Mercurial > hg > nginx-quic
view src/core/ngx_shmtx.h @ 4113:a28ba1cdec27
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
| author | Maxim Dounin <mdounin@mdounin.ru> |
|---|---|
| date | Thu, 15 Sep 2011 15:25:42 +0000 |
| parents | 0daede16d68b |
| children | 3f6040cd731e 4919fb357a5d |
line wrap: on
line source
/* * Copyright (C) Igor Sysoev */ #ifndef _NGX_SHMTX_H_INCLUDED_ #define _NGX_SHMTX_H_INCLUDED_ #include <ngx_config.h> #include <ngx_core.h> typedef struct { #if (NGX_HAVE_ATOMIC_OPS) ngx_atomic_t *lock; #if (NGX_HAVE_POSIX_SEM) ngx_uint_t semaphore; sem_t sem; #endif #else ngx_fd_t fd; u_char *name; #endif ngx_uint_t spin; } ngx_shmtx_t; ngx_int_t ngx_shmtx_create(ngx_shmtx_t *mtx, void *addr, u_char *name); void ngx_shmtx_destory(ngx_shmtx_t *mtx); ngx_uint_t ngx_shmtx_trylock(ngx_shmtx_t *mtx); void ngx_shmtx_lock(ngx_shmtx_t *mtx); void ngx_shmtx_unlock(ngx_shmtx_t *mtx); #endif /* _NGX_SHMTX_H_INCLUDED_ */