2006-01-17 00:50:04 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
|
2006-05-19 03:09:15 +08:00
|
|
|
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* This copyrighted material is made available to anyone wishing to use,
|
|
|
|
* modify, copy, or redistribute it subject to the terms and conditions
|
2006-09-01 23:05:15 +08:00
|
|
|
* of the GNU General Public License version 2.
|
2006-01-17 00:50:04 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/completion.h>
|
|
|
|
#include <linux/buffer_head.h>
|
2006-02-28 06:23:27 +08:00
|
|
|
#include <linux/gfs2_ondisk.h>
|
2006-09-19 13:56:29 +08:00
|
|
|
#include <linux/lm_interface.h>
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
#include "gfs2.h"
|
2006-02-28 06:23:27 +08:00
|
|
|
#include "incore.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
#include "bmap.h"
|
|
|
|
#include "glock.h"
|
|
|
|
#include "glops.h"
|
|
|
|
#include "inode.h"
|
|
|
|
#include "log.h"
|
|
|
|
#include "meta_io.h"
|
|
|
|
#include "recovery.h"
|
|
|
|
#include "rgrp.h"
|
2006-02-28 06:23:27 +08:00
|
|
|
#include "util.h"
|
2006-10-03 23:10:41 +08:00
|
|
|
#include "trans.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2006-10-03 23:10:41 +08:00
|
|
|
/**
|
|
|
|
* ail_empty_gl - remove all buffers for a given lock from the AIL
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
* None of the buffers should be dirty, locked, or pinned.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
struct gfs2_sbd *sdp = gl->gl_sbd;
|
|
|
|
unsigned int blocks;
|
|
|
|
struct list_head *head = &gl->gl_ail_list;
|
|
|
|
struct gfs2_bufdata *bd;
|
|
|
|
struct buffer_head *bh;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
blocks = atomic_read(&gl->gl_ail_count);
|
|
|
|
if (!blocks)
|
|
|
|
return;
|
|
|
|
|
|
|
|
error = gfs2_trans_begin(sdp, 0, blocks);
|
|
|
|
if (gfs2_assert_withdraw(sdp, !error))
|
|
|
|
return;
|
|
|
|
|
|
|
|
gfs2_log_lock(sdp);
|
|
|
|
while (!list_empty(head)) {
|
|
|
|
bd = list_entry(head->next, struct gfs2_bufdata,
|
|
|
|
bd_ail_gl_list);
|
|
|
|
bh = bd->bd_bh;
|
2007-08-27 16:45:26 +08:00
|
|
|
gfs2_remove_from_ail(NULL, bd);
|
2007-09-03 18:01:33 +08:00
|
|
|
bd->bd_bh = NULL;
|
|
|
|
bh->b_private = NULL;
|
|
|
|
bd->bd_blkno = bh->b_blocknr;
|
|
|
|
gfs2_assert_withdraw(sdp, !buffer_busy(bh));
|
|
|
|
gfs2_trans_add_revoke(sdp, bd);
|
2006-10-03 23:10:41 +08:00
|
|
|
}
|
|
|
|
gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
|
|
|
|
gfs2_log_unlock(sdp);
|
|
|
|
|
|
|
|
gfs2_trans_end(sdp);
|
|
|
|
gfs2_log_flush(sdp, NULL);
|
|
|
|
}
|
2006-07-26 23:27:10 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* gfs2_pte_inval - Sync and invalidate all PTEs associated with a glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void gfs2_pte_inval(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
struct gfs2_inode *ip;
|
|
|
|
struct inode *inode;
|
|
|
|
|
|
|
|
ip = gl->gl_object;
|
|
|
|
inode = &ip->i_inode;
|
2006-11-02 01:22:46 +08:00
|
|
|
if (!ip || !S_ISREG(inode->i_mode))
|
2006-07-26 23:27:10 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
unmap_shared_mapping_range(inode->i_mapping, 0, 0);
|
|
|
|
if (test_bit(GIF_SW_PAGED, &ip->i_flags))
|
|
|
|
set_bit(GLF_DIRTY, &gl->gl_flags);
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
|
|
|
* meta_go_sync - sync out the metadata for this glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
* Called when demoting or unlocking an EX glock. We must flush
|
|
|
|
* to disk all dirty buffers/pages relating to this glock, and must not
|
|
|
|
* not return to caller to demote/unlock the glock until I/O is complete.
