On 07/14/2010 12:10 PM, Radha Ramachandran wrote: > Hi Jens, > As I was verifying the latest code from head, I realized that we > actually did not need the IO_U_F_FILLED flag, we can just > use(overload) the buf_filled_len to check if the buffer is actually > filled (as this is reset to 0 on a read). This also gave me slight > performance bump. Attached is the patch for it. Good point, there's no need for that flag/field at all. Will apply your patch, thanks. -- Jens Axboe -- To unsubscribe from this list: send the line "unsubscribe fio" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
