Re: [BENCHMARK] 2.4.{18,19{-ck9},20rc1{-aa1}} with contest

[Andrew Morton]

Andrea Arcangeli wrote:
> 
> the slowdown happens in this case:
> 
>         queue 5 6 7 8 9
> 
> insert read 3
> 
>         queue 3 5 6 7 8 9

read-latency will not do that.
 
> However I think even read-latency is more a workarond to a problem in
> the I/O queue dimensions.

The problem is the 2.4 algorithm.  If a read is not mergeable or
insertable it is placed at the tail of the queue.  Which is the
worst possible place it can be put because applications wait on
reads, not on writes.