-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1


On Mon, 9 Jan 2006, Denny White wrote:

Date: Mon, 9 Jan 2006 12:13:38 +0000 (UTC)
From: Denny White <[EMAIL PROTECTED]>
To: OpenBSD Questions Mailing List <misc@openbsd.org>
Subject: Tuning NFS file transfer speed

I know the usual complaint is, it's not fast enough. My
question is, after doing much googling - mail archive
reading, is there a way to slow the file transfer speed
down? I've asked the list before about a rebooting problem
I have on this box, & it's still here, but now only when
I transfer large files from another box. I thought for a
while, it might be something with the XP system on another
box, but the same problem exists when I try it from my
FreeBSD box. I've fought with the BIOS settings for weeks
now, & once thought I had the problem fixed. Later, my
friend, unbeknownst to me & thinking he was helping, tried
tweaking the BIOS some more, before I had a chance to write
down all the settings. Since, I have not been able to duplicate
a problem free incoming NFS file transfer, unless it's a small
file. Anything over 6-8MB & down she goes. I can, on the other
hand, mount exported shares from my XP or FreeBSD boxes and
copy really large files to them from this OpenBSD box. I've
swapped cables, to no avail. I've checked the hd, the simms,
everything showing okay. I have the proper cable on the hd,
80 pin. Dmesg shows it using Ultra DMA 66. I'll include the
dmesg at end of message. Several times in the past, the box
rebooted too, when updating the locate database, or when
running fsck. That seems to have disappeared since making
some changes in the BIOS, the most important one being,
according to some BIOS/reboot problems I read about on Google,
getting the cmos clock & the os clock synced properly. I'm
now using /etc/localtime -> /usr/share/zoneinfo/UTC instead of
Central like before. Thanks for any help I can get on this. I
really tried to solve this before asking for help. Right now,
can't afford another box, mobo, etc. Everything else on here
works great. Cvsup, rebuilding kernel & userland, & so forth.

