Dear Experts!
In the beginning of my code, several output root files are created and each is then filled with histograms with identical names accross files. This is because the files describe systematic variations of the same computation. Closing the files takes a long time. The first takes the longest then the second one is a bit faster and so on, the last one is really fast. I think this has to do with ROOT’s internal bookkeeping of the histograms, but I don’t know how I could mitigate the issue.
Any ideas?
Here is a minimum working example:
#include <iostream>
#include <vector>
#include <map>
#include <TROOT.h>
#include <TH1.h>
#include <TH1D.h>
#include <TFile.h>
#include <TBenchmark.h>
class OutputHandler{
public:
TFile *outFile;
std::map<std::string, TH1D* > h_controlHists;
OutputHandler(const char*);
void close();
};
OutputHandler::OutputHandler(const char* fName){
outFile = new TFile(fName, "RECREATE");
TH1::SetDefaultSumw2();
for (int i=0; i<10; i++){
TDirectory* tempTDirPtr = outFile->mkdir(("dir_" + std::to_string(i)).c_str());
tempTDirPtr -> cd();
for (int j=0; j<1000; j++){
std::string hName = "name_" + std::to_string(i) + "_" + std::to_string(j);
h_controlHists[hName] = new TH1D(hName.c_str(), "", 10, 0, 10);
h_controlHists[hName]->Fill(3.0,5);
}
}
}
void OutputHandler::close(){
TBenchmark time;
time.Start("time2");
outFile->Write();
time.Stop("time2");
std::cout<<"Write: Real time = "<<time.GetRealTime("time2")<<" s"<<std::endl;
// outFile->GetList()->Clear();
gROOT->GetListOfFiles()->Remove(outFile);
time.Start("time3");
outFile->Close();
time.Stop("time3");
std::cout<<"Close: Real time = "<<time.GetRealTime("time3")<<" s"<<std::endl;
}
int main(int argc, char** argv)
{
TBenchmark time;
time.Start("time");
OutputHandler a("test1.root"), b("test2.root"), c("test3.root");
a.close();
b.close();
c.close();
time.Stop("time");
float cputime = time.GetCpuTime("time");
float realtime = time.GetRealTime("time");
std::cout<<"CPU time = "<<cputime<<" s, Real time = "<<realtime<<" s"<<std::endl;
return 0;
}
