Thread (55 messages) 55 messages, 9 authors, 2019-11-30

Re: [PATCH v7 05/24] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages

From: John Hubbard <jhubbard@nvidia.com>
Date: 2019-11-21 22:25:22
Also in: bpf, dri-devel, kvm, linux-block, linux-doc, linux-fsdevel, linux-kselftest, linux-media, linux-mm, linux-rdma, lkml, netdev

On 11/21/19 8:59 AM, Dan Williams wrote:
On Thu, Nov 21, 2019 at 12:57 AM John Hubbard [off-list ref] wrote:
quoted
On 11/21/19 12:05 AM, Christoph Hellwig wrote:
quoted
So while this looks correct and I still really don't see the major
benefit of the new code organization, especially as it bloats all
put_page callers.

I'd love to see code size change stats for an allyesconfig on this
commit.
Right, I'm running that now, will post the results. (btw, if there is
a script and/or standard format I should use, I'm all ears. I'll dig
through lwn...)
Just run:

     size vmlinux
Beautiful. I thought it would involve a lot more. Here's results:

linux.git (Linux 5.4-rc8+):
==============================================
   text	   data	    bss	    dec	    hex	filename
227578032	213267935	76877984	517723951	1edbd72f	vmlinux


With patches 4 and 5 applied to linux.git:
==========================================
   text	   data	    bss	    dec	    hex	filename
229698560	213288379	76853408	519840347	1efc225b	vmlinux


Analysis:
=========

This increased the size of text by 0.93%. Which is a measurable bloat, so
the inlining really is undesirable here, yes. I'll do it differently.

thanks,
-- 
John Hubbard
NVIDIA
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help