ovsdb-data: Deduplicate string atoms.

ovsdb-server spends a lot of time cloning atoms for various reasons,
e.g. to create a diff of two rows or to clone a row to the transaction.
All atoms, except for strings, contains a simple value that could be
copied in efficient way, but duplicating strings every time has a
significant performance impact.

Introducing a new reference-counted structure 'ovsdb_atom_string'
that allows to not copy strings every time, but just increase a
reference counter.

This change allows to increase transaction throughput in benchmarks
up to 2x for standalone databases and 3x for clustered databases, i.e.
number of transactions that ovsdb-server can handle per second.
It also noticeably reduces memory consumption of ovsdb-server.

Next step will be to consolidate this structure with json strings,
so we will not need to duplicate strings while converting database
objects to json and back.

Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Acked-by: Dumitru Ceara <dceara@redhat.com>
Acked-by: Mark D. Gray <mark.d.gray@redhat.com>

python/ovs/db/data.py

@@ -204,7 +204,7 @@ class Atom(object):
             else:
                 return '.boolean = false'
         elif self.type == ovs.db.types.StringType:
-            return '.string = "%s"' % escapeCString(self.value)
+            return '.s = %s' % escapeCString(self.value)
         elif self.type == ovs.db.types.UuidType:
             return '.uuid = %s' % ovs.ovsuuid.to_c_assignment(self.value)
 
@@ -563,16 +563,41 @@ class Datum(object):
         if n == 0:
             return ["static struct ovsdb_datum %s = { .n = 0 };"]
 
-        s = ["static union ovsdb_atom %s_keys[%d] = {" % (name, n)]
-        for key in sorted(self.values):
-            s += ["    { %s }," % key.cInitAtom(key)]
-        s += ["};"]
+        s = []
+        if self.type.key.type == ovs.db.types.StringType:
+            s += ["static struct ovsdb_atom_string %s_key_strings[%d] = {"
+                  % (name, n)]
+            for key in sorted(self.values):
+                s += ['    { .string = "%s", .n_refs = 2 },'
+                      % escapeCString(key.value)]
+            s += ["};"]
+            s += ["static union ovsdb_atom %s_keys[%d] = {" % (name, n)]
+            for i in range(n):
+                s += ["    { .s = &%s_key_strings[%d] }," % (name, i)]
+            s += ["};"]
+        else:
+            s = ["static union ovsdb_atom %s_keys[%d] = {" % (name, n)]
+            for key in sorted(self.values):
+                s += ["    { %s }," % key.cInitAtom(key)]
+            s += ["};"]
 
         if self.type.value:
-            s = ["static union ovsdb_atom %s_values[%d] = {" % (name, n)]
-            for k, v in sorted(self.values.items()):
-                s += ["    { %s }," % v.cInitAtom(v)]
-            s += ["};"]
+            if self.type.value.type == ovs.db.types.StringType:
+                s += ["static struct ovsdb_atom_string %s_val_strings[%d] = {"
+                      % (name, n)]
+                for k, v in sorted(self.values):
+                    s += ['    { .string = "%s", .n_refs = 2 },'
+                          % escapeCString(v.value)]
+                s += ["};"]
+                s += ["static union ovsdb_atom %s_values[%d] = {" % (name, n)]
+                for i in range(n):
+                    s += ["    { .s = &%s_val_strings[%d] }," % (name, i)]
+                s += ["};"]
+            else:
+                s = ["static union ovsdb_atom %s_values[%d] = {" % (name, n)]
+                for k, v in sorted(self.values.items()):
+                    s += ["    { %s }," % v.cInitAtom(v)]
+                s += ["};"]
 
         s += ["static struct ovsdb_datum %s = {" % name]
         s += ["    .n = %d," % n]

python/ovs/db/types.py

@@ -48,6 +48,16 @@ class AtomicType(object):
     def to_string(self):
         return self.name
 
+    def to_rvalue_string(self):
+        if self == StringType:
+            return 's->' + self.name
+        return self.name
+
+    def to_lvalue_string(self):
+        if self == StringType:
+            return 's'
+        return self.name
+
     def to_json(self):
         return self.name
 
@@ -373,18 +383,7 @@ class BaseType(object):
                 return "%(dst)s = *%(src)s;" % args
             return ("%(dst)s = %(src)s->header_.uuid;") % args
         elif self.type == StringType:
-            return "%(dst)s = xstrdup(%(src)s);" % args
-        else:
-            return "%(dst)s = %(src)s;" % args
-
-    def assign_c_value_casting_away_const(self, dst, src, refTable=True):
-        args = {'dst': dst, 'src': src}
-        if self.ref_table_name:
-            if not refTable:
-                return "%(dst)s = *%(src)s;" % args
-            return ("%(dst)s = %(src)s->header_.uuid;") % args
-        elif self.type == StringType:
-            return "%(dst)s = CONST_CAST(char *, %(src)s);" % args
+            return "%(dst)s = ovsdb_atom_string_create(%(src)s);" % args
         else:
             return "%(dst)s = %(src)s;" % args