From: Max Kellermann <max.kellermann@ionos.com>
To: tytso@mit.edu, adilger.kernel@dilger.ca,
libaokun@linux.alibaba.com, jack@suse.cz, ojaswin@linux.ibm.com,
ritesh.list@gmail.com, yi.zhang@huawei.com,
linux-ext4@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Max Kellermann <max.kellermann@ionos.com>
Subject: [PATCH 0/3] ext4: reduce per-inode memory overhead
Date: Wed, 11 Nov 2026 13:52:39 +0100 [thread overview]
Message-ID: <20261111125242.1078620-1-max.kellermann@ionos.com> (raw)
This series reduces the size of `struct ext4_inode_info` by improving
timestamp packing and allowing fast commit and bigalloc support to be
omitted at compile time.
The incremental reductions are:
Disable CONFIG_EXT4_FS_FAST_COMMIT 48 bytes
Disable CONFIG_EXT4_FS_BIGALLOC 8 bytes
Compact creation time, with fast commit off 8 bytes
--------
Total 64 bytes
On our production server with 35 million ext4 inode objects (a big
fscache partition), this saves 2.1 GB RAM.
Both new Kconfig options default to enabled. Without fast commit
support, clean filesystems use ordinary journal commits; journals
requiring fast commit recovery are rejected. Without bigalloc
support, bigalloc filesystems are rejected before journal recovery,
including for read-only mounts.
Max Kellermann (3):
ext4: make fast commit support optional
ext4: make bigalloc support optional
ext4: store creation time in separate seconds and nanoseconds
Documentation/filesystems/ext4/bigalloc.rst | 6 ++
Documentation/filesystems/ext4/journal.rst | 7 ++
fs/ext4/Kconfig | 31 ++++++++
fs/ext4/Makefile | 3 +-
fs/ext4/ext4.h | 83 +++++++++++++++++++--
fs/ext4/extents_status.c | 44 ++++++++++-
fs/ext4/extents_status.h | 15 ++++
fs/ext4/ialloc.c | 3 +-
fs/ext4/inode.c | 8 +-
fs/ext4/super.c | 40 ++++++++--
fs/ext4/sysfs.c | 6 ++
include/trace/events/ext4.h | 3 +
12 files changed, 227 insertions(+), 22 deletions(-)
--
2.53.0
next reply other threads:[~2026-11-11 12:52 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-11 12:52 Max Kellermann [this message]
2026-11-11 12:52 ` [PATCH 1/3] ext4: make fast commit support optional Max Kellermann
2026-11-11 12:52 ` [PATCH 2/3] ext4: make bigalloc " Max Kellermann
2026-11-11 12:52 ` [PATCH 3/3] ext4: store creation time in separate seconds and nanoseconds Max Kellermann
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=20261111125242.1078620-1-max.kellermann@ionos.com \
--to=max.kellermann@ionos.com \
--cc=adilger.kernel@dilger.ca \
--cc=jack@suse.cz \
--cc=libaokun@linux.alibaba.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ojaswin@linux.ibm.com \
--cc=ritesh.list@gmail.com \
--cc=tytso@mit.edu \
--cc=yi.zhang@huawei.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
all inboxes | Powered by JetHome®