>I think the point Chuck was trying to make was not that preserving
>buffers was good because of making a pool of quick-allocation free
>buffers, but because doing so preserved the *contents* of those
>buffers ---- this is because try_to_free_buffers() doesn't take into
Impossible. Buffers in the freelist are not hashed in the buffer queue so
can't be reached and can't work for caching purposes.
>account whether the buffers on any particular pages are often
>referenced. So if the buffers contain the disk blocks corresponding to
My lru-pagemap code take it into account because if the buffer is searched
often it won't be at the end of the lru list.
>While I agree with you that leaving b_coutn as 1 is a really horrible
>way of fixing this problem, the real solution which is quite urgently
>needed is to put some more smarts into try_to_free_buffers....
I just fixed it from ages. try_to_free_buffers() here is called only on
buffers that are been not used since a long time.
Andrea Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/