Commit c028ea24 authored by Jim Fulton's avatar Jim Fulton

tag

parents 16dd2c12 1a896e9c
......@@ -37,6 +37,8 @@ New Features
- Multi-version concurrency control and iteration
- Explicit support dfor demo-storage stacking via push and pop methods.
- Wen calling ZODB.DB to create a database, you can now pass a file
name, rather than a storage to use a file storage.
......
This diff is collapsed.
......@@ -19,7 +19,9 @@ to be layered over a base database.
The base storage must not change.
"""
import os
import random
import weakref
import tempfile
import threading
import ZODB.blob
......@@ -36,35 +38,41 @@ class DemoStorage(object):
ZODB.interfaces.IStorageIteration,
)
def __init__(self, name=None, base=None, changes=None,
keep_base_open=False):
self._keep_base_open = keep_base_open
def __init__(self, name=None, base=None, changes=None):
if base is None:
base = ZODB.MappingStorage.MappingStorage()
self._temporary_base = True
else:
self._temporary_base = False
self.base = base
if changes is None:
changes = ZODB.MappingStorage.MappingStorage()
zope.interface.alsoProvides(self, ZODB.interfaces.IBlobStorage)
self._temporary_changes = True
self._blob_dir = None
else:
if ZODB.interfaces.IBlobStorage.providedBy(changes):
zope.interface.alsoProvides(self, ZODB.interfaces.IBlobStorage)
self._temporary_changes = False
self.changes = changes
if name is None:
name = 'DemoStorage(%r, %r)' % (base.getName(), changes.getName())
self.__name__ = name
self._copy_methods_from_changes(changes)
def _blobify(self):
if self._temporary_changes and self._blob_dir is None:
self._blob_dir = tempfile.mkdtemp('blobs')
self.changes = ZODB.blob.BlobStorage(self._blob_dir, self.changes)
if (self._temporary_changes and
isinstance(self.changes, ZODB.MappingStorage.MappingStorage)
):
blob_dir = tempfile.mkdtemp('.demoblobs')
_temporary_blobdirs[
weakref.ref(self, cleanup_temporary_blobdir)
] = blob_dir
self.changes = ZODB.blob.BlobStorage(blob_dir, self.changes)
self._copy_methods_from_changes(self.changes)
return True
......@@ -73,11 +81,10 @@ class DemoStorage(object):
self.changes.cleanup()
def close(self):
if not self._keep_base_open:
if not self._temporary_base:
self.base.close()
self.changes.close()
if getattr(self, '_blob_dir', ''):
ZODB.blob.remove_committed_dir(self._blob_dir)
if not self._temporary_changes:
self.changes.close()
def _copy_methods_from_changes(self, changes):
for meth in (
......@@ -195,6 +202,13 @@ class DemoStorage(object):
pass # The gc arg isn't supported. Don't pack
raise
def pop(self):
self.changes.close()
return self.base
def push(self, changes=None):
return self.__class__(base=self, changes=changes)
def store(self, oid, serial, data, version, transaction):
assert version=='', "versions aren't supported"
......@@ -231,3 +245,12 @@ class DemoStorage(object):
if self._blobify():
return self.changes.temporaryDirectory()
raise
_temporary_blobdirs = {}
def cleanup_temporary_blobdir(
ref,
_temporary_blobdirs=_temporary_blobdirs, # Make sure it stays around
):
blob_dir = _temporary_blobdirs.pop(ref, None)
if blob_dir and os.path.exists(blob_dir):
ZODB.blob.remove_committed_dir(blob_dir)
......@@ -120,37 +120,66 @@ Undo methods are simply copied from the changes storage:
... ]
[True, True, True, True]
>>> db.close()
Normally, when we close a demo storage, the changes and base storages
are closed:
Storage Stacking
================
>>> db.close()
>>> base._file.closed
A common use case is to stack demo storages. DemoStorage provides
some helper functions to help with this. The push method, just
creates a new demo storage who's base is the original demo storage:
>>> demo = DemoStorage()
>>> demo2 = demo.push()
>>> demo2.base is demo
True
>>> changes._file.closed
We can also supply an explicit changes storage, if we wish:
>>> from ZODB.MappingStorage import MappingStorage
>>> changes = MappingStorage()
>>> demo3 = demo2.push(changes)
>>> demo3.changes is changes, demo3.base is demo2
(True, True)
The pop method closes the changes storage and returns the base
*without* closing it:
>>> demo3.pop() is demo2
True
A common use case is to stack multiple DemoStorages, returning to a
previous state by popping a DemoStorage off the stack. In this case,
we want to leave the base storage open:
>>> changes.opened()
False
>>> base = FileStorage('base.fs', read_only=True)
>>> storage = DemoStorage(base=base, keep_base_open=True)
Special backward compatibility support
--------------------------------------
Here, we didn't specify a changes storage. A MappingStorage was
automatically created:
Normally, when a demo storage is closed, it's base and changes
storage are closed:
>>> type(storage.changes).__name__
'MappingStorage'
>>> demo = DemoStorage(base=MappingStorage(), changes=MappingStorage())
>>> demo.close()
>>> demo.base.opened(), demo.changes.opened()
(False, False)
Because we specified the keep_base_open option, the base storage is
left open when we close the DemoStorage:
Older versions of DemoStorage didn't have a separate changes storage
and didn't close or discard their changes when they were closed. When
a stack was built solely of demo storages, the close method
effectively did nothing. To maintain backward compatibility, when no
base or changes storage is supplied in the constructor, the underlying
storage created by the demo storage isn't closed by the demo storage.
