SERVER-60087 Add stats under collStats for timeseries bucket compression

7 files changed, 172 insertions, 7 deletions

diff --git a/src/mongo/db/commands/SConscript b/src/mongo/db/commands/SConscript
index fde798457c6..4d75bf91168 100644
--- a/src/mongo/db/commands/SConscript
+++ b/src/mongo/db/commands/SConscript
@@ -368,6 +368,7 @@ env.Library(
         '$BUILD_DIR/mongo/db/timeseries/catalog_helper',
         '$BUILD_DIR/mongo/db/timeseries/timeseries_conversion_util',
         '$BUILD_DIR/mongo/db/timeseries/timeseries_options',
+        '$BUILD_DIR/mongo/db/timeseries/timeseries_stats',
         '$BUILD_DIR/mongo/db/transaction',
         '$BUILD_DIR/mongo/db/views/views_mongod',
         '$BUILD_DIR/mongo/executor/async_request_executor',
diff --git a/src/mongo/db/commands/write_commands.cpp b/src/mongo/db/commands/write_commands.cpp
index 9452f0c74b3..61f6b31d0a0 100644
--- a/src/mongo/db/commands/write_commands.cpp
+++ b/src/mongo/db/commands/write_commands.cpp
@@ -69,6 +69,7 @@
 #include "mongo/db/timeseries/bucket_catalog.h"
 #include "mongo/db/timeseries/bucket_compression.h"
 #include "mongo/db/timeseries/timeseries_constants.h"
+#include "mongo/db/timeseries/timeseries_stats.h"
 #include "mongo/db/transaction_participant.h"
 #include "mongo/db/views/view_catalog.h"
 #include "mongo/db/write_concern.h"
@@ -690,11 +691,16 @@ public:
                 return SingleWriteResult();
             }
 
-            auto bucketCompressionFunc =
-                [&closedBucket](const BSONObj& bucketDoc) -> boost::optional<BSONObj> {
+            boost::optional<int> beforeSize;
+            boost::optional<int> afterSize;
+
+            auto bucketCompressionFunc = [&](const BSONObj& bucketDoc) -> boost::optional<BSONObj> {
+                beforeSize = bucketDoc.objsize();
+                // Reset every time we run to ensure we never use a stale value
+                afterSize = boost::none;
                 auto compressed = timeseries::compressBucket(bucketDoc, closedBucket.timeField);
                 // If compressed object size is larger than uncompressed, skip compression update.
-                if (compressed && compressed->objsize() > bucketDoc.objsize()) {
+                if (compressed && compressed->objsize() >= *beforeSize) {
                     LOGV2_DEBUG(5857802,
                                 1,
                                 "Skipping time-series bucket compression, compressed object is "
@@ -703,13 +709,27 @@ public:
                                 "compressedSize"_attr = compressed->objsize());
                     return boost::none;
                 }
+                afterSize = compressed->objsize();
                 return compressed;
             };
 
-            return _getTimeseriesSingleWriteResult(write_ops_exec::performUpdates(
-                opCtx,
-                _makeTimeseriesCompressionOp(opCtx, closedBucket.bucketId, bucketCompressionFunc),
-                OperationSource::kStandard));
+            auto compressionOp =
+                _makeTimeseriesCompressionOp(opCtx, closedBucket.bucketId, bucketCompressionFunc);
+            auto result = _getTimeseriesSingleWriteResult(
+                write_ops_exec::performUpdates(opCtx, compressionOp, OperationSource::kStandard));
+
+            // Report stats, if we fail before running the transform function then just skip
+            // reporting.
+            if (result.isOK() && beforeSize) {
+                auto coll = CollectionCatalog::get(opCtx)->lookupCollectionByNamespaceForRead(
+                    opCtx, compressionOp.getNamespace());
+                if (coll) {
+                    const auto& stats = TimeseriesStats::get(coll.get());
+                    stats.onBucketClosed(*beforeSize, afterSize);
+                }
+            }
+
+            return result;
         }
 