|
|
|
|
*/
|
|
|
|
|
2006-11-20 23:37:45 +08:00
|
|
|
static void meta_go_sync(struct gfs2_glock *gl)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2007-01-23 01:15:34 +08:00
|
|
|
if (gl->gl_state != LM_ST_EXCLUSIVE)
|
|
|
|
return;
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
if (test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) {
|
2006-04-07 23:17:32 +08:00
|
|
|
gfs2_log_flush(gl->gl_sbd, gl);
|
2006-09-22 05:05:23 +08:00
|
|
|
gfs2_meta_sync(gl);
|
2006-11-20 23:37:45 +08:00
|
|
|
gfs2_ail_empty_gl(gl);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* meta_go_inval - invalidate the metadata for this glock
|
|
|
|
* @gl: the glock
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void meta_go_inval(struct gfs2_glock *gl, int flags)
|
|
|
|
{
|
|
|
|
if (!(flags & DIO_METADATA))
|
|
|
|
return;
|
|
|
|
|
|
|
|
gfs2_meta_inval(gl);
|
|
|
|
gl->gl_vn++;
|
|
|
|
}
|
|
|
|
|
2007-01-23 01:15:34 +08:00
|
|
|
/**
|
|
|
|
* inode_go_sync - Sync the dirty data and/or metadata for an inode glock
|
|
|
|
* @gl: the glock protecting the inode
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void inode_go_sync(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
struct gfs2_inode *ip = gl->gl_object;
|
|
|
|
|
|
|
|
if (ip && !S_ISREG(ip->i_inode.i_mode))
|
|
|
|
ip = NULL;
|
|
|
|
|
|
|
|
if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
|
2007-08-16 23:03:57 +08:00
|
|
|
if (ip && !gfs2_is_jdata(ip))
|
2007-01-23 01:15:34 +08:00
|
|
|
filemap_fdatawrite(ip->i_inode.i_mapping);
|
[GFS2] flush the glock completely in inode_go_sync
Fix for bz #231910
When filemap_fdatawrite() is called on the inode mapping in data=ordered mode,
it will add the glock to the log. In inode_go_sync(), if you do the
gfs2_log_flush() before this, after the filemap_fdatawrite() call, the glock
and its associated data buffers will be on the log again. This means you can
demote a lock from exclusive, without having it flushed from the log. The
attached patch simply moves the gfs2_log_flush up to after the
filemap_fdatawrite() call.
Originally, I tried moving the gfs2_log_flush to after gfs2_meta_sync(), but
that caused me to trip the following assert.
GFS2: fsid=cypher-36:test.0: fatal: assertion "!buffer_busy(bh)" failed
GFS2: fsid=cypher-36:test.0: function = gfs2_ail_empty_gl, file = fs/gfs2/glops.c, line = 61
It appears that gfs2_log_flush() puts some of the glocks buffers in the busy
state and the filemap_fdatawrite() call is necessary to flush them. This makes
me worry slightly that a related problem could happen because of moving the
gfs2_log_flush() after the initial filemap_fdatawrite(), but I assume that
gfs2_ail_empty_gl() would catch that case as well.
Signed-off-by: Benjamin E. Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-05-02 22:44:03 +08:00
|
|
|
gfs2_log_flush(gl->gl_sbd, gl);
|
2007-08-16 23:03:57 +08:00
|
|
|
if (ip && gfs2_is_jdata(ip))
|
|
|
|
filemap_fdatawrite(ip->i_inode.i_mapping);
|
2007-01-23 01:15:34 +08:00
|
|
|
gfs2_meta_sync(gl);
|
|
|
|
if (ip) {
|
|
|
|
struct address_space *mapping = ip->i_inode.i_mapping;
|
|
|
|
int error = filemap_fdatawait(mapping);
|
2007-05-08 15:23:25 +08:00
|
|
|
mapping_set_error(mapping, error);
|
2007-01-23 01:15:34 +08:00
|
|
|
}
|
|
|
|
clear_bit(GLF_DIRTY, &gl->gl_flags);
|
|
|
|
gfs2_ail_empty_gl(gl);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
|
|
|
* inode_go_xmote_th - promote/demote a glock
|
|
|
|
* @gl: the glock
|
|
|
|
* @state: the requested state
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2007-01-23 01:15:34 +08:00
|
|
|
static void inode_go_xmote_th(struct gfs2_glock *gl)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
|
|
|
if (gl->gl_state != LM_ST_UNLOCKED)
|
|
|
|
gfs2_pte_inval(gl);
|
2007-01-23 01:15:34 +08:00
|
|
|
if (gl->gl_state == LM_ST_EXCLUSIVE)
|
|
|
|
inode_go_sync(gl);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* inode_go_xmote_bh - After promoting/demoting a glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void inode_go_xmote_bh(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
struct gfs2_holder *gh = gl->gl_req_gh;
|
|
|
|
struct buffer_head *bh;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
if (gl->gl_state != LM_ST_UNLOCKED &&
|
|
|
|
(!gh || !(gh->gh_flags & GL_SKIP))) {
|
2006-09-22 05:05:23 +08:00
|
|
|
error = gfs2_meta_read(gl, gl->gl_name.ln_number, 0, &bh);
|
2006-01-17 00:50:04 +08:00
|
|
|
if (!error)
|
|
|
|
brelse(bh);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* inode_go_drop_th - unlock a glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
* Invoked from rq_demote().
