Date: Fri, 12 Jul 1996 19:10:46 +0300 (EET DST) From: "Bror 'Count' Heinola" <count@key.hole.fi> To: freebsd-hardware@freebsd.org Subject: 100M ethernet, weird problem Message-ID: <199607121610.TAA02055@key.hole.fi>
next in thread | raw e-mail | index | archive | help
I built a P166 machine with FreeBSD 2.1.5-GAMMA today, and installed
a AT-2560TX 10/100M ethernet card into it, just to see if it would
work at all. The card is Intel based and gets recongnized as
fxp0 <Intel EtherExpress Pro/100B Fast Ethernet> rev 1 int a irq 11 on pci0:11
It works in both 10M and 100M modes, though I didn't test it at 10M
more than booted up, pinged a few hosts and rebooted, just because
I have hordes of nice 10M cards which do work and my goals are
a bit higher than that.
Basically, the problem is of throughput. I can send stuff to the
machine over three times faster than I can receive from it!
If I do a 'time ping -f -s 1024 -c 100000 thrush' I get something
like 1.6M/second but on the other way I get over 5M/sec. The
machine thrush is a SUN Ultra 1 which is quite capable of going
even faster.
Any ideas? I'll include dmesg info, kernel config etc. below.
FreeBSD 2.1.5-GAMMA #0: Fri Jul 12 14:56:52 EET DST 1996
count@lark2.sms.fi:/usr/src/sys/compile/LARK2
CPU: 166-MHz Pentium 735\\90 or 815\\100 (Pentium-class CPU)
Origin = "GenuineIntel" Id = 0x52c Stepping=12
Features=0x1bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8>
real memory = 67108864 (65536K bytes)
avail memory = 64204800 (62700K bytes)
Probing for devices on PCI bus 0:
chip0 <Intel 82439> rev 1 on pci0:0
chip1 <Intel 82371 PCI-ISA bridge> rev 0 on pci0:7:0
chip2 <Intel 82371 Bus-Master IDE controller> rev 0 on pci0:7:1
pci0:7:2: Intel Corporation, device=0x7020, class=0x0c, subclass=0x03 int d irq 9 [no driver assigned]
vga0 <VGA-compatible display device> rev 0 int a irq 9 on pci0:9
chip3 <DEC 21050 PCI-PCI bridge> rev 2 on pci0:10
fxp0 <Intel EtherExpress Pro/100B Fast Ethernet> rev 1 int a irq 11 on pci0:11
fxp0: Ethernet address 00:a0:c9:05:e9:77
Probing for devices on PCI bus 1:
ahc0 <Adaptec 3940 SCSI host adapter> rev 3 int a irq 12 on pci1:4
ahc0: aic7870 Channel A, SCSI Id=7, 16 SCBs
ahc0: target 0 Tagged Queuing Device
(ahc0:0:0): "SEAGATE ST51080N 0943" type 0 fixed SCSI 2
sd0(ahc0:0:0): Direct-Access 1030MB (2109840 512 byte sectors)
ahc0: target 1 Tagged Queuing Device
(ahc0:1:0): "HP C3725S 6039" type 0 fixed SCSI 2
sd1(ahc0:1:0): Direct-Access 2047MB (4194058 512 byte sectors)
ahc0: target 2 Tagged Queuing Device
(ahc0:2:0): "HP C3725S 6039" type 0 fixed SCSI 2
sd2(ahc0:2:0): Direct-Access 2047MB (4194058 512 byte sectors)
ahc1 <Adaptec 3940 SCSI host adapter> rev 3 int a irq 9 on pci1:5
ahc1: aic7870 Channel B, SCSI Id=7, 16 SCBs
ahc1: target 0 Tagged Queuing Device
(ahc1:0:0): "HP C3725S 6039" type 0 fixed SCSI 2
sd3(ahc1:0:0): Direct-Access 2047MB (4194058 512 byte sectors)
ahc1: target 1 Tagged Queuing Device
(ahc1:1:0): "HP C3725S 6039" type 0 fixed SCSI 2
sd4(ahc1:1:0): Direct-Access 2047MB (4194058 512 byte sectors)
Probing for devices on the ISA bus:
sc0 at 0x60-0x6f irq 1 on motherboard
sc0: VGA color <16 virtual consoles, flags=0x0>
sio0 at 0x3f8-0x3ff irq 4 on isa
sio0: type 16550A
sio1 at 0x2f8-0x2ff irq 3 on isa
sio1: type 16550A
lpt0 at 0x378-0x37f irq 7 on isa
lpt0: Interrupt-driven port
lp0: TCP/IP capable interface
fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa
fdc0: NEC 72065B
fd0: 1.44MB 3.5in
fe0 at 0x300-0x31f irq 15 on isa
fe0: address 00:00:f4:d0:5f:38, type AT1700/RE2000
npx0 on motherboard
npx0: INT 16 interface
ccd0: Concatenated disk driver
machine "i386"
cpu "I586_CPU"
ident LARK_II
maxusers 16
options INET #InterNETworking
options FFS #Berkeley Fast Filesystem
options NFS #Network Filesystem
options PROCFS #Process filesystem
options "COMPAT_43" #Compatible with BSD 4.3
options UCONSOLE #Allow users to grab the console
options SYSVSHM
options SYSVSEM
options SYSVMSG
options AHC_TAGENABLE
options "NMBCLUSTERS=4096"
options DUMMY_NOPS
options "AUTO_EOI_1"
options "AUTO_EOI_2"
options FAT_CURSOR
options HARDFONTS
config kernel root on sd0
controller isa0
controller pci0
controller fdc0 at isa? port "IO_FD1" bio irq 6 drq 2 vector fdintr
disk fd0 at fdc0 drive 0
controller ahc0
controller ahc1
controller scbus0
device sd0
device st0
device cd0 #Only need one of these, the code dynamically grows
device sc0 at isa? port "IO_KBD" tty irq 1 vector scintr
device npx0 at isa? port "IO_NPX" irq 13 vector npxintr
device sio0 at isa? port "IO_COM1" tty irq 4 vector siointr
device sio1 at isa? port "IO_COM2" tty irq 3 vector siointr
device lpt0 at isa? port? tty irq 7 vector lptintr
device de0
device fxp0
device fe0 at isa? port 0x300 net irq ? vector feintr
pseudo-device loop
pseudo-device ether
pseudo-device log
pseudo-device pty 64
pseudo-device gzip # Exec gzipped a.out's
pseudo-device ccd 1
The machine lark2.sms.fi is a P166 (Asus P/I-P55T2P4) with 64M RAM.
1G disk is used for the OS and the 4 2G disks are striped together
by using ccd. I don't think that it affects the ethernet performance.
The other end, thrush.sms.fi is a SUN Ultra 1/170.
In between those two machines is a Cisco Catalyst 5000 switch, but
don't bother to point at it being the culprit :)
--
Bror 'Count' Heinola % count@key.hole.fi % http://pobox.com/~count/
Pengerkatu 13b A5 % IRC: Count NIC: BH271 %
FI-00530 HELSINKI % Work: bror@sms.fi % Roads? Where we're going,
Cell: +358-40-5533-554 % Santa Monica Software % we don't need roads.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199607121610.TAA02055>