Messages in this thread | | | Date | Fri, 14 Mar 2014 17:57:41 +0800 | From | Daniel J Blueman <> | Subject | Re: [PATCH] Fix northbridge quirk to assign correct NUMA node |
| |
Hi Boris,
On 14/03/2014 17:06, Borislav Petkov wrote: > On Thu, Mar 13, 2014 at 07:43:01PM +0800, Daniel J Blueman wrote: >> For systems with multiple servers and routed fabric, all northbridges get >> assigned to the first server. Fix this by also using the node reported from >> the PCI bus. For single-fabric systems, the northbriges are on PCI bus 0 >> by definition, which are on NUMA node 0 by definition, so this is invarient >> on most systems. > > Yeah, I think this is of very low risk for !Numascale setups. :-) So > > Acked-by: Borislav Petkov <bp@suse.de> > >> Tested on fam10h and fam15h single and multi-fabric systems and candidate >> for stable. > > I'm not sure about it - this is only reporting the wrong node, right? > Does anything depend on that node setting being correct and breaks due > to this?
It's only reporting the wrong node, yes. The irqbalance daemon uses /sys/devices/.../numa_node, and we found we have to disable it to prevent hangs on certain systems after a while, but I didn't establish a link just yet, though found this to be incorrect.
Thanks, Daniel -- Daniel J Blueman Principal Software Engineer, Numascale
| |