<div dir="auto"><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Hello Jonathan,</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">We have updated all the graphs with updated COBALT code and BQL enabled.</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Wiki Link:<br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><a href="https://github.com/Daipu/COBALT/wiki" style="text-decoration-line:none;color:rgb(66,133,244)">https://github.com/Daipu/COBALT/wiki</a></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Diff for COBALT code:</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><a href="https://github.com/Daipu/COBALT/commit/624d0c761b9d1de99499918cb2078195f8b796b5" style="text-decoration-line:none;color:rgb(66,133,244)">https://github.com/Daipu/COBALT/commit/624d0c761b9d1de99499918cb2078195f8b796b5</a><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Thanks and Regards,</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Shefali Gupta<br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Jendaipou Palmei</div></div><br><div class="gmail_quote"><div dir="ltr">On Wed 23 Jan 2019, 10:57 p.m. Shefali Gupta <<a href="mailto:shefaligups11@gmail.com">shefaligups11@gmail.com</a> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="auto"><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Hi Jonathan,</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Thanks!</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">First, we noticed that cobalt_cache_init method was not implemented in ns-3 COBALT, so we implemented it (but this wasn't the main reason for the wrong behaviour).</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Later, we found that the data types used in the implementation of COBALT in ns-3 were different from those used in Linux.</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">e.g., uint32_t was used instead of int64_t for the variables with datatype ktime_t in Linux.</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Results improved considerably after these changes.<br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">We will update the wiki with latest results.</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Regards,</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Shefali Gupta</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Jendaipou Palmei</div></div><br><div class="gmail_quote"><div dir="ltr">On Wed 23 Jan 2019, 9:53 p.m. Jonathan Morton <<a href="mailto:chromatix99@gmail.com" target="_blank" rel="noreferrer">chromatix99@gmail.com</a> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">> On 23 Jan, 2019, at 6:19 pm, Shefali Gupta <<a href="mailto:shefaligups11@gmail.com" rel="noreferrer noreferrer" target="_blank">shefaligups11@gmail.com</a>> wrote:<br>
> <br>
> We believe we have spotted the issue now. The new plot is attached below.<br>
<br>
That does look considerably improved. What was the problem in the end?<br>
<br>
Now would be a good time to regenerate all the test graphs, and make sure there are results for each test for each qdisc tested. Ideally all graphs should be generated from the same run(s), to ensure their data is mutually consistent.<br>
<br>
- Jonathan Morton<br>
<br>
</blockquote></div>
</blockquote></div>