On Fri, Oct 26, 2012 at 03:47:19PM +0800, Ni zhan Chen wrote:On 10/26/2012 03:36 PM, Fengguang Wu wrote:Ah OK, I'm talking about the typical case. The default readahead sizeOn Fri, Oct 26, 2012 at 03:19:57PM +0800, Ni zhan Chen wrote:Yeah, I mean why the 4th readahead size will be 0(disabled)? What'sOn 10/26/2012 03:09 PM, Fengguang Wu wrote:It's this line in shrink_readahead_size_eio():On Fri, Oct 26, 2012 at 03:03:12PM +0800, Ni zhan Chen wrote:But from function shrink_readahead_size_eio and its callerOn 10/26/2012 02:58 PM, Fengguang Wu wrote:The original behavior is '/= 4' on each error.Hi Fengguang,static void shrink_readahead_size_eio(struct file *filp,Yes immediately disabling readahead may hurt IO performance, the
struct file_ra_state *ra)
{
- ra->ra_pages /= 4;
+ spin_lock(&filp->f_lock);
+ filp->f_mode |= FMODE_RANDOM;
+ spin_unlock(&filp->f_lock);
As the example in comment above this function, the read maybe still
sequential, and it will waste IO bandwith if modify to FMODE_RANDOM
directly.
original '/ 4' may perform better when there are only 1-3 IO errors
encountered.
Why the number should be 1-3?
After 1 errors, readahead size will be shrinked by 1/4
After 2 errors, readahead size will be shrinked by 1/16
After 3 errors, readahead size will be shrinked by 1/64
After 4 errors, readahead size will be effectively 0 (disabled)
filemap_fault I can't find the behavior you mentioned. How you
figure out it?
ra->ra_pages /= 4;
the original value of ra->ra_pages? How can guarantee the 4th shrink
readahead size can be 0?
is 128k, which will become 0 after / 256. The reasonable good ra size
for hard disks is 1MB=256pages, which also becomes 1page after 4 errors.
Thanks,
Fengguang