This patch tracks various statistics related to the performance of a RAID 5
or 6 array. These have been useful to us in the past to help solve
performance issues. They are reported via /proc/mdstat.
I realize that the format of the statistics may not be the best, and
there may be a better location than /proc/mdstat, so I welcome suggestions
on where to put them.
I will add documentation once we've decided on the format and location (or
if nobody objects to the current format and location.)
Signed-off-by: Jody McIntyre <scjody@xxxxxxx>
Index: linux-2.6/drivers/md/raid5.c
===================================================================
--- linux-2.6.orig/drivers/md/raid5.c
+++ linux-2.6/drivers/md/raid5.c
@@ -136,7 +136,7 @@ static inline int raid6_next_disk(int di
return (disk < raid_disks) ? disk : 0;
}
-static void return_io(struct bio *return_bi)
+static void return_io(struct bio *return_bi, raid5_conf_t *conf)
{
struct bio *bi = return_bi;
while (bi) {
@@ -145,6 +145,7 @@ static void return_io(struct bio *return
bi->bi_next = NULL;
bi->bi_size = 0;
bio_endio(bi, 0);
+ atomic_dec(&conf->in_reqs_in_queue);
bi = return_bi;
}
}
@@ -167,10 +168,12 @@ static void __release_stripe(raid5_conf_
if (test_bit(STRIPE_DELAYED, &sh->state)) {
list_add_tail(&sh->lru, &conf->delayed_list);
blk_plug_device(conf->mddev->queue);
+ atomic_inc(&conf->delayed);
} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
sh->bm_seq - conf->seq_write > 0) {
list_add_tail(&sh->lru, &conf->bitmap_list);
blk_plug_device(conf->mddev->queue);
+ atomic_inc(&conf->bit_delayed);
} else {
clear_bit(STRIPE_BIT_DELAY, &sh->state);
list_add_tail(&sh->lru, &conf->handle_list);
@@ -347,6 +350,7 @@ static struct stripe_head *get_active_st
if (noblock && sh == NULL)
break;
if (!sh) {
+ atomic_inc(&conf->out_of_stripes);
conf->inactive_blocked = 1;
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list) &&
@@ -369,6 +373,10 @@ static struct stripe_head *get_active_st
!test_bit(STRIPE_EXPANDING, &sh->state))
BUG();
list_del_init(&sh->lru);
+ if (test_bit(STRIPE_DELAYED, &sh->state))
+ atomic_dec(&conf->delayed);
+ if (test_bit(STRIPE_BIT_DELAY, &sh->state))
+ atomic_dec(&conf->bit_delayed);
}
}
} while (sh == NULL);
@@ -406,10 +414,13 @@ static void ops_run_io(struct stripe_hea
bi = &sh->dev[i].req;
bi->bi_rw = rw;
- if (rw == WRITE)
+ if (rw == WRITE) {
+ atomic_inc(&conf->writes_out);
bi->bi_end_io = raid5_end_write_request;
- else
+ } else {
+ atomic_inc(&conf->reads_out);
bi->bi_end_io = raid5_end_read_request;
+ }
rcu_read_lock();
rdev = rcu_dereference(conf->disks[i].rdev);
@@ -444,6 +455,7 @@ static void ops_run_io(struct stripe_hea
test_bit(R5_ReWrite, &sh->dev[i].flags))
atomic_add(STRIPE_SECTORS,
&rdev->corrected_errors);
+ atomic_inc(&conf->out_reqs_in_queue);
generic_make_request(bi);
} else {
if (rw == WRITE)
@@ -547,7 +559,7 @@ static void ops_complete_biofill(void *s
spin_unlock_irq(&conf->device_lock);
clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
- return_io(return_bi);
+ return_io(return_bi, conf);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
@@ -1074,6 +1086,8 @@ static void raid5_end_read_request(struc
mdk_rdev_t *rdev;
+ atomic_dec(&conf->out_reqs_in_queue);
+
for (i=0 ; i<disks; i++)
if (bi == &sh->dev[i].req)
break;
