Hi Christoph, Following is SGI's stand on this issue: SGI recommends that customers use the -sn2 kernel. This is the kernel that is installed by our factory when we ship systems. The -sn2 kernel is a
On Tue, Aug 02, 2005 at 04:13:57PM -0700, Ravinandan Arakali wrote: Hi Christoph, Following is SGI's stand on this issue: SGI recommends that customers use the -sn2 kernel. This is the kernel that is
This patch relates to mostly performance related changes. 1. Fixed incorrect computation of PANIC level in rx_buffer_level(). 2. Removed unnecessary PIOs(read/write of tx_traffic_int and rx_traffic_
I thought that an mmiowb() was called for here (to order the PIO writes above more cheaply than doing the readq()). I posted a patch like this some time ago: http://marc.theaimsgroup.com/?l=linux-ne
On an Altix machine I believe the readq was necessary to flush the PIO writes. How long did you run the tests? I had seen in long duration tests that an occasional write (TXDL control word and the a
wmb() does no such thing. It only has influence on load and store instructions done by the local processor, it has no effect on what the PCI bus may do with PIO writes (ie. post them). If you need a
David S. Miller wrote: If you need a PIO to complete in a specific order, you have to read it back. If you need PIO operations to occur Correct. A PCI read is the only way to ensure that all the CPU/
The most recent tests I did used pktgen, and they ran for a total time of ~.5 hours (changing pkt_size every 30 seconds or so). The pktgen tests and other tests (like nttcp) have been run several tim
Thanks for pointing that out. We will wait for any other comments on our 12 patches. If there are no other, will send out a patch13 to include the mmiowb() change. Thanks, Ravi --Original Message--
this enabled it only on kernel that are built to only run on SN2 hardware, which is completely useless in practice. Besides that defining a CONFIG_ symbol from source files is a big no-go. What exac
In short, this is one of the ASIC modes where headers and payload are separated by the hardware, and placed in separate receive buffers. (More details are in the ASIC programming manual that is post
The two-buffer mode was added as a configurable option to Kconfig file several months ago. Hence the macro is CONFIG_2BUFF_MODE. The two-buffer receive mode involves two buffers (128 byte aligned) fo
We're saying that you should choose CONFIG_2BUFF_MODE, when CONFIG_IA64_SGI_SN2 is set, inside the Kconfig file using the "default" Kconfig directive. You should never change the setting of CONFIG_*
And that doesn't help either, CONFIG_IA64_SGI_SN2 isn't used in practice, any production Altix with 26 kernels runs CONFIG_IA64_GENERIC kernels. You have to make this run-time selectable.
Okay, got it. Will submit patch on Kconfig file after the macro for SGI platforms is confirmed. Ravi --Original Message-- From: David S. Miller [mailto:davem@xxxxxxxxxxxxx] Sent: Tuesday, July 12, 20
We are trying to use the "default" directive in Kconfig. We tried using an unconditional directive(just to test it out) such as "default y" and a conditional one such as "default y if CONFIG_IA64_SG