Re: [Bug 18632] "INFO: task" dpkg "blocked for more than 120 seconds.

[Wu Fengguang <fengguang.wu@intel.com>]

On Sun, Jun 19, 2011 at 11:56:46PM +0800, Christoph Hellwig wrote:
> On Fri, Jun 10, 2011 at 11:21:49AM +0800, Wu Fengguang wrote:
> > > Can you check if that helps with your livelock test case?  (And yes, I
> > > should go and try it myself.  Will do as soon as I'll get a bit more
> > > time).
> > 
> > My pleasure. It's easier to compare results on the same test bed and
> > I've made it very convenient to test patches :)
> 
> Here's one that should be even better, although in it's current form it
> break a subtile corner case of sync semantics, so it'll need more work
> if I go down that way:

The sync(1)s are much faster now, in most invocations it's in the same
level as ext4 :)

root@fat /home/wfg# ./sync-livelock.sh

sync time: 3
sync time: 5
sync time: 5
sync time: 6
sync time: 15
sync time: 5
sync time: 5
sync time: 5
sync time: 4
sync time: 10
sync time: 4
sync time: 4

Thanks,
Fengguang

> Index: xfs/fs/xfs/linux-2.6/xfs_sync.c
> ===================================================================
> --- xfs.orig/fs/xfs/linux-2.6/xfs_sync.c	2011-06-17 14:16:18.442399481 +0200
> +++ xfs/fs/xfs/linux-2.6/xfs_sync.c	2011-06-18 17:55:44.864025123 +0200
> @@ -359,14 +359,16 @@ xfs_quiesce_data(
>  {
>  	int			error, error2 = 0;
>  
> -	/* push non-blocking */
> -	xfs_sync_data(mp, 0);
>  	xfs_qm_sync(mp, SYNC_TRYLOCK);
> -
> -	/* push and block till complete */
> -	xfs_sync_data(mp, SYNC_WAIT);
>  	xfs_qm_sync(mp, SYNC_WAIT);
>  
> +	/* flush all pending size updates and unwritten extent conversions */
> +	flush_workqueue(xfsconvertd_workqueue);
> +	flush_workqueue(xfsdatad_workqueue);
> +
> +	/* force out the newly dirtied log buffers */
> +	xfs_log_force(mp, XFS_LOG_SYNC);
> +
>  	/* write superblock and hoover up shutdown errors */
>  	error = xfs_sync_fsdata(mp);
>  
> Index: xfs/fs/xfs/linux-2.6/xfs_super.c
> ===================================================================
> --- xfs.orig/fs/xfs/linux-2.6/xfs_super.c	2011-06-18 17:51:05.660705925 +0200
> +++ xfs/fs/xfs/linux-2.6/xfs_super.c	2011-06-18 17:52:50.107367305 +0200
> @@ -929,45 +929,12 @@ xfs_fs_write_inode(
>  		 * ->sync_fs call do that for thus, which reduces the number
>  		 * of synchronous log foces dramatically.
>  		 */
> -		xfs_ioend_wait(ip);
>  		xfs_ilock(ip, XFS_ILOCK_SHARED);
> -		if (ip->i_update_core) {
> +		if (ip->i_update_core)
>  			error = xfs_log_inode(ip);
> -			if (error)
> -				goto out_unlock;
> -		}
> -	} else {
> -		/*
> -		 * We make this non-blocking if the inode is contended, return
> -		 * EAGAIN to indicate to the caller that they did not succeed.
> -		 * This prevents the flush path from blocking on inodes inside
> -		 * another operation right now, they get caught later by
> -		 * xfs_sync.
> -		 */
> -		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
> -			goto out;
> -
> -		if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
> -			goto out_unlock;
> -
> -		/*
> -		 * Now we have the flush lock and the inode is not pinned, we
> -		 * can check if the inode is really clean as we know that
> -		 * there are no pending transaction completions, it is not
> -		 * waiting on the delayed write queue and there is no IO in
> -		 * progress.
> -		 */
> -		if (xfs_inode_clean(ip)) {
> -			xfs_ifunlock(ip);
> -			error = 0;
> -			goto out_unlock;
> -		}
> -		error = xfs_iflush(ip, SYNC_TRYLOCK);
> +		xfs_iunlock(ip, XFS_ILOCK_SHARED);
>  	}
>  
> - out_unlock:
> -	xfs_iunlock(ip, XFS_ILOCK_SHARED);
> - out:
>  	/*
>  	 * if we failed to write out the inode then mark
>  	 * it dirty again so we'll try again later.