@@ -1153,6 +1167,8 @@ static void raid5_end_write_request(stru
int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
+ atomic_dec(&conf->out_reqs_in_queue);
+
for (i=0 ; i<disks; i++)
if (bi == &sh->dev[i].req)
break;
@@ -2131,6 +2147,7 @@ static void handle_stripe_dirtying5(raid
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
+ atomic_inc(&conf->reads_for_rmw);
} else {
set_bit(STRIPE_DELAYED, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
@@ -2154,6 +2171,7 @@ static void handle_stripe_dirtying5(raid
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
+ atomic_inc(&conf->reads_for_rcw);
} else {
set_bit(STRIPE_DELAYED, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
@@ -2219,6 +2237,7 @@ static void handle_stripe_dirtying6(raid
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
+ atomic_inc(&conf->reads_for_rcw);
} else {
pr_debug("Request delayed stripe %llu "
"block %d for Reconstruct\n",
@@ -2556,6 +2575,8 @@ static bool handle_stripe5(struct stripe
clear_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
+ atomic_inc(&conf->handle_called);
+
s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
@@ -2789,7 +2810,7 @@ static bool handle_stripe5(struct stripe
ops_run_io(sh, &s);
- return_io(return_bi);
+ return_io(return_bi, conf);
return blocked_rdev == NULL;
}
@@ -2816,6 +2837,8 @@ static bool handle_stripe6(struct stripe
clear_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
+ atomic_inc(&conf->handle_called);
+
s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
@@ -3011,7 +3034,7 @@ static bool handle_stripe6(struct stripe
ops_run_io(sh, &s);
- return_io(return_bi);
+ return_io(return_bi, conf);
return blocked_rdev == NULL;
}
@@ -3039,6 +3062,7 @@ static void raid5_activate_delayed(raid5
if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
list_add_tail(&sh->lru, &conf->hold_list);
+ atomic_dec(&conf->delayed);
}
} else
blk_plug_device(conf->mddev->queue);
@@ -3217,6 +3241,7 @@ static void raid5_align_endio(struct bio
raid_bi->bi_next = NULL;
rdev_dec_pending(rdev, conf->mddev);
+ atomic_dec(&conf->out_reqs_in_queue);
if (!error && uptodate) {
bio_endio(raid_bi, 0);
@@ -3265,6 +3290,7 @@ static int chunk_aligned_read(struct req
pr_debug("chunk_aligned_read : non aligned\n");
return 0;
}
+ atomic_inc(&conf->aligned_reads);
/*
* use bio_clone to make a copy of the bio
*/
@@ -3287,11 +3313,13 @@ static int chunk_aligned_read(struct req
&pd_idx,
conf);
+ atomic_dec(&conf->in_reqs_in_queue);
rcu_read_lock();
rdev = rcu_dereference(conf->disks[dd_idx].rdev);
if (rdev && test_bit(In_sync, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
+ atomic_inc(&conf->reads_out);
raid_bio->bi_next = (void*)rdev;
align_bi->bi_bdev = rdev->bdev;
align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
@@ -3311,6 +3339,7 @@ static int chunk_aligned_read(struct req
atomic_inc(&conf->active_aligned_reads);
spin_unlock_irq(&conf->device_lock);
+ atomic_inc(&conf->out_reqs_in_queue);
generic_make_request(align_bi);
return 1;
} else {
@@ -3384,6 +3413,8 @@ static int make_request(struct request_q
const int rw = bio_data_dir(bi);
int cpu, remaining;
+ atomic_inc(&conf->in_reqs_in_queue);
+
if (unlikely(bio_barrier(bi))) {
bio_endio(bi, -EOPNOTSUPP);
return 0;
@@ -3397,6 +3428,11 @@ static int make_request(struct request_q
