From: Jeff Layton <jlayton@poochiereds.net>
To: bfields@fieldses.org
Cc: linux-nfs@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH v4 00/16] nfsd: open file caching
Date: Fri, 11 Sep 2015 06:54:26 -0400 [thread overview]
Message-ID: <1441968882-7851-1-git-send-email-jeff.layton@primarydata.com> (raw)
v4:
- squash some of the patches down into one patch to reduce churn
- close cached open files after unlink instead of before
- don't just close files after nfsd does an unlink, must do it
after any vfs-layer unlink. Use fsnotify to handle that.
- use a SRCU notifier chain for setlease
- add patch to allow non-kthreads to do a fput_sync
v3:
- open files are now hashed on inode pointer instead of fh
- eliminate the recurring workqueue job in favor of shrinker/LRU and
notifier from lease setting code
- have nfsv4 use the cache as well
- removal of raparms cache
v2:
- changelog cleanups and clarifications
- allow COMMIT to use cached open files
- tracepoints for nfsd_file cache
- proactively close open files prior to REMOVE, or a RENAME over a
positive dentry
This is the fourth iteration of the open file cache patches for nfsd.
There are some rather major changes here vs. the earlier sets,
particularly in how we close cached open files when there is vfs-layer
activity (unlinks or setlease calls in particular).
For those seeing this for the first time, main impetus here is to help
speed up NFSv3 I/O. nfsd will do an open+read/write+close for every READ
or WRITE RPC. This patchset allows us to cache those open files more or
less indefinitely, and close them out in response to certain vfs-layer
activity (unlinks and setlease attempts primarily).
The first few patches in the series make (small) changes to several
subsystems to enable the caching infrastructure. The 8th patch adds
the cache itself, and then the remaining patches hook the nfsd code
up to the cache. The final patch rips out the raparms cache since it's
no longer needed with these changes.
The most controversial piece here I think will be the 3rd patch in the
series which allows fput_sync to run in non-kthread context. This is
necessary to allow userland threads to close out cached nfsd files in
advance of setlease attempts. Al, I'd appreciate it if you could weigh
in on that one. I'm fine with adding more scary warnings to the comment
above it if you think it's warranted.
Jeff Layton (16):
locks: change tracepoint for generic_add_lease
list_lru: add list_lru_rotate
fs: allow __fput_sync to be used by non-kthreads and in modules
fsnotify: export several symbols
locks: create a new notifier chain for lease attempts
nfsd: move include of state.h from trace.c to trace.h
sunrpc: add a new cache_detail operation for when a cache is flushed
nfsd: add a new struct file caching facility to nfsd
nfsd: hook up nfsd_write to the new nfsd_file cache
nfsd: hook up nfsd_read to the nfsd_file cache
nfsd: hook nfsd_commit up to the nfsd_file cache
nfsd: convert nfs4_file->fi_fds array to use nfsd_files
nfsd: have nfsd_test_lock use the nfsd_file cache
nfsd: convert fi_deleg_file and ls_file fields to nfsd_file
nfsd: hook up nfs4_preprocess_stateid_op to the nfsd_file cache
nfsd: rip out the raparms cache
fs/file_table.c | 27 +-
