add tests for isendrecv and isendrecv_replace

[simgrid.git] / docs / source / tuto_disk / analysis.org

diff --git a/docs/source/tuto_disk/analysis.org b/docs/source/tuto_disk/analysis.org
index 92efd2e395a504ddf2f90a56633340c31de620ff..01ed87cacb251814ed39bc0bb7f52f6243afe3b6 100644 (file)
--- a/docs/source/tuto_disk/analysis.org
+++ b/docs/source/tuto_disk/analysis.org
@@ -15,16 +15,23 @@
 
  The paper presents a series of experiments to analyze the performance
  of IO operations (read/write) on different kinds of disks (SATA, SAS,
 
  The paper presents a series of experiments to analyze the performance
  of IO operations (read/write) on different kinds of disks (SATA, SAS,

- SSD). In this tutorial, we show how to extract this data to simulate
- both performance degradation with concurrent operations (Fig. 8 in the
- paper) and variability in IO operations (Fig. 5 to 7).
+ SSD). In this tutorial, we present a detailed example of how to
+ extract experimental data to simulate: i) performance degradation
+ with concurrent operations (Fig. 8 in the paper) and ii) variability
+ in IO operations (Fig. 5 to 7).

 
  - Link for paper: https://hal.inria.fr/hal-01197128
  - Link for data: https://figshare.com/articles/dataset/Companion_of_the_SimGrid_storage_modeling_article/1175156
 
 
  - Link for paper: https://hal.inria.fr/hal-01197128
  - Link for data: https://figshare.com/articles/dataset/Companion_of_the_SimGrid_storage_modeling_article/1175156
 

- *WARNING*: The purpose of this document is to illustrate how we can
+ *Disclaimer*:
+- The purpose of this document is to illustrate how we can

  extract data from experiments and inject on SimGrid. However, the
  extract data from experiments and inject on SimGrid. However, the

- results may *not* reflect the reality.
+ data shown on this page may *not* reflect the reality.
+- You must run similar experiments on your hardware to get realistic
+  data for your context.
+- SimGrid has been in active development since the paper release in
+  2015, thus the XML description used in the paper may have evolved 
+  while MSG was superseeded by S4U since then.

 
 *** Running this tutorial
 
 
 *** Running this tutorial
 


@@ -38,7 +45,7 @@
 *** Scripts
 
  We use a special method to create non-uniform histograms to represent
 *** Scripts
 
  We use a special method to create non-uniform histograms to represent

- the noise in IO operations. 
+ the noise in IO operations.

 
  Unable to install the library properly, I copied the important methods
  here.
 
  Unable to install the library properly, I copied the important methods
  here.


@@ -48,21 +55,21 @@
  #+begin_src R :results output :session *R* :exports none
 #' Variable-width (dagonally cut) histogram
 #'
  #+begin_src R :results output :session *R* :exports none
 #' Variable-width (dagonally cut) histogram
 #'

-#' 
+#'

 #' When constructing a histogram, it is common to make all bars the same width.
 #' One could also choose to make them all have the same area.
 #' These two options have complementary strengths and weaknesses; the equal-width histogram oversmooths in regions of high density, and is poor at identifying sharp peaks; the equal-area histogram oversmooths in regions of low density, and so does not identify outliers.
 #' When constructing a histogram, it is common to make all bars the same width.
 #' One could also choose to make them all have the same area.
 #' These two options have complementary strengths and weaknesses; the equal-width histogram oversmooths in regions of high density, and is poor at identifying sharp peaks; the equal-area histogram oversmooths in regions of low density, and so does not identify outliers.

