Re: [PATCH v3 1/3] driver/base: Optimize memory block registration to reduce boot time

[Mike Rapoport]

Hi Donet,

On Fri, May 09, 2025 at 09:10:34PM +0530, Donet Tom wrote:
> > > 
> > > Then we can drop the call to register_memory_blocks_under_node() from
> > > register_one_node() and add creation of memory blocks to
> > > node_dev_init(),
> > > i.e.
> > > 
> > > node_dev_init()
> > >    for_each_node(nid)
> > >      __register_one_node(nid)
> > >        for_each_mem_region()
> > >          /* create memory block if node matches */
> > 
> > Yes exactly, that makes sense.
> 
> Hi Andrew and Mike
> 
> Based on the discussion so far, it is clear that the patch will work in all cases,
> including when CONFIG_ARCH_KEEP_MEMBLOCK  is disabled. Just checking —
> would you prefer to take this version, or should I send a v4?

During the discussion we concluded that the right thing to do seems to drop
the call to register_memory_blocks_under_node() from register_one_node()
and make node_dev_init() call __register_one_node() and then create memory
blocks for each memblock region.

Can you please make v4 along those lines?
 
> Thanks
> Donet

-- 
Sincerely yours,
Mike.