summaryrefslogtreecommitdiff
path: root/string.c
diff options
context:
space:
mode:
authornobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2017-10-21 23:21:05 +0000
committernobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2017-10-21 23:21:05 +0000
commit80c50308f9db813e999367ec5d116e2d2be9f840 (patch)
tree85b28d288cf288c7c2ac7e6329616c6d3bf9778b /string.c
parentd808918583d406d93c9007cf14a9f39af7e4b83e (diff)
downloadruby-80c50308f9db813e999367ec5d116e2d2be9f840.tar.gz
Improve performance of string interpolation
This patch will add pre-allocation in string interpolation. By this, unecessary capacity resizing is avoided. For small strings, optimized `rb_str_resurrect` operation is faster, so pre-allocation is done only when concatenated strings are large. `MIN_PRE_ALLOC_SIZE` was decided by experimenting with local machine (x86_64-apple-darwin 16.5.0, Apple LLVM version 8.1.0 (clang - 802.0.42)). String interpolation will be faster around 72% when large string is created. * Before ``` Calculating ------------------------------------- Large string interpolation 1.276M (± 5.9%) i/s - 6.358M in 5.002022s Small string interpolation 5.156M (± 5.5%) i/s - 25.728M in 5.005731s ``` * After ``` Calculating ------------------------------------- Large string interpolation 2.201M (± 5.8%) i/s - 11.063M in 5.043724s Small string interpolation 5.192M (± 5.7%) i/s - 25.971M in 5.020516s ``` * Test code ```ruby require 'benchmark/ips' Benchmark.ips do |x| x.report "Large string interpolation" do |t| a = "Hellooooooooooooooooooooooooooooooooooooooooooooooooooo" b = "Wooooooooooooooooooooooooooooooooooooooooooooooooooorld" t.times do "#{a}, #{b}!" end end x.report "Small string interpolation" do |t| a = "Hello" b = "World" t.times do "#{a}, #{b}!" end end end ``` [Fix GH-1626] From: Nao Minami <south37777@gmail.com> git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60320 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'string.c')
-rw-r--r--string.c23
1 files changed, 19 insertions, 4 deletions
diff --git a/string.c b/string.c
index c1e986fb9a..411ec314d7 100644
--- a/string.c
+++ b/string.c
@@ -2903,15 +2903,30 @@ rb_str_append(VALUE str, VALUE str2)
return rb_str_buf_append(str, str2);
}
+#define MIN_PRE_ALLOC_SIZE 48
+
VALUE
rb_str_concat_literals(size_t num, const VALUE *strary)
{
VALUE str;
- size_t i;
+ size_t i, s;
+ long len = 1;
+
+ if (UNLIKELY(!num)) return rb_str_new(0, 0);
+ if (UNLIKELY(num == 1)) return rb_str_resurrect(strary[0]);
+
+ for (i = 0; i < num; ++i) { len += RSTRING_LEN(strary[i]); }
+ if (LIKELY(len < MIN_PRE_ALLOC_SIZE)) {
+ str = rb_str_resurrect(strary[0]);
+ s = 1;
+ }
+ else {
+ str = rb_str_buf_new(len);
+ rb_enc_copy(str, strary[0]);
+ s = 0;
+ }
- if (!num) return rb_str_new(0, 0);
- str = rb_str_resurrect(strary[0]);
- for (i = 1; i < num; ++i) {
+ for (i = s; i < num; ++i) {
const VALUE v = strary[i];
int encidx = ENCODING_GET(v);