linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Theodore Tso <tytso@mit.edu>,
	Christoph Hellwig <hch@infradead.org>,
	Dave Chinner <david@fromorbit.com>,
	Chris Mason <chris.mason@oracle.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	"Li Shaohua" <shaohua.li@intel.com>,
	"Myklebust Trond" <Trond.Myklebust@netapp.com>,
	"jens.axboe@oracle.com" <jens.axboe@oracle.com>,
	Jan Kara <jack@suse.cz>, Nick Piggin <npiggin@suse.de>,
	<linux-fsdevel@vger.kernel.org>,
	Wu Fengguang <fengguang.wu@intel.com>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 26/45] block: pass the non-rotational queue flag to backing_dev_info
Date: Wed, 07 Oct 2009 15:38:44 +0800	[thread overview]
Message-ID: <20091007074904.473079627@intel.com> (raw)
In-Reply-To: 20091007073818.318088777@intel.com

[-- Attachment #1: block-bdi-nonrot.patch --]
[-- Type: text/plain, Size: 5313 bytes --]

For now only pass the non-rotational bit to the queue's bdi.

To support hierarchical dm/md configurations, blk_set_rotational()
shall be expanded to make several iterations of the bdi list and call
its bdi->rotational_fn to pass the bit up.  But that would imply we
don's support mixed SSD/HD arrays.

CC: Jens Axboe <jens.axboe@oracle.com> 
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
 block/blk-core.c             |   14 ++++++++++++++
 block/blk-sysfs.c            |    7 +------
 drivers/block/nbd.c          |    2 +-
 drivers/block/xen-blkfront.c |    1 +
 drivers/mmc/card/queue.c     |    2 +-
 drivers/scsi/sd.c            |    2 +-
 include/linux/backing-dev.h  |    8 ++++++++
 include/linux/blkdev.h       |    1 +
 8 files changed, 28 insertions(+), 9 deletions(-)

--- linux.orig/block/blk-sysfs.c	2009-10-06 23:37:44.000000000 +0800
+++ linux/block/blk-sysfs.c	2009-10-06 23:39:26.000000000 +0800
@@ -162,12 +162,7 @@ static ssize_t queue_nonrot_store(struct
 	unsigned long nm;
 	ssize_t ret = queue_var_store(&nm, page, count);
 
-	spin_lock_irq(q->queue_lock);
-	if (nm)
-		queue_flag_clear(QUEUE_FLAG_NONROT, q);
-	else
-		queue_flag_set(QUEUE_FLAG_NONROT, q);
-	spin_unlock_irq(q->queue_lock);
+	blk_set_rotational(q, nm);
 
 	return ret;
 }
--- linux.orig/include/linux/backing-dev.h	2009-10-06 23:38:44.000000000 +0800
+++ linux/include/linux/backing-dev.h	2009-10-06 23:39:26.000000000 +0800
@@ -29,6 +29,7 @@ enum bdi_state {
 	BDI_wb_alloc,		/* Default embedded wb allocated */
 	BDI_async_congested,	/* The async (write) queue is getting full */
 	BDI_sync_congested,	/* The sync queue is getting full */
+	BDI_non_rotational,	/* Underlying device is SSD or virtual */
 	BDI_registered,		/* bdi_register() was done */
 	BDI_unused,		/* Available bits start here */
 };
@@ -254,6 +255,8 @@ int bdi_set_max_ratio(struct backing_dev
 #define BDI_CAP_NO_ACCT_WB	0x00000080
 #define BDI_CAP_SWAP_BACKED	0x00000100
 
+#define BDI_CAP_NONROT		0x00000200
+
 #define BDI_CAP_VMFLAGS \
 	(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
 
@@ -291,6 +294,11 @@ static inline int can_submit_background_
        return !test_and_set_bit(WB_FLAG_BACKGROUND_WORK, &bdi->wb_mask);
 }
 
+static inline bool bdi_nonrot(struct backing_dev_info *bdi)
+{
+	return bdi->state & (1 << BDI_non_rotational);
+}
+
 static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 {
 	if (bdi->congested_fn)
--- linux.orig/block/blk-core.c	2009-10-06 23:37:44.000000000 +0800
+++ linux/block/blk-core.c	2009-10-06 23:39:26.000000000 +0800
@@ -2486,6 +2486,20 @@ free_and_out:
 }
 EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
 