fs/locks.c | 37 +++
fs/nfsd/Kconfig | 2 +
fs/nfsd/Makefile | 3 +-
fs/nfsd/export.c | 14 +
fs/nfsd/filecache.c | 552 ++++++++++++++++++++++++++++++++++++++++
fs/nfsd/filecache.h | 37 +++
fs/nfsd/nfs3proc.c | 2 +-
fs/nfsd/nfs4layouts.c | 12 +-
fs/nfsd/nfs4proc.c | 32 +--
fs/nfsd/nfs4state.c | 174 ++++++-------
fs/nfsd/nfs4xdr.c | 16 +-
fs/nfsd/nfsproc.c | 2 +-
fs/nfsd/nfssvc.c | 16 +-
fs/nfsd/state.h | 10 +-
fs/nfsd/trace.c | 2 -
fs/nfsd/trace.h | 129 ++++++++++
fs/nfsd/vfs.c | 220 +++-------------
fs/nfsd/vfs.h | 8 +-
fs/nfsd/xdr4.h | 15 +-
fs/notify/group.c | 2 +
fs/notify/mark.c | 3 +
include/linux/file.h | 2 +-
include/linux/fs.h | 1 +
include/linux/list_lru.h | 13 +
include/linux/sunrpc/cache.h | 1 +
include/trace/events/filelock.h | 38 ++-
kernel/acct.c | 2 +-
mm/list_lru.c | 15 ++
net/sunrpc/cache.c | 3 +
30 files changed, 1027 insertions(+), 363 deletions(-)
create mode 100644 fs/nfsd/filecache.c
create mode 100644 fs/nfsd/filecache.h
--
2.4.3
next reply other threads:[~2015-09-11 10:54 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-11 10:54 Jeff Layton [this message]
2015-09-11 10:54 ` [PATCH v4 01/16] locks: change tracepoint for generic_add_lease Jeff Layton
2015-09-11 10:54 ` [PATCH v4 02/16] list_lru: add list_lru_rotate Jeff Layton
2015-09-11 10:54 ` [PATCH v4 03/16] fs: allow __fput_sync to be used by non-kthreads and in modules Jeff Layton
[not found] ` <1441968882-7851-4-git-send-email-jeff.layton-7I+n7zu2hftEKMMhf/gKZA@public.gmane.org>
2015-09-11 14:00 ` Al Viro
[not found] ` <20150911140049.GN22011-3bDd1+5oDREiFSDQTTA3OLVCufUGDwFn@public.gmane.org>
2015-09-11 14:38 ` Jeff Layton
2015-09-11 10:54 ` [PATCH v4 04/16] fsnotify: export several symbols Jeff Layton
[not found] ` <1441968882-7851-1-git-send-email-jeff.layton-7I+n7zu2hftEKMMhf/gKZA@public.gmane.org>
2015-09-11 10:54 ` [PATCH v4 05/16] locks: create a new notifier chain for lease attempts Jeff Layton
2015-09-11 10:54 ` [PATCH v4 08/16] nfsd: add a new struct file caching facility to nfsd Jeff Layton
2015-09-11 10:54 ` [PATCH v4 09/16] nfsd: hook up nfsd_write to the new nfsd_file cache Jeff Layton
2015-09-11 10:54 ` [PATCH v4 10/16] nfsd: hook up nfsd_read to the " Jeff Layton
2015-09-11 10:54 ` [PATCH v4 11/16] nfsd: hook nfsd_commit up " Jeff Layton
2015-09-11 10:54 ` [PATCH v4 13/16] nfsd: have nfsd_test_lock use " Jeff Layton
2015-09-11 10:54 ` [PATCH v4 15/16] nfsd: hook up nfs4_preprocess_stateid_op to " Jeff Layton
2015-09-11 10:54 ` [PATCH v4 06/16] nfsd: move include of state.h from trace.c to trace.h Jeff Layton
2015-09-11 10:54 ` [PATCH v4 07/16] sunrpc: add a new cache_detail operation for when a cache is flushed Jeff Layton
2015-09-11 10:54 ` [PATCH v4 12/16] nfsd: convert nfs4_file->fi_fds array to use nfsd_files Jeff Layton
2015-09-11 10:54 ` [PATCH v4 14/16] nfsd: convert fi_deleg_file and ls_file fields to nfsd_file Jeff Layton
2015-09-11 10:54 ` [PATCH v4 16/16] nfsd: rip out the raparms cache Jeff Layton
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=1441968882-7851-1-git-send-email-jeff.layton@primarydata.com \
--to=jlayton@poochiereds.net \
--cc=bfields@fieldses.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.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).