bio_sectors(bi));
part_stat_unlock();
+ if (rw == WRITE)
+ atomic_inc(&conf->writes_in);
+ else
+ atomic_inc(&conf->reads_in);
+
if (rw == READ &&
mddev->reshape_position == MaxSector &&
chunk_aligned_read(q,bi))
@@ -3508,6 +3544,7 @@ static int make_request(struct request_q
if ( rw == WRITE )
md_write_end(mddev);
+ atomic_dec(&conf->in_reqs_in_queue);
bio_endio(bi, 0);
}
@@ -3862,6 +3899,7 @@ static void raid5d(mddev_t *mddev)
if (!ok)
break;
handled++;
+ atomic_inc(&conf->handled_in_raid5d);
}
sh = __get_priority_stripe(conf);
@@ -3871,6 +3909,7 @@ static void raid5d(mddev_t *mddev)
spin_unlock_irq(&conf->device_lock);
handled++;
+ atomic_inc(&conf->handled_in_raid5d);
handle_stripe(sh, conf->spare_page);
release_stripe(sh);
@@ -4330,15 +4369,37 @@ static void status(struct seq_file *seq,
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
int i;
- seq_printf (seq, " level %d, %dk chunk, algorithm %d", mddev->level, mddev->chunk_size >> 10, mddev->layout);
- seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
+ seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
+ mddev->chunk_size >> 10, mddev->layout);
+ seq_printf(seq, " [%d/%d] [", conf->raid_disks,
+ conf->raid_disks - mddev->degraded);
for (i = 0; i < conf->raid_disks; i++)
- seq_printf (seq, "%s",
+ seq_printf(seq, "%s",
conf->disks[i].rdev &&
test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
- seq_printf (seq, "]");
+ seq_printf(seq, "]\n");
+ seq_printf(seq, "\tin: %u reads, %u writes; out: %u reads, %u writes\n",
+ atomic_read(&conf->reads_in),
+ atomic_read(&conf->writes_in),
+ atomic_read(&conf->reads_out),
+ atomic_read(&conf->writes_out));
+ seq_printf(seq, "\t%u in raid5d, %u out of stripes, %u handle called\n",
+ atomic_read(&conf->handled_in_raid5d),
+ atomic_read(&conf->out_of_stripes),
+ atomic_read(&conf->handle_called));
+ seq_printf(seq, "\treads: %u for rmw, %u for rcw, %u aligned,\n",
+ atomic_read(&conf->reads_for_rmw),
+ atomic_read(&conf->reads_for_rcw),
+ atomic_read(&conf->aligned_reads));
+ seq_printf(seq, "\t%u delayed, %u bit delayed, %u active, ",
+ atomic_read(&conf->delayed),
+ atomic_read(&conf->bit_delayed),
+ atomic_read(&conf->active_stripes));
+ seq_printf(seq, "queues: %u in, %u out\n",
+ atomic_read(&conf->in_reqs_in_queue),
+ atomic_read(&conf->out_reqs_in_queue));
#ifdef DEBUG
- seq_printf (seq, "\n");
+ seq_printf(seq, "\n");
printall(seq, conf);
#endif
}
Index: linux-2.6/include/linux/raid/raid5.h
===================================================================
--- linux-2.6.orig/include/linux/raid/raid5.h
+++ linux-2.6/include/linux/raid/raid5.h
@@ -385,6 +385,26 @@ struct raid5_private_data {
int pool_size; /* number of disks in stripeheads in pool */
spinlock_t device_lock;
struct disk_info *disks;
+
+ /*
+ * Stats
+ */
+ atomic_t reads_in;
+ atomic_t writes_in;
+ atomic_t reads_out;
+ atomic_t writes_out;
+ atomic_t handled_in_raid5d;
+ atomic_t out_of_stripes;
+ atomic_t reads_for_rmw;
+ atomic_t reads_for_rcw;
+ atomic_t aligned_reads;
+ atomic_t writes_zcopy;
+ atomic_t writes_copied;
+ atomic_t handle_called;
+ atomic_t delayed;
+ atomic_t bit_delayed;
+ atomic_t in_reqs_in_queue;
+ atomic_t out_reqs_in_queue;
};
typedef struct raid5_private_data raid5_conf_t;
--
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
