From 1cf8ca2c6e57cf8cd9794d5bb6bb4f8b22711560 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Thu, 4 Jul 2019 03:49:51 +0000
Subject: http: use gperf for common fields optimization

GNU gperf is a commonly-used tool for generating perfect hashes
and available on every platform unicorn runs on.  C Ruby, gcc,
glibc all already use it.

Using a hash lookup instead of a linear scan already shows
measurable improvements when memoized header keys are all
used:

* test/benchmark/http_parser.rb (no options):

   100000 iterations
         user     system      total        real
  -  0.411857   0.000200   0.412057 (  0.412070)
  +  0.397960   0.000181   0.398141 (  0.398149)

Results which require generating a new string from an unmemoized
header is less significant, but still consistent measurable:

* test/benchmark/http_parser.rb -H 'DNT: 1'

   100000 iterations
         user     system      total        real
  -  0.461416   0.000000   0.461416 (  0.461417)
  +  0.461329   0.000000   0.461329 (  0.461363)

Most importantly, this change allows us to memoize more keys
without worrying too much about the overhead of a O(n) scan.
---
 ext/unicorn_http/common_fields.gperf | 56 ++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 ext/unicorn_http/common_fields.gperf

(limited to 'ext/unicorn_http/common_fields.gperf')

diff --git a/ext/unicorn_http/common_fields.gperf b/ext/unicorn_http/common_fields.gperf
new file mode 100644
index 0000000..179afe5
--- /dev/null
+++ b/ext/unicorn_http/common_fields.gperf
@@ -0,0 +1,56 @@
+%{
+#include <ruby.h>
+%}
+%compare-lengths
+%enum
+%global-table
+%language=ANSI-C
+%pic
+%struct-type
+%define hash-function-name cf_hash
+%define length-table-name cf_lengthtable
+%define lookup-function-name cf_lookup
+%define string-pool-name cf_stringpool
+%define word-array-name cf_wordlist
+
+struct common_field { size_t name; VALUE value; };
+%%
+ACCEPT
+ACCEPT_CHARSET
+ACCEPT_ENCODING
+ACCEPT_LANGUAGE
+ALLOW
+AUTHORIZATION
+CACHE_CONTROL
+CONNECTION
+CONTENT_ENCODING
+CONTENT_LENGTH
+CONTENT_TYPE
+COOKIE
+DATE
+EXPECT
+FROM
+HOST
+IF_MATCH
+IF_MODIFIED_SINCE
+IF_NONE_MATCH
+IF_RANGE
+IF_UNMODIFIED_SINCE
+# Firefox sends Keep-Alive (or maybe only old versions?)
+KEEP_ALIVE
+MAX_FORWARDS
+PRAGMA
+PROXY_AUTHORIZATION
+RANGE
+REFERER
+TE
+TRAILER
+TRANSFER_ENCODING
+UPGRADE
+USER_AGENT
+VIA
+# common proxies set some of these X- headers
+X_FORWARDED_FOR
+X_FORWARDED_PROTO
+X_REAL_IP
+WARNING
-- 
cgit v1.2.3-24-ge0c7