On Mon, Jun 13, 2011 at 11:43:43PM +0200, Leon Woestenberg wrote: > Hello, > > On Mon, Jun 13, 2011 at 11:34 PM, Jon Mason <jon.mason@xxxxxxxx> wrote: > > There is a sizable performance boost for having the largest possible > > maximum payload size on each PCI-E device. However, the maximum payload > > size must be uniform on a given PCI-E fabric, and each device, bridge, > > and root port can have a different max size. To find and configure the > > optimal MPS settings, one must walk the fabric and determine the largest > > MPS available on all the devices on the given fabric. > > > > Wow, Linux not did this already? Not yet :) > I'll see if I can find a system where all systems have 256+ bytes > payload capability across the system to test this one. Thanks! If you have a system with hotplug, it would be even more appreciated. On my buggy BIOS system, I see the following: $ dmesg | grep "Setting MaxPayload" pci 0000:00:01.0: Setting MaxPayload to 256 pci 0000:00:02.0: Setting MaxPayload to 256 pci 0000:0d:02.0: Setting MaxPayload to 256 pci 0000:0d:04.0: Setting MaxPayload to 256 pci 0000:0f:00.0: Setting MaxPayload to 256 pci 0000:0e:00.0: Setting MaxPayload to 256 pci 0000:00:04.0: Setting MaxPayload to 256 pci 0000:00:05.0: Setting MaxPayload to 256 pci 0000:00:06.0: Setting MaxPayload to 256 pci 0000:00:07.0: Setting MaxPayload to 256 pci 0000:00:08.0: Setting MaxPayload to 256 pci 0000:00:09.0: Setting MaxPayload to 256 pci 0000:00:0a.0: Setting MaxPayload to 256 Thanks, Jon > > Regards, > -- > Leon -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