This backward-compatibility is deprecated.
>>> storage.close()
>>> base._file.closed
False
>>> storage.changes.opened()
False
>>> demo = DemoStorage()
>>> demo.close()
>>> demo.changes.opened(), demo.base.opened()
(True, True)
>>> demo = DemoStorage(base=MappingStorage())
>>> demo2 = demo.push()
>>> demo2.close()
>>> demo2.changes.opened(), demo2.base.base.opened()
(True, False)
Blob Support
============
......@@ -236,6 +265,65 @@ storage wrapped around it when necessary:
.. Check that the temporary directory is gone
For now, it won't go until the storage does.
>>> transaction.abort()
>>> conn.close()
>>> blobdir = storage.temporaryDirectory()
>>> del db, conn, storage, _
>>> import gc
>>> _ = gc.collect()
>>> import os
>>> os.path.exists(storage.temporaryDirectory())
>>> os.path.exists(blobdir)
False
ZConfig support
===============
You can configure demo storages using ZConfig, using name, changes,
and base options:
>>> import ZODB.config
>>> storage = ZODB.config.storageFromString("""
... <demostorage>
... </demostorage>
... """)
>>> storage.getName()
"DemoStorage('MappingStorage', 'MappingStorage')"
>>> storage = ZODB.config.storageFromString("""
... <demostorage>
... <filestorage base>
... path base.fs
... </filestorage>
...
... <filestorage changes>
... path changes.fs
... </filestorage>
... </demostorage>
... """)
>>> storage.getName()
"DemoStorage('base.fs', 'changes.fs')"
>>> storage.close()
>>> storage = ZODB.config.storageFromString("""
... <demostorage>
... name bob
... <filestorage>
... path base.fs
... </filestorage>
...
... <filestorage changes>
... path changes.fs
... </filestorage>
... </demostorage>
... """)
>>> storage.getName()
'bob'
>>> storage.base.getName()
'base.fs'
>>> storage.close()
......@@ -175,8 +175,7 @@
<sectiontype name="demostorage" datatype=".DemoStorage"
implements="ZODB.storage">
<key name="name" />
<section type="ZODB.storage" name="*" attribute="base" />
<section type="ZODB.storage" name="changes" attribute="changes" />
<multisection type="ZODB.storage" name="*" attribute="factories" />
</sectiontype>
......
......@@ -120,15 +120,17 @@ class MappingStorage(BaseConfig):
class DemoStorage(BaseConfig):
def open(self):
base = changes = None
for factory in self.config.factories:
if factory.name == 'changes':
changes = factory.open()
else:
if base is None:
base = factory.open()
else:
raise ValueError("Too many base storages defined!")
from ZODB.DemoStorage import DemoStorage
if self.config.base:
base = self.config.base.open()
else:
base = None
if self.config.changes:
changes = self.config.changes.open()
else:
changes = None
return DemoStorage(self.config.name, base=base, changes=changes)
class FileStorage(BaseConfig):
......
......@@ -13,11 +13,7 @@ development continues on a "development" head.
A database can be opened historically ``at`` or ``before`` a given transaction
serial or datetime. Here's a simple example. It should work with any storage
that supports ``loadBefore``. Unfortunately that does not include
MappingStorage, so we use a FileStorage instance. Also unfortunately, as of
this writing there is no reliable way to determine if a storage truly
implements loadBefore, or if it simply returns None (as in BaseStorage), other
than reading code.
that supports ``loadBefore``.
