Minor performance improvement to SADD and HSET (#12019)

For sets and hashes that will eventually be stored as the hash encoding, it's much faster to immediately convert them to their hash encoding and then perform the insertions since it avoids the O(N) search and frequent reallocations. This change checks the number of arguments in the incoming command, and converts the data-structure if the number of new entries exceeds the listpack-max-entries configuration. This can cause us to over-allocate memory if their are duplicate entries in the input, which is unexpected.

unstable

Summary:
  throughput summary: 805.54 requests per second
  latency summary (msec):
          avg       min       p50       p95       p99       max
       61.908    25.680    68.351    73.279    75.967    79.295
hset-improvement

Summary:
  throughput summary: 4701.46 requests per second
  latency summary (msec):
          avg       min       p50       p95       p99       max
       10.546     0.832    11.959    12.471    13.119    14.967

1 files changed, 10 insertions, 0 deletions

diff --git a/src/t_hash.c b/src/t_hash.c
index 6005f4442..f7d5af649 100644
--- a/src/t_hash.c
+++ b/src/t_hash.c
@@ -43,6 +43,16 @@ void hashTypeTryConversion(robj *o, robj **argv, int start, int end) {
 
     if (o->encoding != OBJ_ENCODING_LISTPACK) return;
 
+    /* We guess that most of the values in the input are unique, so
+     * if there are enough arguments we create a pre-sized hash, which
+     * might overallocate memory if their are duplicates. */
+    size_t new_fields = (end - start + 1) / 2;
+    if (new_fields > server.hash_max_listpack_entries) {
+        hashTypeConvert(o, OBJ_ENCODING_HT);
+        dictExpand(o->ptr, new_fields);
+        return;
+    }
+
     for (i = start; i <= end; i++) {
         if (!sdsEncodedObject(argv[i]))
             continue;