On Tue, 2012-01-31 at 09:48 +0100, Eric Dumazet wrote:

Le mardi 31 janvier 2012 A  15:59 +0800, Shaohua Li a A(C)crit :

quoted

Herbert Poetzl reported a performance regression since 2.6.39. The test
is a simple dd read, but with big block size. The reason is:

T1: ra (A, A+128k), (A+128k, A+256k)
T2: lock_page for page A, submit the 256k
T3: hit page A+128K, ra (A+256k, A+384). the range isn't submitted
because of plug and there isn't any lock_page till we hit page A+256k
because all pages from A to A+256k is in memory
T4: hit page A+256k, ra (A+384, A+ 512). Because of plug, the range isn't
submitted again.
T5: lock_page A+256k, so (A+256k, A+512k) will be submitted. The task is
waitting for (A+256k, A+512k) finish.

There is no request to disk in T3 and T4, so readahead pipeline breaks.

We really don't need block plug for generic_file_aio_read() for buffered
I/O. The readahead already has plug and has fine grained control when I/O
should be submitted. Deleting plug for buffered I/O fixes the regression.

One side effect is plug makes the request size 256k, the size is 128k
without it. This is because default ra size is 128k and not a reason we
need plug here.

Signed-off-by: Shaohua Li <redacted>
Tested-by: Herbert Poetzl <redacted>
Tested-by: Eric Dumazet <redacted>

Hmm, this is not exactly the patch I tested from Wu Fengguang 

I'll test this one before adding my "Tested-by: ..."

That added lines should not matter. We still need plug for direct-io
case.
Really sorry for this, I should ask you test it before adding the
Tested-by.

Thanks,
Shaohua

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>