[CRIU] [PATCH] criu: add make lazy support to crit

[Pavel Emelyanov]

On 05/04/2016 08:03 PM, Adrian Reber wrote:
> On Wed, May 04, 2016 at 07:49:14PM +0300, Pavel Emelyanov wrote:
>> On 04/29/2016 11:39 AM, Adrian Reber wrote:
>>> From: Adrian Reber <areber at redhat.com>
>>>
>>> This enables crit to remove all memory pages from a checkpoint
>>> directory which can be lazily restored using userfaultfd. This
>>> changes the pagemap.img and pages.img to no longer contain pages
>>> which can be handled by userfaultfd (MAP_PRIVATE && MAP_ANON).
>>>
>>> Usage:
>>>
>>>  $ crit/crit make-lazy /tmp/4/ /tmp/5
>>>  $ du -hs /tmp/4 /tmp/5
>>>  201M	/tmp/4
>>>  116K	/tmp/5
>>>
>>> The checkpoint in /tmp/5 can be used by the actual restore process
>>> and the checkpoint in /tmp/4 (with all memory pages) can be used
>>> by the uffd daemon which then transfers the pages into the restored
>>> on demand.
>>
>> OK, but what's the use case you see for this?
> 
> To be able to remove the lazy pages from a checkpoint after the dump to
> be able to restore it lazily.

But if you did full dump (and killed tasks) then removed lazy pages from
images, where would you take the pages from?

> Also for testing, as a conformation, that
> the restore actually works with all lazy pages removed.
> 
> 		Adrian
> 
>>> Signed-off-by: Adrian Reber <areber at redhat.com>
>>> ---
>>>  crit/crit | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>>>  1 file changed, 78 insertions(+)
>>>
>>> diff --git a/crit/crit b/crit/crit
>>> index 93cbc98..0e97fe5 100755
>>> --- a/crit/crit
>>> +++ b/crit/crit
>>> @@ -217,6 +217,75 @@ explorers = { 'ps': explore_ps, 'fds': explore_fds, 'mems': explore_mems }
>>>  def explore(opts):
>>>  	explorers[opts['what']](opts)
>>>  
>>> +def make_lazy(opts):
>>> +	""" This function takes the pages from the input directory
>>> +	and removes all pages which can be restored lazily.
>>> +	MAP_PRIVATE && MAP_ANON and not VDSO and not VSYSCALL. """
>>> +	# page size is hardcoded to 0x1000; probably a bad idea
>>> +	ps = 0x1000
>>> +	ps_img = pycriu.images.load(dinf(opts, 'pstree.img'))
>>> +	vids = vma_id()
>>> +	lazy_pages = []
>>> +	for p in ps_img['entries']:
>>> +		pid = p['pid']
>>> +		mmi = pycriu.images.load(dinf(opts, 'mm-%d.img' % pid))['entries'][0]
>>> +
>>> +		print "%d" % pid
>>> +
>>> +		for vma in mmi['vmas']:
>>> +			st = vma['status']
>>> +			# 'MAP_PRIVATE', 0x2
>>> +			# 'MAP_ANON',    0x20
>>> +			if (vma['flags'] & 0x2) and (vma['flags'] & 0x20):
>>> +				# (1 << 2) vsyscall
>>> +				# (1 << 3) vdso
>>> +				if not (st & (1 << 2)) and not (st & (1 << 3)):
>>> +					vaddr = vma['start']
>>> +					while vaddr < vma['end']:
>>> +						lazy_pages.append(vaddr)
>>> +						vaddr += ps
>>> +
>>> +		pms = pycriu.images.load(dinf(opts, 'pagemap-%d.img' % pid))
>>> +		new = []
>>> +
>>> +		# find first pages_id
>>> +		pages_id = -1
>>> +		for pm in pms['entries']:
>>> +			if pm.has_key('pages_id'):
>>> +				pages_id = pm['pages_id']
>>> +
>>> +		if pages_id == -1:
>>> +			# something went wrong
>>> +			raise Exception('No pages_id found in pagemap!')
>>> +
>>> +		# open the original pages.img to remove the lazy pages
>>> +		pages_in = os.path.join(opts['dir'], 'pages-%d.img' % pages_id)
>>> +		pages_in = open(pages_in, 'rb')
>>> +
>>> +		pages_out = os.path.join(opts['outdir'], 'pages-%d.img' % pages_id)
>>> +
>>> +		pages_out = open(pages_out, 'wb')
>>> +
>>> +		for pm in pms['entries']:
>>> +			if pm.has_key('pages_id'):
>>> +				new.append(pm)
>>> +				continue
>>> +			vaddr = pm['vaddr']
>>> +			i = 0
>>> +			start = 0
>>> +			while vaddr < pm['vaddr'] + (pm['nr_pages'] * 0x1000):
>>> +				page_buffer = pages_in.read(ps)
>>> +				if vaddr not in lazy_pages:
>>> +					if start == 0:
>>> +						start = vaddr
>>> +					i +=1
>>> +					pages_out.write(page_buffer)
>>> +				vaddr += ps
>>> +			if i != 0:
>>> +				new.append({'nr_pages': i, 'vaddr': start})
>>> +		pms['entries'] = new
>>> +		pycriu.images.dump(pms, open(os.path.join(opts['outdir'], 'pagemap-%d.img' % pid), 'w+'))
>>> +
>>>  def main():
>>>  	desc = 'CRiu Image Tool'
>>>  	parser = argparse.ArgumentParser(description=desc,
>>> @@ -267,6 +336,15 @@ def main():
>>>  	show_parser.add_argument("in")
>>>  	show_parser.set_defaults(func=decode, pretty=True, out=None)
>>>  
>>> +	# Make Lazy
>>> +	lazy_parser = subparsers.add_parser('make-lazy',
>>> +			help = "remove memory pages from image which can be restored lazily")
>>> +	lazy_parser.add_argument('dir',
>>> +			help = "criu checkpoint directory used as input")
>>> +	lazy_parser.add_argument('outdir',
>>> +			help = "output directory for new pages.img and pagemap.img")
>>> +	lazy_parser.set_defaults(func=make_lazy)
>>> +
>>>  	opts = vars(parser.parse_args())
>>>  
>>>  	opts["func"](opts)
>>>
> .
>