From: ldo@nz.invalid   
      
   On Wed, 12 Nov 2025 21:43:40 +0000, David Wade wrote:   
      
   > Why won't it scale to 460,000 nodes?   
      
   Because a cluster of on the order of tens of machines (like your SysPlex   
   and VMScluster) can depend on algorithms with polynomial complexity, that   
   would no longer be practicable when you have hundreds of thousands of   
   nodes.   
      
   > Why would you need that many nodes, well unless you are google?   
      
   All the hyperscalers are running clusters of that sort of size.   
      
   And not just them. Supercomputers are now built out of millions of nodes,   
   with the added twist of having a high-speed interconnect.   
      
   Let’s see you build a SysPlex or VMScluster on that sort of scale ...   
      
   > p.s. No one should assume the world stands still. A virtual Intel/X64   
   > cluster has nothing in common with a PC from the 1990s. A current IBM   
   > Mainframe has little in common with an S/360 from 1960's EXCEPT the   
   > modern mainframe will run user mode 24-bit code from the start of time.   
      
   Did you know that when Debian boots on an IBM mainframe, it has to pretend   
   it’s getting punched cards from a card reader?   
      
   “World doesn’t stand still” and “little in common with the 1960s” my   
   bum ...   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)