All of lore.kernel.org
 help / color / mirror / Atom feed
From: Pavel Emelyanov <xemul-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
To: fuse-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
	Miklos Szeredi <miklos-sUDqSbJrdHQHWmgEVkV9KA@public.gmane.org>,
	Alexander Viro
	<viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org>,
	linux-fsdevel
	<linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Cc: Kirill Korotaev <dev-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>,
	James Bottomley
	<jbottomley-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
Subject: [PATCH 9/10] fuse: Turn writeback on
Date: Tue, 03 Jul 2012 19:57:09 +0400	[thread overview]
Message-ID: <4FF31655.2050900@parallels.com> (raw)
In-Reply-To: <4FF3156E.8030109-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>

Introduce a bit kernel and userspace exchange between each-other on
the init stage and turn writeback on if the userspace want this.

Also add each writable file into per-inode write list and call the
generic_file_aio_write to make use of the Linux page cache engine.

Signed-off-by: Pavel Emelyanov <xemul-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
---
 fs/fuse/file.c       |    5 +++++
 fs/fuse/inode.c      |    4 +++-
 include/linux/fuse.h |    1 +
 3 files changed, 9 insertions(+), 1 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 058498d..e3a1cc8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -209,6 +209,8 @@ void fuse_finish_open(struct inode *inode, struct file *file)
 		spin_unlock(&fc->lock);
 		fuse_invalidate_attr(inode);
 	}
+	if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache)
+		fuse_link_write_file(file);
 }
 
 int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
@@ -999,6 +1001,9 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	struct iov_iter i;
 	loff_t endbyte = 0;
 
+	if (get_fuse_conn(inode)->writeback_cache)
+		return generic_file_aio_write(iocb, iov, nr_segs, pos);
+
 	WARN_ON(iocb->ki_pos != pos);
 
 	ocount = 0;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 88c577f..df1dc83 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -836,6 +836,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				fc->big_writes = 1;
 			if (arg->flags & FUSE_DONT_MASK)
 				fc->dont_mask = 1;
+			if (arg->flags & FUSE_WRITEBACK_CACHE)
+				fc->writeback_cache = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
 			fc->no_lock = 1;
@@ -861,7 +863,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 	arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
 		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
-		FUSE_FLOCK_LOCKS;
+		FUSE_FLOCK_LOCKS | FUSE_WRITEBACK_CACHE;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index 9303348..7ed5ced 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -176,6 +176,7 @@ struct fuse_file_lock {
 #define FUSE_BIG_WRITES		(1 << 5)
 #define FUSE_DONT_MASK		(1 << 6)
 #define FUSE_FLOCK_LOCKS	(1 << 10)
+#define FUSE_WRITEBACK_CACHE	(1 << 11)
 
 /**
  * CUSE INIT request/reply flags
-- 
1.5.5.6

------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and 
threat landscape has changed and how IT managers can respond. Discussions 
will include endpoint security, mobile security and the latest in malware 
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/

  parent reply	other threads:[~2012-07-03 15:57 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-07-03 15:53 [PATCH 0/10] fuse: An attempt to implement a write-back cache policy Pavel Emelyanov
2012-07-03 15:53 ` [PATCH 1/10] fuse: Linking file to inode helper Pavel Emelyanov
2012-07-03 15:54 ` [PATCH 2/10] fuse: Getting file for writeback helper Pavel Emelyanov
2012-07-03 15:54 ` [PATCH 3/10] fuse: Prepare to handle short reads Pavel Emelyanov
2012-07-03 15:55 ` [PATCH 4/10] fuse: Prepare to handle multiple pages in writeback Pavel Emelyanov
2012-07-04 13:06   ` Miklos Szeredi
2012-07-04 14:26     ` Pavel Emelyanov
     [not found] ` <4FF3156E.8030109-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2012-07-03 15:55   ` [PATCH 5/10] fuse: Connection bit for enabling writeback Pavel Emelyanov
2012-07-03 15:56   ` [PATCH 7/10] fuse: Flush files on wb close Pavel Emelyanov
2012-07-03 15:56   ` [PATCH 8/10] fuse: Implement writepages and write_begin/write_end callbacks Pavel Emelyanov
2012-07-03 15:57   ` Pavel Emelyanov [this message]
2012-07-04  3:01   ` [PATCH 0/10] fuse: An attempt to implement a write-back cache policy Nikolaus Rath
     [not found]     ` <87a9zg1b7q.fsf-sKB8Sp2ER+yL2G7IJ6k9tw@public.gmane.org>
2012-07-04  7:11       ` Pavel Emelyanov
2012-07-04 13:22         ` Nikolaus Rath
     [not found]           ` <4FF4438B.8050807-BTH8mxji4b0@public.gmane.org>
2012-07-04 14:33             ` Pavel Emelyanov
     [not found]               ` <4FF45447.5000705-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2012-07-04 17:08                 ` Nikolaus Rath
2012-07-05  9:01                   ` Pavel Emelyanov
2012-07-05 13:07         ` Nikolaus Rath
2012-07-05 14:08           ` Pavel Emelyanov
2012-07-05 14:29             ` Nikolaus Rath
2012-07-05 14:34               ` Pavel Emelyanov
2012-07-06  2:04                 ` Nikolaus Rath
     [not found]                   ` <8762a1odbf.fsf-sKB8Sp2ER+yL2G7IJ6k9tw@public.gmane.org>
2012-07-06  8:46                     ` Pavel Emelyanov
2012-07-05 19:31   ` Anand Avati
     [not found]     ` <4FF5EB85.1050701-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2012-07-05 20:07       ` Pavel Emelyanov
2012-07-06 11:52         ` [fuse-devel] " Kirill Korotaev
2012-07-03 15:55 ` [PATCH 6/10] fuse: Trust kernel i_size only Pavel Emelyanov
2012-07-04 14:39   ` Miklos Szeredi
2012-07-05 14:10     ` Pavel Emelyanov
2012-07-10  5:53     ` Pavel Emelyanov
2012-07-13 16:30       ` Miklos Szeredi
2012-07-16  3:32         ` Pavel Emelyanov
2012-07-17 15:17           ` Miklos Szeredi
     [not found]     ` <8762a3pp3m.fsf-d8RdFUjzFsbxNFs70CDYszOMxtEWgIxa@public.gmane.org>
2012-10-01 17:30       ` Maxim V. Patlasov
2012-11-16  9:49         ` Miklos Szeredi
2012-11-16 10:32           ` Maxim V. Patlasov
2012-07-03 15:57 ` [PATCH 10/10] mm: Account for WRITEBACK_TEMP in balance_dirty_pages Pavel Emelyanov
     [not found]   ` <4FF3166B.5090800-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2012-07-13 16:57     ` Miklos Szeredi
2012-07-16  3:27       ` Pavel Emelyanov
2012-07-17 19:11         ` Miklos Szeredi
2012-07-27  4:01           ` Pavel Emelyanov
     [not found]             ` <5012127C.8070203-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2012-08-07 17:30               ` Miklos Szeredi
2012-07-05 19:26 ` [fuse-devel] [PATCH 0/10] fuse: An attempt to implement a write-back cache policy Anand Avati

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=4FF31655.2050900@parallels.com \
    --to=xemul-bzqdu9zft3wakbo8gow8eq@public.gmane.org \
    --cc=dev-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org \
    --cc=fuse-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org \
    --cc=jbottomley-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org \
    --cc=linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=miklos-sUDqSbJrdHQHWmgEVkV9KA@public.gmane.org \
    --cc=viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.