On Mon, Feb 22, 2010 at 6:40 PM, Nicolas Pitre [off-list ref] wrote:
read() is not always a winner. A read() call will always have the data
duplicated in memory. Especially with large files, it is more efficient
on the system as a whole to mmap() a 50 MB file rather than allocating
Agreed. I meant it was faster on data that I measured, which was <=1Mb.
IMHO, read() should be used up to 64Kb.
Dmitry