aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorRichard Purdie <richard.purdie@linuxfoundation.org>2023-01-21 19:31:43 +0000
committerRichard Purdie <richard.purdie@linuxfoundation.org>2023-01-24 21:59:17 +0000
commitf24bbaaddb36f479a59a958e7fc90ef454c19473 (patch)
tree9f2180a775851e2a1948560282546ae9432fcd90
parentf45a94e6720dacf7f51ac147c115a6f608769093 (diff)
downloadbitbake-contrib-f24bbaaddb36f479a59a958e7fc90ef454c19473.tar.gz
data: Add support for new BB_HASH_CODEPARSER_VALS for cache optimisation
Currently the codeparser cache ends up being extended for every parse run since there are values in the functions such as the result of os.getpid() from LOGFIFO in OE-Core. Digging into that issue, there are also lots of similar but different functions being parsed where the change might just be a path to WORKDIR, a change in PN or PV or something like DATE/TIME. There is no reason we have to use these changing values when computing the dependenies of the functions. Even with a small tweak like: BB_HASH_CODEPARSER_VALS = "LOGFIFO=/ T=/ WORKDIR=/ DATE=1234 TIME=1234 PV=0.0-1 PN=nopn" the cache is reduced from ~4.6MB, increasing by ~300kb for every parse run to around 1.3MB and remaining static for oe-core and meta-oe. In my local build, admittedly heavily experimented with, the cache had grown to 120MB. The benefits of doing this are: * faster load time for bitbake since the cache is smaller to read from disk and load into memory * being able to skip saving the cache upon shutdown * lower memory footprint for bitbake * faster codeparser data lookups (since there is less data to search) We only use these special values when passing code fragments to the codeparser to parse so the real variable values should otherwise be used in the hash data. The overall effect of this change, combined with others to avoid saving unchanged cache files can be ~2s on a ~16s parse on my local system and results in a more responsive feeling bitbake. It also allows parsing performance to be investigated more consistently. Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
-rw-r--r--lib/bb/data.py15
-rw-r--r--lib/bb/tests/codeparser.py14
2 files changed, 17 insertions, 12 deletions
diff --git a/lib/bb/data.py b/lib/bb/data.py
index 841369699..f3ae06202 100644
--- a/lib/bb/data.py
+++ b/lib/bb/data.py
@@ -261,7 +261,7 @@ def emit_func_python(func, o=sys.__stdout__, d = init()):
newdeps |= set((d.getVarFlag(dep, "vardeps") or "").split())
newdeps -= seen
-def build_dependencies(key, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d):
+def build_dependencies(key, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d, codeparsedata):
def handle_contains(value, contains, exclusions, d):
newvalue = []
if value:
@@ -312,14 +312,14 @@ def build_dependencies(key, keys, mod_funcs, shelldeps, varflagsexcl, ignored_va
value = varflags.get("vardepvalue")
elif varflags.get("func"):
if varflags.get("python"):
- value = d.getVarFlag(key, "_content", False)
+ value = codeparsedata.getVarFlag(key, "_content", False)
parser = bb.codeparser.PythonParser(key, logger)
parser.parse_python(value, filename=varflags.get("filename"), lineno=varflags.get("lineno"))
deps = deps | parser.references
deps = deps | (keys & parser.execs)
value = handle_contains(value, parser.contains, exclusions, d)
else:
- value, parsedvar = d.getVarFlag(key, "_content", False, retparser=True)
+ value, parsedvar = codeparsedata.getVarFlag(key, "_content", False, retparser=True)
parser = bb.codeparser.ShellParser(key, logger)
parser.parse_shell(parsedvar.value)
deps = deps | shelldeps
@@ -378,12 +378,17 @@ def generate_dependencies(d, ignored_vars):
shelldeps = set(key for key in d.getVar("__exportlist", False) if d.getVarFlag(key, "export", False) and not d.getVarFlag(key, "unexport", False))
