[sheepdog] [PATCH v1 2/3] sheepfs: make fetching data for cache become async operation

[Liu Yuan]

On Thu, Mar 06, 2014 at 03:47:20PM +0800, Robin Dong wrote:
> From: Robin Dong <sanbai at taobao.com>
> 
> Currently, we have add cache for http interface of sheepfs.But it will
> only fetch data from http request when fuse operation has read out of
> the cache.
> 
> For better performance, we use 'double buffer' tech: fuse is reading
> one buffer and a new created thread could read future data onto another
> buffer at the same time. It will make reading operation more smoothly
> and faster.
> 
> We use two pointer: 'ready' and 'prepare' to point the double buffers
> and use classic 'consumer and producer model' to avoid race condition.
> 
> Signed-off-by: Robin Dong <sanbai at taobao.com>
> ---
>  sheepfs/http.c | 165 +++++++++++++++++++++++++++++++++++++++++++--------------
>  1 file changed, 124 insertions(+), 41 deletions(-)
> 
> diff --git a/sheepfs/http.c b/sheepfs/http.c
> index 7df05ad..5610110 100644
> --- a/sheepfs/http.c
> +++ b/sheepfs/http.c
> @@ -19,6 +19,7 @@
>  #include <stdio.h>
>  #include <time.h>
>  #include <curl/curl.h>
> +#include <semaphore.h>
>  
>  #include "strbuf.h"
>  #include "sheepfs.h"
> @@ -157,16 +158,17 @@ static size_t curl_read_object(const char *url, char *buf, size_t size,
>  		}
>  		if ((size_t)content_length > size) {
>  			sheepfs_pr("Failed to get correct CONTENT_LENGTH, "
> -			       "content_length: %"PRIu64", get_size: %"PRIu64,
> -			       (size_t)content_length, size);
> +				   "content_length: %"PRIu64", get_size: %"
> +				   PRIu64, (size_t)content_length, size);
>  			size = 0;
>  		} else {
> -			sd_debug("Read out %"PRIu64" data from %s", size, url);
> +			sheepfs_pr("Read out %"PRIu64" data from %s", size,
> +				   url);
>  			size = (size_t)content_length;
>  		}
>  	} else {
>  		sheepfs_pr("Failed to call libcurl res: %s, url: %s",
> -		       curl_easy_strerror(res), url);
> +			   curl_easy_strerror(res), url);
>  		size = 0;
>  	}
>  out:
> @@ -234,19 +236,69 @@ out:
>  /* no rationale */
>  #define CACHE_SIZE	(64 * 1024 * 1024)
>  
> -struct cache_handle {
> +struct cache_s {
>  	char *mem;
>  	off_t offset;
>  	size_t size;
>  };

What _s means? I'd sugguest struct read_cache

>  
> +struct cache_handle {
> +	char            path[PATH_MAX];
> +	struct cache_s  *ready;
> +	struct cache_s  *prepare;
> +	pthread_t       fetch_thread;
> +	sem_t		ready_sem;
> +	sem_t		prepare_sem;

why choose sem_t over pthread mutex, any reason?

> +	bool            stop;
> +	uatomic_bool	fetching;
> +	off_t		fetch_offset;
> +	size_t		obj_size;

I think we should avoid use size_t, since its incompatible in 32 and 64 bits
use uint64_t explicitly.

Thanks
Yuan