From: Jens Axboe <jens.axboe@oracle.com>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, torvalds@linux-foundation.org
Subject: Re: [rfc patch 4/4] splice: use do_generic_file_read()
Date: Tue, 24 Jun 2008 10:05:57 +0200 [thread overview]
Message-ID: <20080624080557.GK20851@kernel.dk> (raw)
In-Reply-To: <20080621154727.808329488@szeredi.hu>
On Sat, Jun 21 2008, Miklos Szeredi wrote:
> From: Miklos Szeredi <mszeredi@suse.cz>
>
> __generic_file_splice_read() duplicates a lot of stuff common with the
> generic page cache reading. So reuse that code instead to simplify
> the page cache splice code.
>
> This also fixes some corner cases which weren't properly handled in
> the splice code because of complexity issues. In particular it fixes
> a problem when the filesystem (e.g. fuse) invalidates pages during the
> splice operation.
>
> There might be some slight fall in performance due to the removal of
> the gang lookup for pages. However I'm not sure if this is
> significant enough to warrant the extra complication.
This makes everything sync, it's a no go. Why don't we look into fixing
the invalidate problem that fuse sees (can you elaborate on that?)?
I tried to do a quick performance test with your patches for comparison
in the cached case, but it crashes immediately in spd_release_page()
--
Jens Axboe
WARNING: multiple messages have this Message-ID (diff)
From: Jens Axboe <jens.axboe@oracle.com>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, torvalds@linux-foundation.org
Subject: Re: [rfc patch 4/4] splice: use do_generic_file_read()
Date: Tue, 24 Jun 2008 10:05:57 +0200 [thread overview]
Message-ID: <20080624080557.GK20851@kernel.dk> (raw)
In-Reply-To: <20080621154727.808329488@szeredi.hu>
On Sat, Jun 21 2008, Miklos Szeredi wrote:
> From: Miklos Szeredi <mszeredi@suse.cz>
>
> __generic_file_splice_read() duplicates a lot of stuff common with the
> generic page cache reading. So reuse that code instead to simplify
> the page cache splice code.
>
> This also fixes some corner cases which weren't properly handled in
> the splice code because of complexity issues. In particular it fixes
> a problem when the filesystem (e.g. fuse) invalidates pages during the
> splice operation.
>
> There might be some slight fall in performance due to the removal of
> the gang lookup for pages. However I'm not sure if this is
> significant enough to warrant the extra complication.
This makes everything sync, it's a no go. Why don't we look into fixing
the invalidate problem that fuse sees (can you elaborate on that?)?
I tried to do a quick performance test with your patches for comparison
in the cached case, but it crashes immediately in spd_release_page()
--
Jens Axboe
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2008-06-24 8:06 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-06-21 15:46 [rfc patch 0/4] splice: cleanups and fixes Miklos Szeredi
2008-06-21 15:46 ` Miklos Szeredi
2008-06-21 15:46 ` [rfc patch 1/4] splice: fix comment Miklos Szeredi
2008-06-21 15:46 ` Miklos Szeredi, Miklos Szeredi
2008-06-21 15:46 ` [rfc patch 2/4] splice: remove steal from pipe_buf_operations Miklos Szeredi
2008-06-21 15:46 ` Miklos Szeredi, Miklos Szeredi
2008-06-24 8:01 ` Jens Axboe
2008-06-24 8:01 ` Jens Axboe
2008-06-24 8:50 ` Miklos Szeredi
2008-06-24 8:50 ` Miklos Szeredi
2008-06-24 12:21 ` Nick Piggin
2008-06-24 12:21 ` Nick Piggin
2008-06-21 15:46 ` [rfc patch 3/4] splice: remove confirm " Miklos Szeredi
2008-06-21 15:46 ` Miklos Szeredi, Miklos Szeredi
2008-06-24 8:04 ` Jens Axboe
2008-06-24 8:04 ` Jens Axboe
2008-06-24 8:54 ` Miklos Szeredi
2008-06-24 8:54 ` Miklos Szeredi
2008-06-24 11:19 ` Jens Axboe
2008-06-24 11:19 ` Jens Axboe
2008-06-24 11:36 ` Miklos Szeredi
2008-06-24 11:36 ` Miklos Szeredi
2008-06-24 11:46 ` Evgeniy Polyakov
2008-06-24 11:46 ` Evgeniy Polyakov
2008-06-24 12:02 ` Miklos Szeredi
2008-06-24 12:02 ` Miklos Szeredi
2008-06-24 12:15 ` Evgeniy Polyakov
2008-06-24 12:15 ` Evgeniy Polyakov
2008-06-24 12:16 ` Nick Piggin
2008-06-24 12:16 ` Nick Piggin
2008-06-24 12:22 ` Jens Axboe
2008-06-24 12:22 ` Jens Axboe
2008-06-24 13:00 ` Miklos Szeredi
2008-06-24 13:00 ` Miklos Szeredi
2008-06-24 17:30 ` Linus Torvalds
2008-06-24 17:30 ` Linus Torvalds
2008-06-24 18:24 ` Miklos Szeredi
2008-06-24 18:24 ` Miklos Szeredi
2008-06-24 18:31 ` Linus Torvalds
2008-06-24 18:31 ` Linus Torvalds
2008-06-24 19:05 ` Miklos Szeredi
2008-06-24 19:05 ` Miklos Szeredi
2008-06-24 19:17 ` Linus Torvalds
2008-06-24 19:17 ` Linus Torvalds
2008-06-24 19:24 ` Miklos Szeredi
2008-06-24 19:24 ` Miklos Szeredi
2008-06-24 19:26 ` Miklos Szeredi
2008-06-24 19:26 ` Miklos Szeredi
2008-06-24 19:32 ` Miklos Szeredi
2008-06-24 19:32 ` Miklos Szeredi
2008-06-24 19:47 ` Linus Torvalds
2008-06-24 19:47 ` Linus Torvalds
2008-06-24 20:06 ` Miklos Szeredi
2008-06-24 20:06 ` Miklos Szeredi
2008-06-24 19:45 ` Linus Torvalds
2008-06-24 19:45 ` Linus Torvalds
2008-06-21 15:46 ` [rfc patch 4/4] splice: use do_generic_file_read() Miklos Szeredi
2008-06-21 15:46 ` Miklos Szeredi, Miklos Szeredi
2008-06-24 8:05 ` Jens Axboe [this message]
2008-06-24 8:05 ` Jens Axboe
2008-06-24 11:11 ` Miklos Szeredi
2008-06-24 11:11 ` Miklos Szeredi
2008-06-21 17:20 ` [rfc patch 0/4] splice: cleanups and fixes Subrata Modak
2008-06-22 6:16 ` Miklos Szeredi
2008-06-23 15:26 ` Subrata Modak
2008-06-25 13:17 ` [LTP] " Subrata Modak
2008-06-25 14:00 ` Miklos Szeredi
[not found] ` <E1KBVXV-000618-C9-8f8m9JG5TPIdUIPVzhDTVZP2KDSNp7ea@public.gmane.org>
2008-06-26 7:34 ` Subrata Modak
2008-10-22 12:41 ` [LTP] " Subrata Modak
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=20080624080557.GK20851@kernel.dk \
--to=jens.axboe@oracle.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=miklos@szeredi.hu \
--cc=torvalds@linux-foundation.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.