CVSROOT: /cvs/cluster
Module name: cluster
Branch: RHEL5
Changes by: jbrassow@sourceware.org 2008-01-21 20:37:03

Modified files:
cmirror-kernel/src: dm-clog.c

Log message:
- name change s/clustered_/clustered-/

Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/cmirror-kernel/src/dm-clog.c.diff?cvsroot=cluster&only_with_tag=RHEL5&r1 =1.2.2.5&r2=1.2.2.6

--- cluster/cmirror-kernel/src/dm-clog.c 2008/01/14 22:46:58 1.2.2.5
+++ cluster/cmirror-kernel/src/dm-clog.c 2008/01/21 20:37:03 1.2.2.6
@@ -123,7 +123,7 @@
{
int i, r;
if ((argc < 3) || (argc > 4)) {
- DMERR("Too %s arguments to clustered_core mirror log type.",
+ DMERR("Too %s arguments to clustered-core mirror log type.",
(argc < 2) ? "few" : "many");
DMERR(" %d arguments supplied:", argc);
for (i = 0; i < argc; i++)
@@ -154,7 +154,7 @@
{
int i;
if ((argc < 4) || (argc > 5)) {
- DMERR("Too %s arguments to clustered_disk mirror log type.",
+ DMERR("Too %s arguments to clustered-disk mirror log type.",
(argc < 3) ? "few" : "many");
DMERR(" %d arguments supplied:", argc);
for (i = 0; i < argc; i++)
@@ -575,7 +575,7 @@
}

static struct dirty_log_type _clustered_core_type = {
- .name = "clustered_core",
+ .name = "clustered-core",
.module = THIS_MODULE,
.ctr = cluster_core_ctr,
.dtr = cluster_dtr,
@@ -597,7 +597,7 @@
};

static struct dirty_log_type _clustered_disk_type = {
- .name = "clustered_disk",
+ .name = "clustered-disk",
.module = THIS_MODULE,
.ctr = cluster_disk_ctr,
.dtr = cluster_dtr,
@@ -639,7 +639,7 @@

r = dm_register_dirty_log_type(&_clustered_core_type);
if (r) {
- DMWARN("Couldn't register clustered_core dirty log type");
+ DMWARN("Couldn't register clustered-core dirty log type");
dm_clog_tfr_exit();
mempool_destroy(flush_entry_pool);
return r;
@@ -647,7 +647,7 @@

r = dm_register_dirty_log_type(&_clustered_disk_type);
if (r) {
- DMWARN("Couldn't register clustered_disk dirty log type");
+ DMWARN("Couldn't register clustered-disk dirty log type");
dm_unregister_dirty_log_type(&_clustered_core_type );
dm_clog_tfr_exit();
mempool_destroy(flush_entry_pool);

CVSROOT: /cvs/cluster
Module name: cluster
Branch: RHEL5
Changes by: jbrassow@sourceware.org 2008-02-13 15:06:23

Modified files:
cmirror-kernel/src: dm-clog.c

Log message:
- change the way 'is_remote_recovering' works to improve overall
performance.

Before a mirror issues a write, it must call 'is_remote_recovering'
to ensure that another machine will not be recovering the region during
the write. This function can dramatically slow things down. One way to
increase performance is to note when the mirror is in-sync - then
is_remote_recovering can return 0 without having to send the request
around the cluster. (This has already been done.) This greatly speeds up
I/O during nominal mirror operation. However, I/O during mirror resyncing
is still greatly reduced. The problem is that the cluster network is
consumed with handling 'is_remote_recovering' calls that it becomes hard
to actually do the recovery. The fix is to only allow one
is_remote_recovering call to go to the cluster every 1/4 sec. When the
call goes up to userspace, it also retrieves info about how far along
the resync is. If a request is determined to already be in sync by that
info, then the region is not recovering and can safely be answered without
having to send the request on to the cluster. This approach has greatly
improved both the recovery and nominal throughput.

Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/cmirror-kernel/src/dm-clog.c.diff?cvsroot=cluster&only_with_tag=RHEL5&r1 =1.2.2.9&r2=1.2.2.10

--- cluster/cmirror-kernel/src/dm-clog.c 2008/02/08 14:21:04 1.2.2.9
+++ cluster/cmirror-kernel/src/dm-clog.c 2008/02/13 15:06:23 1.2.2.10
@@ -23,7 +23,7 @@
char *ctr_str; /* Gives ability to restart if userspace dies */
uint32_t ctr_size;

- uint32_t in_sync_hint;
+ uint64_t in_sync_hint;

spinlock_t flush_lock;
struct list_head flush_list; /* only for clear and mark requests */
@@ -588,8 +588,8 @@
if (r)
return 0;

- if (sync_count == lc->region_count)
- lc->in_sync_hint = 1;
+ if (sync_count >= lc->region_count)
+ lc->in_sync_hint = lc->region_count;
/*
* get_sync_count is never called after the
* initial sync=1
@@ -644,9 +644,10 @@
static int cluster_is_remote_recovering(struct dirty_log *log, region_t region)
{
int r;
- int is_recovering;
- int rdata_size;
struct log_c *lc = (struct log_c *)log->context;
+ static unsigned long long limit = 0;
+ struct { int is_recovering; uint64_t sync_search; } pkg;
+ int rdata_size = sizeof(pkg);

/*
* Once the mirror has been reported to be in-sync,
@@ -655,14 +656,21 @@
* recovering if the device is in-sync. (in_sync_hint
* must be reset at resume time.)
*/
- if (lc->in_sync_hint)
+ if (region < lc->in_sync_hint)
return 0;
+ else if (jiffies < limit)
+ return 1;

- rdata_size = sizeof(is_recovering);
+ limit = jiffies + (HZ / 4);
r = cluster_do_request(lc, lc->uuid, DM_CLOG_IS_REMOTE_RECOVERING,
(char *)&region, sizeof(region),
- (char *)&is_recovering, &rdata_size);
- return (r) ? 1 : is_recovering;
+ (char *)&pkg, &rdata_size);
+ if (r)
+ return 1;
+
+ lc->in_sync_hint = pkg.sync_search;
+
+ return pkg.is_recovering;
}

static struct dirty_log_type _clustered_core_type = {