OpenBSD 3.8-stable (GENERIC) #2: Wed Dec 28 10:03:01 CST 2005
   [EMAIL PROTECTED]:/usr/src/sys/arch/i386/compile/GENERIC
cpu0: Intel Pentium III ("GenuineIntel" 686-class) 601 MHz
cpu0: FPU,V86,DE,PSE,TSC,MSR,PAE,MCE,CX8,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,MMX,FXSR,SSE
real mem  = 335060992 (327208K)
avail mem = 298348544 (291356K)
using 4115 buffers containing 16855040 bytes (16460K) of memory
mainbus0 (root)
bios0 at mainbus0: AT/286+(a7) BIOS, date 01/31/02, BIOS32 rev. 0 @ 0xfb4f0
apm0 at bios0: Power Management spec V1.2
apm0: AC on, battery charge unknown
apm0: flags 70102 dobusy 1 doidle 1
pcibios0 at bios0: rev 2.1 @ 0xf0000/0xb970
pcibios0: PCI IRQ Routing Table rev 1.0 @ 0xfdd90/144 (7 entries)
pcibios0: PCI Exclusive IRQs: 5 9 10 11
pcibios0: PCI Interrupt Router at 000:07:0 ("VIA VT82C596A ISA" rev 0x00)
pcibios0: PCI bus #1 is the last bus
bios0: ROM list: 0xc0000/0x8000 0xc8000/0x800
cpu0 at mainbus0
pci0 at mainbus0 bus 0: configuration mode 1 (no bios)
pchb0 at pci0 dev 0 function 0 "VIA VT82C691 PCI" rev 0xc4
ppb0 at pci0 dev 1 function 0 "VIA VT82C598 AGP" rev 0x00
pci1 at ppb0 bus 1
pcib0 at pci0 dev 7 function 0 "VIA VT82C686 ISA" rev 0x22
pciide0 at pci0 dev 7 function 1 "VIA VT82C571 IDE" rev 0x10: ATA66, channel 0 configured to compatibility, channel 1 configured to compatibility
wd0 at pciide0 channel 0 drive 0: <WDC WD400BB-00AUA1>
wd0: 16-sector PIO, LBA, 38166MB, 78165360 sectors
wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 4
atapiscsi0 at pciide0 channel 1 drive 0
scsibus0 at atapiscsi0: 2 targets
cd0 at scsibus0 targ 0 lun 0: <HP, CD-Writer+ 9500b, 1.06> SCSI0 5/cdrom removable
atapiscsi1 at pciide0 channel 1 drive 1
scsibus1 at atapiscsi1: 2 targets
cd1 at scsibus1 targ 0 lun 0: <ASUS, CD-S500/A, 1.0K> SCSI0 5/cdrom removable
cd0(pciide0:1:0): using PIO mode 4, DMA mode 2
cd1(pciide0:1:1): using PIO mode 4, Ultra-DMA mode 2
uhci0 at pci0 dev 7 function 2 "VIA VT83C572 USB" rev 0x10: irq 9
usb0 at uhci0: USB revision 1.0
uhub0 at usb0
uhub0: VIA UHCI root hub, rev 1.00/1.00, addr 1
uhub0: 2 ports with 2 removable, self powered
uhci1 at pci0 dev 7 function 3 "VIA VT83C572 USB" rev 0x10: irq 9
usb1 at uhci1: USB revision 1.0
uhub1 at usb1
uhub1: VIA UHCI root hub, rev 1.00/1.00, addr 1
uhub1: 2 ports with 2 removable, self powered
viaenv0 at pci0 dev 7 function 4 "VIA VT82C686 SMBus" rev 0x30
auvia0 at pci0 dev 7 function 5 "VIA VT82C686 AC97" rev 0x20: irq 5
ac97: codec id 0x83847644 (SigmaTel STAC9744/45)
ac97: codec features 18 bit DAC, 18 bit ADC, SigmaTel 3D
audio0 at auvia0
xl0 at pci0 dev 13 function 0 "3Com 3c905C 100Base-TX" rev 0x78: irq 11, address 00:01:03:1a:2f:21
bmtphy0 at xl0 phy 24: Broadcom 3C905C internal PHY, rev. 7
vga1 at pci0 dev 15 function 0 "3DFX Interactive Voodoo3" rev 0x01
wsdisplay0 at vga1 mux 1: console (80x25, vt100 emulation)
wsdisplay0: screen 1-5 added (80x25, vt100 emulation)
isa0 at pcib0
isadma0 at isa0
pckbc0 at isa0 port 0x60/5
pckbd0 at pckbc0 (kbd slot)
pckbc0: using irq 1 for kbd slot
wskbd0 at pckbd0: console keyboard, using wsdisplay0
pmsi0 at pckbc0 (aux slot)
pckbc0: using irq 12 for aux slot
wsmouse0 at pmsi0 mux 0
pcppi0 at isa0 port 0x61
midi0 at pcppi0: <PC speaker>
spkr0 at pcppi0
sysbeep0 at pcppi0
lpt0 at isa0 port 0x378/4 irq 7
npx0 at isa0 port 0xf0/16: using exception 16
pccom0 at isa0 port 0x3f8/8 irq 4: ns16550a, 16 byte fifo
pccom1 at isa0 port 0x2f8/8 irq 3: ns16550a, 16 byte fifo
fdc0 at isa0 port 0x3f0/6 irq 6 drq 2
fd0 at fdc0 drive 0: 1.44MB 80 cyl, 2 head, 18 sec
biomask e745 netmask ef45 ttymask ffc7
pctr: 686-class user-level performance counters enabled
mtrr: Pentium Pro MTRR support
dkcsum: wd0 matches BIOS drive 0x80
root on wd0a
rootdev=0x0 rrootdev=0x300 rawdev=0x302
wsdisplay0: screen 6 added (80x25, vt100 emulation)
wsdisplay0: screen 7 added (80x25, vt100 emulation)

Also including ifconfig output. Have tried switching nics,
thinking problem might be there too, but it didn't help.
Thought maybe the nic could be causing the problem.

lo0: flags=8049<UP,LOOPBACK,RUNNING,MULTICAST> mtu 33224
        groups: lo
        inet 127.0.0.1 netmask 0xff000000
        inet6 ::1 prefixlen 128
        inet6 fe80::1%lo0 prefixlen 64 scopeid 0x5
xl0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> mtu 1500
        lladdr 00:01:03:1a:2f:21
        groups: egress
        media: Ethernet autoselect (100baseTX full-duplex)
        status: active
        inet 192.168.1.104 netmask 0xffffff00 broadcast 192.168.1.255
        inet6 fe80::201:3ff:fe1a:2f21%xl0 prefixlen 64 scopeid 0x1
pflog0: flags=141<UP,RUNNING,PROMISC> mtu 33224
pfsync0: flags=0<> mtu 1348
enc0: flags=0<> mtu 1536


 Today ober contributed the following:
What are your nfs mount options?
Those could help in determining the issue.