         void _commitTimeseriesBucket(OperationContext* opCtx,
diff --git a/src/mongo/db/stats/SConscript b/src/mongo/db/stats/SConscript
index d7a439cd38e..b27a81181ac 100644
--- a/src/mongo/db/stats/SConscript
+++ b/src/mongo/db/stats/SConscript
@@ -129,6 +129,7 @@ env.Library(
         '$BUILD_DIR/mongo/db/index/index_access_method',
         '$BUILD_DIR/mongo/db/pipeline/document_sources_idl',
         '$BUILD_DIR/mongo/db/timeseries/bucket_catalog',
+        '$BUILD_DIR/mongo/db/timeseries/timeseries_stats',
         'fill_locker_info',
         'top',
     ],
diff --git a/src/mongo/db/stats/storage_stats.cpp b/src/mongo/db/stats/storage_stats.cpp
index 96067384f6a..a2253d49706 100644
--- a/src/mongo/db/stats/storage_stats.cpp
+++ b/src/mongo/db/stats/storage_stats.cpp
@@ -38,6 +38,7 @@
 #include "mongo/db/index/index_access_method.h"
 #include "mongo/db/index/index_descriptor.h"
 #include "mongo/db/timeseries/bucket_catalog.h"
+#include "mongo/db/timeseries/timeseries_stats.h"
 #include "mongo/db/views/view_catalog.h"
 #include "mongo/logv2/log.h"
 
@@ -99,6 +100,7 @@ Status appendCollectionStorageStats(OperationContext* opCtx,
             bob.append("avgBucketSize", collection->averageObjectSize(opCtx));
         }
         BucketCatalog::get(opCtx).appendExecutionStats(collNss.getTimeseriesViewNamespace(), &bob);
+        TimeseriesStats::get(collection.get()).append(&bob);
     } else {
         result->appendNumber("count", numRecords);
         if (numRecords) {
diff --git a/src/mongo/db/timeseries/SConscript b/src/mongo/db/timeseries/SConscript
index 2a5ac31b204..e8b0f135c81 100644
--- a/src/mongo/db/timeseries/SConscript
+++ b/src/mongo/db/timeseries/SConscript
@@ -47,6 +47,16 @@ env.Library(
 )
 
