R not using more than 4GB of memory

I'm running 64 bit R on Ubuntu 12.10 AMD64. I recently added additional 8GB of memory to my system making it a total of 12GB. But I notice that R gives me an error whenever the memory usage (of a single R session) goes above 4GB. When I ran 6 R sessions in parallel, each consuming ~ 3 GB of memory, my over all memory usage increased up to 11 GB. But a single R session is not able to use more than 4GB! I need to train a random forest model over a large data set and I need > 4GB with a single R session.

Update:

R> sessionInfo()

R version 2.15.1 (2012-06-22)
Platform: x86_64-pc-linux-gnu (64-bit)

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=C                 LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods  
[7] base     

loaded via a namespace (and not attached):
[1] tools_2.15.1

Update 2:

$ ulimit -a
core file size          (blocks, -c) 0
data seg size           (kbytes, -d) unlimited
scheduling priority             (-e) 0
file size               (blocks, -f) unlimited
pending signals                 (-i) 92787
max locked memory       (kbytes, -l) 64
max memory size         (kbytes, -m) unlimited
open files                      (-n) 1024
pipe size            (512 bytes, -p) 8
POSIX message queues     (bytes, -q) 819200
real-time priority              (-r) 0
stack size              (kbytes, -s) 8192
cpu time               (seconds, -t) unlimited
max user processes              (-u) 92787
virtual memory          (kbytes, -v) unlimited
file locks                      (-x) unlimited

回答1:

I suspect that you have process limits in place, restricting any given process to 4G.

Try ulimit -a and look for any non-unlimited values related to memory.

Also, examine the file /etc/security/limits.conf and any files in /etc/security/limits.d/ for entries on memory limits.

In particular, these two:

data
as

See man limits.conf for the quotas that can be enforced by PAM.

回答2:

In a Windows OS, by default, R installs both 32 and 64 bit versions. Although, it looks like Linux does not. If you are using an IDE like RStudio it, if installed, points to the 32-bit version. You can change this in the Rstudio settings.