linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Alex Shi <seakeel@gmail.com>
To: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: alexs@kernel.org, Vitaly Wool <vitaly.wool@konsulko.com>,
	Miaohe Lin <linmiaohe@huawei.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	minchan@kernel.org, willy@infradead.org, david@redhat.com,
	42.hyeyoo@gmail.com, Yosry Ahmed <yosryahmed@google.com>,
	nphamcs@gmail.com
Subject: Re: [PATCH v7 00/21] mm/zsmalloc: add zpdesc memory descriptor for zswap.zpool
Date: Tue, 3 Sep 2024 16:01:29 +0800	[thread overview]
Message-ID: <1ec2f951-8ce8-485a-9f51-e3b9f4eba73e@gmail.com> (raw)
In-Reply-To: <20240903034542.GD9738@google.com>



On 9/3/24 11:45 AM, Sergey Senozhatsky wrote:
> On (24/09/03 12:35), Sergey Senozhatsky wrote:
>> On (24/09/02 15:21), alexs@kernel.org wrote:
>>> The descriptor still overlays the struct page; nothing has changed
>>> in that regard.
>>> [..]
>>> This patachset does not increase the descriptor size nor introduce any
>>> functional changes, and could save about 122Kbytes zsmalloc.o size.
>>
>> Is this number accurate?  Where does such a large saving come from?

Hi Sergey,

Thanks for asking, I collected some data on Aug 2, before the patchset,
zsmalloc.o is 1200960 bytes, after patched, it's 1076144 bytes. At that
time it's saved about 124KB, about 10%, with some debug option enabled.

Just test again with x86defconfig + ZSMALLOC + ZSMALLOC_STAT, 
on mm-unstable tree, zsmalloc.o reduces to 34960 bytes from 37328 bytes,
that's 6.3% saved.

The bloat-o-meter show in machine:
$ ./scripts/bloat-o-meter x86def/mm/zsmalloc.o x86def/mm/zsmalloc-patched.o 
add/remove: 1/1 grow/shrink: 1/5 up/down: 100/-1068 (-968)
Function                                     old     new   delta
create_zpdesc_chain                            -      92     +92
zs_compact                                  2352    2360      +8
zs_malloc                                   1334    1277     -57
__free_zspage                                291     223     -68
free_zspage                                  289     211     -78
create_page_chain                             95       -     -95
zs_page_migrate                              950     807    -143
async_free_zspage                           1252     625    -627
Total: Before=11868, After=10900, chg -8.16%

> 
> ./scripts/bloat-o-meter mm/zsmalloc.o-base mm/zsmalloc.o-patched
> add/remove: 0/0 grow/shrink: 2/6 up/down: 7/-843 (-836)
> Function                                     old     new   delta
> obj_free                                     211     215      +4
> zs_unmap_object                              568     571      +3
> zs_map_object                                661     633     -28
> SetZsPageMovable                             135      86     -49
> free_zspage                                  310     253     -57
> __free_zspage                                284     226     -58
> zs_page_migrate                             1304    1136    -168
> async_free_zspage                           1099     616    -483

Many thanks for detailed data here!

Thanks
Alex


  reply	other threads:[~2024-09-03  8:01 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-02  7:21 [PATCH v7 00/21] mm/zsmalloc: add zpdesc memory descriptor for zswap.zpool alexs
2024-09-02  7:21 ` [PATCH v7 01/21] " alexs
2024-12-03 16:51   ` Matthew Wilcox
2024-09-02  7:21 ` [PATCH v7 02/21] mm/zsmalloc: use zpdesc in trylock_zspage()/lock_zspage() alexs
2024-09-02  7:21 ` [PATCH v7 03/21] mm/zsmalloc: convert __zs_map_object/__zs_unmap_object to use zpdesc alexs
2024-09-02  7:21 ` [PATCH v7 04/21] mm/zsmalloc: add and use pfn/zpdesc seeking funcs alexs
2024-09-02  7:21 ` [PATCH v7 05/21] mm/zsmalloc: convert obj_malloc() to use zpdesc alexs
2024-09-02  7:21 ` [PATCH v7 06/21] mm/zsmalloc: convert create_page_chain() and its users " alexs
2024-09-02  7:21 ` [PATCH v7 07/21] mm/zsmalloc: convert obj_allocated() and related helpers " alexs
2024-09-02  7:21 ` [PATCH v7 08/21] mm/zsmalloc: convert init_zspage() " alexs
2024-09-02  7:21 ` [PATCH v7 09/21] mm/zsmalloc: convert obj_to_page() and zs_free() " alexs
2024-09-02  7:21 ` [PATCH v7 10/21] mm/zsmalloc: add zpdesc_is_isolated()/zpdesc_zone() helper for zs_page_migrate() alexs
2024-09-02  7:21 ` [PATCH v7 11/21] mm/zsmalloc: rename reset_page to reset_zpdesc and use zpdesc in it alexs
2024-09-02  7:21 ` [PATCH v7 12/21] mm/zsmalloc: convert __free_zspage() to use zdsesc alexs
2024-09-02  7:21 ` [PATCH v7 13/21] mm/zsmalloc: convert location_to_obj() to take zpdesc alexs
2024-09-02  7:21 ` [PATCH v7 14/21] mm/zsmalloc: convert migrate_zspage() to use zpdesc alexs
2024-09-02  7:21 ` [PATCH v7 15/21] mm/zsmalloc: convert get_zspage() to take zpdesc alexs
2024-09-02  7:21 ` [PATCH v7 16/21] mm/zsmalloc: convert SetZsPageMovable and remove unused funcs alexs
2024-09-02  7:21 ` [PATCH v7 17/21] mm/zsmalloc: convert get/set_first_obj_offset() to take zpdesc alexs
2024-09-02  7:21 ` [PATCH v7 18/21] mm/zsmalloc: introduce __zpdesc_clear_movable alexs
2024-09-02  7:21 ` [PATCH v7 19/21] mm/zsmalloc: introduce __zpdesc_clear/set_zsmalloc() alexs
2024-09-02  7:21 ` [PATCH v7 20/21] mm/zsmalloc: introduce zpdesc_clear_first() helper alexs
2024-09-02  7:21 ` [PATCH v7 21/21] mm/zsmalloc: update comments for page->zpdesc changes alexs
2024-09-03  3:35 ` [PATCH v7 00/21] mm/zsmalloc: add zpdesc memory descriptor for zswap.zpool Sergey Senozhatsky
2024-09-03  3:45   ` Sergey Senozhatsky
2024-09-03  8:01     ` Alex Shi [this message]
2024-09-04  6:54 ` Alex Shi
2024-09-04 20:04   ` Vishal Moola
2024-09-12  2:28     ` Alex Shi
2024-12-02 20:05     ` Vishal Moola
2024-12-03 13:58       ` Alex Shi
2024-12-04 14:01         ` Hyeonggon Yoo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1ec2f951-8ce8-485a-9f51-e3b9f4eba73e@gmail.com \
    --to=seakeel@gmail.com \
    --cc=42.hyeyoo@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexs@kernel.org \
    --cc=david@redhat.com \
    --cc=linmiaohe@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=nphamcs@gmail.com \
    --cc=senozhatsky@chromium.org \
    --cc=vitaly.wool@konsulko.com \
    --cc=willy@infradead.org \
    --cc=yosryahmed@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).