On Sun, 2006-01-22 at 21:14 -0500, Ariel wrote:

On Sun, 22 Jan 2006, Arjan van de Ven wrote:

quoted

quoted

quoted

On Sun, 2006-01-22 at 09:16 +0100, Arjan van de Ven wrote:

quoted

On Sat, 2006-01-21 at 21:13 -0500, Ariel wrote:

quoted

quoted

quoted

quoted

quoted

I have a memory leak in scsi_cmd_cache.

quoted

quoted

quoted

quoted

does this happen without the binary nvidia driver too? (it appears
you're using that). That's a good datapoint to have if so...

quoted

please repeat this without nvidia ever being loaded. Just having a
module loaded before can already cause corruption that ripples through
later, so just unloading is not enough to get a clean result.

I rebooted without nvidia or vmware ever being loaded and got a 
leak of 1.12KB/s. So I think we can rule that out.

great

A commonality I'm noticing is SATA. SATA had a big update in this 
version, so perhaps that's where to start looking.

I wonder if it can be narrowed even more, like to the exact chipset
driver?