+void blk_set_rotational(struct request_queue *q, int rotational)
+{
+	spin_lock_irq(q->queue_lock);
+	if (rotational) {
+		queue_flag_clear(QUEUE_FLAG_NONROT, q);
+		clear_bit(BDI_non_rotational, &q->backing_dev_info.state);
+	} else {
+		queue_flag_set(QUEUE_FLAG_NONROT, q);
+		set_bit(BDI_non_rotational, &q->backing_dev_info.state);
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_set_rotational);
+
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 {
 	return queue_work(kblockd_workqueue, work);
--- linux.orig/include/linux/blkdev.h	2009-10-06 23:37:44.000000000 +0800
+++ linux/include/linux/blkdev.h	2009-10-06 23:39:26.000000000 +0800
@@ -666,6 +666,7 @@ static inline void blk_clear_queue_full(
 		queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q);
 }
 
+void blk_set_rotational(struct request_queue *q, int rotational);
 
 /*
  * mergeable request must not have _NOMERGE or _BARRIER bit set, nor may
--- linux.orig/drivers/block/nbd.c	2009-10-06 23:37:44.000000000 +0800
+++ linux/drivers/block/nbd.c	2009-10-06 23:39:26.000000000 +0800
@@ -772,7 +772,7 @@ static int __init nbd_init(void)
 		/*
 		 * Tell the block layer that we are not a rotational device
 		 */
-		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
+		blk_set_rotational(disk->queue, 0);
 	}
 
 	if (register_blkdev(NBD_MAJOR, "nbd")) {
--- linux.orig/drivers/block/xen-blkfront.c	2009-10-06 23:37:44.000000000 +0800
+++ linux/drivers/block/xen-blkfront.c	2009-10-06 23:39:26.000000000 +0800
@@ -342,6 +342,7 @@ static int xlvbd_init_blk_queue(struct g
 		return -1;
 
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+	blk_set_rotational(rq, 0);
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
 	blk_queue_logical_block_size(rq, sector_size);
--- linux.orig/drivers/mmc/card/queue.c	2009-10-06 23:37:44.000000000 +0800
+++ linux/drivers/mmc/card/queue.c	2009-10-06 23:39:26.000000000 +0800
@@ -127,7 +127,7 @@ int mmc_init_queue(struct mmc_queue *mq,
 
 	blk_queue_prep_rq(mq->queue, mmc_prep_request);
 	blk_queue_ordered(mq->queue, QUEUE_ORDERED_DRAIN, NULL);
-	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
+	blk_set_rotational(mq->queue, 0);
 
 #ifdef CONFIG_MMC_BLOCK_BOUNCE
 	if (host->max_hw_segs == 1) {
--- linux.orig/drivers/scsi/sd.c	2009-10-06 23:37:44.000000000 +0800
+++ linux/drivers/scsi/sd.c	2009-10-06 23:39:26.000000000 +0800
@@ -1898,7 +1898,7 @@ static void sd_read_block_characteristic
 	rot = get_unaligned_be16(&buffer[4]);
 
 	if (rot == 1)
-		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, sdkp->disk->queue);
+		blk_set_rotational(sdkp->disk->queue, 0);
 
 	kfree(buffer);
 }

  parent reply	other threads:[~2009-10-07  7:38 UTC|newest]

