linux/drivers/md/md-cluster.c
Goldwyn Rodrigues e94987db2e Initiate recovery on node failure
The DLM informs us in case of node failure with the DLM slot number.
cluster_info->recovery_map sets the bit corresponding to the slot number
and wakes up the recovery thread.

The recovery thread:
1. Derives the slot number from the recovery_map
2. Locks the bitmap corresponding to the slot
3. Copies the set bits to the node-local bitmap

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
2015-02-23 09:59:05 -06:00

449 lines
11 KiB
C

/*
* Copyright (C) 2015, SUSE
*
* 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, or (at your option)
* any later version.
*
*/
#include <linux/module.h>
#include <linux/dlm.h>
#include <linux/sched.h>
#include "md.h"
#include "bitmap.h"
#include "md-cluster.h"
#define LVB_SIZE 64
struct dlm_lock_resource {
dlm_lockspace_t *ls;
struct dlm_lksb lksb;
char *name; /* lock name. */
uint32_t flags; /* flags to pass to dlm_lock() */
struct completion completion; /* completion for synchronized locking */
void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
struct mddev *mddev; /* pointing back to mddev. */
};
struct suspend_info {
int slot;
sector_t lo;
sector_t hi;
struct list_head list;
};
struct resync_info {
__le64 lo;
__le64 hi;
};
struct md_cluster_info {
/* dlm lock space and resources for clustered raid. */
dlm_lockspace_t *lockspace;
int slot_number;
struct completion completion;
struct dlm_lock_resource *sb_lock;
struct mutex sb_mutex;
struct dlm_lock_resource *bitmap_lockres;
struct list_head suspend_list;
spinlock_t suspend_lock;
struct md_thread *recovery_thread;
unsigned long recovery_map;
};
static void sync_ast(void *arg)
{
struct dlm_lock_resource *res;
res = (struct dlm_lock_resource *) arg;
complete(&res->completion);
}
static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
{
int ret = 0;
init_completion(&res->completion);
ret = dlm_lock(res->ls, mode, &res->lksb,
res->flags, res->name, strlen(res->name),
0, sync_ast, res, res->bast);
if (ret)
return ret;
wait_for_completion(&res->completion);
return res->lksb.sb_status;
}
static int dlm_unlock_sync(struct dlm_lock_resource *res)
{
return dlm_lock_sync(res, DLM_LOCK_NL);
}
static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
{
struct dlm_lock_resource *res = NULL;
int ret, namelen;
struct md_cluster_info *cinfo = mddev->cluster_info;
res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
if (!res)
return NULL;
res->ls = cinfo->lockspace;
res->mddev = mddev;
namelen = strlen(name);
res->name = kzalloc(namelen + 1, GFP_KERNEL);
if (!res->name) {
pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
goto out_err;
}
strlcpy(res->name, name, namelen + 1);
if (with_lvb) {
res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
if (!res->lksb.sb_lvbptr) {
pr_err("md-cluster: Unable to allocate LVB for resource %s\n", name);
goto out_err;
}
res->flags = DLM_LKF_VALBLK;
}
if (bastfn)
res->bast = bastfn;
res->flags |= DLM_LKF_EXPEDITE;
ret = dlm_lock_sync(res, DLM_LOCK_NL);
if (ret) {
pr_err("md-cluster: Unable to lock NL on new lock resource %s\n", name);
goto out_err;
}
res->flags &= ~DLM_LKF_EXPEDITE;
res->flags |= DLM_LKF_CONVERT;
return res;
out_err:
kfree(res->lksb.sb_lvbptr);
kfree(res->name);
kfree(res);
return NULL;
}
static void lockres_free(struct dlm_lock_resource *res)
{
if (!res)
return;
init_completion(&res->completion);
dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
wait_for_completion(&res->completion);
kfree(res->name);
kfree(res->lksb.sb_lvbptr);
kfree(res);
}
static char *pretty_uuid(char *dest, char *src)
{
int i, len = 0;
for (i = 0; i < 16; i++) {
if (i == 4 || i == 6 || i == 8 || i == 10)
len += sprintf(dest + len, "-");
len += sprintf(dest + len, "%02x", (__u8)src[i]);
}
return dest;
}
static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres,
sector_t lo, sector_t hi)
{
struct resync_info *ri;
ri = (struct resync_info *)lockres->lksb.sb_lvbptr;
ri->lo = cpu_to_le64(lo);
ri->hi = cpu_to_le64(hi);
}
static struct suspend_info *read_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres)
{
struct resync_info ri;
struct suspend_info *s = NULL;
sector_t hi = 0;
dlm_lock_sync(lockres, DLM_LOCK_CR);
memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info));
hi = le64_to_cpu(ri.hi);
if (ri.hi > 0) {
s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
if (!s)
goto out;
s->hi = hi;
s->lo = le64_to_cpu(ri.lo);
}
dlm_unlock_sync(lockres);
out:
return s;
}
void recover_bitmaps(struct md_thread *thread)
{
struct mddev *mddev = thread->mddev;
struct md_cluster_info *cinfo = mddev->cluster_info;
struct dlm_lock_resource *bm_lockres;
char str[64];
int slot, ret;
struct suspend_info *s, *tmp;
sector_t lo, hi;
while (cinfo->recovery_map) {
slot = fls64((u64)cinfo->recovery_map) - 1;
/* Clear suspend_area associated with the bitmap */
spin_lock_irq(&cinfo->suspend_lock);
list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
if (slot == s->slot) {
list_del(&s->list);
kfree(s);
}
spin_unlock_irq(&cinfo->suspend_lock);
snprintf(str, 64, "bitmap%04d", slot);
bm_lockres = lockres_init(mddev, str, NULL, 1);
if (!bm_lockres) {
pr_err("md-cluster: Cannot initialize bitmaps\n");
goto clear_bit;
}
ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
if (ret) {
pr_err("md-cluster: Could not DLM lock %s: %d\n",
str, ret);
goto clear_bit;
}
ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi);
if (ret)
pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
dlm_unlock_sync(bm_lockres);
clear_bit:
clear_bit(slot, &cinfo->recovery_map);
}
}
static void recover_prep(void *arg)
{
}
static void recover_slot(void *arg, struct dlm_slot *slot)
{
struct mddev *mddev = arg;
struct md_cluster_info *cinfo = mddev->cluster_info;
pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n",
mddev->bitmap_info.cluster_name,
slot->nodeid, slot->slot,
cinfo->slot_number);
set_bit(slot->slot - 1, &cinfo->recovery_map);
if (!cinfo->recovery_thread) {
cinfo->recovery_thread = md_register_thread(recover_bitmaps,
mddev, "recover");
if (!cinfo->recovery_thread) {
pr_warn("md-cluster: Could not create recovery thread\n");
return;
}
}
md_wakeup_thread(cinfo->recovery_thread);
}
static void recover_done(void *arg, struct dlm_slot *slots,
int num_slots, int our_slot,
uint32_t generation)
{
struct mddev *mddev = arg;
struct md_cluster_info *cinfo = mddev->cluster_info;
cinfo->slot_number = our_slot;
complete(&cinfo->completion);
}
static const struct dlm_lockspace_ops md_ls_ops = {
.recover_prep = recover_prep,
.recover_slot = recover_slot,
.recover_done = recover_done,
};
static int gather_all_resync_info(struct mddev *mddev, int total_slots)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
int i, ret = 0;
struct dlm_lock_resource *bm_lockres;
struct suspend_info *s;
char str[64];
for (i = 0; i < total_slots; i++) {
memset(str, '\0', 64);
snprintf(str, 64, "bitmap%04d", i);
bm_lockres = lockres_init(mddev, str, NULL, 1);
if (!bm_lockres)
return -ENOMEM;
if (i == (cinfo->slot_number - 1))
continue;
bm_lockres->flags |= DLM_LKF_NOQUEUE;
ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
if (ret == -EAGAIN) {
memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE);
s = read_resync_info(mddev, bm_lockres);
if (s) {
pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n",
__func__, __LINE__,
(unsigned long long) s->lo,
(unsigned long long) s->hi, i);
spin_lock_irq(&cinfo->suspend_lock);
s->slot = i;
list_add(&s->list, &cinfo->suspend_list);
spin_unlock_irq(&cinfo->suspend_lock);
}
ret = 0;
lockres_free(bm_lockres);
continue;
}
if (ret)
goto out;
/* TODO: Read the disk bitmap sb and check if it needs recovery */
dlm_unlock_sync(bm_lockres);
lockres_free(bm_lockres);
}
out:
return ret;
}
static int join(struct mddev *mddev, int nodes)
{
struct md_cluster_info *cinfo;
int ret, ops_rv;
char str[64];
if (!try_module_get(THIS_MODULE))
return -ENOENT;
cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL);
if (!cinfo)
return -ENOMEM;
init_completion(&cinfo->completion);
mutex_init(&cinfo->sb_mutex);
mddev->cluster_info = cinfo;
memset(str, 0, 64);
pretty_uuid(str, mddev->uuid);
ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
DLM_LSFL_FS, LVB_SIZE,
&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
if (ret)
goto err;
wait_for_completion(&cinfo->completion);
if (nodes <= cinfo->slot_number) {
pr_err("md-cluster: Slot allotted(%d) greater than available slots(%d)", cinfo->slot_number - 1,
nodes);
ret = -ERANGE;
goto err;
}
cinfo->sb_lock = lockres_init(mddev, "cmd-super",
NULL, 0);
if (!cinfo->sb_lock) {
ret = -ENOMEM;
goto err;
}
pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
if (!cinfo->bitmap_lockres)
goto err;
if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
pr_err("Failed to get bitmap lock\n");
ret = -EINVAL;
goto err;
}
INIT_LIST_HEAD(&cinfo->suspend_list);
spin_lock_init(&cinfo->suspend_lock);
ret = gather_all_resync_info(mddev, nodes);
if (ret)
goto err;
return 0;
err:
lockres_free(cinfo->bitmap_lockres);
lockres_free(cinfo->sb_lock);
if (cinfo->lockspace)
dlm_release_lockspace(cinfo->lockspace, 2);
mddev->cluster_info = NULL;
kfree(cinfo);
module_put(THIS_MODULE);
return ret;
}
static int leave(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
if (!cinfo)
return 0;
md_unregister_thread(&cinfo->recovery_thread);
lockres_free(cinfo->sb_lock);
lockres_free(cinfo->bitmap_lockres);
dlm_release_lockspace(cinfo->lockspace, 2);
return 0;
}
/* slot_number(): Returns the MD slot number to use
* DLM starts the slot numbers from 1, wheras cluster-md
* wants the number to be from zero, so we deduct one
*/
static int slot_number(struct mddev *mddev)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
return cinfo->slot_number - 1;
}
static void resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi);
/* Re-acquire the lock to refresh LVB */
dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
}
static struct md_cluster_operations cluster_ops = {
.join = join,
.leave = leave,
.slot_number = slot_number,
.resync_info_update = resync_info_update,
};
static int __init cluster_init(void)
{
pr_warn("md-cluster: EXPERIMENTAL. Use with caution\n");
pr_info("Registering Cluster MD functions\n");
register_md_cluster_operations(&cluster_ops, THIS_MODULE);
return 0;
}
static void cluster_exit(void)
{
unregister_md_cluster_operations();
}
module_init(cluster_init);
module_exit(cluster_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Clustering support for MD");