Adrian,Thanks for the work on bisecting & getting to the bottom to the long standing stability issues and the chance for stable, recent Linux Kernels. Those were a long standing issue for me as I am running a few of the heavily impacted systems (UltraSPARC III).
Are there any pre-built images of the kernel available? Preferably SMP.As far as I know, there are no ("Beta")-install-images yet, which hinders testing a bit for me...
I don't have a working build environment atm and am chronically short on time due to work,
but I do have test systems for UltraSPARC I, II, III, T1 & T2+- installing from CD & just swapping the kernel would be possible, as I'm really interested in getting this tested & helping getting this into official images.
Also, I have multiple early UltraSPARC III system (SunFire 280R) which I'm unsure if it works with Linux at all (I seem to remember something about the crossbar bus SMP architecture made them crash on early boot and the FC-AL Disks are unusable...). Might test as well, if someone can provide a prebuilt kernel.
Greetings, Robin Am 30.08.2025 um 09:40 schrieb John Paul Adrian Glaubitz:
On Fri, 2025-08-29 at 18:41 -0400, Dennis Clarke wrote:I will hunt around and see what I have laying about in a back room. I know I have old Netra X1 stuff and maybe a few other units with very old UltraSPARC processors in them. They will be horrifically slow. The SPARC M7 or M8 will be a unicorn. Heard of only in myth.While I don't assume you have a SPARC M7-compatible machine, I think chances are good you might have a T1 machine. As a bonus, a test on an UltraSPARC I or II is very welcome as well. To clarify this: The kernel code in question contains optimizations for different CPUs, namely: - UltraSPARC I - UltraSPARC III - Niagara 1 - Niagara 2 - Niagara 4 - SPARC M7 All but Niagara 2 had bugs which Michael Karcher fixed. So far, I successfully tested on UltraSPARC III and Niagara 4 as I have access to these machines. I also own a Niagara 2 machine, but there is no testing necessary as the code was not touched. I also tested on QEMU which emulates an UltraSPARC II, meaning that the UltraSPARC I code was tested (there is no UltraSPARC II code). I used a patched kernel to force Niagara 4 to use the Niagara 1 code which worked without problems. Still, it would be nice to have testing on real machines of these types: - UltraSPARC I or II - Niagara 1 - SPARC M7 Adrian
Attachment:
smime.p7s
Description: Kryptografische S/MIME-Signatur