linux/fs/xfs/linux-2.6/xfs_quotaops.c

141 lines
3.1 KiB
C
Raw Normal View History

/*
* Copyright (c) 2008, Christoph Hellwig
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_dmapi.h"
#include "xfs_sb.h"
#include "xfs_inum.h"
xfs: Improve scalability of busy extent tracking When we free a metadata extent, we record it in the per-AG busy extent array so that it is not re-used before the freeing transaction hits the disk. This array is fixed size, so when it overflows we make further allocation transactions synchronous because we cannot track more freed extents until those transactions hit the disk and are completed. Under heavy mixed allocation and freeing workloads with large log buffers, we can overflow this array quite easily. Further, the array is sparsely populated, which means that inserts need to search for a free slot, and array searches often have to search many more slots that are actually used to check all the busy extents. Quite inefficient, really. To enable this aspect of extent freeing to scale better, we need a structure that can grow dynamically. While in other areas of XFS we have used radix trees, the extents being freed are at random locations on disk so are better suited to being indexed by an rbtree. So, use a per-AG rbtree indexed by block number to track busy extents. This incures a memory allocation when marking an extent busy, but should not occur too often in low memory situations. This should scale to an arbitrary number of extents so should not be a limitation for features such as in-memory aggregation of transactions. However, there are still situations where we can't avoid allocating busy extents (such as allocation from the AGFL). To minimise the overhead of such occurences, we need to avoid doing a synchronous log force while holding the AGF locked to ensure that the previous transactions are safely on disk before we use the extent. We can do this by marking the transaction doing the allocation as synchronous rather issuing a log force. Because of the locking involved and the ordering of transactions, the synchronous transaction provides the same guarantees as a synchronous log force because it ensures that all the prior transactions are already on disk when the synchronous transaction hits the disk. i.e. it preserves the free->allocate order of the extent correctly in recovery. By doing this, we avoid holding the AGF locked while log writes are in progress, hence reducing the length of time the lock is held and therefore we increase the rate at which we can allocate and free from the allocation group, thereby increasing overall throughput. The only problem with this approach is that when a metadata buffer is marked stale (e.g. a directory block is removed), then buffer remains pinned and locked until the log goes to disk. The issue here is that if that stale buffer is reallocated in a subsequent transaction, the attempt to lock that buffer in the transaction will hang waiting the log to go to disk to unlock and unpin the buffer. Hence if someone tries to lock a pinned, stale, locked buffer we need to push on the log to get it unlocked ASAP. Effectively we are trading off a guaranteed log force for a much less common trigger for log force to occur. Ideally we should not reallocate busy extents. That is a much more complex fix to the problem as it involves direct intervention in the allocation btree searches in many places. This is left to a future set of modifications. Finally, now that we track busy extents in allocated memory, we don't need the descriptors in the transaction structure to point to them. We can replace the complex busy chunk infrastructure with a simple linked list of busy extents. This allows us to remove a large chunk of code, making the overall change a net reduction in code size. Signed-off-by: Dave Chinner <david@fromorbit.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-21 02:07:08 +00:00
#include "xfs_log.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_quota.h"
#include "xfs_trans.h"
#include "xfs_bmap_btree.h"
#include "xfs_inode.h"
#include "quota/xfs_qm.h"
#include <linux/quota.h>
STATIC int
xfs_quota_type(int type)
{
switch (type) {
case USRQUOTA:
return XFS_DQ_USER;
case GRPQUOTA:
return XFS_DQ_GROUP;
default:
return XFS_DQ_PROJ;
}
}
STATIC int
xfs_fs_get_xstate(
struct super_block *sb,
struct fs_quota_stat *fqs)
{
struct xfs_mount *mp = XFS_M(sb);
if (!XFS_IS_QUOTA_RUNNING(mp))
return -ENOSYS;
return -xfs_qm_scall_getqstat(mp, fqs);
}
STATIC int
xfs_fs_set_xstate(
struct super_block *sb,
unsigned int uflags,
int op)
{
struct xfs_mount *mp = XFS_M(sb);
unsigned int flags = 0;
if (sb->s_flags & MS_RDONLY)
return -EROFS;
if (op != Q_XQUOTARM && !XFS_IS_QUOTA_RUNNING(mp))
return -ENOSYS;
if (uflags & XFS_QUOTA_UDQ_ACCT)
flags |= XFS_UQUOTA_ACCT;
if (uflags & XFS_QUOTA_PDQ_ACCT)
flags |= XFS_PQUOTA_ACCT;
if (uflags & XFS_QUOTA_GDQ_ACCT)
flags |= XFS_GQUOTA_ACCT;
if (uflags & XFS_QUOTA_UDQ_ENFD)
flags |= XFS_UQUOTA_ENFD;
if (uflags & (XFS_QUOTA_PDQ_ENFD|XFS_QUOTA_GDQ_ENFD))
flags |= XFS_OQUOTA_ENFD;
switch (op) {
case Q_XQUOTAON:
return -xfs_qm_scall_quotaon(mp, flags);
case Q_XQUOTAOFF:
if (!XFS_IS_QUOTA_ON(mp))
return -EINVAL;
return -xfs_qm_scall_quotaoff(mp, flags);
case Q_XQUOTARM:
if (XFS_IS_QUOTA_ON(mp))
return -EINVAL;
return -xfs_qm_scall_trunc_qfiles(mp, flags);
}
return -EINVAL;
}
STATIC int
xfs_fs_get_dqblk(
struct super_block *sb,
int type,
qid_t id,
struct fs_disk_quota *fdq)
{
struct xfs_mount *mp = XFS_M(sb);
if (!XFS_IS_QUOTA_RUNNING(mp))
return -ENOSYS;
if (!XFS_IS_QUOTA_ON(mp))
return -ESRCH;
return -xfs_qm_scall_getquota(mp, id, xfs_quota_type(type), fdq);
}
STATIC int
xfs_fs_set_dqblk(
struct super_block *sb,
int type,
qid_t id,
struct fs_disk_quota *fdq)
{
struct xfs_mount *mp = XFS_M(sb);
if (sb->s_flags & MS_RDONLY)
return -EROFS;
if (!XFS_IS_QUOTA_RUNNING(mp))
return -ENOSYS;
if (!XFS_IS_QUOTA_ON(mp))
return -ESRCH;
return -xfs_qm_scall_setqlim(mp, id, xfs_quota_type(type), fdq);
}
const struct quotactl_ops xfs_quotactl_operations = {
.get_xstate = xfs_fs_get_xstate,
.set_xstate = xfs_fs_set_xstate,
.get_dqblk = xfs_fs_get_dqblk,
.set_dqblk = xfs_fs_set_dqblk,
};