From: Jan Kara <jack@suse.cz>
To: Matthew Wilcox <willy@infradead.org>
Cc: <linux-fsdevel@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>, Jan Kara <jack@suse.cz>
Subject: [PATCH 0/23 v2] mm: Speedup page cache truncation
Date: Wed, 22 Apr 2020 17:02:33 +0200 [thread overview]
Message-ID: <20200422150256.23473-1-jack@suse.cz> (raw)
Hello,
this is a second version of my patches to avoid clearing marks from xas_store()
and thus fix regression in page cache truncation.
Changes since v1
- rebased on 5.7-rc2
- drop xas_for_each_marked() fix as it was already merged
- reworked the whole series based on Matthew's feedback - we now create new
function xas_store_noinit() and use it instead of changing xas_store()
behavior. Note that for xas_store_range() and __xa_cmpxchg() I didn't bother
to change names although they stop clearing marks as well. This is because
there are only very few callers so it's easy to verify them, also chances of
a clash with other patch introducing new callers are very small.
Original motivation:
Conversion of page cache to xarray (commit 69b6c1319b6 "mm: Convert truncate to
XArray" in particular) has regressed performance of page cache truncation
by about 10% (see my original report here [1]). This patch series aims at
improving the truncation to get some of that regression back.
The first patch fixes a long standing bug with xas_for_each_marked() that I've
uncovered when debugging my patches. The remaining patches then work towards
the ability to stop clearing marks in xas_store() which improves truncation
performance by about 6%.
The patches have passed radix_tree tests in tools/testing and also fstests runs
for ext4 & xfs.
Honza
[1] https://lore.kernel.org/linux-mm/20190226165628.GB24711@quack2.suse.cz
next reply other threads:[~2020-04-22 15:06 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-22 15:02 Jan Kara [this message]
2020-04-22 15:02 ` [PATCH 01/23] xarray: Remove stale comment Jan Kara
2020-04-22 15:02 ` [PATCH 02/23] xarray: Provide xas_erase() and xas_store_noinit() helpers Jan Kara
2020-04-22 15:02 ` [PATCH 03/23] xarray: Use xas_store_noinit() in __xa_store, __xa_insert, __xa_alloc Jan Kara
2020-04-22 15:02 ` [PATCH 04/23] xarray: Switch xa_store_range() to use xas_store_noinit() Jan Kara
2020-04-22 15:02 ` [PATCH 05/23] xarray: Use xas_erase() in __xa_erase() Jan Kara
2020-04-22 15:02 ` [PATCH 06/23] xarray: Explicitely set XA_FREE_MARK in __xa_cmpxchg() Jan Kara
2020-04-22 15:02 ` [PATCH 07/23] xarray: Switch __xa_cmpxchg() to use xas_store_noinit() Jan Kara
2020-04-22 15:02 ` [PATCH 08/23] dax: Use xas_erase() in __dax_invalidate_entry() Jan Kara
2020-04-22 15:02 ` [PATCH 09/23] dax: Use dax_store_noinit() in grab_mapping_entry() Jan Kara
2020-04-22 15:02 ` [PATCH 10/23] dax: Convert xas_store() to xas_store_noinit() Jan Kara
2020-04-22 15:02 ` [PATCH 11/23] mm: Use xas_erase() in page_cache_delete_batch() Jan Kara
2020-04-22 15:02 ` [PATCH 12/23] mm: Use xas_erase() in collapse_file() Jan Kara
2020-04-22 15:02 ` [PATCH 13/23] mm: Use xas_store_noinit() when storing non-NULL Jan Kara
2020-04-22 15:02 ` [PATCH 14/23] workingset: Use xas_store_noinit() to clear shadow entry Jan Kara
2020-04-22 15:02 ` [PATCH 15/23] swap: Use xas_erase() when removing page from swap cache Jan Kara
2020-04-22 15:02 ` [PATCH 16/23] idr: Use xas_erase() in ida_destroy() Jan Kara
2020-04-22 15:02 ` [PATCH 17/23] idr: Use xas_erase() in ida_free() Jan Kara
2020-04-22 15:02 ` [PATCH 18/23] idr: Convert xas_store() to xas_store_noinit() Jan Kara
2020-04-22 15:02 ` [PATCH 19/23] testing: Use xas_erase() to remove entries from xarray Jan Kara
2020-04-22 15:02 ` [PATCH 20/23] testing: Use xas_store_noinit() for non-NULL entries Jan Kara
2020-04-22 15:02 ` [PATCH 21/23] testing: Introduce xa_erase_order() and use it Jan Kara
2020-04-22 15:02 ` [PATCH 22/23] testing: Switch xa_store_order() to xas_store_noinit() Jan Kara
2020-04-22 15:02 ` [PATCH 23/23] xarray: Remove xas_store() Jan Kara
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=20200422150256.23473-1-jack@suse.cz \
--to=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=willy@infradead.org \
/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).