-#' We describe a compromise approach which avoids both of these defects. We regard the histogram as an exploratory device, rather than as an estimate of a density. 
-#' @title Diagonally Cut Histogram 
+#' We describe a compromise approach which avoids both of these defects. We regard the histogram as an exploratory device, rather than as an estimate of a density.
+#' @title Diagonally Cut Histogram

 #' @param x is a numeric vector (the data)
 #' @param a is the scaling factor, default is 5 * IQR
 #' @param nbins is the number of bins, default is assigned by the Stuges method
 #' @param x is a numeric vector (the data)
 #' @param a is the scaling factor, default is 5 * IQR
 #' @param nbins is the number of bins, default is assigned by the Stuges method

-#' @param rx  is the range used for the left of the left-most bin to the right of the right-most bin  
+#' @param rx  is the range used for the left of the left-most bin to the right of the right-most bin

 #' @param eps used to set artificial bound on min width / max height of bins as described in Denby and Mallows (2009) on page 24.
 #' @param eps used to set artificial bound on min width / max height of bins as described in Denby and Mallows (2009) on page 24.

-#' @param xlab is label for the x axis 
+#' @param xlab is label for the x axis

 #' @param plot = TRUE produces the plot, FALSE returns the heights, breaks and counts
 #' @param lab.spikes = TRUE labels the \% of data in the spikes
 #' @param plot = TRUE produces the plot, FALSE returns the heights, breaks and counts
 #' @param lab.spikes = TRUE labels the \% of data in the spikes

-#' @return list with two elements, heights of length n and breaks of length n+1 indicating the heights and break points of the histogram bars. 
+#' @return list with two elements, heights of length n and breaks of length n+1 indicating the heights and break points of the histogram bars.

 #' @author Lorraine Denby, Colin Mallows
 #' @references Lorraine Denby, Colin Mallows. Journal of Computational and Graphical Statistics. March 1, 2009, 18(1): 21-31. doi:10.1198/jcgs.2009.0002.
  dhist<-function(x, a=5*iqr(x),
 #' @author Lorraine Denby, Colin Mallows
 #' @references Lorraine Denby, Colin Mallows. Journal of Computational and Graphical Statistics. March 1, 2009, 18(1): 21-31. doi:10.1198/jcgs.2009.0002.
  dhist<-function(x, a=5*iqr(x),


@@ -90,7 +97,7 @@
                                          # upper and lower corners in the ecdf
      ylower <- yupper - a/n
                                          #
                                          # upper and lower corners in the ecdf
      ylower <- yupper - a/n
                                          #

-     cmtx <- cbind(cut(yupper, breaks = ybr), cut(yupper, breaks = 
+     cmtx <- cbind(cut(yupper, breaks = ybr), cut(yupper, breaks =

                                  ybr, left.include = TRUE), cut(ylower, breaks = ybr),
                    cut(ylower, breaks = ybr, left.include = TRUE))
      cmtx[1, 3] <- cmtx[1, 4] <- 1
                                  ybr, left.include = TRUE), cut(ylower, breaks = ybr),
                    cut(ylower, breaks = ybr, left.include = TRUE))
      cmtx[1, 3] <- cmtx[1, 4] <- 1


@@ -170,7 +177,7 @@
    amt.txt<-0
    end.y<-(-10000)
    if(plot) {
    amt.txt<-0
    end.y<-(-10000)
    if(plot) {

-     barplot(heights, abs(diff(xbr)), space = 0, density = -1, xlab = 
+     barplot(heights, abs(diff(xbr)), space = 0, density = -1, xlab =

              xlab, plot = TRUE, xaxt = "n",yaxt='n')
      at <- pretty(xbr)
      axis(1, at = at - xbr[1], labels = as.character(at))
              xlab, plot = TRUE, xaxt = "n",yaxt='n')
      at <- pretty(xbr)
      axis(1, at = at - xbr[1], labels = as.character(at))


@@ -207,7 +214,7 @@
 #' Calculates the 25th and 75th quantiles given a vector x; used in function \link{dhist}.
 #' @title Interquartile range
 #' @param x vector
 #' Calculates the 25th and 75th quantiles given a vector x; used in function \link{dhist}.
 #' @title Interquartile range
 #' @param x vector

-#' @return numeric vector of length 2, with the 25th and 75th quantiles of input vector x. 
+#' @return numeric vector of length 2, with the 25th and 75th quantiles of input vector x.

  iqr<-function(x){
    return(diff(quantile(x, c(0.25, 0.75), na.rm = TRUE)))
  }
  iqr<-function(x){
    return(diff(quantile(x, c(0.25, 0.75), na.rm = TRUE)))
  }


@@ -357,7 +364,7 @@
  from the one in the paper. Probably, we need to further clean the
  available data to obtain exaclty the same results.
 
  from the one in the paper. Probably, we need to further clean the
  available data to obtain exaclty the same results.
 