-Ober

Here's what all I can think of to include:

/etc/exports

#       $OpenBSD: exports,v 1.2 2002/05/31 08:15:44 pjanzen Exp $
#
# NFS exports Database
# See exports(5) for more information.  Be very careful:  misconfiguration
# of this file can result in your filesystems being readable by the world.
#
/home -alldirs 192.168.1.100 192.168.1.101 192.168.1.103 /data -alldirs 192.168.1.100 192.168.1.101 192.168.1.103

/etc/fstab

/dev/wd0a / ffs rw 1 1
/dev/wd0h /data ffs rw,nodev,nosuid 1 2
/dev/wd0f /home ffs rw,nodev,nosuid 1 2
/dev/wd0g /tmp ffs rw,nodev,nosuid 1 2
/dev/wd0e /usr ffs rw,nodev 1 2
/dev/wd0d /var ffs rw,nodev,nosuid 1 2
#/dev/wd1a /altroot ffs xx 0 0
#/dev/wd1d /data2 ffs rw,nodev,nosuid 0 0 /usr/swap /usr/swap swap sw 0 0
#/data2/swap /data2/swap swap sw 0 0
/dev/cd0a /mntcd1 cd9660 ro,noauto 0 0
/dev/cd1a /mntcd2 cd9660 ro,noauto 0 0
/dev/fd0a /mntflop msdos rw,noauto 0 0

Disregard hashed out altroot & data2 stuff in fstab. Disconnected
2nd hd, thinking maybe I had a power supply problem & that
maybe reducing hardware would help. Also, the /usr/swap was added,
thinking maybe more swap space would help. That was just a shot in
the dark.

nfs settings in /etc/rc.conf

nfs_server=YES          # see sysctl.conf for nfs client configuration
nfsd_flags="-t -u -tun 4 -n 4"        # Crank the 4 for a busy NFS fileserver

rpcinfo -p

  program vers proto   port
   100000    2   tcp    111  portmapper
   100000    2   udp    111  portmapper
   100005    1   udp    719  mountd
   100005    3   udp    719  mountd
   100005    1   tcp    831  mountd
   100005    3   tcp    831  mountd
   100003    2   udp   2049  nfs
   100003    3   udp   2049  nfs
   100003    2   tcp   2049  nfs
   100003    3   tcp   2049  nfs

sysctl -a | grep nfs:

vfs.nfs.iothreads=8

Forgot to mention in original post, have also tried hard rather than
soft mounting from the other box. Didn't help. Also tried just using
udp, rather than tcp. No help. Let me know if there's any other info
I can provide to help. Always learning, and a lot further ahead of the
game from when I started, but will probably always consider myself a
newbie.
Denny White


On Jan 9 Denny White contributed the following:

Last night, I tried disconnecting the slave cdrom on the
secondary ide controller, reconnecting my extra hd as slave
on secondary, mounting it and exporting a share & then copying
a large file to it from the winbox to see if maybe the problem
was with the primary ide controller. The extra hd had always
run as slave on the primary ide before. Didn't solve it. System
rebooted. Read up on man 4 wd & flags for disabling Ultra DMA.
Also read up on man 8 boot_config, man 4 pciide, & man 4 wdc.
But, before going into config -e bsd.test /bsd & doing it, I
figured I'd just disable it in the BIOS, since nothing else
but OpenBSD is on this system, no dual-boot. Disabled Ultra
DMA in the BIOS, rebooted, fscked everything, mounted all &
ctrl-d. When system was up & running, ran the large file copy
test (49MB) again. No problem this time. Also mounted a share
from the winbox on this box & copied a large file to & from.
No more problems. Before I got the cd & did a release install,
cvsup for stable & the rebuild everything dance, I was running
current for about 3 weeks. During that time, I'm sure I had nfs
shares mounted & did large file copying without incident. Does
current handle dma differently? Just wondering. I am certainly
no programmer or developer. Just an end user trying to learn
obsd & get weaned off the ms tit as much as possible, once &
for all.
Denny White

Please do not CC me. Already subscribed to mailing list.

GnuPG key  : 0x1644E79A  |  http://wwwkeys.nl.pgp.net
Fingerprint: D0A9 AD44 1F10 E09E 0E67  EC25 CB44 F2E5 1644 E79A
iD8DBQFDw55cy0Ty5RZE55oRAoavAJkBh6ZhtF+RJvEKHPCJ/nSSBwF7RwCdFZ66
Tn2xB7RfVzZtX404CcMdgts=
=sDs5
-----END PGP SIGNATURE-----

Reply via email to