|
|
|
|
* Another node needs the lock in EXCLUSIVE mode, or lock (unused for too long)
|
|
|
|
* is being purged from our node's glock cache; we're dropping lock.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void inode_go_drop_th(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
gfs2_pte_inval(gl);
|
2007-01-23 01:15:34 +08:00
|
|
|
if (gl->gl_state == LM_ST_EXCLUSIVE)
|
|
|
|
inode_go_sync(gl);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* inode_go_inval - prepare a inode glock to be released
|
|
|
|
* @gl: the glock
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void inode_go_inval(struct gfs2_glock *gl, int flags)
|
|
|
|
{
|
2006-11-23 23:51:34 +08:00
|
|
|
struct gfs2_inode *ip = gl->gl_object;
|
2006-01-17 00:50:04 +08:00
|
|
|
int meta = (flags & DIO_METADATA);
|
|
|
|
|
|
|
|
if (meta) {
|
|
|
|
gfs2_meta_inval(gl);
|
2006-11-23 23:51:34 +08:00
|
|
|
if (ip)
|
|
|
|
set_bit(GIF_INVALID, &ip->i_flags);
|
|
|
|
}
|
|
|
|
|
2007-10-15 22:40:33 +08:00
|
|
|
if (ip && S_ISREG(ip->i_inode.i_mode))
|
2006-11-23 23:51:34 +08:00
|
|
|
truncate_inode_pages(ip->i_inode.i_mapping, 0);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
* Returns: 1 if it's ok
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int inode_go_demote_ok(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
struct gfs2_sbd *sdp = gl->gl_sbd;
|
|
|
|
int demote = 0;
|
|
|
|
|
2006-02-28 06:23:27 +08:00
|
|
|
if (!gl->gl_object && !gl->gl_aspace->i_mapping->nrpages)
|
2006-01-17 00:50:04 +08:00
|
|
|
demote = 1;
|
|
|
|
else if (!sdp->sd_args.ar_localcaching &&
|
|
|
|
time_after_eq(jiffies, gl->gl_stamp +
|
|
|
|
gfs2_tune_get(sdp, gt_demote_secs) * HZ))
|
|
|
|
demote = 1;
|
|
|
|
|
|
|
|
return demote;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* inode_go_lock - operation done after an inode lock is locked by a process
|
|
|
|
* @gl: the glock
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
* Returns: errno
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int inode_go_lock(struct gfs2_holder *gh)
|
|
|
|
{
|
|
|
|
struct gfs2_glock *gl = gh->gh_gl;
|
2006-02-28 06:23:27 +08:00
|
|
|
struct gfs2_inode *ip = gl->gl_object;
|
2006-01-17 00:50:04 +08:00
|
|
|
int error = 0;
|
|
|
|
|
|
|
|
if (!ip)
|
|
|
|
return 0;
|
|
|
|
|
2006-11-02 05:05:38 +08:00
|
|
|
if (test_bit(GIF_INVALID, &ip->i_flags)) {
|
2006-01-17 00:50:04 +08:00
|
|
|
error = gfs2_inode_refresh(ip);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
if ((ip->i_di.di_flags & GFS2_DIF_TRUNC_IN_PROG) &&
|
|
|
|
(gl->gl_state == LM_ST_EXCLUSIVE) &&
|
2007-01-23 01:10:39 +08:00
|
|
|
(gh->gh_state == LM_ST_EXCLUSIVE))
|
2006-01-17 00:50:04 +08:00
|
|
|
error = gfs2_truncatei_resume(ip);
|
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* inode_go_unlock - operation done before an inode lock is unlocked by a
|
|
|
|
* process
|
|
|
|
* @gl: the glock
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void inode_go_unlock(struct gfs2_holder *gh)
|
|
|
|
{
|
|
|
|
struct gfs2_glock *gl = gh->gh_gl;
|
2006-02-28 06:23:27 +08:00
|
|
|
struct gfs2_inode *ip = gl->gl_object;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2006-11-09 04:45:46 +08:00
|
|
|
if (ip)
|
|
|
|
gfs2_meta_cache_flush(ip);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
* Returns: 1 if it's ok
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int rgrp_go_demote_ok(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
return !gl->gl_aspace->i_mapping->nrpages;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rgrp_go_lock - operation done after an rgrp lock is locked by
|
|
|
|
* a first holder on this node.
