Mercurial > hg
view tests/test-ancestor.py @ 40021:c537144fdbef
wireprotov2: support response caching
One of the things I've learned from managing VCS servers over the
years is that they are hard to scale. It is well known that some
companies have very beefy (read: very expensive) servers to power
their VCS needs. It is also known that specialized servers for
various VCS exist in order to facilitate scaling servers. (Mercurial
is in this boat.)
One of the aspects that make a VCS server hard to scale is the
high CPU load incurred by constant client clone/pull operations.
To alleviate the scaling pain associated with data retrieval
operations, I want to integrate caching into the Mercurial wire
protocol server as robustly as possible such that servers can
aggressively cache responses and defer as much server load as
possible.
This commit represents the initial implementation of a general
caching layer in wire protocol version 2.
We define a new interface and behavior for a wire protocol cacher
in repository.py. (This is probably where a reviewer should look
first to understand what is going on.)
The bulk of the added code is in wireprotov2server.py, where we
define how a command can opt in to being cached and integrate
caching into command dispatching.
From a very high-level:
* A command can declare itself as cacheable by providing a callable
that can be used to derive a cache key.
* At dispatch time, if a command is cacheable, we attempt to
construct a cacher and use it for serving the request and/or
caching the request.
* The dispatch layer handles the bulk of the business logic for
caching, making cachers mostly "dumb content stores."
* The mechanism for invalidating cached entries (one of the harder
parts about caching in general) is by varying the cache key when
state changes. As such, cachers don't need to be concerned with
cache invalidation.
Initially, we've hooked up support for caching "manifestdata" and
"filedata" commands. These are the simplest to cache, as they should
be immutable over time. Caching of commands related to changeset
data is a bit harder (because cache validation is impacted by
changes to bookmarks, phases, etc). This will be implemented later.
(Strictly speaking, censoring a file should invalidate caches. I've
added an inline TODO to track this edge case.)
To prove it works, this commit implements a test-only extension
providing in-memory caching backed by an lrucachedict. A new test
showing this extension behaving properly is added. FWIW, the
cacher is ~50 lines of code, demonstrating the relative ease with
which a cache can be added to a server.
While the test cacher is not suitable for production workloads, just
for kicks I performed a clone of just the changeset and manifest data
for the mozilla-unified repository. With a fully warmed cache (of just
the manifest data since changeset data is not cached), server-side
CPU usage dropped from ~73s to ~28s. That's pretty significant and
demonstrates the potential that response caching has on server
scalability!
Differential Revision: https://phab.mercurial-scm.org/D4773
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Wed, 26 Sep 2018 17:16:56 -0700 |
parents | bdb177923291 |
children | d097dd0afc19 |
line wrap: on
line source
