Re: Latencies around 10 seconds for I/Os in a trace!!!

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Not sure what does 512 means in your wait statements. I would also
recommend to use blktrace+btrecord+btreplay to replay block I/O
workloads on a single HDD. That is more accurate replay method and
tested by the community.

Good luck with your experiments.

On Tue, Apr 7, 2015 at 11:46 AM, Mansour Shafaei Moghaddam
<mansoor.shafaei@xxxxxxxxx> wrote:
> Thanks for the response But I am pretty sure about the functionality
> of wait command. The device is a conventional magnetic disk.
>
> On Tue, Apr 7, 2015 at 12:39 PM, Alireza Haghdoost <haghdoost@xxxxxxxxx> wrote:
>> Sounds like your wait statements are not correct. Referring to HOWTO.txt :
>>
>> wait       Wait for 'offset' microseconds. Everything below 100 is
>> discarded.
>>
>>
>> What kind of storage device do you have under /dev/sdb ?
>>
>>
--
To unsubscribe from this list: send the line "unsubscribe fio" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux Kernel]     [Linux SCSI]     [Linux IDE]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux SCSI]

  Powered by Linux