Thread overview: 116+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-10-07  7:38 [PATCH 00/45] some writeback experiments Wu Fengguang
2009-10-07  7:38 ` [PATCH 01/45] writeback: reduce calls to global_page_state in balance_dirty_pages() Wu Fengguang
2009-10-09 15:12   ` Jan Kara
2009-10-09 15:18     ` Peter Zijlstra
2009-10-09 15:47       ` Jan Kara
2009-10-11  2:28         ` Wu Fengguang
2009-10-11  7:44           ` Peter Zijlstra
2009-10-11 10:50             ` Wu Fengguang
2009-10-11 10:58               ` Peter Zijlstra
2009-10-11 11:25               ` Peter Zijlstra
2009-10-12  1:26                 ` Wu Fengguang
2009-10-12  9:07                   ` Peter Zijlstra
2009-10-12  9:24                     ` Wu Fengguang
2009-10-10 21:33     ` Wu Fengguang
2009-10-12 21:18       ` Jan Kara
2009-10-13  3:24         ` Wu Fengguang
2009-10-13  8:41           ` Peter Zijlstra
2009-10-13 18:12           ` Jan Kara
2009-10-13 18:28             ` Peter Zijlstra
2009-10-14  1:38               ` Wu Fengguang
2009-10-14 11:22                 ` Peter Zijlstra
2009-10-17  5:30                   ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 02/45] writeback: reduce calculation of bdi dirty thresholds Wu Fengguang
2009-10-07  7:38 ` [PATCH 03/45] ext4: remove unused parameter wbc from __ext4_journalled_writepage() Wu Fengguang
2009-10-07  7:38 ` [PATCH 04/45] writeback: remove unused nonblocking and congestion checks Wu Fengguang
2009-10-09 15:26   ` Jan Kara
2009-10-10 13:47     ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 05/45] writeback: remove the always false bdi_cap_writeback_dirty() test Wu Fengguang
2009-10-07  7:38 ` [PATCH 06/45] writeback: use larger ratelimit when dirty_exceeded Wu Fengguang
2009-10-07  8:53   ` Peter Zijlstra
2009-10-07  9:17     ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 07/45] writeback: dont redirty tail an inode with dirty pages Wu Fengguang
2009-10-09 15:45   ` Jan Kara
2009-10-07  7:38 ` [PATCH 08/45] writeback: quit on wrap for .range_cyclic (write_cache_pages) Wu Fengguang
2009-10-07  7:38 ` [PATCH 09/45] writeback: quit on wrap for .range_cyclic (pohmelfs) Wu Fengguang
2009-10-07 12:32   ` Evgeniy Polyakov
2009-10-07 14:23     ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 10/45] writeback: quit on wrap for .range_cyclic (btrfs) Wu Fengguang
2009-10-07  7:38 ` [PATCH 11/45] writeback: quit on wrap for .range_cyclic (cifs) Wu Fengguang
2009-10-07  7:38 ` [PATCH 12/45] writeback: quit on wrap for .range_cyclic (ext4) Wu Fengguang
2009-10-07  7:38 ` [PATCH 13/45] writeback: quit on wrap for .range_cyclic (gfs2) Wu Fengguang
2009-10-07  7:38 ` [PATCH 14/45] writeback: quit on wrap for .range_cyclic (afs) Wu Fengguang
2009-10-07  7:38 ` [PATCH 15/45] writeback: fix queue_io() ordering Wu Fengguang
2009-10-07  7:38 ` [PATCH 16/45] writeback: merge for_kupdate and !for_kupdate cases Wu Fengguang
2009-10-07  7:38 ` [PATCH 17/45] writeback: only allow two background writeback works Wu Fengguang
2009-10-07  7:38 ` [PATCH 18/45] writeback: introduce wait queue for balance_dirty_pages() Wu Fengguang
2009-10-08  1:01   ` KAMEZAWA Hiroyuki
2009-10-08  1:58     ` Wu Fengguang
2009-10-08  2:40       ` KAMEZAWA Hiroyuki
2009-10-08  4:01         ` Wu Fengguang
2009-10-08  5:59           ` KAMEZAWA Hiroyuki
2009-10-08  6:07             ` Wu Fengguang
2009-10-08  6:28             ` Wu Fengguang
2009-10-08  6:39               ` KAMEZAWA Hiroyuki
2009-10-08  8:08       ` Peter Zijlstra
2009-10-08  8:11         ` KAMEZAWA Hiroyuki
2009-10-08  8:36         ` Jens Axboe
2009-10-09  2:52           ` [PATCH] writeback: account IO throttling wait as iowait Wu Fengguang
2009-10-09 10:41             ` Jens Axboe
2009-10-09 10:58               ` Wu Fengguang
2009-10-09 11:01                 ` Jens Axboe
2009-10-08  8:05     ` [PATCH 18/45] writeback: introduce wait queue for balance_dirty_pages() Peter Zijlstra
2009-10-07  7:38 ` [PATCH 19/45] writeback: remove the loop in balance_dirty_pages() Wu Fengguang