from __future__ import absolute_import, print_function import binascii import getopt import math import os import random import sys import time from mercurial.node import nullrev from mercurial import ( ancestor, debugcommands, hg, pycompat, ui as uimod, util, ) if pycompat.ispy3: long = int xrange = range def buildgraph(rng, nodes=100, rootprob=0.05, mergeprob=0.2, prevprob=0.7): '''nodes: total number of nodes in the graph rootprob: probability that a new node (not 0) will be a root mergeprob: probability that, excluding a root a node will be a merge prevprob: probability that p1 will be the previous node return value is a graph represented as an adjacency list. ''' graph = [None] * nodes for i in xrange(nodes): if i == 0 or rng.random() < rootprob: graph[i] = [nullrev] elif i == 1: graph[i] = [0] elif rng.random() < mergeprob: if i == 2 or rng.random() < prevprob: # p1 is prev p1 = i - 1 else: p1 = rng.randrange(i - 1) p2 = rng.choice(list(range(0, p1)) + list(range(p1 + 1, i))) graph[i] = [p1, p2] elif rng.random() < prevprob: graph[i] = [i - 1] else: graph[i] = [rng.randrange(i - 1)] return graph def buildancestorsets(graph): ancs = [None] * len(graph) for i in xrange(len(graph)): ancs[i] = {i} if graph[i] == [nullrev]: continue for p in graph[i]: ancs[i].update(ancs[p]) return ancs class naiveincrementalmissingancestors(object): def __init__(self, ancs, bases): self.ancs = ancs self.bases = set(bases) def addbases(self, newbases): self.bases.update(newbases) def removeancestorsfrom(self, revs): for base in self.bases: if base != nullrev: revs.difference_update(self.ancs[base]) revs.discard(nullrev) def missingancestors(self, revs): res = set() for rev in revs: if rev != nullrev: res.update(self.ancs[rev]) for base in self.bases: if base != nullrev: res.difference_update(self.ancs[base]) return sorted(res) def test_missingancestors(seed, rng): # empirically observed to take around 1 second graphcount = 100 testcount = 10 inccount = 10 nerrs = [0] # the default mu and sigma give us a nice distribution of mostly # single-digit counts (including 0) with some higher ones def lognormrandom(mu, sigma): return int(math.floor(rng.lognormvariate(mu, sigma))) def samplerevs(nodes, mu=1.1, sigma=0.8): count = min(lognormrandom(mu, sigma), len(nodes)) return rng.sample(nodes, count) def err(seed, graph, bases, seq, output, expected): if nerrs[0] == 0: print('seed:', hex(seed)[:-1], file=sys.stderr) if gerrs[0] == 0: print('graph:', graph, file=sys.stderr) print('* bases:', bases, file=sys.stderr) print('* seq: ', seq, file=sys.stderr) print('* output: ', output, file=sys.stderr) print('* expected:', expected, file=sys.stderr) nerrs[0] += 1 gerrs[0] += 1 for g in xrange(graphcount): graph = buildgraph(rng) ancs = buildancestorsets(graph) gerrs = [0] for _ in xrange(testcount): # start from nullrev to include it as a possibility graphnodes = range(nullrev, len(graph)) bases = samplerevs(graphnodes) # fast algorithm inc = ancestor.incrementalmissingancestors(graph.__getitem__, bases) # reference slow algorithm naiveinc = naiveincrementalmissingancestors(ancs, bases) seq = [] revs = [] for _ in xrange(inccount): if rng.random() < 0.2: newbases = samplerevs(graphnodes) seq.append(('addbases', newbases)) inc.addbases(newbases) naiveinc.addbases(newbases) if rng.random() < 0.4: # larger set so that there are more revs to remove from revs = samplerevs(graphnodes, mu=1.5) seq.append(('removeancestorsfrom', revs)) hrevs = set(revs) rrevs = set(revs) inc.removeancestorsfrom(hrevs) naiveinc.removeancestorsfrom(rrevs) if hrevs != rrevs: err(seed, graph, bases, seq, sorted(hrevs), sorted(rrevs)) else: revs = samplerevs(graphnodes) seq.append(('missingancestors', revs)) h = inc.missingancestors(revs) r = naiveinc.missingancestors(revs) if h != r: err(seed, graph, bases, seq, h, r) # graph is a dict of child->parent adjacency lists for this graph: # o 