>i think that's the key. moving this bit of code from getblk() to
>find_buffer() is a measureable slowdown, it turns out:
Really I was talking about my lru_cache_mkyoung() (that replaced
setbit(PG_referenced)), but yes, the put_last_lru() performance-hurt issue
is equivalent.
>i removed it completely (along with put_last_lru() since now no-one uses
>it), since these lists are no longer LRU, and found that performance
I just noticed in the last days that nobody seems using the lru-buffer
information. Right now it looks like to me that you are perfectly right.
>but this also means that you should be *very* careful where you put your
>"touch_buffer(bh)" because you don't want that in a performance path like
>find_buffer(). leaving touch_buffer() in bread() and brw_page() might be
Hmm, yes probably this is a good idea, I'll think about that tomorrow.
Thanks!!
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/