sk98lin, jumbo frames, and memory fragmentation

sk98lin, jumbo frames, and memory fragmentation

[Chris Friesen]

Hi all,

We're considering some hardware that uses the sk98lin network hardware, 
and we'll be using jumbo frames.  Looking at the driver, when using a 
9KB MTU it seems like it would end up trying to atomically allocate a 
16KB buffer.

Has anyone heard of this been a problem?  It would seem like trying to 
atomically allocate four physically contiguous pages could become tricky 
after the system has been running for a while.

The reason I ask is that we ran into this with the e1000.  Before they 
added the new jumbo frame code it was trying to atomically allocate 32KB 
buffers and we would start getting allocation failures after a month or 
so of uptime.

Any information anyone can provide would be appreciated.


Thanks,

Chris

Re: sk98lin, jumbo frames, and memory fragmentation

[John Heffner]

Yes it has this problem.  I've observed it in practice on a busy firewall.

   -John


Chris Friesen wrote:
> 
> Hi all,
> 
> We're considering some hardware that uses the sk98lin network hardware, 
> and we'll be using jumbo frames.  Looking at the driver, when using a 
> 9KB MTU it seems like it would end up trying to atomically allocate a 
> 16KB buffer.
> 
> Has anyone heard of this been a problem?  It would seem like trying to 
> atomically allocate four physically contiguous pages could become tricky 
> after the system has been running for a while.
> 
> The reason I ask is that we ran into this with the e1000.  Before they 
> added the new jumbo frame code it was trying to atomically allocate 32KB 
> buffers and we would start getting allocation failures after a month or 
> so of uptime.
> 
> Any information anyone can provide would be appreciated.
> 
> 
> Thanks,
> 
> Chris
> -
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: sk98lin, jumbo frames, and memory fragmentation

[Jeff Garzik]

Chris Friesen wrote:
> We're considering some hardware that uses the sk98lin network hardware, 
> and we'll be using jumbo frames.  Looking at the driver, when using a 
> 9KB MTU it seems like it would end up trying to atomically allocate a 
> 16KB buffer.

The sk98lin driver is going away, please don't use it.

It's unmaintained and full of known bugs.

	Jeff

Re: sk98lin, jumbo frames, and memory fragmentation

[Stephen Hemminger]

On Mon, 01 Oct 2007 14:35:48 -0600
"Chris Friesen" <cfriesen@nortel.com> wrote:

> 
> Hi all,
> 
> We're considering some hardware that uses the sk98lin network hardware, 
> and we'll be using jumbo frames.  Looking at the driver, when using a 
> 9KB MTU it seems like it would end up trying to atomically allocate a 
> 16KB buffer.
> 
> Has anyone heard of this been a problem?  It would seem like trying to 
> atomically allocate four physically contiguous pages could become tricky 
> after the system has been running for a while.
> 
> The reason I ask is that we ran into this with the e1000.  Before they 
> added the new jumbo frame code it was trying to atomically allocate 32KB 
> buffers and we would start getting allocation failures after a month or 
> so of uptime.
> 
> Any information anyone can provide would be appreciated.

Adding fragmentation support to skge driver is on my list of
possible extensions. sky2 driver already supports it (yet one
more feature that the vendor sk98lin driver doesn't do).

-- 
Stephen Hemminger <shemminger@linux-foundation.org>

Re: sk98lin, jumbo frames, and memory fragmentation

[Chris Friesen]

Jeff Garzik wrote:

> The sk98lin driver is going away, please don't use it.
> 
> It's unmaintained and full of known bugs.

Okay...so it looks like the proper driver for the Marvell Yukon 88E8062 
is the sky2 driver, and this one does avoid order>0 allocations.  Am I 
on track?

Chris

Re: sk98lin, jumbo frames, and memory fragmentation

[Chris Friesen]

Stephen Hemminger wrote:

> Adding fragmentation support to skge driver is on my list of
> possible extensions. sky2 driver already supports it (yet one
> more feature that the vendor sk98lin driver doesn't do).

Thanks for speaking up.  As I mentioned in my email to Jeff it looks 
like the sky2 driver is what I need (Marvel Yukon 88E8062).  However, 
I'm on 2.6.14 and it doesn't exist there...do you anticipate any issues 
if I were to backport it?

Thanks,

Chris

Re: sk98lin, jumbo frames, and memory fragmentation

[Stephen Hemminger]

On Mon, 01 Oct 2007 15:15:59 -0600
"Chris Friesen" <cfriesen@nortel.com> wrote:

> Stephen Hemminger wrote:
> 
> > Adding fragmentation support to skge driver is on my list of
> > possible extensions. sky2 driver already supports it (yet one
> > more feature that the vendor sk98lin driver doesn't do).
> 
> Thanks for speaking up.  As I mentioned in my email to Jeff it looks 
> like the sky2 driver is what I need (Marvel Yukon 88E8062).  However, 
> I'm on 2.6.14 and it doesn't exist there...do you anticipate any issues 
> if I were to backport it?

Nothing but usual annoying kernel API changes..


-- 
Stephen Hemminger <shemminger@linux-foundation.org>