crush: add chooseleaf_stable tunable

Add a tunable to fix the bug that chooseleaf may cause unnecessary pg
migrations when some device fails.

Reflects ceph.git commit fdb3f664448e80d984470f32f04e2e6f03ab52ec.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>

1 files changed, 7 insertions, 1 deletions

diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 48b49305716b..be8f12b8f195 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -59,7 +59,8 @@ enum {
         CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */
         CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10,
         CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11,
-        CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12
+        CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12,
+        CRUSH_RULE_SET_CHOOSELEAF_STABLE = 13
 };
 
 /*
@@ -205,6 +206,11 @@ struct crush_map {
          * mappings line up a bit better with previous mappings. */
         __u8 chooseleaf_vary_r;
 
+        /* if true, it makes chooseleaf firstn to return stable results (if
+         * no local retry) so that data migrations would be optimal when some
+         * device fails. */
+        __u8 chooseleaf_stable;
+
 #ifndef __KERNEL__
         /*
          * version 0 (original) of straw_calc has various flaws.  version 1