Decentralized counters for ETS ordered_set with write_concurrency

Previously, all ETS tables used centralized counter variables to keep
track of the number of items stored and the amount of memory
consumed. These counters can cause scalability problems (especially on
big NUMA systems). This commit adds an implementation of a
decentralized counter and modifies the implementation of ETS so that
ETS tables of type ordered_set with write_concurrency enabled use the
decentralized counter. [Experiments][1] indicate that this change
substantially improves the scalability of ETS ordered_set tables with
write_concurrency enabled in scenarios with frequent `ets:insert/2`
and `ets:delete/2` calls.

The new counter is implemented in the module erts_flxctr
(`erts_flxctr.h` and `erts_flxctr.c`). The module has the suffix
flxctr as it contains the implementation of a flexible counter (i.e.,
counter instances can be configured to be either centralized or
decentralized). Counters that are configured to be centralized are
implemented with a single counter variable which is modified with
atomic operations. Decentralized counters are spread over several
cache lines (how many can be configured with the parameter
`+dcg`). The scheduler threads are mapped to cache lines so that there
is no single point of contention when decentralized counters are
updated. The thread progress functionality of the Erlang VM is
utilized to implement support for linearizable snapshots of
decentralized counters. The snapshot functionality is used by the
`ets:info/1` and `ets:info/2` functions.

[1]: http://winsh.me/ets_catree_benchmark/flxctr_res.html

1 files changed, 15 insertions, 4 deletions

diff --git a/erts/emulator/beam/erl_db_util.h b/erts/emulator/beam/erl_db_util.h
index e3d3c0e804..97f2848679 100644
--- a/erts/emulator/beam/erl_db_util.h
+++ b/erts/emulator/beam/erl_db_util.h
@@ -21,6 +21,7 @@
 #ifndef _DB_UTIL_H
 #define _DB_UTIL_H
 
+#include "erl_flxctr.h"
 #include "global.h"
 #include "erl_message.h"
 #include "erl_bif_unique.h"
@@ -207,8 +208,12 @@ typedef struct db_table_method
             enum DbIterSafety*);
     int (*db_take)(Process *, DbTable *, Eterm, Eterm *);
 
-    SWord (*db_delete_all_objects)(Process* p, DbTable* db, SWord reds);
-
+    SWord (*db_delete_all_objects)(Process* p,
+                                   DbTable* db,
+                                   SWord reds,
+                                   Eterm* nitems_holder_wb);
+    Eterm (*db_delete_all_objects_get_nitems_from_holder)(Process* p,
+                                                          Eterm nitems_holder);
     int (*db_free_empty_table)(DbTable* db);
     SWord (*db_free_table_continue)(DbTable* db, SWord reds);
     
@@ -257,6 +262,9 @@ typedef struct {
     DbTable *prev;
 } DbTableList;
 
+#define ERTS_DB_TABLE_NITEMS_COUNTER_ID 0
+#define ERTS_DB_TABLE_MEM_COUNTER_ID 1
+
 /*
  * This structure contains data for all different types of database
  * tables. Note that these fields must match the same fields
@@ -281,8 +289,11 @@ typedef struct db_table_common {
     Eterm the_name;           /* an atom */
     Binary *btid;
     DbTableMethod* meth;      /* table methods */
-    erts_atomic_t nitems; /* Total number of items in table */
-    erts_atomic_t memory_size;/* Total memory size. NOTE: in bytes! */
+    /* The ErtsFlxCtr below contains:
+     * - Total number of items in table
+     * - Total memory size (NOTE: in bytes!) */
+    ErtsFlxCtr counters;
+    char extra_for_flxctr[ERTS_FLXCTR_NR_OF_EXTRA_BYTES(2)];
     struct {                  /* Last fixation time */
 	ErtsMonotonicTime monotonic;
 	ErtsMonotonicTime offset;