From e2b149cc4ba00766aceb87950c6de72ea7fc8b2e Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 19 Mar 2014 16:58:37 +0200 Subject: crush: add chooseleaf_vary_r tunable The current crush_choose_firstn code will re-use the same 'r' value for the recursive call. That means that if we are hitting a collision or rejection for some reason (say, an OSD that is marked out) and need to retry, we will keep making the same (bad) choice in that recursive selection. Introduce a tunable that fixes that behavior by incorporating the parent 'r' value into the recursive starting point, so that a different path will be taken in subsequent placement attempts. Note that this was done from the get-go for the new crush_choose_indep algorithm. This was exposed by a user who was seeing PGs stuck in active+remapped after reweight-by-utilization because the up set mapped to a single OSD. Reflects ceph.git commit a8e6c9fbf88bad056dd05d3eb790e98a5e43451a. Signed-off-by: Ilya Dryomov Reviewed-by: Josh Durgin --- include/linux/crush/crush.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/crush') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index acaa5615d634..75f36a6c7f67 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -173,6 +173,12 @@ struct crush_map { * apply to a collision: in that case we will retry as we used * to. */ __u32 chooseleaf_descend_once; + + /* if non-zero, feed r into chooseleaf, bit-shifted right by (r-1) + * bits. a value of 1 is best for new clusters. for legacy clusters + * that want to limit reshuffling, a value of 3 or 4 will make the + * mappings line up a bit better with previous mappings. */ + __u8 chooseleaf_vary_r; }; -- cgit