From 71b2c2a6dd288e2bb8ec73cff3e909a0f12f2b5c Mon Sep 17 00:00:00 2001
From: "J. Eric Ivancich" <ivancich@redhat.com>
Date: Sat, 18 Mar 2023 14:35:39 -0400
Subject: [PATCH] rgw: add unordered listing to reindex to force stats update

By including an unordered listing in the script, we will complete
placing objects in the bucket index and allow stats to be updated
rather than waiting for this to happen organically at a user's
request. Unordered is preferred as it can run more efficiently.

Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
---
 src/rgw/rgw-restore-bucket-index | 75 ++++++++++++++++++++++++++++----
 1 file changed, 66 insertions(+), 9 deletions(-)

diff --git a/src/rgw/rgw-restore-bucket-index b/src/rgw/rgw-restore-bucket-index
index e8503ca47562b..05665811925d4 100755
--- a/src/rgw/rgw-restore-bucket-index
+++ b/src/rgw/rgw-restore-bucket-index
@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-# version 2023-03-07
+# version 2023-03-21
 
 # rgw-restore-bucket-index is an EXPERIMENTAL tool to use in case
 # bucket index entries for objects in the bucket are somehow lost. It
@@ -34,6 +34,18 @@ export obj_list=/tmp/rgwrbi-object-list.$$
 export zone_info=/tmp/rgwrbi-zone-info.$$
 export clean_temps=1
 
+# number of seconds for a bucket index pending op to be completed via
+# dir_suggest mechanism
+pending_op_secs=120
+
+#
+if which radosgw-admin > /dev/null ;then
+  :
+else
+  echo 'Error: must have command `radosgw-admin` installed and on $PATH for operation.'
+  exit 1
+fi
+
 # make sure jq is available
 if which jq > /dev/null ;then
   :
@@ -126,6 +138,12 @@ bucket=$1
 radosgw-admin metadata get bucket:$bucket >$bkt_entry 2>/dev/null
 marker=$(strip_quotes $(jq ".data.bucket.marker" $bkt_entry))
 bucket_id=$(strip_quotes $(jq ".data.bucket.bucket_id" $bkt_entry))
+if [ -z "$marker" -o -z "$bucket_id" ] ;then
+    echo "ERROR: unable to read entry-point metadata for bucket \"$bucket\"."
+    clean
+    exit 1
+fi
+
 echo marker is $marker
 echo bucket_id is $bucket_id
 
@@ -134,11 +152,17 @@ radosgw-admin metadata get bucket.instance:${bucket}:$bucket_id >$bkt_inst 2>/de
 
 # handle versioned buckets
 bkt_flags=$(jq ".data.bucket_info.flags" $bkt_inst)
-is_versioned=$(( $bkt_flags & 2)) # mask bit indicating it's a versioned bucket
+if [ -z "$bkt_flags" ] ;then
+    echo "ERROR: unable to read instance metadata for bucket \"$bucket\"."
+    exit 1
+fi
+
+# mask bit indicating it's a versioned bucket
+is_versioned=$(( $bkt_flags & 2))
 if [ "$is_versioned" -ne 0 ] ;then
-   echo "Error: this bucket appears to be versioned, and this tool cannot work with versioned buckets."
-   clean
-   exit 1
+    echo "Error: this bucket appears to be versioned, and this tool cannot work with versioned buckets."
+    clean
+    exit 1
 fi
 
 # examine number of bucket index shards
@@ -156,11 +180,11 @@ echo data pool is $pool
 
 # handle the case where the resulting object list file is empty
 if [ -s $obj_list ] ;then
-  :
+    :
 else
-  echo "NOTICE: No head objects for bucket \"$bucket\" were found in pool \"$pool\", so nothing was recovered."
-  clean
-  exit 0
+    echo "NOTICE: No head objects for bucket \"$bucket\" were found in pool \"$pool\", so nothing was recovered."
+    clean
+    exit 0
 fi
 
 if [ -z "$proceed" ] ;then
@@ -188,6 +212,39 @@ fi
 
 # execute object rewrite on all of the head objects
 radosgw-admin object reindex --bucket=$bucket --objects-file=$obj_list 2>/dev/null
+reindex_done=$(date +%s)
+
+# note: large is 2^30
+export large=1073741824
+
+listcmd="radosgw-admin bucket list --bucket=$bucket --allow-unordered --max-entries=$large"
+
+if [ -n "$proceed" ] ;then
+    sleep $pending_op_secs
+    $listcmd >/dev/null 2>/dev/null
+else
+    echo "NOTICE: Bucket stats are currently incorrect. They can be restored with the following command after 2 minutes:"
+    echo "    $listcmd"
+
+    while true ; do
+	read -p "Would you like to take the time to recalculate bucket stats now? [yes/no] " action
+	if [ "$action" == "no" ] ;then
+	    break
+	elif [ "$action" == "yes" ] ;then
+	    # make sure at least $pending_op_secs since reindex completed
+	    now=$(date +%s)
+	    sleep_time=$(expr $pending_op_secs - $now + $reindex_done)
+	    if [ "$sleep_time" -gt 0 ] ;then
+		sleep $sleep_time
+	    fi
+
+	    $listcmd >/dev/null 2>/dev/null
+	    break
+	else
+	    echo "Error: response \"$action\" is not understood."
+	fi
+    done
+fi
 
 clean
 echo Done
-- 
2.39.5