|
Home > Archive > Data Storage > February 2005 > ethernet to USB is very slow...help?
You are viewing an archived Text-only version of the thread.
To view this thread in it's original format and/or if you want to reply to
this thread please [click here]
| Author |
ethernet to USB is very slow...help?
|
|
| jtsnow 2005-02-05, 5:45 pm |
| When I send data over my home LAN ethernet to a hard drive running on a USB
2.0 its very slow data transfer. This is PC to PC over 100baseT wired home
LAN to do disk backups. The slowness occurs in the translation from
10baseT100 to the USB 2.0 and the CPU is 100% utilized.
Are there cards that offload the CPU processing needed to do this
translation?
I have a PCI combo card (w/firewire), brand new installed.
The following clues narrow the problem down to the USB to ethernet
conversion as the problem.:
PC to PC over ethernet from installed HD to installed HD is very fast.
PC from its own C: drive to the USB 2.0 drive is very fast.
but when do PC to PC over ethernet to save data on theh USB 2.0 drive its
very very slow...like 5x slower then drive C: to USB 2.0.
Any thoughts?
| |
| Nik Simpson 2005-02-05, 5:45 pm |
| jtsnow wrote:
> When I send data over my home LAN ethernet to a hard drive running on a USB
> 2.0 its very slow data transfer. This is PC to PC over 100baseT wired home
> LAN to do disk backups. The slowness occurs in the translation from
> 10baseT100 to the USB 2.0 and the CPU is 100% utilized.
>
> Are there cards that offload the CPU processing needed to do this
> translation?
>
> I have a PCI combo card (w/firewire), brand new installed.
At a very rough guess, did you install this PCI card in the last slot
you had available (i.e. the bottom slot on the motherboard. On a lot of
boards, this slot is shared with an ISA slot and is incapable of bus
mastering. If that's the case, then card is dumbing itself down to
handle the condition and generating an interrupt for each I/O transfer
which will bring the CPU to its knees. Try moving the card to another
slot and see if that makes any difference.
--
Nik Simpson
| |
| Maxim S. Shatskih 2005-02-05, 5:45 pm |
| Install Windows service pack. Unpatched WinXP had a problem with high speed
on USB 2.0 - 100% CPU and all is slow.
--
Maxim Shatskih, Windows DDK MVP
StorageCraft Corporation
maxim@storagecraft.com
http://www.storagecraft.com
"Nik Simpson" <n_simpson@bellsouth.net> wrote in message
news:420511D0.3070104@bellsouth.net...
> jtsnow wrote:
>
> At a very rough guess, did you install this PCI card in the last slot
> you had available (i.e. the bottom slot on the motherboard. On a lot of
> boards, this slot is shared with an ISA slot and is incapable of bus
> mastering. If that's the case, then card is dumbing itself down to
> handle the condition and generating an interrupt for each I/O transfer
> which will bring the CPU to its knees. Try moving the card to another
> slot and see if that makes any difference.
>
>
> --
> Nik Simpson
| |
| jtsnow 2005-02-05, 5:45 pm |
| im using XP sp2...so im good there
"Maxim S. Shatskih" <maxim@storagecraft.com> wrote in message
news:cu35ao$lnc$1@gavrilo.mtu.ru...
> Install Windows service pack. Unpatched WinXP had a problem with high
> speed
> on USB 2.0 - 100% CPU and all is slow.
>
> --
> Maxim Shatskih, Windows DDK MVP
> StorageCraft Corporation
> maxim@storagecraft.com
> http://www.storagecraft.com
>
> "Nik Simpson" <n_simpson@bellsouth.net> wrote in message
> news:420511D0.3070104@bellsouth.net...
>
>
| |
| jtsnow 2005-02-05, 5:45 pm |
| ok...Ill take a look. I dont think it is but thats a good suggestion.
"Nik Simpson" <n_simpson@bellsouth.net> wrote in message
news:420511D0.3070104@bellsouth.net...
> jtsnow wrote:
>
> At a very rough guess, did you install this PCI card in the last slot you
> had available (i.e. the bottom slot on the motherboard. On a lot of
> boards, this slot is shared with an ISA slot and is incapable of bus
> mastering. If that's the case, then card is dumbing itself down to handle
> the condition and generating an interrupt for each I/O transfer which will
> bring the CPU to its knees. Try moving the card to another slot and see if
> that makes any difference.
>
>
> --
> Nik Simpson
|
|
|
|
|