13 # | # | o 12 # | | # | | o 11 # | | |\ # | | | | o 10 # | | | | | # | o---+ | 9 # | | | | | # o | | | | 8 # / / / / # | | o | 7 # | | | | # o---+ | 6 # / / / # | | o 5 # | |/ # | o 4 # | | # o | 3 # | | # | o 2 # |/ # o 1 # | # o 0 graph = {0: [-1, -1], 1: [0, -1], 2: [1, -1], 3: [1, -1], 4: [2, -1], 5: [4, -1], 6: [4, -1], 7: [4, -1], 8: [-1, -1], 9: [6, 7], 10: [5, -1], 11: [3, 7], 12: [9, -1], 13: [8, -1]} def genlazyancestors(revs, stoprev=0, inclusive=False): print(("%% lazy ancestor set for %s, stoprev = %s, inclusive = %s" % (revs, stoprev, inclusive))) return ancestor.lazyancestors(graph.get, revs, stoprev=stoprev, inclusive=inclusive) def printlazyancestors(s, l): print('membership: %r' % [n for n in l if n in s]) print('iteration: %r' % list(s)) def test_lazyancestors(): # Empty revs s = genlazyancestors([]) printlazyancestors(s, [3, 0, -1]) # Standard example s = genlazyancestors([11, 13]) printlazyancestors(s, [11, 13, 7, 9, 8, 3, 6, 4, 1, -1, 0]) # Standard with ancestry in the initial set (1 is ancestor of 3) s = genlazyancestors([1, 3]) printlazyancestors(s, [1, -1, 0]) # Including revs s = genlazyancestors([11, 13], inclusive=True) printlazyancestors(s, [11, 13, 7, 9, 8, 3, 6, 4, 1, -1, 0]) # Test with stoprev s = genlazyancestors([11, 13], stoprev=6) printlazyancestors(s, [11, 13, 7, 9, 8, 3, 6, 4, 1, -1, 0]) s = genlazyancestors([11, 13], stoprev=6, inclusive=True) printlazyancestors(s, [11, 13, 7, 9, 8, 3, 6, 4, 1, -1, 0]) # Test with stoprev >= min(initrevs) s = genlazyancestors([11, 13], stoprev=11, inclusive=True) printlazyancestors(s, [11, 13, 7, 9, 8, 3, 6, 4, 1, -1, 0]) s = genlazyancestors([11, 13], stoprev=12, inclusive=True) printlazyancestors(s, [11, 13, 7, 9, 8, 3, 6, 4, 1, -1, 0]) # Contiguous chains: 5->4, 2->1 (where 1 is in seen set), 1->0 s = genlazyancestors([10, 1], inclusive=True) printlazyancestors(s, [2, 10, 4, 5, -1, 0, 1]) # The C gca algorithm requires a real repo. These are textual descriptions of # DAGs that have been known to be problematic, and, optionally, known pairs # of revisions and their expected ancestor list. dagtests = [ (b'+2*2*2/*3/2', {}), (b'+3*3/*2*2/*4*4/*4/2*4/2*2', {}), (b'+2*2*/2*4*/4*/3*2/4', {(6, 7): [3, 5]}), ] def test_gca(): u = uimod.ui.load() for i, (dag, tests) in enumerate(dagtests): repo = hg.repository(u, b'gca%d' % i, create=1) cl = repo.changelog if not util.safehasattr(cl.index, 'ancestors'): # C version not available return debugcommands.debugbuilddag(u, repo, dag) # Compare the results of the Python and C versions. This does not # include choosing a winner when more than one gca exists -- we make # sure both return exactly the same set of gcas. # Also compare against expected results, if available. for a in cl: for b in cl: cgcas = sorted(cl.index.ancestors(a, b)) pygcas = sorted(ancestor.ancestors(cl.parentrevs, a, b)) expected = None if (a, b) in tests: expected = tests[(a, b)] if cgcas != pygcas or (expected and cgcas != expected): print("test_gca: for dag %s, gcas for %d, %d:" % (dag, a, b)) print(" C returned: %s" % cgcas) print(" Python returned: %s" % pygcas) if expected: print(" expected: %s" % expected) def main(): seed = None opts, args = getopt.getopt(sys.argv[1:], 's:', ['seed=']) for o, a in opts: if o in ('-s', '--seed'): seed = long(a, base=0) # accepts base 10 or 16 strings if seed is None: try: seed = long(binascii.hexlify(os.urandom(16)), 16) except AttributeError: seed = long(time.time() * 1000) rng = random.Random(seed) test_missingancestors(seed, rng) test_lazyancestors() test_gca() if __name__ == '__main__': main()