dm mpath: add start_io and nr_bytes to path selectors
This patch makes two additions to the dm path selector interface for
dynamic load balancers:
o a new hook, start_io()
o a new parameter 'nr_bytes' to select_path()/start_io()/end_io()
to pass the size of the I/O
start_io() is called when a target driver actually submits I/O
to the selected path.
Path selectors can use it to start accounting of the I/O.
(e.g. counting the number of in-flight I/Os.)
The start_io hook is based on the patch posted by Stefan Bader:
https://www.redhat.com/archives/dm-devel/2005-October/msg00050.html
nr_bytes, the size of the I/O, is so path selectors can take the
size of the I/O into account when deciding which path to use.
dm-service-time uses it to estimate service time, for example.
(Added the nr_bytes member to dm_mpath_io instead of using existing
details.bi_size, since request-based dm patch deletes it.)
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index f1cf8f7..890c0e8 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -101,6 +101,7 @@
struct dm_mpath_io {
struct pgpath *pgpath;
struct dm_bio_details details;
+ size_t nr_bytes;
};
typedef int (*action_fn) (struct pgpath *pgpath);
@@ -244,11 +245,12 @@
m->pg_init_count = 0;
}
-static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg)
+static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg,
+ size_t nr_bytes)
{
struct dm_path *path;
- path = pg->ps.type->select_path(&pg->ps, &m->repeat_count);
+ path = pg->ps.type->select_path(&pg->ps, &m->repeat_count, nr_bytes);
if (!path)
return -ENXIO;
@@ -260,7 +262,7 @@
return 0;
}
-static void __choose_pgpath(struct multipath *m)
+static void __choose_pgpath(struct multipath *m, size_t nr_bytes)
{
struct priority_group *pg;
unsigned bypassed = 1;
@@ -272,12 +274,12 @@
if (m->next_pg) {
pg = m->next_pg;
m->next_pg = NULL;
- if (!__choose_path_in_pg(m, pg))
+ if (!__choose_path_in_pg(m, pg, nr_bytes))
return;
}
/* Don't change PG until it has no remaining paths */
- if (m->current_pg && !__choose_path_in_pg(m, m->current_pg))
+ if (m->current_pg && !__choose_path_in_pg(m, m->current_pg, nr_bytes))
return;
/*
@@ -289,7 +291,7 @@
list_for_each_entry(pg, &m->priority_groups, list) {
if (pg->bypassed == bypassed)
continue;
- if (!__choose_path_in_pg(m, pg))
+ if (!__choose_path_in_pg(m, pg, nr_bytes))
return;
}
} while (bypassed--);
@@ -320,6 +322,7 @@
struct dm_mpath_io *mpio, unsigned was_queued)
{
int r = DM_MAPIO_REMAPPED;
+ size_t nr_bytes = bio->bi_size;
unsigned long flags;
struct pgpath *pgpath;
@@ -328,7 +331,7 @@
/* Do we need to select a new pgpath? */
if (!m->current_pgpath ||
(!m->queue_io && (m->repeat_count && --m->repeat_count == 0)))
- __choose_pgpath(m);
+ __choose_pgpath(m, nr_bytes);
pgpath = m->current_pgpath;
@@ -353,6 +356,11 @@
r = -EIO; /* Failed */
mpio->pgpath = pgpath;
+ mpio->nr_bytes = nr_bytes;
+
+ if (r == DM_MAPIO_REMAPPED && pgpath->pg->ps.type->start_io)
+ pgpath->pg->ps.type->start_io(&pgpath->pg->ps, &pgpath->path,
+ nr_bytes);
spin_unlock_irqrestore(&m->lock, flags);
@@ -431,7 +439,7 @@
goto out;
if (!m->current_pgpath)
- __choose_pgpath(m);
+ __choose_pgpath(m, 0);
pgpath = m->current_pgpath;
@@ -1209,7 +1217,7 @@
if (pgpath) {
ps = &pgpath->pg->ps;
if (ps->type->end_io)
- ps->type->end_io(ps, &pgpath->path);
+ ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
}
if (r != DM_ENDIO_INCOMPLETE)
mempool_free(mpio, m->mpio_pool);
@@ -1425,7 +1433,7 @@
spin_lock_irqsave(&m->lock, flags);
if (!m->current_pgpath)
- __choose_pgpath(m);
+ __choose_pgpath(m, 0);
if (m->current_pgpath) {
bdev = m->current_pgpath->path.dev->bdev;