<div dir="ltr">Ok, and I spoke too soon and reported numbers for 17.5 :P<div><br></div><div>I've collected 17.5 and 18.0-rc1-109-gb5f3973 by the same method as in my previous post. The summaries in R are:</div><div><br></div><div><div>> r17 <- read.csv('data-17.5.txt', header=FALSE)</div><div>> r18 <- read.csv('data_OTP-18.0-rc1-109-gb5f3973.txt', header=FALSE)</div><div>> r17$version <- 17</div><div>> r18$version <- 18</div><div>> x <- rbind(r17, r18)</div><div>> summary(r17)</div><div> V1 version </div><div> Min. :0.1900 Min. :17 </div><div> 1st Qu.:0.1930 1st Qu.:17 </div><div> Median :0.1940 Median :17 </div><div> Mean :0.1946 Mean :17 </div><div> 3rd Qu.:0.1960 3rd Qu.:17 </div><div> Max. :0.2040 Max. :17 </div><div>> summary(r18)</div><div> V1 version </div><div> Min. :0.2100 Min. :18 </div><div> 1st Qu.:0.2790 1st Qu.:18 </div><div> Median :0.2840 Median :18 </div><div> Mean :0.2968 Mean :18 </div><div> 3rd Qu.:0.3493 3rd Qu.:18 </div><div> Max. :0.4050 Max. :18 </div></div><div><br></div><div>This is more like it! They are vastly different, with the r18 version having a much much larger spread. How large?</div><div><br></div><div>install.packages('ggplot2')</div><div>m <- ggplot(x, aes(x = V1, colour=version, group=version)</div><div>m + geom_density(fill=NA)</div><div><br></div><div>The kernel density plot on imgur:</div><div><br></div><div><a href="http://imgur.com/9i8YE0U">http://imgur.com/9i8YE0U</a><br></div><div><br></div><div>which clearly shows that bootup of 17.5 is consistent, whereas bootup of the 18.0-rc1++ version I run is highly erratic. Is this due to timer wheel bootup and the new time tracking code?</div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Apr 13, 2015 at 10:38 PM, Jesper Louis Andersen <span dir="ltr"><<a href="mailto:jesper.louis.andersen@gmail.com" target="_blank">jesper.louis.andersen@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><span class=""><br><div class="gmail_quote">On Mon, Apr 13, 2015 at 6:44 PM, José Valim <span dir="ltr"><<a href="mailto:jose.valim@plataformatec.com.br" target="_blank">jose.valim@plataformatec.com.br</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">2. The time to start, write to stdio and shutdown the erlang system is higher on 18.0</blockquote></div><br></span>I was interested in this one, because I think I've perceived startup times being less regular, and this is a good check. I did:</div><div class="gmail_extra"><br></div><div class="gmail_extra"><div class="gmail_extra">[jlouis@lady-of-pain 2]$ for i in $(seq 1 100); do time erl -eval "io:format(hello, []), halt()." ; done > collected.txt 2>&1</div><div class="gmail_extra">grep real collected.txt | sed -e 's/^.*m//g' -e s/s$//g > data.txt</div><div class="gmail_extra"><br></div><div class="gmail_extra">To collect the necessary data. On a FreeBSD system, you might need the jot(1) command rather than the seq(1) command, but the idea is the same.</div><div class="gmail_extra"><br></div><div class="gmail_extra">In R:</div><div class="gmail_extra"><br></div><div class="gmail_extra">x <- read.csv('data.txt', header=FALSE)</div><div class="gmail_extra">> summary(x)</div><div class="gmail_extra"> V1 </div><div class="gmail_extra"> Min. :0.1890 </div><div class="gmail_extra"> 1st Qu.:0.1930 </div><div class="gmail_extra"> Median :0.1940 </div><div class="gmail_extra"> Mean :0.1948 </div><div class="gmail_extra"> 3rd Qu.:0.1963 </div><div class="gmail_extra"> Max. :0.2050 </div><div><br></div>In other words, my hunch was soundly destroyed by data. I've seen what I perceive to be longer boot times as well, and they seem to deviate more. But the human perception is so bad at precise measurements. Consider using the above script-idea together with R to obtain some more data and better numbers. The mean is usually only a good statistic if you have other data.<span class="HOEnZb"><font color="#888888"><br clear="all"><div><br></div>-- <br><div>J.</div>
</font></span></div></div>
</blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature">J.</div>
</div>