Merge pull request #47221 from markhpc/wip-faster-rocksdb

[WIP] kv/RocksDBStore: Improved RocksDB Settings and Tombstone behavior

2 files changed, 40 insertions, 1 deletions

diff --git a/src/common/options/global.yaml.in b/src/common/options/global.yaml.in
index bfab547af22..08d388c4e05 100644
--- a/src/common/options/global.yaml.in
+++ b/src/common/options/global.yaml.in
@@ -3548,6 +3548,36 @@ options:
 # osd_*_priority determines the ratio of available io between client and
 # recovery.  Each option may be set between
 # 1..63.
+- name: rocksdb_cf_compact_on_deletion
+  type: bool
+  level: dev
+  desc: Compact the column family when a certain number of tombstones are observed within a given window.
+  long_desc: 'This setting instructs RocksDB to compact a column family when a certain
+    number of tombstones are observed during iteration within a certain sliding window.
+    For instance if rocksdb_cf_compact_on_deletion_sliding_window is 8192 and
+    rocksdb_cf_compact_on_deletion_trigger is 4096,  then once 4096 tombstones are
+    observed after iteration over 8192 entries, the column family will be compacted.'
+  default: true
+  with_legacy: true
+  see_also:
+  - rocksdb_cf_compact_on_deletion_sliding_window
+  - rocksdb_cf_compact_on_deletion_trigger
+- name: rocksdb_cf_compact_on_deletion_sliding_window
+  type: int
+  level: dev
+  desc: The sliding window to use when rocksdb_cf_compact_on_deletion is enabled.
+  default: 32768
+  with_legacy: true
+  see_also:
+  - rocksdb_cf_compact_on_deletion
+- name: rocksdb_cf_compact_on_deletion_trigger
+  type: int
+  level: dev
+  desc: The trigger to use when rocksdb_cf_compact_on_deletion is enabled.
+  default: 16384
+  with_legacy: true
+  see_also:
+  - rocksdb_cf_compact_on_deletion
 - name: osd_client_op_priority
   type: uint
   level: advanced
@@ -4911,7 +4941,7 @@ options:
   type: str
   level: advanced
   desc: Full set of rocksdb settings to override
-  default: compression=kNoCompression,max_write_buffer_number=4,min_write_buffer_number_to_merge=1,recycle_log_file_num=4,write_buffer_size=268435456,writable_file_max_buffer_size=0,compaction_readahead_size=2097152,max_background_compactions=2,max_total_wal_size=1073741824
+  default: compression=kNoCompression,max_write_buffer_number=128,min_write_buffer_number_to_merge=16,compaction_style=kCompactionStyleLevel,write_buffer_size=8388608,max_background_jobs=4,level0_file_num_compaction_trigger=8,max_bytes_for_level_base=1073741824,max_bytes_for_level_multiplier=8,compaction_readahead_size=2MB,max_total_wal_size=1073741824,writable_file_max_buffer_size=0,ttl=21600
   with_legacy: true
 - name: bluestore_rocksdb_options_annex
   type: str
diff --git a/src/kv/RocksDBStore.cc b/src/kv/RocksDBStore.cc
index be032b4fa86..a3ecf3a5a1f 100644
--- a/src/kv/RocksDBStore.cc
+++ b/src/kv/RocksDBStore.cc
@@ -18,6 +18,7 @@
 #include "rocksdb/cache.h"
 #include "rocksdb/filter_policy.h"
 #include "rocksdb/utilities/convenience.h"
+#include "rocksdb/utilities/table_properties_collectors.h"
 #include "rocksdb/merge_operator.h"
 
 #include "common/perf_counters.h"
@@ -934,6 +935,14 @@ int RocksDBStore::update_column_family_options(const std::string& base_name,
       return r;
     }
   }
+
+  // Set Compact on Deletion Factory
+  if (cct->_conf->rocksdb_cf_compact_on_deletion) {
+    size_t sliding_window = cct->_conf->rocksdb_cf_compact_on_deletion_sliding_window;
+    size_t trigger = cct->_conf->rocksdb_cf_compact_on_deletion_trigger;
+    cf_opt->table_properties_collector_factories.emplace_back(
+        rocksdb::NewCompactOnDeletionCollectorFactory(sliding_window, trigger));
+  }
   return 0;
 }