 env.Library(
+    target='timeseries_stats',
+    source=[
+        'timeseries_stats.cpp',
+    ],
+    LIBDEPS_PRIVATE=[
+        '$BUILD_DIR/mongo/base',
+    ],
+)
+
+env.Library(
     target='catalog_helper',
     source=[
         'catalog_helper.cpp',
diff --git a/src/mongo/db/timeseries/timeseries_stats.cpp b/src/mongo/db/timeseries/timeseries_stats.cpp
new file mode 100644
index 00000000000..33cafb386ff
--- /dev/null
+++ b/src/mongo/db/timeseries/timeseries_stats.cpp
@@ -0,0 +1,65 @@
+/**
+ *    Copyright (C) 2021-present MongoDB, Inc.
+ *
+ *    This program is free software: you can redistribute it and/or modify
+ *    it under the terms of the Server Side Public License, version 1,
+ *    as published by MongoDB, Inc.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    Server Side Public License for more details.
+ *
+ *    You should have received a copy of the Server Side Public License
+ *    along with this program. If not, see
+ *    <http://www.mongodb.com/licensing/server-side-public-license>.
+ *
+ *    As a special exception, the copyright holders give permission to link the
+ *    code of portions of this program with the OpenSSL library under certain
+ *    conditions as described in each individual source file and distribute
+ *    linked combinations including the program with the OpenSSL library. You
+ *    must comply with the Server Side Public License in all respects for
+ *    all of the code used other than as permitted herein. If you modify file(s)
+ *    with this exception, you may extend this exception to your version of the
+ *    file(s), but you are not obligated to do so. If you do not wish to do so,
+ *    delete this exception statement from your version. If you delete this
+ *    exception statement from all source files in the program, then also delete
+ *    it in the license file.
+ */
+
+#include "mongo/db/timeseries/timeseries_stats.h"
+
+#include "mongo/db/catalog/collection.h"
+
+namespace mongo {
+namespace {
+
+const auto getTimeseriesStatsDecoration =
+    SharedCollectionDecorations::declareDecoration<TimeseriesStats>();
+
+}  // namespace
+
+const TimeseriesStats& TimeseriesStats::get(const Collection* coll) {
+    return getTimeseriesStatsDecoration(coll->getSharedDecorations());
+}
+
+void TimeseriesStats::onBucketClosed(int uncompressedSize,
+                                     boost::optional<int> compressedSize) const {
+    _uncompressedSize.fetchAndAddRelaxed(uncompressedSize);
+    if (compressedSize) {
+        _compressedSize.fetchAndAddRelaxed(*compressedSize);
+        _numCompressedBuckets.fetchAndAddRelaxed(1);
+    } else {
+        _compressedSize.fetchAndAddRelaxed(uncompressedSize);
+        _numUncompressedBuckets.fetchAndAddRelaxed(1);
+    }
+}
+
+void TimeseriesStats::append(BSONObjBuilder* builder) const {
+    builder->appendNumber("numBytesUncompressed", _uncompressedSize.load());
+    builder->appendNumber("numBytesCompressed", _compressedSize.load());
+    builder->appendNumber("numCompressedBuckets", _numCompressedBuckets.load());
+    builder->appendNumber("numUncompressedBuckets", _numUncompressedBuckets.load());
+}
+
+}  // namespace mongo
diff --git a/src/mongo/db/timeseries/timeseries_stats.h b/src/mongo/db/timeseries/timeseries_stats.h
new file mode 100644
index 00000000000..c7870f34d35
--- /dev/null
+++ b/src/mongo/db/timeseries/timeseries_stats.h
@@ -0,0 +1,66 @@
+/**
+ *    Copyright (C) 2021-present MongoDB, Inc.
+ *
+ *    This program is free software: you can redistribute it and/or modify
+ *    it under the terms of the Server Side Public License, version 1,
+ *    as published by MongoDB, Inc.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    Server Side Public License for more details.
+ *
+ *    You should have received a copy of the Server Side Public License
+ *    along with this program. If not, see
+ *    <http://www.mongodb.com/licensing/server-side-public-license>.
+ *
+ *    As a special exception, the copyright holders give permission to link the
+ *    code of portions of this program with the OpenSSL library under certain
+ *    conditions as described in each individual source file and distribute
+ *    linked combinations including the program with the OpenSSL library. You
+ *    must comply with the Server Side Public License in all respects for
+ *    all of the code used other than as permitted herein. If you modify file(s)
+ *    with this exception, you may extend this exception to your version of the
+ *    file(s), but you are not obligated to do so. If you do not wish to do so,
+ *    delete this exception statement from your version. If you delete this
+ *    exception statement from all source files in the program, then also delete
+ *    it in the license file.
+ */
+
+#pragma once
+
+#include <boost/optional.hpp>
+
+#include "mongo/db/catalog/collection.h"
+
+namespace mongo {
+/**
+ * Timeseries statistics at Collection-level. Decorates 'SharedCollectionDecorations' and is not
+ * versioned per Collection instance.
+ *
+ * Used for timeseries statistics the BucketCatalog is unable to keep track of.
+ */
+class TimeseriesStats {
+public:
+    static const TimeseriesStats& get(const Collection* coll);
+
+    /**
+     * Records stats for a closed time-series bucket. 'boost::none' for compressedSize means
+     * compression failed for any reason.
+     */
+    void onBucketClosed(int uncompressedSize, boost::optional<int> compressedSize) const;
+
+    /**
+     * Appends current stats to the given BSONObjBuilder.
+     */
+    void append(BSONObjBuilder* builder) const;
+
+private:
+    // We need to be able to record stats on a time-series bucket collection without requiring a
+    // non-const Collection (which requires MODE_X collection lock).
+    mutable AtomicWord<long long> _uncompressedSize;
+    mutable AtomicWord<long long> _compressedSize;
+    mutable AtomicWord<long long> _numCompressedBuckets;
+    mutable AtomicWord<long long> _numUncompressedBuckets;
+};
+}  // namespace mongo