On 8 Mar 2000 nbecker@fred.net wrote:
>Sorry if this is not news, I haven't been actively following 2.3.xxx.
>I'm trying out 2.3.50. It's working OK so far, but I was wondering if
>these messages are reason for concern:
>
>03:07: elevator nr_segments 116 should be 117
>__elevator_merge: req latency 4082 req latency 4076
>03:07: elevator nr_segments 74 should be 75
>03:07: elevator nr_segments 159 should be 160
>03:07: elevator nr_segments 125 should be 126
>__elevator_merge: req latency 4072 req latency 4063
>03:07: elevator nr_segments 91 should be 92
>__elevator_merge: req latency 4056 req latency 4050
>
I posted a fix for the nr_segments thing a few days ago (that was a bug in
the code). Don't worry, it's completly harmless. You can ignore it for
now.
I debugged the __elevator_merge message and such printk has to be
definitely deleted. It's the printk that is wrong, the code is _right_,
So ignore it too for now.
I am now in the process of partially rewriting the request merging code so
that I don't seek back and forth if not necessary. I am trying to exploit
all possible optimizations. As other change I am now considering special
requests (inserted in the queue by the device driver itself) as barriers
for the I/O scheduler (that seems the right thing to do to me).
So basically stay tuned and ignore the elevator messages for now, there's
nothing to worry about and it's just stable.
Thanks for the report.
Andrea
-
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/
This archive was generated by hypermail 2b29 : Wed Mar 15 2000 - 21:00:14 EST