ovsdb: Perform conversion with no data for clustered databases.

Currently, database schema conversion in case of clustered database
produces a transaction record with both new schema and converted
database data.  So, the sequence of events is following:

  1. Get the new schema.
  2. Convert the database to a new schema.
  3. Translate the newly converted database into JSON.
  4. Write the schema + data JSON to the storage.
  5. Destroy converted version of a database.
  6. Read schema + data JSON from the storage and parse.
  7. Create a new database from a parsed database data.
  8. Replace current database with the new one.

Most of these steps are very computationally expensive.  Also,
conversion to/from JSON is much more expensive than direct database
conversion with ovsdb_convert() that can make use of shallow data
copies.

Instead of doing all that, let's make use of previously introduced
ability to not write the converted data into the storage.  The process
will look like this then:

  1. Get the new schema.
  2. Convert the database to a new schema
     (to verify that it is possible).
  3. Write the schema to the storage.
  4. Destroy converted version of a database.
  5. Read the new schema from the storage and parse.
  6. Convert the database to a new schema.
  7. Replace current database with the new one.

Most of the operations here are performed on the small schema object,
instead of the actual database data.  Two remaining data operations
(actual conversion) are noticeably faster than conversion to/from
JSON due to reference counting and shallow data copies.

Steps 4-6 can be optimized later to not convert twice on the
process that initiates the conversion.

The change results in following performance improvements in conversion
of OVN_Southbound database schema from version 20.23.0 to 20.27.0
(measured on a single-server RAFT cluster with no clients):

          |       Before                |         After
          +---------+-------------------+---------+------------------
  DB size |  Total  | Max poll interval |  Total  | Max poll interval
  --------+---------+-------------------+---------+------------------
   542 MB | 47 sec. |     26 sec.       | 15 sec. |     10 sec.
   225 MB | 19 sec. |     10 sec.       |  6 sec. |    4.5 sec.

542 MB database had 19.5 M atoms, 225 MB database had 7.5 M atoms.

Overall performance improvement is about 3x.

Also, note that before this change database conversion basically
doubles the database file on disk.  Now it only writes a small
schema JSON.

Since the change requires backward-incompatible database file format
changes, documentation is updated on how to perform an upgrade.
Handled the same way as we did for the previous incompatible format
change in 2.15 (column diffs).

Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2022-December/052140.html
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Dumitru Ceara <dceara@redhat.com>
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>

4 files changed, 52 insertions, 3 deletions

diff --git a/ovsdb/ovsdb-server.c b/ovsdb/ovsdb-server.c
index 91c284e99..b64814076 100644
--- a/ovsdb/ovsdb-server.c
+++ b/ovsdb/ovsdb-server.c
@@ -1971,6 +1971,7 @@ parse_options(int argc, char *argv[],
         OPT_ACTIVE,
         OPT_NO_DBS,
         OPT_FILE_COLUMN_DIFF,
+        OPT_FILE_NO_DATA_CONVERSION,
         VLOG_OPTION_ENUMS,
         DAEMON_OPTION_ENUMS,
         SSL_OPTION_ENUMS,
@@ -1996,6 +1997,8 @@ parse_options(int argc, char *argv[],
         {"active", no_argument, NULL, OPT_ACTIVE},
         {"no-dbs", no_argument, NULL, OPT_NO_DBS},
         {"disable-file-column-diff", no_argument, NULL, OPT_FILE_COLUMN_DIFF},
+        {"disable-file-no-data-conversion", no_argument, NULL,
+         OPT_FILE_NO_DATA_CONVERSION},
         {NULL, 0, NULL, 0},
     };
     char *short_options = ovs_cmdl_long_options_to_short_options(long_options);
@@ -2092,6 +2095,10 @@ parse_options(int argc, char *argv[],
             ovsdb_file_column_diff_disable();
             break;
 
+        case OPT_FILE_NO_DATA_CONVERSION:
+            ovsdb_no_data_conversion_disable();
+            break;
+
         case '?':
             exit(EXIT_FAILURE);
 
diff --git a/ovsdb/ovsdb.c b/ovsdb/ovsdb.c
index afec96264..f67b836d7 100644
--- a/ovsdb/ovsdb.c
+++ b/ovsdb/ovsdb.c
@@ -39,6 +39,7 @@
 #include "transaction.h"
 #include "transaction-forward.h"
 #include "trigger.h"
+#include "unixctl.h"
 
 #include "openvswitch/vlog.h"
 VLOG_DEFINE_THIS_MODULE(ovsdb);
@@ -177,6 +178,39 @@ ovsdb_is_valid_version(const char *s)
     return ovsdb_parse_version(s, &version);
 }
 
+/* If set to 'true', database schema conversion operations in the storage
+ * may not contain the converted data, only the schema.  Currently affects
+ * only the clustered storage. */
+static bool use_no_data_conversion = true;
+
+static void
+ovsdb_no_data_conversion_enable(struct unixctl_conn *conn, int argc OVS_UNUSED,
+                                const char *argv[] OVS_UNUSED,
+                                void *arg OVS_UNUSED)
+{
+    use_no_data_conversion = true;
+    unixctl_command_reply(conn, NULL);
+}
+
+void
+ovsdb_no_data_conversion_disable(void)
+{
+    if (!use_no_data_conversion) {
+        return;
+    }
+    use_no_data_conversion = false;
+    unixctl_command_register("ovsdb/file/no-data-conversion-enable", "",
+                             0, 0, ovsdb_no_data_conversion_enable, NULL);
+}
+
+/* Returns true if the database storage allows conversion records without
+ * data specified. */
+bool
+ovsdb_conversion_with_no_data_supported(const struct ovsdb *db)
+{
+    return use_no_data_conversion && ovsdb_storage_is_clustered(db->storage);
+}
+
 /* Returns the number of tables in 'schema''s root set. */
 static size_t
 root_set_size(const struct ovsdb_schema *schema)
diff --git a/ovsdb/ovsdb.h b/ovsdb/ovsdb.h
index 13d8bf407..d45630e8f 100644
--- a/ovsdb/ovsdb.h
+++ b/ovsdb/ovsdb.h
@@ -132,6 +132,9 @@ extern size_t n_weak_refs;
 struct ovsdb *ovsdb_create(struct ovsdb_schema *, struct ovsdb_storage *);
 void ovsdb_destroy(struct ovsdb *);
 
+void ovsdb_no_data_conversion_disable(void);
+bool ovsdb_conversion_with_no_data_supported(const struct ovsdb *);
+
 void ovsdb_get_memory_usage(const struct ovsdb *, struct simap *usage);
 
 struct ovsdb_table *ovsdb_get_table(const struct ovsdb *, const char *);
diff --git a/ovsdb/trigger.c b/ovsdb/trigger.c
index 3c93ae580..0706d66cc 100644
--- a/ovsdb/trigger.c
+++ b/ovsdb/trigger.c
@@ -280,9 +280,14 @@ ovsdb_trigger_try(struct ovsdb_trigger *t, long long int now)
                 return false;
             }
 
-            /* Make the new copy into a transaction log record. */
-            struct json *txn_json = ovsdb_to_txn_json(
-                newdb, "converted by ovsdb-server", true);
+            struct json *txn_json;
+            if (ovsdb_conversion_with_no_data_supported(t->db)) {
+                txn_json = json_null_create();
+            } else {
+                /* Make the new copy into a transaction log record. */
+                txn_json = ovsdb_to_txn_json(
+                                newdb, "converted by ovsdb-server", true);
+            }
 
             /* Propose the change. */
             t->progress = ovsdb_txn_propose_schema_change(