[Rcpp-devel] Using Rcpp::Function in parallel with TBB mutex lock & a reference.

[Kumar MS]

Hello Rcpp developers,

The following R/Rcpp code attempts to take in a data frame, a model formula
(passed as string),  and uses Rcpp::Function to call R's model matrix
function to create model matrices B times in parallel. Each time a model
matrix is created, it is formed after permuting a given column in the data
frame.

To avoid multi-threaded access to R, I had used the "locking" idea from the
Boost example from RInside to use a scoped lock on a mutex, and use a
single set of Rcpp::Function reference variables initialized ones.
Unfortunately, the code compiles fine, but when I run the code, I get a :

Error: C stack usage close to the limit.

I would greatly appreciate any advice !

Thank you, SK.

#### ---- C++ CODE ---------------########

// [[Rcpp::depends(RcppParallel)]]
// [[Rcpp::depends(RcppArmadillo)]]
#include <RcppArmadillo.h>
#include <RcppParallel.h>
#include <tbb/tbb.h>

using namespace arma;
using namespace Rcpp;
using namespace RcppParallel;
typedef tbb::spin_mutex FreeListMutexType;

class testParallelCallingR : public Worker {
private:
  Rcpp::String col2perm;
  Rcpp::String formulaStr;
  Rcpp::DataFrame& df0;
  arma::vec& results;

  Rcpp::Environment& stats, base;
  Rcpp::Function& formula, modelMatrix, subset ;
  SEXP& formulaObj;

  FreeListMutexType FreeListMutex;

public:
  explicit testParallelCallingR( Rcpp::String col2perm1,
                                 Rcpp::String formulaStr1,
                                 Rcpp::DataFrame& df0, arma::vec& res,
                                 Rcpp::Environment& stats,
Rcpp::Environment& base,
                                 Rcpp::Function& formula, Rcpp::Function&
modelMatrix, Rcpp::Function& subset, SEXP& formulaObj
                                 ): df0(df0), results(res), stats(stats),
base(base),
                                 formula(formula),
modelMatrix(modelMatrix), subset(subset), formulaObj(formulaObj) {
    col2perm=col2perm1;
    formulaStr=formulaStr1;
  }

  arma::mat getModelMat(){

    //lock
    FreeListMutexType::scoped_lock lock(FreeListMutex);

    //permute the column col2perm
    std::string timestr(col2perm);
    Rcpp::DataFrame dfw = Rcpp::clone(df0);
    Rcpp::NumericVector timevals = df0[timestr]; std::random_shuffle(
timevals.begin(), timevals.end() );
    dfw[timestr]=timevals;

    //construct model mat with the dataframe with the permuted column
    SEXP modelMatw=modelMatrix( formulaObj, dfw );
    arma::mat Z = Rcpp::as<arma::mat>( modelMatw );
    return Z;

  }


  void operator()( std::size_t begin, std::size_t end ) {
    for( std::size_t j=begin; j < end; j++   ){
      arma::mat Z=getModelMat();
      results(j)=Z(0,0); //just as an example result, store the first index
say
    }
  }
};


// [[Rcpp::export]]
arma::vec permDf( int B, Rcpp::String col2perm, Rcpp::String formulaStr,
Rcpp::DataFrame df0  ){

  Rcpp::Environment stats("package:stats");
  Rcpp::Environment base("package:base");
  Rcpp::Function formula = stats["formula"];
  Rcpp::Function modelMatrix=stats["model.matrix"];
  Rcpp::Function subset("[.data.frame");
  SEXP formulaObj = formula(formulaStr);
  arma::vec results( B, arma::fill::zeros );
  testParallelCallingR tpc( col2perm, formulaStr, df0, results,
                            stats, base,
                            formula, modelMatrix, subset,
                            formulaObj
                            );
  parallelFor( 0, B, tpc);
  return results;
}


# -- Call function from R side --

#      Create B permutatations of the column Sepal.Width, and form model matrice

permDf( B=10,

        col2perm = "Sepal.Width",

        formulaStr = "~Sepal.Width + Sepal.Length",

        df0=iris

          )

# -- Output --

Error: C stack usage  17587445176704 is too close to the limit

Error: C stack usage  17587449383296 is too close to the limit

Error: C stack usage  17587419937152 is too close to the limit

Error: C stack usage  17587432556928 is too close to the limit

Error: C stack usage  17587436763520 is too close to the limit

Error: C stack usage  17587440970112 is too close to the limit

Error: C stack usage  17587428350336 is too close to the limit

Error: C stack usage  17587424143744 is too close to the limit

Error: C stack usage  17587453589888 is too close to the limit

Execution halted
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/rcpp-devel/attachments/20250207/d6f02238/attachment.htm>