Re: [PATCH 1/8] xfs: use per-filesystem I/O completion workqueues

xfs

Re: [PATCH 1/8] xfs: use per-filesystem I/O completion workqueues

To:	Christoph Hellwig <hch@xxxxxxxxxxxxx>
Subject:	Re: [PATCH 1/8] xfs: use per-filesystem I/O completion workqueues
From:	Mark Tinguely <tinguely@xxxxxxx>
Date:	Tue, 28 Feb 2012 10:13:17 -0600
Cc:	xfs@xxxxxxxxxxx
In-reply-to:	<20120221003906.124899527@xxxxxxxxxxxxxxxxxxxxxx>
References:	<20120221003824.415885674@xxxxxxxxxxxxxxxxxxxxxx> <20120221003906.124899527@xxxxxxxxxxxxxxxxxxxxxx>
User-agent:	Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20120122 Thunderbird/9.0

On 02/20/12 18:38, Christoph Hellwig wrote:

The new concurrency managed workqueues are cheap enough that we can create
per-filesystem instead of global workqueues.  This allows us to remove the
trylock or defer scheme on the ilock, which is not helpful once we have
outstanding log reservations until finishing a size update.

Also allow the default concurrency on this workqueues so that I/O completions
blocking on the ilock for one inode do not block process for another inode.

Signed-off-by: Christoph Hellwig<hch@xxxxxx>


Looks good.

Reviewed-by: Mark Tinguely <tinguely@xxxxxxx>

[More with this subject...]

<Prev in Thread]	Current Thread	[Next in Thread>
Re: [PATCH 4/8] xfs: log file size updates at I/O completion time, (continued) Re: [PATCH 4/8] xfs: log file size updates at I/O completion time, Christoph Hellwig [PATCH 8/8] xfs: add back fdatasync support, Christoph Hellwig Re: [PATCH 8/8] xfs: add back fdatasync support, Dave Chinner [PATCH 6/8] xfs: make xfs_inode_item_size idempotent, Christoph Hellwig Re: [PATCH 6/8] xfs: make xfs_inode_item_size idempotent, Dave Chinner Re: [PATCH 6/8] xfs: make xfs_inode_item_size idempotent, Christoph Hellwig [PATCH 2/8] xfs: do not require an ioend for new EOF calculation, Christoph Hellwig Re: [PATCH 2/8] xfs: do not require an ioend for new EOF calculation, Mark Tinguely [PATCH 1/8] xfs: use per-filesystem I/O completion workqueues, Christoph Hellwig Re: [PATCH 1/8] xfs: use per-filesystem I/O completion workqueues, Dave Chinner Re: [PATCH 1/8] xfs: use per-filesystem I/O completion workqueues, Mark Tinguely <= [PATCH 7/8] xfs: split in-core and on-disk inode log item fields, Christoph Hellwig Re: [PATCH 7/8] xfs: split in-core and on-disk inode log item fields, Dave Chinner [PATCH 5/8] xfs: log timestamp updates, Christoph Hellwig Re: [PATCH 5/8] xfs: log timestamp updates, Dave Chinner

Previous by Date:	Re: [PATCH] xfs: fix deadlock in xfs_rtfree_extent with kernel v3.x, Kamal Dasu
Next by Date:	Re: [PATCH 2/8] xfs: do not require an ioend for new EOF calculation, Mark Tinguely
Previous by Thread:	Re: [PATCH 1/8] xfs: use per-filesystem I/O completion workqueues, Dave Chinner
Next by Thread:	[PATCH 7/8] xfs: split in-core and on-disk inode log item fields, Christoph Hellwig
Indexes:	[Date] [Thread] [Top] [All Lists]