Buffers reuse in chunked filter. There were 2 buffers allocated on each buffer chain sent through chunked filter (one buffer for chunk size, another one for trailing CRLF, about 120 bytes in total on 32-bit platforms). This resulted in large memory consumption with long-lived requests sending many buffer chains. Usual example of problematic scenario is streaming though proxy with proxy_buffering set to off. Introduced buffers reuse reduces memory consumption in the above problematic scenario. See here for initial report: http://mailman.nginx.org/pipermail/nginx/2010-April/019814.html

/*
 * Copyright (C) Igor Sysoev
 */


#ifndef _NGX_CRC_H_INCLUDED_
#define _NGX_CRC_H_INCLUDED_


#include <ngx_config.h>
#include <ngx_core.h>


/* 32-bit crc16 */

static ngx_inline uint32_t
ngx_crc(u_char *data, size_t len)
{
    uint32_t  sum;

    for (sum = 0; len; len--) {

        /*
         * gcc 2.95.2 x86 and icc 7.1.006 compile
         * that operator into the single "rol" opcode,
         * msvc 6.0sp2 compiles it into four opcodes.
         */
        sum = sum >> 1 | sum << 31;

        sum += *data++;
    }

    return sum;
}


#endif /* _NGX_CRC_H_INCLUDED_ */