summaryrefslogtreecommitdiffstats
path: root/drivers/md/md-cluster.c
diff options
context:
space:
mode:
authorGoldwyn Rodrigues <rgoldwyn@suse.com>2014-06-07 00:45:22 -0500
committerGoldwyn Rodrigues <rgoldwyn@suse.com>2015-02-23 09:59:05 -0600
commite94987db2ed983aea4e45d22db9e17c6bbf2a623 (patch)
treed216701edf17d2f1b6781be78da780a8c9cf6c18 /drivers/md/md-cluster.c
parent11dd35daaab86d12270d23a10e8d242846a8830a (diff)
downloadop-kernel-dev-e94987db2ed983aea4e45d22db9e17c6bbf2a623.zip
op-kernel-dev-e94987db2ed983aea4e45d22db9e17c6bbf2a623.tar.gz
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>
Diffstat (limited to 'drivers/md/md-cluster.c')
-rw-r--r--drivers/md/md-cluster.c58
1 files changed, 58 insertions, 0 deletions
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index b59c3a0..1f82d0d 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -13,6 +13,7 @@
#include <linux/dlm.h>
#include <linux/sched.h>
#include "md.h"
+#include "bitmap.h"
#include "md-cluster.h"
#define LVB_SIZE 64
@@ -49,6 +50,8 @@ struct md_cluster_info {
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)
@@ -184,6 +187,50 @@ 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)
{
}
@@ -197,6 +244,16 @@ static void recover_slot(void *arg, struct dlm_slot *slot)
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,
@@ -338,6 +395,7 @@ static int leave(struct mddev *mddev)
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);
OpenPOWER on IntegriCloud