如何防止挑起写入时复制，当我叉我的过程中，GC？ 我最近一直在分析Ruby的垃圾收集器的行为，因为我在我的计划遇到了一些内存问题（我我60core 0.5TB的机器上运行的内存甚至是相当小的任务）。 对我来说，这真的限制了红宝石的多核服务器上运行的程序的有效性。 我想在这里提出我的实验和结果。
当垃圾回收器分叉过程中运行，这个问题就出现了。 我已经调查三种情况来说明问题。
情况1：我们分配大量的对象使用阵列中的存储器（串超过20个字节不再）。 该字符串使用随机数和字符串格式创建的。 当进程叉和我们迫使GC在孩子跑，所有的共享内存变为私有，导致初始存储的重复。
情况2：我们分配大量使用阵列中的存储器中的对象（串）的，但是使用rand.to_s函数创建字符串，因此我们去掉相比前情况下，数据的格式。 我们最终得到的存储器较小量被使用，这可能是由于以下的垃圾。 当进程叉和我们迫使GC在孩子跑，只有记忆的一部分变为私有。 我们最初的记忆的重复，但程度较小。
案例3：我们比以前更少的分配对象，但对象是大，使得分配的内存大小保持不变，如前面的情况。 当进程叉和我们迫使GC在所有的内存共享撑子上运行，即没有存储重复。
在这里，我贴已用于这些实验的Ruby代码。 案件之间进行切换，你只需要在memory_object功能改变“选项”值。 码一个Ubuntu 14.04机器上使用Ruby 2.2.2，2.2.1，2.1.3，2.1.5和1.9.3中进行测试。
样品输出壳体1：
ruby version 2.2.2
proces pid log priv_dirty shared_dirty
Parent 3897 post alloc 38 0
Parent 3897 4 fork 0 37
Child 3937 4 initial 0 37
Child 3937 8 empty GC 35 5
完全相同的代码已经写在Python和在所有情况下牛工作完全正常。
样品输出壳体1：
python version 2.7.6 (default, Mar 22 2014, 22:59:56)
[GCC 4.8.2]
proces pid log priv_dirty shared_dirty
Parent 4308 post alloc 35 0
Parent 4308 4 fork 0 35
Child 4309 4 initial 0 35
Child 4309 10 empty GC 1 34
Ruby代码
$start_time=Time.new
# Monitor use of Resident and Virtual memory.
class Memory
shared_dirty = '.+?Shared_Dirty:\s+(\d+)'
priv_dirty = '.+?Private_Dirty:\s+(\d+)'
MEM_REGEXP = /#{shared_dirty}#{priv_dirty}/m
# get memory usage
def self.get_memory_map( pids)
memory_map = {}
memory_map[ :pids_found] = {}
memory_map[ :shared_dirty] = 0
memory_map[ :priv_dirty] = 0
pids.each do |pid|
begin
lines = nil
lines = File.read( "/proc/#{pid}/smaps")
rescue
lines = nil
end
if lines
lines.scan(MEM_REGEXP) do |shared_dirty, priv_dirty|
memory_map[ :pids_found][pid] = true
memory_map[ :shared_dirty] += shared_dirty.to_i
memory_map[ :priv_dirty] += priv_dirty.to_i
end
end
end
memory_map[ :pids_found] = memory_map[ :pids_found].keys
return memory_map
end
# get the processes and get the value of the memory usage
def self.memory_usage( )
pids = [ $$]
result = self.get_memory_map( pids)
result[ :pids] = pids
return result
end
# print the values of the private and shared memories
def self.log( process_name='', log_tag="")
if process_name == "header"
puts " %-6s %5s %-12s %10s %10s\n" % ["proces", "pid", "log", "priv_dirty", "shared_dirty"]
else
time = Time.new - $start_time
mem = Memory.memory_usage( )
puts " %-6s %5d %-12s %10d %10d\n" % [process_name, $$, log_tag, mem[:priv_dirty]/1000, mem[:shared_dirty]/1000]
end
end
end
# function to delay the processes a bit
def time_step( n)
while Time.new - $start_time < n
sleep( 0.01)
end
end
# create an object of specified size. The option argument can be changed from 0 to 2 to visualize the behavior of the GC in various cases
#
# case 0 (default) : we make a huge array of small objects by formatting a string
# case 1 : we make a huge array of small objects without formatting a string (we use the to_s function)
# case 2 : we make a smaller array of big objects
def memory_object( size, option=1)
result = []
count = size/20
if option > 3 or option < 1
count.times do
result << "%20.18f" % rand
end
elsif option == 1
count.times do
result << rand.to_s
end
elsif option == 2
count = count/10
count.times do
result << ("%20.18f" % rand)*30
end
end
return result
end
##### main #####
puts "ruby version #{RUBY_VERSION}"
GC.disable
# print the column headers and first line
Memory.log( "header")
# Allocation of memory
big_memory = memory_object( 1000 * 1000 * 10)
Memory.log( "Parent", "post alloc")
lab_time = Time.new - $start_time
if lab_time < 3.9
lab_time = 0
end
# start the forking
pid = fork do
time = 4
time_step( time + lab_time)
Memory.log( "Child", "#{time} initial")
# force GC when nothing happened
GC.enable; GC.start; GC.disable
time = 8
time_step( time + lab_time)
Memory.log( "Child", "#{time} empty GC")
sleep( 1)
STDOUT.flush
exit!