We'll begin our example with a fairly standard set up. We
......@@ -28,11 +24,8 @@ We'll begin our example with a fairly standard set up. We
- modify the database again; and
- commit a transaction.
>>> import ZODB.FileStorage
>>> storage = ZODB.FileStorage.FileStorage(
... 'HistoricalConnectionTests.fs', create=True)
>>> import ZODB
>>> db = ZODB.DB(storage)
>>> import ZODB.MappingStorage
>>> db = ZODB.MappingStorage.DB()
>>> conn = db.open()
>>> import persistent.mapping
......@@ -42,14 +35,13 @@ We'll begin our example with a fairly standard set up. We
>>> import transaction
>>> transaction.commit()
We wait for some ttime to pass, and then make some other changes.
We wait for some time to pass, record he time, and then make some other changes.
>>> import time
>>> t = time.time()
>>> while time.time() <= t:
... time.sleep(.001)
>>> import datetime
>>> now = datetime.datetime.utcnow()
......@@ -164,186 +156,80 @@ historical connection should be kept.
>>> db.getHistoricalTimeout()
400
All three of these values can be specified in a ZConfig file. We're using
mapping storage for simplicity, but remember, as we said at the start of this
document, mapping storage will not work for historical connections (and in fact
may seem to work but then fail confusingly) because it does not implement
loadBefore.
All three of these values can be specified in a ZConfig file.
>>> import ZODB.config
>>> db2 = ZODB.config.databaseFromString('''
... <zodb>
... <mappingstorage/>
... historical-pool-size 5
... historical-pool-size 3
... historical-cache-size 1500
... historical-timeout 6m
... </zodb>
... ''')
>>> db2.getHistoricalPoolSize()
5
3
>>> db2.getHistoricalCacheSize()
1500
>>> db2.getHistoricalTimeout()
360
Let's actually look at these values at work by shining some light into what
has been a black box up to now. We'll actually do some white box examination
of what is going on in the database, pools and connections.
Historical connections are held in a single connection pool with mappings
from the ``before`` TID to available connections. First we'll put a new
pool on the database so we have a clean slate.
>>> historical_conn.close()
>>> from ZODB.DB import KeyedConnectionPool
>>> db.historical_pool = KeyedConnectionPool(
... db.historical_pool.size, db.historical_pool.timeout)
Now lets look what happens to the pool when we create and close an historical
connection.
The pool lets us reuse connections. To see this, we'll open some
connections, close them, and then open them again:
>>> pool = db.historical_pool
>>> len(pool.all)
0
>>> len(pool.available)
0
>>> historical_conn = db.open(
... transaction_manager=transaction1, before=serial)
>>> len(pool.all)
1
>>> len(pool.available)
0
>>> historical_conn in pool.all
True
>>> historical_conn.close()
>>> len(pool.all)
1
>>> len(pool.available)
1
>>> pool.available.keys()[0] == serial
True
>>> len(pool.available.values()[0])
1
>>> conns1 = [db2.open(before=serial) for i in range(4)]
>>> _ = [c.close() for c in conns1]
>>> conns2 = [db2.open(before=serial) for i in range(4)]
Now we'll open and close two for the same serial to see what happens to the
data structures.
Now let's look at what we got. The first connection in conns 2 is the
last connection in conns1, because it was the last connection closed.
>>> historical_conn is db.open(
... transaction_manager=transaction1, before=serial)
>>> conns2[0] is conns1[-1]
True
>>> len(pool.all)
1
>>> len(pool.available)
0
>>> transaction2 = transaction.TransactionManager()
>>> historical_conn2 = db.open(
... transaction_manager=transaction2, before=serial)
>>> len(pool.all)
2
>>> len(pool.available)
0
>>> historical_conn2.close()
>>> len(pool.all)
2
>>> len(pool.available)
1
>>> len(pool.available.values()[0])
1
>>> historical_conn.close()
>>> len(pool.all)
2
>>> len(pool.available)
1
>>> len(pool.available.values()[0])
2
If you change the historical cache size, that changes the size of the
persistent cache on our connection.
Also for the next two:
>>> historical_conn._cache.cache_size
2000
>>> db.setHistoricalCacheSize(1500)
>>> historical_conn._cache.cache_size
1500
>>> (conns2[1] is conns1[-2]), (conns2[2] is conns1[-3])
(True, True)
Now let's look at pool sizes. We'll set it to two, then open and close three
connections. We should end up with only two available connections.
