mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-02 11:56:40 +07:00
553abd046a
The old recovery map was a bitmap of node numbers. This was sufficient for the maximum node number of 254. Going forward, we want node numbers to be UINT32. Thus, we need a new recovery map. Note that we can't keep track of slots here. We must write down the node number to recovery *before* we get the locks needed to convert a node number into a slot number. The recovery map is now an array of unsigned ints, max_slots in size. It moves to journal.c with the rest of recovery. Because it needs to be initialized, we move all of recovery initialization into a new function, ocfs2_recovery_init(). This actually cleans up ocfs2_initialize_super() a little as well. Following on, recovery cleaup becomes part of ocfs2_recovery_exit(). A number of node map functions are rendered obsolete and are removed. Finally, waiting on recovery is wrapped in a function rather than naked checks on the recovery_event. This is a cleanup from Mark. Signed-off-by: Joel Becker <joel.becker@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
193 lines
4.9 KiB
C
193 lines
4.9 KiB
C
/* -*- mode: c; c-basic-offset: 8; -*-
|
|
* vim: noexpandtab sw=8 ts=8 sts=0:
|
|
*
|
|
* heartbeat.c
|
|
*
|
|
* Register ourselves with the heartbaet service, keep our node maps
|
|
* up to date, and fire off recovery when needed.
|
|
*
|
|
* 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.
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/types.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/kmod.h>
|
|
|
|
#include <dlm/dlmapi.h>
|
|
|
|
#define MLOG_MASK_PREFIX ML_SUPER
|
|
#include <cluster/masklog.h>
|
|
|
|
#include "ocfs2.h"
|
|
|
|
#include "alloc.h"
|
|
#include "heartbeat.h"
|
|
#include "inode.h"
|
|
#include "journal.h"
|
|
|
|
#include "buffer_head_io.h"
|
|
|
|
static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map,
|
|
int bit);
|
|
static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map,
|
|
int bit);
|
|
|
|
/* special case -1 for now
|
|
* TODO: should *really* make sure the calling func never passes -1!! */
|
|
static void ocfs2_node_map_init(struct ocfs2_node_map *map)
|
|
{
|
|
map->num_nodes = OCFS2_NODE_MAP_MAX_NODES;
|
|
memset(map->map, 0, BITS_TO_LONGS(OCFS2_NODE_MAP_MAX_NODES) *
|
|
sizeof(unsigned long));
|
|
}
|
|
|
|
void ocfs2_init_node_maps(struct ocfs2_super *osb)
|
|
{
|
|
spin_lock_init(&osb->node_map_lock);
|
|
ocfs2_node_map_init(&osb->osb_recovering_orphan_dirs);
|
|
}
|
|
|
|
static void ocfs2_do_node_down(int node_num,
|
|
struct ocfs2_super *osb)
|
|
{
|
|
BUG_ON(osb->node_num == node_num);
|
|
|
|
mlog(0, "ocfs2: node down event for %d\n", node_num);
|
|
|
|
if (!osb->dlm) {
|
|
/*
|
|
* No DLM means we're not even ready to participate yet.
|
|
* We check the slots after the DLM comes up, so we will
|
|
* notice the node death then. We can safely ignore it
|
|
* here.
|
|
*/
|
|
return;
|
|
}
|
|
|
|
ocfs2_recovery_thread(osb, node_num);
|
|
}
|
|
|
|
/* Called from the dlm when it's about to evict a node. We may also
|
|
* get a heartbeat callback later. */
|
|
static void ocfs2_dlm_eviction_cb(int node_num,
|
|
void *data)
|
|
{
|
|
struct ocfs2_super *osb = (struct ocfs2_super *) data;
|
|
struct super_block *sb = osb->sb;
|
|
|
|
mlog(ML_NOTICE, "device (%u,%u): dlm has evicted node %d\n",
|
|
MAJOR(sb->s_dev), MINOR(sb->s_dev), node_num);
|
|
|
|
ocfs2_do_node_down(node_num, osb);
|
|
}
|
|
|
|
void ocfs2_setup_hb_callbacks(struct ocfs2_super *osb)
|
|
{
|
|
/* Not exactly a heartbeat callback, but leads to essentially
|
|
* the same path so we set it up here. */
|
|
dlm_setup_eviction_cb(&osb->osb_eviction_cb,
|
|
ocfs2_dlm_eviction_cb,
|
|
osb);
|
|
}
|
|
|
|
void ocfs2_stop_heartbeat(struct ocfs2_super *osb)
|
|
{
|
|
int ret;
|
|
char *argv[5], *envp[3];
|
|
|
|
if (ocfs2_mount_local(osb))
|
|
return;
|
|
|
|
if (!osb->uuid_str) {
|
|
/* This can happen if we don't get far enough in mount... */
|
|
mlog(0, "No UUID with which to stop heartbeat!\n\n");
|
|
return;
|
|
}
|
|
|
|
argv[0] = (char *)o2nm_get_hb_ctl_path();
|
|
argv[1] = "-K";
|
|
argv[2] = "-u";
|
|
argv[3] = osb->uuid_str;
|
|
argv[4] = NULL;
|
|
|
|
mlog(0, "Run: %s %s %s %s\n", argv[0], argv[1], argv[2], argv[3]);
|
|
|
|
/* minimal command environment taken from cpu_run_sbin_hotplug */
|
|
envp[0] = "HOME=/";
|
|
envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
|
|
envp[2] = NULL;
|
|
|
|
ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
|
|
if (ret < 0)
|
|
mlog_errno(ret);
|
|
}
|
|
|
|
static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map,
|
|
int bit)
|
|
{
|
|
set_bit(bit, map->map);
|
|
}
|
|
|
|
void ocfs2_node_map_set_bit(struct ocfs2_super *osb,
|
|
struct ocfs2_node_map *map,
|
|
int bit)
|
|
{
|
|
if (bit==-1)
|
|
return;
|
|
BUG_ON(bit >= map->num_nodes);
|
|
spin_lock(&osb->node_map_lock);
|
|
__ocfs2_node_map_set_bit(map, bit);
|
|
spin_unlock(&osb->node_map_lock);
|
|
}
|
|
|
|
static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map,
|
|
int bit)
|
|
{
|
|
clear_bit(bit, map->map);
|
|
}
|
|
|
|
void ocfs2_node_map_clear_bit(struct ocfs2_super *osb,
|
|
struct ocfs2_node_map *map,
|
|
int bit)
|
|
{
|
|
if (bit==-1)
|
|
return;
|
|
BUG_ON(bit >= map->num_nodes);
|
|
spin_lock(&osb->node_map_lock);
|
|
__ocfs2_node_map_clear_bit(map, bit);
|
|
spin_unlock(&osb->node_map_lock);
|
|
}
|
|
|
|
int ocfs2_node_map_test_bit(struct ocfs2_super *osb,
|
|
struct ocfs2_node_map *map,
|
|
int bit)
|
|
{
|
|
int ret;
|
|
if (bit >= map->num_nodes) {
|
|
mlog(ML_ERROR, "bit=%d map->num_nodes=%d\n", bit, map->num_nodes);
|
|
BUG();
|
|
}
|
|
spin_lock(&osb->node_map_lock);
|
|
ret = test_bit(bit, map->map);
|
|
spin_unlock(&osb->node_map_lock);
|
|
return ret;
|
|
}
|
|
|