Re: MD/RAID time out writing superblock

[Tejun Heo]

Hello,

Mark Lord wrote:
>> That's interesting.  One important side effect of issuing IDENTIFY is
>> that they will serialize command streams as they are not NCQ commands
>> and thus could change command patterns significantly.
> ..
> 
> SMART is the opcode that is most frequently implicated here, not IDENTIFY.

Yeap, any non-NCQ commands would do it.

> Note that even a barrier FLUSH CACHE is non NCQ and will serialize
> the stream.

Yeah, I was just thinking that issuing non-NCQ commands mixed with NCQ
commands would make the command stream fluctuate more.  Modern drives
are pretty good at lowering power consumption while idle so being more
fluctuative (is it a word?) might have something to do with the
problem.  Just a wild speculation tho.

Thanks.

-- 
tejun
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/