I'll work on changing the source code then.
I thought there was something like what Faban does, and I did not know.
anyway, thanks for the help
Best,
Rajiv
On 15/05/16 17:40, Mihailovic Ivo wrote:
Hi,
I'm sure it's possible to get nginx stats, but you'll have to refer to
nginx documentation to figure out how to do this. I don't know why
you'd want to do this, though.
Throughput is the number of replies per second received by a client.
The average throughput is reported at the end of the benchmark as
"Reply rate". Latency is the amount of time that passes between a
client issuing a request and receiving the reply for that request. The
average latency is reported at the end of the benchmark as "Reply
time". You can also see these number per client in the log files in
the client container's /output directory.
You can change the number of clients at runtime if you are willing to
modify the source code of the benchmark to do what you want. There are
no actual videos, they are just simulated from logs that define the
access pattern. Again, you can change the logs to create a different
access pattern and thus change the request rate, if you are willing to
modify the source code to do this.
Best,
Ivo
------------------------------------------------------------------------
*From:* nishtala <[email protected]>
*Sent:* Sunday, May 15, 2016 3:21 PM
*To:* [email protected]
*Subject:* Media streaming benchmark metric and varying number of
clients.
Hi all,
I'm trying to run Media Streaming benchmark from cloudsuite 3.0 on an
ARM Juno platform.
I have three questions:
- Is it possible to get runtime statistics from the server side
(nginx) instead of client side (httperf)?
how are the throughput and qos metric (maybe latency?) defined?
- One of httperf webpages
<http://www.labs.hpe.com/research/linux/httperf/wisp98/html/doc004.html>
defines throughput as number of replies received to the time taken.
so from the client-side statistics obtained throughput is the
request-rate, right?
- Is it possible to change the number of clients on httperf at
runtime? or the bitrate of the video?
this should allow us to vary the throughput (request rate), right?
Regarding the qos metric, how do we capture this? I have not found any
specific documentation for this.
Any help will be appreciated.
Best,
Rajiv
WARNING / LEGAL TEXT: This message is intended only for the use of the
individual or entity to which it is addressed and may contain
information which is privileged, confidential, proprietary, or exempt
from disclosure under applicable law. If you are not the intended
recipient or the person responsible for delivering the message to the
intended recipient, you are strictly prohibited from disclosing,
distributing, copying, or in any way using this message. If you have
received this communication in error, please notify the sender and
destroy and delete any copies you may have received.
http://www.bsc.es/disclaimer
WARNING / LEGAL TEXT: This message is intended only for the use of the
individual or entity to which it is addressed and may contain
information which is privileged, confidential, proprietary, or exempt
from disclosure under applicable law. If you are not the intended
recipient or the person responsible for delivering the message to the
intended recipient, you are strictly prohibited from disclosing,
distributing, copying, or in any way using this message. If you have
received this communication in error, please notify the sender and
destroy and delete any copies you may have received.
http://www.bsc.es/disclaimer
