![Srinivas Eeda](/assets/img/avatar_default.png)
When a dentry is unlinked, the unlinking node takes an EX on the dentry lock before moving the dentry to the orphan directory. Other nodes that have this dentry in cache have a PR on the same dentry lock. When the EX is requested, the other nodes flag the corresponding inode as MAYBE_ORPHANED during downconvert. The inode is finally deleted when the last node to iput the inode sees that i_nlink==0 and the MAYBE_ORPHANED flag is set. A problem arises if a node is forced to free dentry locks because of memory pressure. If this happens, the node will no longer get downconvert notifications for the dentries that have been unlinked on another node. If it also happens that node is actively using the corresponding inode and happens to be the one performing the last iput on that inode, it will fail to delete the inode as it will not have the MAYBE_ORPHANED flag set. This patch fixes this shortcoming by introducing a periodic scan of the orphan directories to delete such inodes. Care has been taken to distribute the workload across the cluster so that no one node has to perform the task all the time. Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
152 lines
5.1 KiB
C
152 lines
5.1 KiB
C
/* -*- mode: c; c-basic-offset: 8; -*-
|
|
* vim: noexpandtab sw=8 ts=8 sts=0:
|
|
*
|
|
* dlmglue.h
|
|
*
|
|
* description here
|
|
*
|
|
* Copyright (C) 2002, 2004 Oracle. 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; either
|
|
* version 2 of the License, or (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will 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 to the
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 021110-1307, USA.
|
|
*/
|
|
|
|
|
|
#ifndef DLMGLUE_H
|
|
#define DLMGLUE_H
|
|
|
|
#include "dcache.h"
|
|
|
|
#define OCFS2_LVB_VERSION 5
|
|
|
|
struct ocfs2_meta_lvb {
|
|
__u8 lvb_version;
|
|
__u8 lvb_reserved0;
|
|
__be16 lvb_idynfeatures;
|
|
__be32 lvb_iclusters;
|
|
__be32 lvb_iuid;
|
|
__be32 lvb_igid;
|
|
__be64 lvb_iatime_packed;
|
|
__be64 lvb_ictime_packed;
|
|
__be64 lvb_imtime_packed;
|
|
__be64 lvb_isize;
|
|
__be16 lvb_imode;
|
|
__be16 lvb_inlink;
|
|
__be32 lvb_iattr;
|
|
__be32 lvb_igeneration;
|
|
__be32 lvb_reserved2;
|
|
};
|
|
|
|
#define OCFS2_QINFO_LVB_VERSION 1
|
|
|
|
struct ocfs2_qinfo_lvb {
|
|
__u8 lvb_version;
|
|
__u8 lvb_reserved[3];
|
|
__be32 lvb_bgrace;
|
|
__be32 lvb_igrace;
|
|
__be32 lvb_syncms;
|
|
__be32 lvb_blocks;
|
|
__be32 lvb_free_blk;
|
|
__be32 lvb_free_entry;
|
|
};
|
|
|
|
#define OCFS2_ORPHAN_LVB_VERSION 1
|
|
|
|
struct ocfs2_orphan_scan_lvb {
|
|
__u8 lvb_version;
|
|
__u8 lvb_reserved[3];
|
|
__be32 lvb_os_seqno;
|
|
};
|
|
|
|
/* ocfs2_inode_lock_full() 'arg_flags' flags */
|
|
/* don't wait on recovery. */
|
|
#define OCFS2_META_LOCK_RECOVERY (0x01)
|
|
/* Instruct the dlm not to queue ourselves on the other node. */
|
|
#define OCFS2_META_LOCK_NOQUEUE (0x02)
|
|
/* don't block waiting for the downconvert thread, instead return -EAGAIN */
|
|
#define OCFS2_LOCK_NONBLOCK (0x04)
|
|
|
|
int ocfs2_dlm_init(struct ocfs2_super *osb);
|
|
void ocfs2_dlm_shutdown(struct ocfs2_super *osb, int hangup_pending);
|
|
void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res);
|
|
void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
|
|
enum ocfs2_lock_type type,
|
|
unsigned int generation,
|
|
struct inode *inode);
|
|
void ocfs2_dentry_lock_res_init(struct ocfs2_dentry_lock *dl,
|
|
u64 parent, struct inode *inode);
|
|
struct ocfs2_file_private;
|
|
void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres,
|
|
struct ocfs2_file_private *fp);
|
|
struct ocfs2_mem_dqinfo;
|
|
void ocfs2_qinfo_lock_res_init(struct ocfs2_lock_res *lockres,
|
|
struct ocfs2_mem_dqinfo *info);
|
|
void ocfs2_lock_res_free(struct ocfs2_lock_res *res);
|
|
int ocfs2_create_new_inode_locks(struct inode *inode);
|
|
int ocfs2_drop_inode_locks(struct inode *inode);
|
|
int ocfs2_rw_lock(struct inode *inode, int write);
|
|
void ocfs2_rw_unlock(struct inode *inode, int write);
|
|
int ocfs2_open_lock(struct inode *inode);
|
|
int ocfs2_try_open_lock(struct inode *inode, int write);
|
|
void ocfs2_open_unlock(struct inode *inode);
|
|
int ocfs2_inode_lock_atime(struct inode *inode,
|
|
struct vfsmount *vfsmnt,
|
|
int *level);
|
|
int ocfs2_inode_lock_full(struct inode *inode,
|
|
struct buffer_head **ret_bh,
|
|
int ex,
|
|
int arg_flags);
|
|
int ocfs2_inode_lock_with_page(struct inode *inode,
|
|
struct buffer_head **ret_bh,
|
|
int ex,
|
|
struct page *page);
|
|
/* 99% of the time we don't want to supply any additional flags --
|
|
* those are for very specific cases only. */
|
|
#define ocfs2_inode_lock(i, b, e) ocfs2_inode_lock_full(i, b, e, 0)
|
|
void ocfs2_inode_unlock(struct inode *inode,
|
|
int ex);
|
|
int ocfs2_super_lock(struct ocfs2_super *osb,
|
|
int ex);
|
|
void ocfs2_super_unlock(struct ocfs2_super *osb,
|
|
int ex);
|
|
int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno, int ex);
|
|
void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno, int ex);
|
|
|
|
int ocfs2_rename_lock(struct ocfs2_super *osb);
|
|
void ocfs2_rename_unlock(struct ocfs2_super *osb);
|
|
int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex);
|
|
void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex);
|
|
int ocfs2_dentry_lock(struct dentry *dentry, int ex);
|
|
void ocfs2_dentry_unlock(struct dentry *dentry, int ex);
|
|
int ocfs2_file_lock(struct file *file, int ex, int trylock);
|
|
void ocfs2_file_unlock(struct file *file);
|
|
int ocfs2_qinfo_lock(struct ocfs2_mem_dqinfo *oinfo, int ex);
|
|
void ocfs2_qinfo_unlock(struct ocfs2_mem_dqinfo *oinfo, int ex);
|
|
|
|
|
|
void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres);
|
|
void ocfs2_simple_drop_lockres(struct ocfs2_super *osb,
|
|
struct ocfs2_lock_res *lockres);
|
|
|
|
/* for the downconvert thread */
|
|
void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb);
|
|
|
|
struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void);
|
|
void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug);
|
|
|
|
/* To set the locking protocol on module initialization */
|
|
void ocfs2_set_locking_protocol(void);
|
|
#endif /* DLMGLUE_H */
|