##// END OF EJS Templates
compression: introduce a `storage.revlog.zlib.level` configuration...
compression: introduce a `storage.revlog.zlib.level` configuration This option control the zlib compression level used when compression revlog chunk. This is also a good excuse to pave the way for a similar configuration option for the zstd compression engine. Having a dedicated option for each compression algorithm is useful because they don't support the same range of values. Using a higher zlib compression impact CPU consumption at compression time, but does not directly affected decompression time. However dealing with small compressed chunk can directly help decompression and indirectly help other revlog logic. I ran some basic test on repositories using different level. I am using the mercurial, pypy, netbeans and mozilla-central clone from our benchmark suite. All tested repository use sparse-revlog and got all their delta recomputed. The different compression level has a small effect on the repository size (about 10% variation in the total range). My quick analysis is that revlog mostly store small delta, that are not affected by the compression level much. So the variation probably mostly comes from better compression of the snapshots revisions, and snapshot revision only represent a small portion of the repository content. I also made some basic timings measurements. The "read" timings are gathered using simple run of `hg perfrevlogrevisions`, the "write" timings using `hg perfrevlogwrite` (restricted to the last 5000 revisions for netbeans and mozilla central). The timings are gathered on a generic machine, (not one of our performance locked machine), so small variation might not be meaningful. However large trend remains relevant. Keep in mind that these numbers are not pure compression/decompression time. They also involve the full revlog logic. In particular the difference in chunk size has an impact on the delta chain structure, affecting performance when writing or reading them. On read/write performance, the compression level has a bigger impact. Counter-intuitively, the higher compression levels improve "write" performance for the large repositories in our tested setting. Maybe because the last 5000 delta chain end up having a very different shape in this specific spot? Or maybe because of a more general trend of better delta chains thanks to the smaller chunk and snapshot. This series does not intend to change the default compression level. However, these result call for a deeper analysis of this performance difference in the future. Full data ========= repo level .hg/store size 00manifest.d read write ---------------------------------------------------------------- mercurial 1 49,402,813 5,963,475 0.170159 53.250304 mercurial 6 47,197,397 5,875,730 0.182820 56.264320 mercurial 9 47,121,596 5,849,781 0.189219 56.293612 pypy 1 370,830,572 28,462,425 2.679217 460.721984 pypy 6 340,112,317 27,648,747 2.768691 467.537158 pypy 9 338,360,736 27,639,003 2.763495 476.589918 netbeans 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans 9 1,197,135,671 155,034,586 141.620281 678.297064 mozilla 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla 9 2,587,542,494 287,018,264 163.622338 739.803002

File last commit:

r40646:13d4ad8d default
r42210:1fac9b93 default
Show More
metadatastore.py
156 lines | 5.2 KiB | text/x-python | PythonLexer
from __future__ import absolute_import
from mercurial.node import hex, nullid
from . import (
basestore,
shallowutil,
)
class unionmetadatastore(basestore.baseunionstore):
def __init__(self, *args, **kwargs):
super(unionmetadatastore, self).__init__(*args, **kwargs)
self.stores = args
self.writestore = kwargs.get(r'writestore')
# If allowincomplete==True then the union store can return partial
# ancestor lists, otherwise it will throw a KeyError if a full
# history can't be found.
self.allowincomplete = kwargs.get(r'allowincomplete', False)
def getancestors(self, name, node, known=None):
"""Returns as many ancestors as we're aware of.
return value: {
node: (p1, p2, linknode, copyfrom),
...
}
"""
if known is None:
known = set()
if node in known:
return []
ancestors = {}
def traverse(curname, curnode):
# TODO: this algorithm has the potential to traverse parts of
# history twice. Ex: with A->B->C->F and A->B->D->F, both D and C
# may be queued as missing, then B and A are traversed for both.
queue = [(curname, curnode)]
missing = []
seen = set()
while queue:
name, node = queue.pop()
if (name, node) in seen:
continue
seen.add((name, node))
value = ancestors.get(node)
if not value:
missing.append((name, node))
continue
p1, p2, linknode, copyfrom = value
if p1 != nullid and p1 not in known:
queue.append((copyfrom or curname, p1))
if p2 != nullid and p2 not in known:
queue.append((curname, p2))
return missing
missing = [(name, node)]
while missing:
curname, curnode = missing.pop()
try:
ancestors.update(self._getpartialancestors(curname, curnode,
known=known))
newmissing = traverse(curname, curnode)
missing.extend(newmissing)
except KeyError:
# If we allow incomplete histories, don't throw.
if not self.allowincomplete:
raise
# If the requested name+node doesn't exist, always throw.
if (curname, curnode) == (name, node):
raise
# TODO: ancestors should probably be (name, node) -> (value)
return ancestors
@basestore.baseunionstore.retriable
def _getpartialancestors(self, name, node, known=None):
for store in self.stores:
try:
return store.getancestors(name, node, known=known)
except KeyError:
pass
raise KeyError((name, hex(node)))
@basestore.baseunionstore.retriable
def getnodeinfo(self, name, node):
for store in self.stores:
try:
return store.getnodeinfo(name, node)
except KeyError:
pass
raise KeyError((name, hex(node)))
def add(self, name, node, data):
raise RuntimeError("cannot add content only to remotefilelog "
"contentstore")
def getmissing(self, keys):
missing = keys
for store in self.stores:
if missing:
missing = store.getmissing(missing)
return missing
def markledger(self, ledger, options=None):
for store in self.stores:
store.markledger(ledger, options)
def getmetrics(self):
metrics = [s.getmetrics() for s in self.stores]
return shallowutil.sumdicts(*metrics)
class remotefilelogmetadatastore(basestore.basestore):
def getancestors(self, name, node, known=None):
"""Returns as many ancestors as we're aware of.
return value: {
node: (p1, p2, linknode, copyfrom),
...
}
"""
data = self._getdata(name, node)
ancestors = shallowutil.ancestormap(data)
return ancestors
def getnodeinfo(self, name, node):
return self.getancestors(name, node)[node]
def add(self, name, node, parents, linknode):
raise RuntimeError("cannot add metadata only to remotefilelog "
"metadatastore")
class remotemetadatastore(object):
def __init__(self, ui, fileservice, shared):
self._fileservice = fileservice
self._shared = shared
def getancestors(self, name, node, known=None):
self._fileservice.prefetch([(name, hex(node))], force=True,
fetchdata=False, fetchhistory=True)
return self._shared.getancestors(name, node, known=known)
def getnodeinfo(self, name, node):
return self.getancestors(name, node)[node]
def add(self, name, node, data):
raise RuntimeError("cannot add to a remote store")
def getmissing(self, keys):
return keys
def markledger(self, ledger, options=None):
pass