2009-10-07  7:38 ` [PATCH 20/45] NFS: introduce writeback wait queue Wu Fengguang
2009-10-07  8:53   ` Peter Zijlstra
2009-10-07  9:07     ` Wu Fengguang
2009-10-07  9:15       ` Peter Zijlstra
2009-10-07  9:19         ` Wu Fengguang
2009-10-07  9:17       ` Nick Piggin
2009-10-07  9:52         ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 21/45] writeback: estimate bdi write bandwidth Wu Fengguang
2009-10-07  8:53   ` Peter Zijlstra
2009-10-07  9:39     ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 22/45] writeback: show bdi write bandwidth in debugfs Wu Fengguang
2009-10-07  7:38 ` [PATCH 23/45] writeback: kill space in debugfs item name Wu Fengguang
2009-10-07  7:38 ` [PATCH 24/45] writeback: remove global nr_to_write and use timeout instead Wu Fengguang
2009-10-07  7:38 ` [PATCH 25/45] writeback: convert wbc.nr_to_write to per-file parameter Wu Fengguang
2009-10-07  7:38 ` Wu Fengguang [this message]
2009-10-07  7:38 ` [PATCH 27/45] writeback: introduce wbc.for_background Wu Fengguang
2009-10-07  7:38 ` [PATCH 28/45] writeback: introduce wbc.nr_segments Wu Fengguang
2009-10-07  7:38 ` [PATCH 29/45] writeback: fix the shmem AOP_WRITEPAGE_ACTIVATE case Wu Fengguang
2009-10-07 11:57   ` Hugh Dickins
2009-10-07 14:00     ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 30/45] vmscan: lumpy pageout Wu Fengguang
2009-10-07  7:38 ` [PATCH 31/45] writeback: sync old inodes first in background writeback Wu Fengguang
2010-07-12  3:01   ` Christoph Hellwig
2010-07-12 15:24     ` Wu Fengguang
2009-10-07  7:38 ` [PATCH 32/45] writeback: update kupdate expire timestamp on each scan of b_io Wu Fengguang
2009-10-07  7:38 ` [PATCH 34/45] writeback: sync livelock - kick background writeback Wu Fengguang
2009-10-07  7:38 ` [PATCH 35/45] writeback: sync livelock - use single timestamp for whole sync work Wu Fengguang
2009-10-07  7:38 ` [PATCH 36/45] writeback: sync livelock - curb dirty speed for inodes to be synced Wu Fengguang
2009-10-07  7:38 ` [PATCH 37/45] writeback: use timestamp to indicate dirty exceeded Wu Fengguang
2009-10-07  7:38 ` [PATCH 38/45] writeback: introduce queue b_more_io_wait Wu Fengguang
2009-10-07  7:38 ` [PATCH 39/45] writeback: remove wbc.more_io Wu Fengguang
2009-10-07  7:38 ` [PATCH 40/45] writeback: requeue_io_wait() on I_SYNC locked inode Wu Fengguang
2009-10-07  7:38 ` [PATCH 41/45] writeback: requeue_io_wait() on pages_skipped inode Wu Fengguang
2009-10-07  7:39 ` [PATCH 42/45] writeback: requeue_io_wait() on blocked inode Wu Fengguang
2009-10-07  7:39 ` [PATCH 43/45] writeback: requeue_io_wait() on fs redirtied inode Wu Fengguang
2009-10-07  7:39 ` [PATCH 44/45] NFS: remove NFS_INO_FLUSHING lock Wu Fengguang
2009-10-07 13:11   ` Peter Staubach
2009-10-07 13:32     ` Wu Fengguang
2009-10-07 13:59       ` Peter Staubach
2009-10-08  1:44         ` Wu Fengguang
2009-10-07  7:39 ` [PATCH 45/45] btrfs: fix race on syncing the btree inode Wu Fengguang
2009-10-07  8:53 ` [PATCH 00/45] some writeback experiments Peter Zijlstra
2009-10-07 10:17 ` [PATCH 14/45] writeback: quit on wrap for .range_cyclic (afs) David Howells
2009-10-07 10:21   ` Nick Piggin
2009-10-07 10:47     ` Wu Fengguang
2009-10-07 11:23       ` Nick Piggin
2009-10-07 12:21         ` Wu Fengguang
2009-10-07 13:47 ` [PATCH 00/45] some writeback experiments Peter Staubach
2009-10-07 15:18   ` Wu Fengguang
2009-10-08  5:33     ` Wu Fengguang
2009-10-08  5:44       ` Wu Fengguang
2009-10-07 14:26 ` Theodore Tso
2009-10-07 14:45   ` 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=20091007074904.473079627@intel.com \
    --to=fengguang.wu@intel.com \
    --cc=Trond.Myklebust@netapp.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=chris.mason@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=jens.axboe@oracle.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=npiggin@suse.de \
    --cc=shaohua.li@intel.com \
    --cc=tytso@mit.edu \
    /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).