- #+begin_src R :results output graphics :file fig/griffon_deg.png :exports both :width 600 :height 400 :session *R* 
+ #+begin_src R :results output graphics :file fig/griffon_deg.png :exports both :width 600 :height 400 :session *R*

    ggplot(data=dfc,aes(x=Jobs,y=BW, color=Operation)) + theme_bw() +
      geom_point(alpha=.3) +
      geom_point(data=dfrange, size=0) +
    ggplot(data=dfc,aes(x=Jobs,y=BW, color=Operation)) + theme_bw() +
      geom_point(alpha=.3) +
      geom_point(data=dfrange, size=0) +


@@ -381,7 +388,7 @@
  toJSON(IO_INFO, pretty = TRUE)
  #+end_src
 
  toJSON(IO_INFO, pretty = TRUE)
  #+end_src
 

- 
+

 ***** Write
 
  Same for write operations.
 ***** Write
 
  Same for write operations.


@@ -393,7 +400,7 @@
  IO_INFO[["griffon"]][["degradation"]][["write"]] = c(mean_job_1$mean, predict(model,data.frame(Jobs=seq(2,15))))
  toJSON(IO_INFO, pretty = TRUE)
  #+end_src
  IO_INFO[["griffon"]][["degradation"]][["write"]] = c(mean_job_1$mean, predict(model,data.frame(Jobs=seq(2,15))))
  toJSON(IO_INFO, pretty = TRUE)
  #+end_src

- 
+

 
 **** Modeling read/write bandwidth variability
 
 
 **** Modeling read/write bandwidth variability
 


@@ -407,7 +414,7 @@
 
 ***** Read
  First, we present the histogram for read operations.
 
 ***** Read
  First, we present the histogram for read operations.

- #+begin_src R :results output graphics :file fig/griffon_read_dhist.png :exports both :width 600 :height 400 :session *R* 
+ #+begin_src R :results output graphics :file fig/griffon_read_dhist.png :exports both :width 600 :height 400 :session *R*

  griffon_read = df %>% filter(grepl("^Griffon", Cluster)) %>% filter(Operation == "Read") %>% select(Bwi)
  dhist(1/griffon_read$Bwi)
  #+end_src
  griffon_read = df %>% filter(grepl("^Griffon", Cluster)) %>% filter(Operation == "Read") %>% select(Bwi)
  dhist(1/griffon_read$Bwi)
  #+end_src


@@ -424,7 +431,7 @@
 ***** Write
 
  Same analysis for write operations.
 ***** Write
 
  Same analysis for write operations.

- #+begin_src R :results output graphics :file fig/griffon_write_dhist.png :exports both :width 600 :height 400 :session *R* 
+ #+begin_src R :results output graphics :file fig/griffon_write_dhist.png :exports both :width 600 :height 400 :session *R*

  griffon_write = df %>% filter(grepl("^Griffon", Cluster)) %>% filter(Operation == "Write") %>% select(Bwi)
  dhist(1/griffon_write$Bwi)
  #+end_src
  griffon_write = df %>% filter(grepl("^Griffon", Cluster)) %>% filter(Operation == "Write") %>% select(Bwi)
  dhist(1/griffon_write$Bwi)
  #+end_src


