summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
authorDan Williams <dan.j.williams@intel.com>2009-10-16 16:25:22 +1100
committerNeilBrown <neilb@suse.de>2009-10-16 16:25:22 +1100
commit417b8d4ac868cf58d6c68f52d72f7648413e0edc (patch)
tree6eefb8b381fdad5235d2b29fc0054bcf537efbcc /drivers/md
parentdce3a7a42d585b74ce68081010b42afe81c8f4c4 (diff)
downloadlinux-3.10-417b8d4ac868cf58d6c68f52d72f7648413e0edc.tar.gz
linux-3.10-417b8d4ac868cf58d6c68f52d72f7648413e0edc.tar.bz2
linux-3.10-417b8d4ac868cf58d6c68f52d72f7648413e0edc.zip
md/raid456: downlevel multicore operations to raid_run_ops
The percpu conversion allowed a straightforward handoff of stripe processing to the async subsytem that initially showed some modest gains (+4%). However, this model is too simplistic and leads to stripes bouncing between raid5d and the async thread pool for every invocation of handle_stripe(). As reported by Holger this can fall into a pathological situation severely impacting throughput (6x performance loss). By downleveling the parallelism to raid_run_ops the pathological stripe_head bouncing is eliminated. This version still exhibits an average 11% throughput loss for: mdadm --create /dev/md0 /dev/sd[b-q] -n 16 -l 6 echo 1024 > /sys/block/md0/md/stripe_cache_size dd if=/dev/zero of=/dev/md0 bs=1024k count=2048 ...but the results are at least stable and can be used as a base for further multicore experimentation. Reported-by: Holger Kiehl <Holger.Kiehl@dwd.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/raid5.c75
-rw-r--r--drivers/md/raid5.h12
2 files changed, 51 insertions, 36 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c3e59677861..25c3c29134d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1139,7 +1139,7 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
&sh->ops.zero_sum_result, percpu->spare_page, &submit);
}
-static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
+static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
@@ -1204,6 +1204,36 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
put_cpu();
}
+#ifdef CONFIG_MULTICORE_RAID456
+static void async_run_ops(void *param, async_cookie_t cookie)
+{
+ struct stripe_head *sh = param;
+ unsigned long ops_request = sh->ops.request;
+
+ clear_bit_unlock(STRIPE_OPS_REQ_PENDING, &sh->state);
+ wake_up(&sh->ops.wait_for_ops);
+
+ __raid_run_ops(sh, ops_request);
+ release_stripe(sh);
+}
+
+static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
+{
+ /* since handle_stripe can be called outside of raid5d context
+ * we need to ensure sh->ops.request is de-staged before another
+ * request arrives
+ */
+ wait_event(sh->ops.wait_for_ops,
+ !test_and_set_bit_lock(STRIPE_OPS_REQ_PENDING, &sh->state));
+ sh->ops.request = ops_request;
+
+ atomic_inc(&sh->count);
+ async_schedule(async_run_ops, sh);
+}
+#else
+#define raid_run_ops __raid_run_ops
+#endif
+
static int grow_one_stripe(raid5_conf_t *conf)
{
struct stripe_head *sh;
@@ -1213,6 +1243,9 @@ static int grow_one_stripe(raid5_conf_t *conf)
memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev));
sh->raid_conf = conf;
spin_lock_init(&sh->lock);
+ #ifdef CONFIG_MULTICORE_RAID456
+ init_waitqueue_head(&sh->ops.wait_for_ops);
+ #endif
if (grow_buffers(sh, conf->raid_disks)) {
shrink_buffers(sh, conf->raid_disks);
@@ -1329,6 +1362,9 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
nsh->raid_conf = conf;
spin_lock_init(&nsh->lock);
+ #ifdef CONFIG_MULTICORE_RAID456
+ init_waitqueue_head(&nsh->ops.wait_for_ops);
+ #endif
list_add(&nsh->lru, &newstripes);
}
@@ -4342,37 +4378,6 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
return handled;
}
-#ifdef CONFIG_MULTICORE_RAID456
-static void __process_stripe(void *param, async_cookie_t cookie)
-{
- struct stripe_head *sh = param;
-
- handle_stripe(sh);
- release_stripe(sh);
-}
-
-static void process_stripe(struct stripe_head *sh, struct list_head *domain)
-{
- async_schedule_domain(__process_stripe, sh, domain);
-}
-
-static void synchronize_stripe_processing(struct list_head *domain)
-{
- async_synchronize_full_domain(domain);
-}
-#else
-static void process_stripe(struct stripe_head *sh, struct list_head *domain)
-{
- handle_stripe(sh);
- release_stripe(sh);
- cond_resched();
-}
-
-static void synchronize_stripe_processing(struct list_head *domain)
-{
-}
-#endif
-
/*
* This is our raid5 kernel thread.
@@ -4386,7 +4391,6 @@ static void raid5d(mddev_t *mddev)
struct stripe_head *sh;
raid5_conf_t *conf = mddev->private;
int handled;
- LIST_HEAD(raid_domain);
pr_debug("+++ raid5d active\n");
@@ -4423,7 +4427,9 @@ static void raid5d(mddev_t *mddev)
spin_unlock_irq(&conf->device_lock);
handled++;
- process_stripe(sh, &raid_domain);
+ handle_stripe(sh);
+ release_stripe(sh);
+ cond_resched();
spin_lock_irq(&conf->device_lock);
}
@@ -4431,7 +4437,6 @@ static void raid5d(mddev_t *mddev)
spin_unlock_irq(&conf->device_lock);
- synchronize_stripe_processing(&raid_domain);
async_tx_issue_pending_all();
unplug_slaves(mddev);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 2390e0e83da..dcefdc9629e 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -214,12 +214,20 @@ struct stripe_head {
int disks; /* disks in stripe */
enum check_states check_state;
enum reconstruct_states reconstruct_state;
- /* stripe_operations
+ /**
+ * struct stripe_operations
* @target - STRIPE_OP_COMPUTE_BLK target
+ * @target2 - 2nd compute target in the raid6 case
+ * @zero_sum_result - P and Q verification flags
+ * @request - async service request flags for raid_run_ops
*/
struct stripe_operations {
int target, target2;
enum sum_check_flags zero_sum_result;
+ #ifdef CONFIG_MULTICORE_RAID456
+ unsigned long request;
+ wait_queue_head_t wait_for_ops;
+ #endif
} ops;
struct r5dev {
struct bio req;
@@ -294,6 +302,8 @@ struct r6_state {
#define STRIPE_FULL_WRITE 13 /* all blocks are set to be overwritten */
#define STRIPE_BIOFILL_RUN 14
#define STRIPE_COMPUTE_RUN 15
+#define STRIPE_OPS_REQ_PENDING 16
+
/*
* Operation request flags
*/