From: Jan Kara <jack@suse.cz>
To: Wu Fengguang <fengguang.wu@intel.com>
Cc: linux-fsdevel@vger.kernel.org, Jan Kara <jack@suse.cz>,
Dave Chinner <david@fromorbit.com>,
Christoph Hellwig <hch@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/9] writeback: make writeback_control.nr_to_write straight
Date: Thu, 30 Jun 2011 18:24:57 +0200 [thread overview]
Message-ID: <20110630162457.GH28475@quack.suse.cz> (raw)
In-Reply-To: <20110629145553.642570515@intel.com>
On Wed 29-06-11 22:52:46, Wu Fengguang wrote:
> Pass struct wb_writeback_work all the way down to writeback_sb_inodes(),
> and initialize the struct writeback_control there.
>
> struct writeback_control is basically designed to control writeback of a
> single file, but we keep abuse it for writing multiple files in
> writeback_sb_inodes() and its callers.
>
> It immediately clean things up, e.g. suddenly wbc.nr_to_write vs
> work->nr_pages starts to make sense, and instead of saving and restoring
> pages_skipped in writeback_sb_inodes it can always start with a clean
> zero value.
>
> It also makes a neat IO pattern change: large dirty files are now
> written in the full 4MB writeback chunk size, rather than whatever
> remained quota in wbc->nr_to_write.
>
> Acked-by: Jan Kara <jack@suse.cz>
> Proposed-by: Christoph Hellwig <hch@infradead.org>
> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Just one minor nit:
> @@ -570,17 +622,25 @@ static int writeback_sb_inodes(struct su
> iput(inode);
> cond_resched();
> spin_lock(&wb->list_lock);
> - if (wbc->nr_to_write <= 0)
> - return 1;
> + /*
> + * bail out to wb_writeback() often enough to check
> + * background threshold and other termination conditions.
> + */
> + if (wrote) {
> + if (jiffies - start_time > HZ / 10UL)
> + break;
I guess this comparison should use time_before() macro - or maybe even
time_is_before_jiffies().
> + if (work->nr_pages <= 0)
> + break;
> + }
> }
> - /* b_io is empty */
> - return 1;
> + return wrote;
> }
>
> -static void __writeback_inodes_wb(struct bdi_writeback *wb,
> - struct writeback_control *wbc)
> +static long __writeback_inodes_wb(struct bdi_writeback *wb,
> + struct wb_writeback_work *work)
> {
> - int ret = 0;
> + unsigned long start_time = jiffies;
> + long wrote = 0;
>
> while (!list_empty(&wb->b_io)) {
> struct inode *inode = wb_inode(wb->b_io.prev);
> @@ -590,33 +650,37 @@ static void __writeback_inodes_wb(struct
> requeue_io(inode, wb);
> continue;
> }
> - ret = writeback_sb_inodes(sb, wb, wbc, false);
> + wrote += writeback_sb_inodes(sb, wb, work);
> drop_super(sb);
>
> - if (ret)
> - break;
> + /* refer to the same tests at the end of writeback_sb_inodes */
> + if (wrote) {
> + if (jiffies - start_time > HZ / 10UL)
> + break;
And the same here.
> + if (work->nr_pages <= 0)
> + break;
> + }
> }
> /* Leave any unwritten inodes on b_io */
> + return wrote;
> }
>
Honza
--
Jan Kara <jack@suse.cz>
SUSE Labs, CR
next prev parent reply other threads:[~2011-06-30 16:24 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-29 14:52 [PATCH 0/9] write bandwidth estimation and writeback fixes v2 Wu Fengguang
2011-06-29 14:52 ` [PATCH 1/9] writeback: make writeback_control.nr_to_write straight Wu Fengguang
2011-06-30 16:24 ` Jan Kara [this message]
2011-07-01 12:03 ` Wu Fengguang
2011-06-29 14:52 ` [PATCH 2/9] writeback: account per-bdi accumulated written pages Wu Fengguang
2011-06-29 14:52 ` [PATCH 3/9] writeback: bdi write bandwidth estimation Wu Fengguang
2011-06-30 19:56 ` Jan Kara
2011-07-01 14:58 ` Wu Fengguang
2011-07-04 3:05 ` Wu Fengguang
2011-07-13 23:30 ` Jan Kara
2011-07-23 7:26 ` Wu Fengguang
2011-07-01 15:20 ` Andrea Righi
2011-07-08 11:53 ` Wu Fengguang
2011-07-01 18:32 ` Vivek Goyal
2011-07-23 8:02 ` Wu Fengguang
2011-07-01 19:19 ` Vivek Goyal
2011-07-01 19:29 ` Vivek Goyal
2011-07-23 8:07 ` Wu Fengguang
2011-06-29 14:52 ` [PATCH 4/9] writeback: show bdi write bandwidth in debugfs Wu Fengguang
2011-06-29 14:52 ` [PATCH 5/9] writeback: consolidate variable names in balance_dirty_pages() Wu Fengguang
2011-06-30 17:26 ` Jan Kara
2011-06-29 14:52 ` [PATCH 6/9] writeback: introduce smoothed global dirty limit Wu Fengguang
2011-07-01 15:20 ` Andrea Righi
2011-07-08 11:51 ` Wu Fengguang
2011-06-29 14:52 ` [PATCH 7/9] writeback: introduce max-pause and pass-good dirty limits Wu Fengguang
2011-06-29 14:52 ` [PATCH 8/9] writeback: scale IO chunk size up to half device bandwidth Wu Fengguang
2011-06-29 14:52 ` [PATCH 9/9] writeback: trace global_dirty_state Wu Fengguang
2011-07-01 15:18 ` Christoph Hellwig
2011-07-01 15:45 ` Wu Fengguang
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=20110630162457.GH28475@quack.suse.cz \
--to=jack@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=fengguang.wu@intel.com \
--cc=hch@infradead.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@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).