@@ -468,7 +475,7 @@
 
 ***** Read
 
 
 ***** Read
 

- #+begin_src R :results output graphics :file fig/edel_read_dhist.png :exports both :width 600 :height 400 :session *R* 
+ #+begin_src R :results output graphics :file fig/edel_read_dhist.png :exports both :width 600 :height 400 :session *R*

  edel_read = df %>% filter(grepl("^Edel", Cluster)) %>% filter(Operation == "Read") %>% select(Bwi)
  dhist(1/edel_read$Bwi)
  #+end_src
  edel_read = df %>% filter(grepl("^Edel", Cluster)) %>% filter(Operation == "Read") %>% select(Bwi)
  dhist(1/edel_read$Bwi)
  #+end_src


@@ -483,7 +490,7 @@
  #+end_src
 
 ***** Write
  #+end_src
 
 ***** Write

- #+begin_src R :results output graphics :file fig/edel_write_dhist.png :exports both :width 600 :height 400 :session *R* 
+ #+begin_src R :results output graphics :file fig/edel_write_dhist.png :exports both :width 600 :height 400 :session *R*

 
  edel_write = df %>% filter(grepl("^Edel", Cluster)) %>% filter(Operation == "Write") %>% select(Bwi)
  dhist(1/edel_write$Bwi)
 
  edel_write = df %>% filter(grepl("^Edel", Cluster)) %>% filter(Operation == "Write") %>% select(Bwi)
  dhist(1/edel_write$Bwi)


@@ -575,15 +582,15 @@ each case.
 We can see that the graphics are quite similar to the ones obtained in
 the real platform.
 
 We can see that the graphics are quite similar to the ones obtained in
 the real platform.
 

- #+begin_src R :results output graphics :file fig/simgrid_results.png :exports both :width 600 :height 400 :session *R* 
+ #+begin_src R :results output graphics :file fig/simgrid_results.png :exports both :width 600 :height 400 :session *R*

  sg_df = read.csv("./simgrid_disk.csv")
  sg_df = sg_df %>% group_by(disk, op, flows) %>% mutate(bw=((size*flows)/elapsed)/10^6, method=if_else(disk=="edel" & op=="read", "loess", "lm"))
  sg_dfd = sg_df %>% filter(flows==1 & op=="write") %>% group_by(disk, op, flows) %>% summarize(mean = mean(bw), sd = sd(bw), se=sd/sqrt(n()))
 
  sg_df[sg_df$op=="write" & sg_df$flows ==1,]$method=""
  sg_df = read.csv("./simgrid_disk.csv")
  sg_df = sg_df %>% group_by(disk, op, flows) %>% mutate(bw=((size*flows)/elapsed)/10^6, method=if_else(disk=="edel" & op=="read", "loess", "lm"))
  sg_dfd = sg_df %>% filter(flows==1 & op=="write") %>% group_by(disk, op, flows) %>% summarize(mean = mean(bw), sd = sd(bw), se=sd/sqrt(n()))
 
  sg_df[sg_df$op=="write" & sg_df$flows ==1,]$method=""

- 
+

  ggplot(data=sg_df, aes(x=flows, y=bw, color=op)) + theme_bw() +
  ggplot(data=sg_df, aes(x=flows, y=bw, color=op)) + theme_bw() +

-     geom_point(alpha=.3) + 
+     geom_point(alpha=.3) +

      geom_smooth(data=sg_df[sg_df$method=="loess",], color="black", method=loess,se=TRUE,fullrange=T) +
      geom_smooth(data=sg_df[sg_df$method=="lm",], color="black", method=lm,se=TRUE) +
      geom_errorbar(data=sg_dfd, aes(x=flows, y=mean, ymin=mean-2*se, ymax=mean+2*se),color="black",width=.6) +
      geom_smooth(data=sg_df[sg_df$method=="loess",], color="black", method=loess,se=TRUE,fullrange=T) +
      geom_smooth(data=sg_df[sg_df$method=="lm",], color="black", method=lm,se=TRUE) +
      geom_errorbar(data=sg_dfd, aes(x=flows, y=mean, ymin=mean-2*se, ymax=mean+2*se),color="black",width=.6) +