From 0ae38df6403942a2438404d46a6e05b503db3485 Mon Sep 17 00:00:00 2001 From: Ashish Pandey Date: Tue, 4 Jul 2017 16:18:20 +0530 Subject: cluster/ec : Don't try to heal when no sink is UP Problem: 4 + 2 EC volume configuration. If untar of linux is going on and we kill a brick, indices will be created for the files/dir which need to be healed. ec_shd_index_sweep spawns threads to scan these entries and start heal. If in the middle of this we kill one more brick, we end up in a situation where we can not heal an entry as there are only "ec->fragment" number of bricks are UP. However, the scan will be continued and it will trigger the heal for those entries. Solution: When a heal is triggered for an entry, check if it *CAN* be healed or not. If not come out with ENOTCONN. Change-Id: I305be7701c289f36bd7bde22491b71074771424f BUG: 1464359 Signed-off-by: Ashish Pandey Reviewed-on: https://review.gluster.org/17692 Smoke: Gluster Build System CentOS-regression: Gluster Build System NetBSD-regression: NetBSD Build System Reviewed-by: Pranith Kumar Karampuri Reviewed-by: Sunil Kumar Acharya Reviewed-by: Xavier Hernandez --- xlators/cluster/ec/src/ec-heald.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'xlators/cluster/ec/src/ec-heald.c') diff --git a/xlators/cluster/ec/src/ec-heald.c b/xlators/cluster/ec/src/ec-heald.c index ffb78d5e950..2e8ece8e3f7 100644 --- a/xlators/cluster/ec/src/ec-heald.c +++ b/xlators/cluster/ec/src/ec-heald.c @@ -199,6 +199,9 @@ ec_shd_index_heal (xlator_t *subvol, gf_dirent_t *entry, loc_t *parent, int ret = 0; ec = healer->this->private; + if (ec->xl_up_count <= ec->fragments) { + return -ENOTCONN; + } if (!ec->shd.enabled) return -EBUSY; @@ -281,6 +284,9 @@ ec_shd_full_heal (xlator_t *subvol, gf_dirent_t *entry, loc_t *parent, int ret = 0; ec = this->private; + if (ec->xl_up_count <= ec->fragments) { + return -ENOTCONN; + } if (!ec->shd.enabled) return -EBUSY; -- cgit