From ceae081cc7df9f82ba03503f4997c2a856c0966e Mon Sep 17 00:00:00 2001
From: Don Mitchell <dmitchell@edx.org>
Date: Tue, 19 Aug 2014 14:49:24 -0400
Subject: [PATCH] Refactored expected indices after email w/ mongo Key order
 has no bearing on key order in queries other than for Key order should be by
 greatest to least cardinality Added sparse and unique declarations.

---
 mongo_indexes.md | 62 +++++++-----------------------------------------
 1 file changed, 9 insertions(+), 53 deletions(-)

diff --git a/mongo_indexes.md b/mongo_indexes.md
index 0764f82afe..df8ce78ce5 100644
--- a/mongo_indexes.md
+++ b/mongo_indexes.md
@@ -20,16 +20,14 @@ which can be `uploadDate`, `display_name`,
 
 Replace existing index which leaves out `run` with this one:
 ```
-ensureIndex({'_id.tag': 1, '_id.org': 1, '_id.course': 1, '_id.category': 1, '_id.run': 1})
-ensureIndex({'content_son.tag': 1, 'content_son.org': 1, 'content_son.course': 1, 'content_son.category': 1, 'content_son.run': 1})
+ensureIndex({'_id.org': 1, '_id.course': 1, '_id.name': 1}, {'sparse': true})
+ensureIndex({'content_son.org': 1, 'content_son.course': 1, 'content_son.name': 1}, {'sparse': true})
+ensureIndex({'_id.org': 1, '_id.course': 1, 'uploadDate': 1}, {'sparse': true})
+ensureIndex({'_id.org': 1, '_id.course': 1, 'display_name': 1}, {'sparse': true})
+ensureIndex({'content_son.org': 1, 'content_son.course': 1, 'uploadDate': 1}, {'sparse': true})
+ensureIndex({'content_son.org': 1, 'content_son.course': 1, 'display_name': 1}, {'sparse': true})
 ```
 
-Note: I'm not advocating adding one which leaves out `category` for now because that would only be
-used for `delete_all_course_assets` which in the future should not actually delete the assets except
-when doing garbage collection.
-
-Remove index on `displayname`
-
 modulestore:
 ============
 
@@ -41,7 +39,7 @@ and no field is omitted.
 Because we often query for some subset of the id, we define this index:
 
 ```
-ensureIndex({'_id.tag': 1, '_id.org': 1, '_id.course': 1, '_id.category': 1, '_id.name': 1, '_id.revision': 1})
+ensureIndex({'_id.org': 1, '_id.course': 1, '_id.category': 1, '_id.name': 1})
 ```
 
 Because we often scan for all category='course' regardless of the value of the other fields:
@@ -51,54 +49,12 @@ ensureIndex({'_id.category': 1})
 
 Because lms calls get_parent_locations frequently (for path generation):
 ```
-ensureIndex({'_id.tag': 1, '_id.org': 1, '_id.course': 1, 'definition.children': 1})
-```
-
-Remove these indices if they exist as I can find no use for them:
-```
- { "_id.course": 1, "_id.org": 1, "_id.revision": 1, "definition.children": 1 }
- { "definition.children": 1 }
-```
-
-NOTE, that index will only aid queries which provide the keys in exactly that form and order. The query can
-omit later fields of the query but not earlier. Thus ```modulestore.find({'_id.org': 'myu'})``` will not use
-the index as it omits the tag. As soon as mongo comes across an index field omitted from the query, it stops
-considering the index. On the other hand, ```modulestore.find({'_id.tag': 'i4x', '_id.org': 'myu', '_id.category': 'problem'})```
-will use the index to get the records matching the tag and org and then will scan all of them
-for matches to the category.
-
-To find out if any records have the wrong id structure, run
-```
-db.fs.files.find({uploadDate: {$gt: startDate, $lt: endDate},
-       $where: function() {
-           var keys = ['category', 'name', 'course', 'tag', 'org', 'revision'];
-           for (var key in this._id) {
-               if (key != keys.shift()) {
-                   return true;
-               }
-           }
-           return false;
-       }},
-       {_id: 1})
+ensureIndex({'definition.children': 1}, {'sparse': true})
 ```
 
 modulestore.active_versions
 ===========================
 
 ```
-ensureIndex({'org': 1, 'offering': 1})
+ensureIndex({'org': 1, 'course': 1, 'run': 1}, {'unique': true})
 ```
-
-modulestore.structures
-======================
-
-```
-ensureIndex({'previous_version': 1})
-```
-
-modulestore.definitions
-=======================
-
-```
-ensureIndex({'category': 1})
-```
\ No newline at end of file