Re: [PATCH] fix readahead pipeline break caused by block plug

[Shaohua Li <shaohua.li@intel.com>]

On Tue, 2012-01-31 at 09:48 +0100, Eric Dumazet wrote:
> Le mardi 31 janvier 2012 à 15:59 +0800, Shaohua Li a écrit :
> > 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 <shaohua.li@intel.com>
> > Tested-by: Herbert Poetzl <herbert@13thfloor.at>
> > Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
> 
> 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