[Disksim-users] A question about time-limited request
q q
6375625 at gmail.com
Wed Jun 12 00:21:00 EDT 2013
Dear Dr Ganger,
Thank you very much for your prompt response.
This is what I want to do with the synthetic workload generator.
There are two generators - A and B. Both of them generate
time-critical requests with probability of 1.0. Generator A generates
the next request immediately once a request is serviced. Generator B
waits for 2000 ms to generate the next request after a request is
serviced. Can I do this using the synthetic workload generator? If
yes, how?
BTW, I don't think I can do it with the "Think time from request to
return" option of disksim_synthio because that is a global option for
all generators.
Looking forward to hearing from you. Thank you very much
On Tue, Jun 11, 2013 at 10:07 PM, Greg Ganger <ganger at ece.cmu.edu> wrote:
>
>
> No. If it finishes before the time limit, its generator doesn't block
> waiting on it. Think of it like a prefetch, for example, where the
> reader only blocks if the prefetch doesn't finish before the reader
> actually needs the data.
>
> Greg
>
>
>
> On Tue, 11 Jun 2013, q q wrote:
>
>> If a time-limited request is serviced before its time limit, does the
>> generator process block and wait till the end of the time limit before
>> generating the next request?
>>
>> Thank you.
>>
>> On Page 42 of the Disksim 4.0 manual,
>>
>> Probability of time-limited request
>> "This specifies the probability that a generated request is
>> time-limited. That is, the corresponding generator process “blocks”
>> and waits for the request to complete (if it is not already complete)
>> after a given amount of think time (specified by the below “time
>> limit” parameters) [5, 2]."
>> _______________________________________________
>> Disksim-users mailing list
>> Disksim-users at ece.cmu.edu
>> https://sos.ece.cmu.edu/mailman/listinfo/disksim-users
More information about the Disksim-users
mailing list