| To: | JiSheng Zhang <jszhang3@xxxxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH] xfs: remove unecessary AIL push wakeups |
| From: | Christoph Hellwig <hch@xxxxxxxxxxxxx> |
| Date: | Tue, 24 Jan 2012 13:02:15 -0500 |
| Cc: | xfs@xxxxxxxxxxx, elder@xxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx |
| In-reply-to: | <20120113013028.6802d878@ustc> |
| References: | <20120113013028.6802d878@ustc> |
| User-agent: | Mutt/1.5.21 (2010-09-15) |
On Fri, Jan 13, 2012 at 01:30:28AM +0800, JiSheng Zhang wrote:
>
> In commit 0030807c66("xfs: revert to using a kthread for AIL pushing"),
> AIL pushing is revert back to use a kthread. But unfortunately, it
> introduced a regression: there are unnecessary AIL push wakeups during
> idle, ~20 wakeups/s. This change remove the wakeups by reverting a bit
> more: set "tout" value as zero during idle.
>
> Signed-off-by: JiSheng Zhang <jszhang3@xxxxxxxxxxxxxxxx>
Looks fine, although I'm a bit worried that I don't have the setup to
reproduce the issue that the patch addressed any more and we might
regress here.
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: How to fix bad superblock or xfs_repair: error - read only 0 of 512 bytes, Christian Kildau |
|---|---|
| Next by Date: | Re: [PATCH] xfs: Fix missing xfs_iunlock() on error recovery path in xfs_readlink(), Christoph Hellwig |
| Previous by Thread: | [PATCH] xfs: remove unecessary AIL push wakeups, JiSheng Zhang |
| Next by Thread: | XFS status update for December 2011, Christoph Hellwig |
| Indexes: | [Date] [Thread] [Top] [All Lists] |