset 0x18000
> iic2 at ki2c1
> wdc0 at macobio0 offset 0x20000 irq 24: DMA
> ohci0 at pci1 dev 24 function 0 "Apple Intrepid USB" rev 0x00: irq 0,
version 1.0, legacy support
> usb0 at ohci0: USB revision 1.0
> uhub0 at usb0
> uhub0: Apple OHCI root hub, rev 1.00/1.00, addr 1
> uhub0: 2 ports with 2 removable, self powered
> ohci1 at pci1 dev 25 function 0 "Apple Intrepid USB" rev 0x00: irq 0,
version 1.0, legacy support
> usb1 at ohci1: USB revision 1.0
> uhub1 at usb1
> uhub1: Apple OHCI root hub, rev 1.00/1.00, addr 1
> uhub1: 2 ports with 2 removable, self powered
> ohci2 at pci1 dev 26 function 0 "Apple Intrepid USB" rev 0x00: irq 29,
version 1.0, legacy support
> usb2 at ohci2: USB revision 1.0
> uhub2 at usb2
> uhub2: Apple OHCI root hub, rev 1.00/1.00, addr 1
> uhub2: 2 ports with 2 removable, self powered
> ohci3 at pci1 dev 27 function 0 "NEC USB" rev 0x43: irq 63, version 1.0
> usb3 at ohci3: USB revision 1.0
> uhub3 at usb3
> uhub3: NEC OHCI root hub, rev 1.00/1.00, addr 1
> uhub3: 3 ports with 3 removable, self powered
> ohci4 at pci1 dev 27 function 1 "NEC USB" rev 0x43: irq 63, version 1.0
> usb4 at ohci4: USB revision 1.0
> uhub4 at usb4
> uhub4: NEC OHCI root hub, rev 1.00/1.00, addr 1
> uhub4: 2 ports with 2 removable, self powered
> ehci0 at pci1 dev 27 function 2 "NEC USB" rev 0x04: irq 63
> usb5 at ehci0: USB revision 2.0
> uhub5 at usb5
> uhub5: NEC EHCI root hub, rev 2.00/1.00, addr 1
> uhub5: 5 ports with 5 removable, self powered
> mpcpcibr2 at mainbus0 pci: uni-north, Revision 0x6
> pci2 at mpcpcibr2 bus 0
> pchb2 at pci2 dev 11 function 0 "Apple UniNorth PCI" rev 0x00
> kauaiata0 at pci2 dev 13 function 0 "Apple Intrepid ATA" rev 0x00
> wdc1 at kauaiata0 irq 39: DMA
> wd0 at wdc1 channel 0 drive 0: <ST9808210A>
> wd0: 16-sector PIO, LBA48, 76319MB, 156301488 sectors
> atapiscsi0 at wdc1 channel 0 drive 1
> scsibus0 at atapiscsi0: 2 targets
> cd0 at scsibus0 targ 0 lun 0: <MATSHITA, CD-RW CW-8123, CAD4> SCSI0 5/cdrom
removable
> wd0(wdc1:0:0): using PIO mode 4, DMA mode 2, Ultra-DMA mode 2
> cd0(wdc1:0:1): using PIO mode 4, DMA mode 2, Ultra-DMA mode 2
> "Apple UniNorth Firewire" rev 0x81 at pci2 dev 14 function 0 not configured
> gem0 at pci2 dev 15 function 0 "Apple Uni-N2 GMAC" rev 0x80: irq 41, address
00:0d:93:60:bd:36
> bmtphy0 at gem0 phy 0: BCM5221 100baseTX PHY, rev. 4
> axe0 at uhub5 port 2 configuration 1 interface 0
> axe0: Linksys USB 2.0 10/100 ethernet controller, rev 2.00/0.01, addr 2,
AX88172, address 00:10:60:25:d0:17
> rlphy0 at axe0 phy 3: RTL8201L 10/100 PHY, rev. 1
> uhidev0 at uhub3 port 1 configuration 1 interface 0
> uhidev0: Tangtop USBPS2, rev 1.10/0.01, addr 2, iclass 3/1
> ukbd0 at uhidev0: 8 modifier keys, 6 key codes
> wskbd0 at ukbd0: console keyboard, using wsdisplay0
> uhidev1 at uhub3 port 1 configuration 1 interface 1
> uhidev1: Tangtop USBPS2, rev 1.10/0.01, addr 2, iclass 3/1
> uhidev1: 3 report ids
> ums0 at uhidev1 reportid 1: 5 buttons and Z dir.
> wsmouse0 at ums0 mux 0
> uhid0 at uhidev1 reportid 2: input=2, output=0, feature=0
> uhid1 at uhidev1 reportid 3: input=1, output=0, feature=0
> bootpath: '/p...@f4000000/at...@d/d...@0/bsd'
> boot device: wd0.
> root on wd0a
> rootdev=0x0 rrootdev=0xb00 rawdev=0xb02
>
> --
> bk