|
|
|
|
* @gl: the glock
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
* Returns: errno
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int rgrp_go_lock(struct gfs2_holder *gh)
|
|
|
|
{
|
2006-02-28 06:23:27 +08:00
|
|
|
return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rgrp_go_unlock - operation done before an rgrp lock is unlocked by
|
|
|
|
* a last holder on this node.
|
|
|
|
* @gl: the glock
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void rgrp_go_unlock(struct gfs2_holder *gh)
|
|
|
|
{
|
2006-02-28 06:23:27 +08:00
|
|
|
gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* trans_go_xmote_th - promote/demote the transaction glock
|
|
|
|
* @gl: the glock
|
|
|
|
* @state: the requested state
|
|
|
|
* @flags:
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2007-01-23 01:15:34 +08:00
|
|
|
static void trans_go_xmote_th(struct gfs2_glock *gl)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
|
|
|
struct gfs2_sbd *sdp = gl->gl_sbd;
|
|
|
|
|
|
|
|
if (gl->gl_state != LM_ST_UNLOCKED &&
|
|
|
|
test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
|
|
|
|
gfs2_meta_syncfs(sdp);
|
|
|
|
gfs2_log_shutdown(sdp);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* trans_go_xmote_bh - After promoting/demoting the transaction glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void trans_go_xmote_bh(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
struct gfs2_sbd *sdp = gl->gl_sbd;
|
2006-06-15 03:32:57 +08:00
|
|
|
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
|
2006-02-28 06:23:27 +08:00
|
|
|
struct gfs2_glock *j_gl = ip->i_gl;
|
2006-10-14 09:47:13 +08:00
|
|
|
struct gfs2_log_header_host head;
|
2006-01-17 00:50:04 +08:00
|
|
|
int error;
|
|
|
|
|
|
|
|
if (gl->gl_state != LM_ST_UNLOCKED &&
|
|
|
|
test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
|
2006-06-15 03:32:57 +08:00
|
|
|
gfs2_meta_cache_flush(GFS2_I(sdp->sd_jdesc->jd_inode));
|
2006-11-20 23:37:45 +08:00
|
|
|
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
error = gfs2_find_jhead(sdp->sd_jdesc, &head);
|
|
|
|
if (error)
|
|
|
|
gfs2_consist(sdp);
|
|
|
|
if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
|
|
|
|
gfs2_consist(sdp);
|
|
|
|
|
|
|
|
/* Initialize some head of the log stuff */
|
|
|
|
if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
|
|
|
|
sdp->sd_log_sequence = head.lh_sequence + 1;
|
|
|
|
gfs2_log_pointers_init(sdp, head.lh_blkno);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* trans_go_drop_th - unlock the transaction glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
* We want to sync the device even with localcaching. Remember
|
|
|
|
* that localcaching journal replay only marks buffers dirty.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void trans_go_drop_th(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
struct gfs2_sbd *sdp = gl->gl_sbd;
|
|
|
|
|
|
|
|
if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
|
|
|
|
gfs2_meta_syncfs(sdp);
|
|
|
|
gfs2_log_shutdown(sdp);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* quota_go_demote_ok - Check to see if it's ok to unlock a quota glock
|
|
|
|
* @gl: the glock
|
|
|
|
*
|
|
|
|
* Returns: 1 if it's ok
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int quota_go_demote_ok(struct gfs2_glock *gl)
|
|
|
|
{
|
|
|
|
return !atomic_read(&gl->gl_lvb_count);
|
|
|
|
}
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_meta_glops = {
|
2007-01-23 01:15:34 +08:00
|
|
|
.go_xmote_th = meta_go_sync,
|
|
|
|
.go_drop_th = meta_go_sync,
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_META,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_inode_glops = {
|
2006-01-17 00:50:04 +08:00
|
|
|
.go_xmote_th = inode_go_xmote_th,
|
|
|
|
.go_xmote_bh = inode_go_xmote_bh,
|
|
|
|
.go_drop_th = inode_go_drop_th,
|
|
|
|
.go_inval = inode_go_inval,
|
|
|
|
.go_demote_ok = inode_go_demote_ok,
|
|
|
|
.go_lock = inode_go_lock,
|
|
|
|
.go_unlock = inode_go_unlock,
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_INODE,
|
[GFS2] delay glock demote for a minimum hold time
When a lot of IO, with some distributed mmap IO, is run on a GFS2 filesystem in
a cluster, it will deadlock. The reason is that do_no_page() will repeatedly
call gfs2_sharewrite_nopage(), because each node keeps giving up the glock
too early, and is forced to call unmap_mapping_range(). This bumps the
mapping->truncate_count sequence count, forcing do_no_page() to retry. This
patch institutes a minimum glock hold time a tenth a second. This insures
that even in heavy contention cases, the node has enough time to get some
useful work done before it gives up the glock.