But not for the last:
>>> db.setHistoricalPoolSize(2)
>>> conns2[3] is conns1[-4]
False
>>> historical_conn = db.open(
... transaction_manager=transaction1, before=serial)
>>> historical_conn2 = db.open(
... transaction_manager=transaction2, before=serial)
>>> transaction3 = transaction.TransactionManager()
>>> historical_conn3 = db.open(
... transaction_manager=transaction3, at=historical_serial)
>>> len(pool.all)
3
>>> len(pool.available)
0
Because the pool size was set to 3.
>>> historical_conn3.close()
>>> len(pool.all)
3
>>> len(pool.available)
1
>>> len(pool.available.values()[0])
1
Connections are also discarded if they haven't been used in a while.
To see this, let's close two of the connections:
>>> historical_conn2.close()
>>> len(pool.all)
3
>>> len(pool.available)
2
>>> len(pool.available.values()[0])
1
>>> len(pool.available.values()[1])
1
>>> conns2[0].close(); conns2[1].close()
>>> historical_conn.close()
>>> len(pool.all)
2
>>> len(pool.available)
1
>>> len(pool.available.values()[0])
2
We'l also set the historical timeout to be very low:
Notice it dumped the one that was closed at the earliest time.
>>> db2.setHistoricalTimeout(.01)
>>> time.sleep(.1)
>>> conns2[2].close(); conns2[3].close()
Finally, we'll look at the timeout. We'll need to monkeypatch ``time`` for
this. (The funky __import__ of DB is because some ZODB __init__ shenanigans
make the DB class mask the DB module.)
Now, when we open 4 connections:
>>> db.getHistoricalTimeout()
400
>>> import time
>>> delta = 200
>>> def stub_time():
... return time.time() + delta
...
>>> DB_module = __import__('ZODB.DB', globals(), locals(), ['chicken'])
>>> original_time = DB_module.time
>>> DB_module.time = stub_time
>>> conns1 = [db2.open(before=serial) for i in range(4)]
>>> historical_conn = db.open(before=serial)
We'll see that only the last 2 connections from conn2 are in the
result:
>>> len(pool.all)
2
>>> len(pool.available)
1
>>> [c in conns1 for c in conns2]
[False, False, True, True]
A close or an open will do garbage collection on the timed out connections.
>>> delta += 200
>>> historical_conn.close()
If you change the historical cache size, that changes the size of the
persistent cache on our connection.
>>> len(pool.all)
1
>>> len(pool.available)
1
>>> len(pool.available.values()[0])
1
>>> historical_conn._cache.cache_size
2000
>>> db.setHistoricalCacheSize(1500)
>>> historical_conn._cache.cache_size
1500
Invalidations
=============
......
......@@ -239,12 +239,12 @@ Closing connections adds them to the stack:
Closing another one will purge the one with MARKER 0 from the stack
(since it was the first added to the stack):
>>> [c.MARKER for c in pool.available.values()]
>>> [c.MARKER for (t, c) in pool.available]
[0, 1, 2]
>>> conns[0].close() # MARKER 3
>>> len(pool.available), len(pool.all)
(3, 5)
>>> [c.MARKER for c in pool.available.values()]
>>> [c.MARKER for (t, c) in pool.available]
[1, 2, 3]
Similarly for the other two:
......@@ -252,7 +252,7 @@ Similarly for the other two:
>>> conns[1].close(); conns[2].close()
>>> len(pool.available), len(pool.all)
(3, 3)
>>> [c.MARKER for c in pool.available.values()]
>>> [c.MARKER for (t, c) in pool.available]
[3, 4, 5]
Reducing the pool size may also purge the oldest closed connections:
......@@ -260,7 +260,7 @@ Reducing the pool size may also purge the oldest closed connections:
>>> db.setPoolSize(2) # gets rid of MARKER 3
>>> len(pool.available), len(pool.all)
(2, 2)
>>> [c.MARKER for c in pool.available.values()]
>>> [c.MARKER for (t, c) in pool.available]
[4, 5]
Since MARKER 5 is still the last one added to the stack, it will be the
......
......@@ -25,10 +25,7 @@ def setUp(test):
def tearDown(test):
test.globs['db'].close()
test.globs['db2'].close()
test.globs['storage'].close()
# the DB class masks the module because of __init__ shenanigans
DB_module = __import__('ZODB.DB', globals(), locals(), ['chicken'])
DB_module.time = test.globs['original_time']
module.tearDown(test)
ZODB.tests.util.tearDown(test)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment