From e772bef5631017145cd0270d72a9ada1378e022a Mon Sep 17 00:00:00 2001
From: Barak Sason Rofman <bsasonro@redhat.com>
Date: Fri, 30 Oct 2020 08:27:47 +0200
Subject: [PATCH 478/478] DHT - Fixing rebalance failure on issuing stop
command
Issuing a stop command for an ongoing rebalance process results in an error.
This issue was brought up in https://bugzilla.redhat.com/1286171 and a patch
(https://review.gluster.org/24103/) was submitted to resolve the issue.
However the submitted patch resolved only part of the
problem by reducing the number of log messages that were printed (since
rebalnace is currently a recursive process, an error message was printed
for every directory) but didn't fully resolve the root cause for the
failure.
This patch fixes the issue by modifying the code-path which handles the
termination of the rebalance process by issuing a stop command.
Upstream:
> Reviewed-on: https://github.com/gluster/glusterfs/pull/1628
> fixes: #1627
> Change-Id: I604f2b0f8b1ccb1026b8425a14200bbd1dc5bd03
> Signed-off-by: Barak Sason Rofman bsasonro@redhat.com
BUG: 1286171
Change-Id: I604f2b0f8b1ccb1026b8425a14200bbd1dc5bd03
Signed-off-by: Barak Sason Rofman <bsasonro@redhat.com>
Reviewed-on: https://code.engineering.redhat.com/gerrit/216896
Tested-by: RHGS Build Bot <nigelb@redhat.com>
Reviewed-by: Sunil Kumar Heggodu Gopala Acharya <sheggodu@redhat.com>
---
xlators/cluster/dht/src/dht-rebalance.c | 22 ++++++++++++----------
1 file changed, 12 insertions(+), 10 deletions(-)
diff --git a/xlators/cluster/dht/src/dht-rebalance.c b/xlators/cluster/dht/src/dht-rebalance.c
index abc10fc..d49a719 100644
--- a/xlators/cluster/dht/src/dht-rebalance.c
+++ b/xlators/cluster/dht/src/dht-rebalance.c
@@ -3113,12 +3113,10 @@ int static gf_defrag_get_entry(xlator_t *this, int i,
struct dht_container *tmp_container = NULL;
if (defrag->defrag_status != GF_DEFRAG_STATUS_STARTED) {
- ret = -1;
goto out;
}
if (dir_dfmeta->offset_var[i].readdir_done == 1) {
- ret = 0;
goto out;
}
@@ -3135,7 +3133,6 @@ int static gf_defrag_get_entry(xlator_t *this, int i,
&(dir_dfmeta->equeue[i]), xattr_req, NULL);
if (ret == 0) {
dir_dfmeta->offset_var[i].readdir_done = 1;
- ret = 0;
goto out;
}
@@ -3161,7 +3158,6 @@ int static gf_defrag_get_entry(xlator_t *this, int i,
while (1) {
if (defrag->defrag_status != GF_DEFRAG_STATUS_STARTED) {
- ret = -1;
goto out;
}
@@ -3273,12 +3269,14 @@ int static gf_defrag_get_entry(xlator_t *this, int i,
}
out:
- if (ret == 0) {
- *container = tmp_container;
- } else {
- if (tmp_container) {
+ if (defrag->defrag_status == GF_DEFRAG_STATUS_STARTED) {
+ if (ret == 0) {
+ *container = tmp_container;
+ } else {
gf_defrag_free_container(tmp_container);
}
+ } else {
+ gf_defrag_free_container(tmp_container);
}
return ret;
@@ -3487,7 +3485,7 @@ gf_defrag_process_dir(xlator_t *this, gf_defrag_info_t *defrag, loc_t *loc,
migrate_data, dir_dfmeta, xattr_req,
&should_commit_hash, perrno);
- if (defrag->defrag_status == GF_DEFRAG_STATUS_STOPPED) {
+ if (defrag->defrag_status != GF_DEFRAG_STATUS_STARTED) {
goto out;
}
@@ -3947,7 +3945,7 @@ gf_defrag_fix_layout(xlator_t *this, gf_defrag_info_t *defrag, loc_t *loc,
ret = gf_defrag_fix_layout(this, defrag, &entry_loc, fix_layout,
migrate_data);
- if (defrag->defrag_status == GF_DEFRAG_STATUS_STOPPED) {
+ if (defrag->defrag_status != GF_DEFRAG_STATUS_STARTED) {
goto out;
}
@@ -4015,6 +4013,10 @@ gf_defrag_fix_layout(xlator_t *this, gf_defrag_info_t *defrag, loc_t *loc,
(defrag->cmd != GF_DEFRAG_CMD_START_LAYOUT_FIX)) {
ret = gf_defrag_process_dir(this, defrag, loc, migrate_data, &perrno);
+ if (defrag->defrag_status != GF_DEFRAG_STATUS_STARTED) {
+ goto out;
+ }
+
if (ret && (ret != 2)) {
if (perrno == ENOENT || perrno == ESTALE) {
ret = 0;
--
1.8.3.1