Calculating memorypool sizes

I have chosen some values from these guidelines from Charlie Hunt’s book. This is the latest ‘R’ code. That last blog entry has the old code.

I am using some of these general rules just as a foundation for further calculation. Generally our capacity planning teams do not have any baseline. I have not investigated the actual justification for some of these figures.

Guidelines for Calculating Java Heap Sizing

2x to 3x old generation space occupancy
after full garbage collection

library(stringr)

this.dir <- dirname(parent.frame(2)$ofile) 
setwd(this.dir)

data <- read.table("D:\\GC Analysis\\gc.log-node1",sep="\n")

parse.mean <- function(){
	fullgc.timestamp( fullgc.read() )
}


# Grep Full GC lines
fullgc.read <- function(){
	return (data$V1[ grep ("(.*)Full GC(.*)", data[,1])])
}

fullgc.data <- function(timedata,memorydata){

   memorydata["Time"] <- "NA"
   memorydata$Time <- unlist(timedata)
   return (fixdate(memorydata))
}

fullgc.timestamp <- function(input){

	time <- str_extract(input,"T[^.]*")
	timeframex<-data.frame(time)
	timeframey<-subset(timeframex, timeframex[1] != "NA")
	timeframey<-substring(timeframey$time,2,9)
	timeframey <- data.frame(timeframey)
	colnames( timeframey ) <- c("Time")
    return (timeframey)	
}

fullgc.memorypool.mean <- function(input){
	data <- str_extract(input,"PSYou.*[/)]")
	data <- str_extract_all(data,"[0-9]+")
	data <- data.frame(matrix(unlist(data),ncol=12,byrow=T))
	colnames(data)[2] <- c("YoungGenAfterFullGC")
	colnames(data)[8] <- c("OldGenAfterFullGC")
	colnames(data)[11] <- c("PermGenAfterFullGC")
    return (data)
}

fixdate <- function(filtereddata){

    filtereddata$Time1<-strptime(filtereddata$Time,"%H:%M:%S")
	offset<-86400
    lasttime<-filtereddata$Time1[1]
    
	filtereddata$Time1[1]<-filtereddata$Time1[1]+offset
	lasttime<-filtereddata$Time1[1]
	for(timedate in 2:length(filtereddata$Time1)) {
		if(as.numeric(filtereddata$Time1[timedate]) < lasttime){
			offset<- offset + 86400
		}
		filtereddata$Time1[timedate]<-filtereddata$Time1[timedate]+offset
		lasttime<-filtereddata$Time1[timedate]
	}
	return(filtereddata)
}

fullgc.youngandoldgen.graph <- function(filtereddata){
	print(filtereddata)
	png(
	"younggenrecommendation.png",
	width =1700, height = 510)
options("scipen"=100, "digits"=4)    
plot( filtereddata$Time1,
      levels(filtereddata$YoungGenAfterFullGC)[filtereddata$YoungGenAfterFullGC],
	  col="darkblue",type="l",
	  ylab="MB",
	  xlab="",
	  las=2,
	  lwd=5.5,
	  cex.lab=1,
	  cex.axis=0.8,
	  xaxt="n",
	  ylim=c(min(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC])),
	         max(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC]))))
axis(1, at = as.numeric(filtereddata$Time1), labels = filtereddata$Time, las = 2,cex.axis=1.2)
mtext("Time", side=1, line=-1, cex=1.3) 
abline(h=mean(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC])),col="yellow")
title("Younggen(1.5*Mean of Oldgen) and Total heap(4 * oldgen mean) recommendation",cex.main=1.5)
	box("figure", col="blue")
points( filtereddata$Time1,
        levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC],
		col="yellow",
		las=2,
		lwd=5.5,
		type="l")
legend("topleft", lty=c(1,1),lwd=c(3.5,3.5),
       c(paste("Younggen = Oldgenmean * 1.5 = ",
	            signif(mean(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC]))/1048*2,digits=2)," "," * 1.5 = ",
				signif((mean(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC]))/1048*2)*1.5,digits=2),"MB"),
				paste("Total heap ",signif((mean(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC]))/1048*2)*4,digits=2),"MB")),
 	   fill=c("darkblue"))

dev.off()
}

fullgc.permandoldgen.graph <- function(filtereddata){

	png(
	"permgenrecommendation.png",
	width =1700, height = 510)
options("scipen"=100, "digits"=4)    
plot( filtereddata$Time1,
      levels(filtereddata$PermGenAfterFullGC)[filtereddata$PermGenAfterFullGC],
	  col="darkblue",type="l",
	  ylab="MB",
	  xlab="",
	  las=2,
	  lwd=5.5,
	  cex.lab=1,
	  cex.axis=0.8,
	  xaxt="n",
	  ylim=c(min(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC])),
	         max(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC]))))
axis(1, at = as.numeric(filtereddata$Time1), labels = filtereddata$Time, las = 2,cex.axis=1.2)
mtext("Time", side=1, line=-1, cex=1.3) 
abline(h=mean(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC])),col="yellow")
abline(h=mean(as.numeric(levels(filtereddata$PermGenAfterFullGC)[filtereddata$PermGenAfterFullGC])),col="darkblue")
title("Permgen(1.5*mean)/Oldgen(2*mean)  recommendation",cex.main=1.5)
	box("figure", col="blue")
points( filtereddata$Time1,
        levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC],
		col="yellow",
		las=2,
		lwd=5.5,
		type="l")
legend("topleft", lty=c(1,1),lwd=c(3.5,3.5),
       c(paste("Oldgen ",signif((mean(as.numeric(levels(filtereddata$OldGenAfterFullGC)[filtereddata$OldGenAfterFullGC]))/1048*2)*2,digits=2),"MB"),
	     paste("Permgen ",signif((mean(as.numeric(levels(filtereddata$PermGenAfterFullGC)[filtereddata$PermGenAfterFullGC]))/1048*2)*1.5,digits=2),"MB")),
 	   fill=c("darkblue","yellow"))

dev.off()
}