Bug #1641
closed
receive errors and FIFO overflow with vr nic
0%
Description
I am experiencing a lot of messages like this
vr0: rx error (09): FIFO overflow
vr0: receive error (0407) overflow
when my system (VIA CN 10000) is under high network load (ftp, nfs, bacula).
tuxillo suggested to look into the recent changes FBSD did to the driver
to get around these problems:
http://svn.freebsd.org/viewvc/base?view=revision&revision=177050
this is the hardware info about the card:
vr0: <VIA VT6102 Rhine II 10/100BaseTX> port 0xe000-0xe0ff mem
0xfdffe000-0xfdffe0ff irq 10 at device 18.0 on pci0
miibus0: <MII bus> on vr0
vr0@pci0:0:18:0: class=0x020000 card=0x01021106 chip=0x30651106
rev=0x78 hdr=0x00
vendor = 'VIA Technologies, Inc.'
device = 'VT6103 Rhine II PCI Fast Ethernet Controller'
class = network
subclass = ethernet
Updated by dillon over 14 years ago
Try bumping VR_RX_LIST_CNT in if_vrreg.h in our driver from 64
to 128. The FBsd driver has some flow control stuff in it too but
that's only for 6105+ chips, and yours is a 6102 or 6103. There
is a RX pause feature commented out in the FBsd driver for 6102+
chips (but its commented out so...).
DragonFly's NFS implementation runs RPCs fully asynchronously so it
can seriously load down the network. Both FBsd and DragonFly have
variable-sized TCP buffers so scp-style transfers should work about
the same, but you can check by looking at the backlog in the sockbuf
on the sender for the connection ('netstat -p tcp' on the sending side)
while it is going full-bore.-Matt
Matthew Dillon
<dillon@backplane.com>
Updated by lentferj about 14 years ago
A patch was committed my Matt that at least improved this.