A second issue is that when gfs2_glock_dq() is called from within a page fault
to demote a lock, and the associated page needs to be written out, it will
try to acqire a lock on it, but it has already been locked at a higher level.
This patch puts makes gfs2_glock_dq() use the work queue as well, to avoid this
issue. This is the same patch as Steve Whitehouse originally proposed to fix
this issue, execpt that gfs2_glock_dq() now grabs a reference to the glock
before it queues up the work on it.
Signed-off-by: Benjamin E. Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-08-24 02:19:05 +08:00
|
|
|
.go_min_hold_time = HZ / 10,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_rgrp_glops = {
|
2007-02-28 22:03:00 +08:00
|
|
|
.go_xmote_th = meta_go_sync,
|
|
|
|
.go_drop_th = meta_go_sync,
|
2006-01-17 00:50:04 +08:00
|
|
|
.go_inval = meta_go_inval,
|
|
|
|
.go_demote_ok = rgrp_go_demote_ok,
|
|
|
|
.go_lock = rgrp_go_lock,
|
|
|
|
.go_unlock = rgrp_go_unlock,
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_RGRP,
|
[GFS2] delay glock demote for a minimum hold time
When a lot of IO, with some distributed mmap IO, is run on a GFS2 filesystem in
a cluster, it will deadlock. The reason is that do_no_page() will repeatedly
call gfs2_sharewrite_nopage(), because each node keeps giving up the glock
too early, and is forced to call unmap_mapping_range(). This bumps the
mapping->truncate_count sequence count, forcing do_no_page() to retry. This
patch institutes a minimum glock hold time a tenth a second. This insures
that even in heavy contention cases, the node has enough time to get some
useful work done before it gives up the glock.
A second issue is that when gfs2_glock_dq() is called from within a page fault
to demote a lock, and the associated page needs to be written out, it will
try to acqire a lock on it, but it has already been locked at a higher level.
This patch puts makes gfs2_glock_dq() use the work queue as well, to avoid this
issue. This is the same patch as Steve Whitehouse originally proposed to fix
this issue, execpt that gfs2_glock_dq() now grabs a reference to the glock
before it queues up the work on it.
Signed-off-by: Benjamin E. Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-08-24 02:19:05 +08:00
|
|
|
.go_min_hold_time = HZ / 10,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_trans_glops = {
|
2006-01-17 00:50:04 +08:00
|
|
|
.go_xmote_th = trans_go_xmote_th,
|
|
|
|
.go_xmote_bh = trans_go_xmote_bh,
|
|
|
|
.go_drop_th = trans_go_drop_th,
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_NONDISK,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_iopen_glops = {
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_IOPEN,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_flock_glops = {
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_FLOCK,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_nondisk_glops = {
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_NONDISK,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_quota_glops = {
|
2006-01-17 00:50:04 +08:00
|
|
|
.go_demote_ok = quota_go_demote_ok,
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_QUOTA,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|
2006-08-30 21:30:00 +08:00
|
|
|
const struct gfs2_glock_operations gfs2_journal_glops = {
|
2006-09-05 22:53:09 +08:00
|
|
|
.go_type = LM_TYPE_JOURNAL,
|
2006-01-17 00:50:04 +08:00
|
|
|
};
|
|
|
|
|