end
time = 4
time_step( time + lab_time)
Memory.log( "Parent", "#{time} fork")
# wait for the child to finish
Process.wait( pid)
Python代码
import re
import time
import os
import random
import sys
import gc
start_time=time.time()
# Monitor use of Resident and Virtual memory.
class Memory:
def __init__(self):
self.shared_dirty = '.+?Shared_Dirty:\s+(\d+)'
self.priv_dirty = '.+?Private_Dirty:\s+(\d+)'
self.MEM_REGEXP = re.compile("{shared_dirty}{priv_dirty}".format(shared_dirty=self.shared_dirty, priv_dirty=self.priv_dirty), re.DOTALL)
# get memory usage
def get_memory_map(self, pids):
memory_map = {}
memory_map[ "pids_found" ] = {}
memory_map[ "shared_dirty" ] = 0
memory_map[ "priv_dirty" ] = 0
for pid in pids:
try:
lines = None
with open( "/proc/{pid}/smaps".format(pid=pid), "r" ) as infile:
lines = infile.read()
except:
lines = None
if lines:
for shared_dirty, priv_dirty in re.findall( self.MEM_REGEXP, lines ):
memory_map[ "pids_found" ][pid] = True
memory_map[ "shared_dirty" ] += int( shared_dirty )
memory_map[ "priv_dirty" ] += int( priv_dirty )
memory_map[ "pids_found" ] = memory_map[ "pids_found" ].keys()
return memory_map
# get the processes and get the value of the memory usage
def memory_usage( self):
pids = [ os.getpid() ]
result = self.get_memory_map( pids)
result[ "pids" ] = pids
return result
# print the values of the private and shared memories
def log( self, process_name='', log_tag=""):
if process_name == "header":
print " %-6s %5s %-12s %10s %10s" % ("proces", "pid", "log", "priv_dirty", "shared_dirty")
else:
global start_time
Time = time.time() - start_time
mem = self.memory_usage( )
print " %-6s %5d %-12s %10d %10d" % (process_name, os.getpid(), log_tag, mem["priv_dirty"]/1000, mem["shared_dirty"]/1000)
# function to delay the processes a bit
def time_step( n):
global start_time
while (time.time() - start_time) < n:
time.sleep( 0.01)
# create an object of specified size. The option argument can be changed from 0 to 2 to visualize the behavior of the GC in various cases
#
# case 0 (default) : we make a huge array of small objects by formatting a string
# case 1 : we make a huge array of small objects without formatting a string (we use the to_s function)
# case 2 : we make a smaller array of big objects
def memory_object( size, option=2):
count = size/20
if option > 3 or option < 1:
result = [ "%20.18f"% random.random() for i in xrange(count) ]
elif option == 1:
result = [ str( random.random() ) for i in xrange(count) ]
elif option == 2:
count = count/10
result = [ ("%20.18f"% random.random())*30 for i in xrange(count) ]
return result
##### main #####
print "python version {version}".format(version=sys.version)
memory = Memory()
gc.disable()
# print the column headers and first line
memory.log( "header") # Print the headers of the columns
# Allocation of memory
big_memory = memory_object( 1000 * 1000 * 10) # Allocate memory
memory.log( "Parent", "post alloc")
lab_time = time.time() - start_time
if lab_time < 3.9:
lab_time = 0
# start the forking
pid = os.fork() # fork the process
if pid == 0:
Time = 4
time_step( Time + lab_time)
memory.log( "Child", "{time} initial".format(time=Time))
# force GC when nothing happened
gc.enable(); gc.collect(); gc.disable();
Time = 10
time_step( Time + lab_time)
memory.log( "Child", "{time} empty GC".format(time=Time))
time.sleep( 1)
sys.exit(0)
Time = 4
time_step( Time + lab_time)
memory.log( "Parent", "{time} fork".format(time=Time))
# Wait for child process to finish
os.waitpid( pid, 0)
编辑
事实上，调用GC多次分叉过程之前解决这个问题，我很惊讶。 我也运行使用Ruby 2.0.0的代码，这个问题甚至没有出现，所以它必须与就像你提到的这代GC。 但是，如果我叫memory_object功能不分配输出到任何变量（我只创建垃圾），那么内存被复制。 被复制的内存量取决于我创作的垃圾量 - 越垃圾，更多的内存变为私有。
任何想法如何避免这种情况？
这里有一些结果
运行在2.0.0的GC
ruby version 2.0.0
proces pid log priv_dirty shared_dirty
Parent 3664 post alloc 67 0
Parent 3664 4 fork 1 69
Child 3700 4 initial 1 69
Child 3700 8 empty GC 6 65
在调用子memory_object（1000 * 1000）
ruby version 2.0.0
proces pid log priv_dirty shared_dirty
Parent 3703 post alloc 67 0
Parent 3703 4 fork 1 70
Child 3739 4 initial 1 70
Child 3739 8 empty GC 15 56
调用memory_object（1000 * 1000 * 10）
ruby version 2.0.0
proces pid log priv_dirty shared_dirty
Parent 3743 post alloc 67 0
Parent 3743 4 fork 1 69
Child 3779 4 initial 1 69
Child 3779 8 empty GC 89 5