varflagsexcl = d.getVar('BB_SIGNATURE_EXCLUDE_FLAGS')
+ codeparserd = d.createCopy()
+ for forced in (d.getVar('BB_HASH_CODEPARSER_VALS') or "").split():
+ key, value = forced.split("=", 1)
+ codeparserd.setVar(key, value)
+
deps = {}
values = {}
tasklist = d.getVar('__BBTASKS', False) or []
for task in tasklist:
- deps[task], values[task] = build_dependencies(task, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d)
+ deps[task], values[task] = build_dependencies(task, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d, codeparserd)
newdeps = deps[task]
seen = set()
while newdeps:
@@ -392,7 +397,7 @@ def generate_dependencies(d, ignored_vars):
newdeps = set()
for dep in nextdeps:
if dep not in deps:
- deps[dep], values[dep] = build_dependencies(dep, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d)
+ deps[dep], values[dep] = build_dependencies(dep, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d, codeparserd)
newdeps |= deps[dep]
newdeps -= seen
#print "For %s: %s" % (task, str(deps[task]))
diff --git a/lib/bb/tests/codeparser.py b/lib/bb/tests/codeparser.py
index a508f23bc..7f5d59ca7 100644
--- a/lib/bb/tests/codeparser.py
+++ b/lib/bb/tests/codeparser.py
@@ -318,7 +318,7 @@ d.getVar(a(), False)
"filename": "example.bb",
})
- deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
+ deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d, self.d)
self.assertEqual(deps, set(["somevar", "bar", "something", "inexpand", "test", "test2", "a"]))
@@ -365,7 +365,7 @@ esac
self.d.setVarFlags("FOO", {"func": True})
self.setEmptyVars(execs)
- deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
+ deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d, self.d)
self.assertEqual(deps, set(["somevar", "inverted"] + execs))
@@ -375,7 +375,7 @@ esac
self.d.setVar("FOO", "foo=oe_libinstall; eval $foo")
self.d.setVarFlag("FOO", "vardeps", "oe_libinstall")
- deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
+ deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d, self.d)
self.assertEqual(deps, set(["oe_libinstall"]))
@@ -384,7 +384,7 @@ esac
self.d.setVar("FOO", "foo=oe_libinstall; eval $foo")
self.d.setVarFlag("FOO", "vardeps", "${@'oe_libinstall'}")
- deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
+ deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d, self.d)
self.assertEqual(deps, set(["oe_libinstall"]))
@@ -399,7 +399,7 @@ esac
# Check dependencies
self.d.setVar('ANOTHERVAR', expr)
self.d.setVar('TESTVAR', 'anothervalue testval testval2')
- deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(), self.d)
+ deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(), self.d, self.d)
self.assertEqual(sorted(values.splitlines()),
sorted([expr,
'TESTVAR{anothervalue} = Set',
@@ -418,14 +418,14 @@ esac
self.d.setVar('ANOTHERVAR', varval)
self.d.setVar('TESTVAR', 'anothervalue testval testval2')
self.d.setVar('TESTVAR2', 'testval3')
- deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(["TESTVAR"]), self.d)
+ deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(["TESTVAR"]), self.d, self.d)
self.assertEqual(sorted(values.splitlines()), sorted([varval]))
self.assertEqual(deps, set(["TESTVAR2"]))
self.assertEqual(self.d.getVar('ANOTHERVAR').split(), ['testval3', 'anothervalue'])
# Check the vardepsexclude flag is handled by contains functionality
self.d.setVarFlag('ANOTHERVAR', 'vardepsexclude', 'TESTVAR')
- deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(), self.d)
+ deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(), self.d, self.d)
self.assertEqual(sorted(values.splitlines()), sorted([varval]))
self.assertEqual(deps, set(["TESTVAR2"]))
self.assertEqual(self.d.getVar('ANOTHERVAR').split(), ['testval3', 'anothervalue'])