From aef8e51b9974603d397cc8f5301b24451d012e46 Mon Sep 17 00:00:00 2001
From: Susant Palai <spalai@redhat.com>
Date: Fri, 24 Apr 2020 13:32:51 +0530
Subject: [PATCH 367/367] dht: Handle setxattr and rm race for directory in
 rebalance

Problem: Selfheal as part of directory does not return an error if
the layout setxattr fails. This is because the actual lookup fop
must have been successful to proceed for layout heal. Hence, we could
not tell if fix-layout failed in rebalance.

Solution: We can check this information in the layout structure that
whether all the xlators have returned error.

> fixes: #1200
> hange-Id: I3e5f2a36c0d934c21476a73a9a5473d8e490cde7
> Signed-off-by: Susant Palai <spalai@redhat.com>
(backport of https://review.gluster.org/#/c/glusterfs/+/24375/)

BUG: 1812789
Change-Id: I897826c4c2e883b3085c9314deff32d649b4588e
Signed-off-by: Susant Palai <spalai@redhat.com>
Reviewed-on: https://code.engineering.redhat.com/gerrit/198726
Reviewed-by: Mohit Agrawal <moagrawa@redhat.com>
Reviewed-by: Sunil Kumar Heggodu Gopala Acharya <sheggodu@redhat.com>
---
 xlators/cluster/dht/src/dht-common.c    | 19 +++++++++++++++++++
 xlators/cluster/dht/src/dht-common.h    |  3 +++
 xlators/cluster/dht/src/dht-rebalance.c | 11 +++++++++++
 3 files changed, 33 insertions(+)

diff --git a/xlators/cluster/dht/src/dht-common.c b/xlators/cluster/dht/src/dht-common.c
index d0b5287..7890e7a 100644
--- a/xlators/cluster/dht/src/dht-common.c
+++ b/xlators/cluster/dht/src/dht-common.c
@@ -11286,3 +11286,22 @@ dht_pt_fgetxattr(call_frame_t *frame, xlator_t *this, fd_t *fd, const char *key,
                FIRST_CHILD(this)->fops->fgetxattr, fd, key, xdata);
     return 0;
 }
+
+/* The job of this function is to check if all the xlators have updated
+ * error in the layout. */
+int
+dht_dir_layout_error_check(xlator_t *this, inode_t *inode)
+{
+    dht_layout_t *layout = NULL;
+    int i = 0;
+
+    layout = dht_layout_get(this, inode);
+    for (i = 0; i < layout->cnt; i++) {
+        if (layout->list[i].err == 0) {
+            return 0;
+        }
+    }
+
+    /* Returning the first xlator error as all xlators have errors */
+    return layout->list[0].err;
+}
diff --git a/xlators/cluster/dht/src/dht-common.h b/xlators/cluster/dht/src/dht-common.h
index ce11f02..4d2aae6 100644
--- a/xlators/cluster/dht/src/dht-common.h
+++ b/xlators/cluster/dht/src/dht-common.h
@@ -1544,4 +1544,7 @@ dht_pt_rename(call_frame_t *frame, xlator_t *this, loc_t *oldloc, loc_t *newloc,
 int32_t
 dht_check_remote_fd_failed_error(dht_local_t *local, int op_ret, int op_errno);
 
+int
+dht_dir_layout_error_check(xlator_t *this, inode_t *inode);
+
 #endif /* _DHT_H */
diff --git a/xlators/cluster/dht/src/dht-rebalance.c b/xlators/cluster/dht/src/dht-rebalance.c
index 7d9df02..33cacfe 100644
--- a/xlators/cluster/dht/src/dht-rebalance.c
+++ b/xlators/cluster/dht/src/dht-rebalance.c
@@ -3928,6 +3928,17 @@ gf_defrag_fix_layout(xlator_t *this, gf_defrag_info_t *defrag, loc_t *loc,
     }
 
     ret = syncop_setxattr(this, loc, fix_layout, 0, NULL, NULL);
+
+    /* In case of a race where the directory is deleted just before
+     * layout setxattr, the errors are updated in the layout structure.
+     * We can use this information to make a decision whether the directory
+     * is deleted entirely.
+     */
+    if (ret == 0) {
+        ret = dht_dir_layout_error_check(this, loc->inode);
+        ret = -ret;
+    }
+
     if (ret) {
         if (-ret == ENOENT || -ret == ESTALE) {
             gf_msg(this->name, GF_LOG_INFO, -ret, DHT_MSG_LAYOUT_FIX_FAILED,
-- 
1.8.3.1