Added the following lines missing from my original post:
strategy1 = timer( 'Default buffer' )
strategy1.start()
Code below is now complete.
Malcolm
SOURCE:
import time
# timer class
class timer( object ):
def __init__( self, message='' ):
self.message = message
def start( self ):
self.starttime = time.time()
print 'Start: %s' % ( self.message )
def stop( self ):
print 'Finish: %s %6.2f' % ( self.message, time.time() -
self.starttime )
# myFileName points to a 2G text file.
myFileName = r'C:\logs\jan2009.dat'
# default buffering
strategy1 = timer( 'Default buffer' )
strategy1.start()
myFile = open( myFileName )
for line in myFile:
pass
myFile.close()
strategy1.stop()
# setting the buffer size to 16M
bufferSize = 2 ** 24
strategy2 = timer( 'Large buffer (%sk)' % (bufferSize/1024) )
strategy2.start()
myFile = open( myFileName, 'rt', bufferSize )
for line in myFile:
pass
myFile.close()
strategy2.stop()
OUTPUT:
Start: Default buffer
Finish: Default buffer 69.98
Start: Large buffer (16384k)
Finish: Large buffer (16384k) 493.88 <--- 7x slower
Any comments regarding this massive slowdown?
Thanks,
Malcolm
--
http://mail.python.org/mailman/listinfo/python-list
