[nginx] Sub filter: eliminate unnecessary buffering.

[Roman Arutyunyan]

details:   http://hg.nginx.org/nginx/rev/f379b32e4733
branches:  
changeset: 6605:f379b32e4733
user:      Roman Arutyunyan <arut at nginx.com>
date:      Sat Jul 02 15:59:53 2016 +0300
description:
Sub filter: eliminate unnecessary buffering.

Previously, when a buffer was processed by the sub filter, its final bytes
could be buffered by the filter even if they don't match any pattern.
This happened because the Boyer-Moore algorithm, employed by the sub filter
since b9447fc457b4 (1.9.4), matches the last characters of patterns prior to
checking other characters.  If the last character is out of scope, initial
bytes of a potential match are buffered until the last character is available.

Now, after receiving a flush or recycled buffer, the filter performs
additional checks to reduce the number of buffered bytes.  The potential match
is checked against the initial parts of all patterns.  Non-matching bytes are
not buffered.  This improves processing of a chunked response from upstream
by sending the entire chunks without buffering unless a partial match is found
at the end of a chunk.

diffstat:

 src/http/modules/ngx_http_sub_filter_module.c |  41 ++++++++++++++++++++++++--
 1 files changed, 37 insertions(+), 4 deletions(-)

diffs (104 lines):

diff -r 0e0adbbc8752 -r f379b32e4733 src/http/modules/ngx_http_sub_filter_module.c
--- a/src/http/modules/ngx_http_sub_filter_module.c	Sat Jul 02 15:59:52 2016 +0300
+++ b/src/http/modules/ngx_http_sub_filter_module.c	Sat Jul 02 15:59:53 2016 +0300
@@ -83,7 +83,7 @@ static ngx_uint_t ngx_http_sub_cmp_index
 static ngx_int_t ngx_http_sub_output(ngx_http_request_t *r,
     ngx_http_sub_ctx_t *ctx);
 static ngx_int_t ngx_http_sub_parse(ngx_http_request_t *r,
-    ngx_http_sub_ctx_t *ctx);
+    ngx_http_sub_ctx_t *ctx, ngx_uint_t flush);
 static ngx_int_t ngx_http_sub_match(ngx_http_sub_ctx_t *ctx, ngx_int_t start,
     ngx_str_t *m);
 
@@ -287,6 +287,7 @@ ngx_http_sub_body_filter(ngx_http_reques
     ngx_int_t                  rc;
     ngx_buf_t                 *b;
     ngx_str_t                 *sub;
+    ngx_uint_t                 flush, last;
     ngx_chain_t               *cl;
     ngx_http_sub_ctx_t        *ctx;
     ngx_http_sub_match_t      *match;
@@ -328,6 +329,9 @@ ngx_http_sub_body_filter(ngx_http_reques
     ngx_log_debug1(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
                    "http sub filter \"%V\"", &r->uri);
 
+    flush = 0;
+    last = 0;
+
     while (ctx->in || ctx->buf) {
 
         if (ctx->buf == NULL) {
@@ -336,11 +340,19 @@ ngx_http_sub_body_filter(ngx_http_reques
             ctx->pos = ctx->buf->pos;
         }
 
+        if (ctx->buf->flush || ctx->buf->recycled) {
+            flush = 1;
+        }
+
+        if (ctx->in == NULL) {
+            last = flush;
+        }
+
         b = NULL;
 
         while (ctx->pos < ctx->buf->last) {
 
-            rc = ngx_http_sub_parse(r, ctx);
+            rc = ngx_http_sub_parse(r, ctx, last);
 
             ngx_log_debug4(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
                            "parse: %i, looked: \"%V\" %p-%p",
@@ -592,7 +604,8 @@ ngx_http_sub_output(ngx_http_request_t *
 
 
 static ngx_int_t
-ngx_http_sub_parse(ngx_http_request_t *r, ngx_http_sub_ctx_t *ctx)
+ngx_http_sub_parse(ngx_http_request_t *r, ngx_http_sub_ctx_t *ctx,
+    ngx_uint_t flush)
 {
     u_char                   *p, c;
     ngx_str_t                *m;
@@ -604,6 +617,7 @@ ngx_http_sub_parse(ngx_http_request_t *r
 
     slcf = ngx_http_get_module_loc_conf(r, ngx_http_sub_filter_module);
     tables = ctx->tables;
+    match = ctx->matches->elts;
 
     offset = ctx->offset;
     end = ctx->buf->last - ctx->pos;
@@ -630,7 +644,6 @@ ngx_http_sub_parse(ngx_http_request_t *r
         /* a potential match */
 
         start = offset - (ngx_int_t) tables->min_match_len + 1;
-        match = ctx->matches->elts;
 
         i = ngx_max(tables->index[c], ctx->index);
         j = tables->index[c + 1];
@@ -671,6 +684,26 @@ ngx_http_sub_parse(ngx_http_request_t *r
         ctx->index = 0;
     }
 
+    if (flush) {
+        for ( ;; ) {
+            start = offset - (ngx_int_t) tables->min_match_len + 1;
+
+            if (start >= end) {
+                break;
+            }
+
+            for (i = 0; i < ctx->matches->nelts; i++) {
+                m = &match[i].match;
+
+                if (ngx_http_sub_match(ctx, start, m) == NGX_AGAIN) {
+                    goto again;
+                }
+            }
+
+            offset++;
+        }
+    }
+
 again:
 
     ctx->offset = offset;