[bitbake-devel,3/5] siggen: Split get_tashhash for performance

Submitted by Richard Purdie on Dec. 15, 2019, 9:41 a.m. | Patch ID: 168030

Details

Message ID 20191215094112.28162-3-richard.purdie@linuxfoundation.org
State New
Headers show

Commit Message

Richard Purdie Dec. 15, 2019, 9:41 a.m.
There are two operations happening in get_taskhash, the building of the
underlying data and the calculation of the hash.

Split these into two funtions since the preparation part doesn't need
to rerun when unihash changes, only the calculation does.

This split allows sigificant performance improvements for hashequiv
in builds where many hashes are equivalent and many hashes are changing.

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
---
 lib/bb/runqueue.py |  1 +
 lib/bb/siggen.py   | 33 ++++++++++++++++++++++++---------
 2 files changed, 25 insertions(+), 9 deletions(-)

Patch hide | download patch | download mbox

diff --git a/lib/bb/runqueue.py b/lib/bb/runqueue.py
index b3648ddb54..515e9d4314 100644
--- a/lib/bb/runqueue.py
+++ b/lib/bb/runqueue.py
@@ -1185,6 +1185,7 @@  class RunQueueData:
         procdep = []
         for dep in self.runtaskentries[tid].depends:
             procdep.append(dep)
+        bb.parse.siggen.prep_taskhash(tid, procdep, self.dataCaches[mc_from_tid(tid)])
         self.runtaskentries[tid].hash = bb.parse.siggen.get_taskhash(tid, procdep, self.dataCaches[mc_from_tid(tid)])
         self.runtaskentries[tid].unihash = bb.parse.siggen.get_unihash(tid)
 
diff --git a/lib/bb/siggen.py b/lib/bb/siggen.py
index 2fec8599b3..e484e5e37d 100644
--- a/lib/bb/siggen.py
+++ b/lib/bb/siggen.py
@@ -52,6 +52,9 @@  class SignatureGenerator(object):
     def get_unihash(self, tid):
         return self.taskhash[tid]
 
+    def prep_taskhash(self, tid, deps, dataCache):
+        return
+
     def get_taskhash(self, tid, deps, dataCache):
         self.taskhash[tid] = hashlib.sha256(tid.encode("utf-8")).hexdigest()
         return self.taskhash[tid]
@@ -198,12 +201,11 @@  class SignatureGeneratorBasic(SignatureGenerator):
             pass
         return taint
 
-    def get_taskhash(self, tid, deps, dataCache):
+    def prep_taskhash(self, tid, deps, dataCache):
 
         (mc, _, task, fn) = bb.runqueue.split_tid_mcfn(tid)
 
-        data = dataCache.basetaskhash[tid]
-        self.basehash[tid] = data
+        self.basehash[tid] = dataCache.basetaskhash[tid]
         self.runtaskdeps[tid] = []
         self.file_checksum_values[tid] = []
         recipename = dataCache.pkg_fn[fn]
@@ -216,7 +218,6 @@  class SignatureGeneratorBasic(SignatureGenerator):
                 continue
             if dep not in self.taskhash:
                 bb.fatal("%s is not in taskhash, caller isn't calling in dependency order?" % dep)
-            data = data + self.get_unihash(dep)
             self.runtaskdeps[tid].append(dep)
 
         if task in dataCache.file_checksums[fn]:
@@ -226,27 +227,41 @@  class SignatureGeneratorBasic(SignatureGenerator):
                 checksums = bb.fetch2.get_file_checksums(dataCache.file_checksums[fn][task], recipename)
             for (f,cs) in checksums:
                 self.file_checksum_values[tid].append((f,cs))
-                if cs:
-                    data = data + cs
 
         taskdep = dataCache.task_deps[fn]
         if 'nostamp' in taskdep and task in taskdep['nostamp']:
             # Nostamp tasks need an implicit taint so that they force any dependent tasks to run
             if tid in self.taints and self.taints[tid].startswith("nostamp:"):
                 # Don't reset taint value upon every call
-                data = data + self.taints[tid][8:]
+                pass
             else:
                 import uuid
                 taint = str(uuid.uuid4())
-                data = data + taint
                 self.taints[tid] = "nostamp:" + taint
 
         taint = self.read_taint(fn, task, dataCache.stamp[fn])
         if taint:
-            data = data + taint
             self.taints[tid] = taint
             logger.warning("%s is tainted from a forced run" % tid)
 
+        return
+
+    def get_taskhash(self, tid, deps, dataCache):
+
+        data = self.basehash[tid]
+        for dep in self.runtaskdeps[tid]:
+            data = data + self.get_unihash(dep)
+
+        for (f, cs) in self.file_checksum_values[tid]:
+            if cs:
+                data = data + cs
+
+        if tid in self.taints:
+            if self.taints[tid].startswith("nostamp:"):
+                data = data + self.taints[tid][8:]
+            else:
+                data = data + self.taints[tid]
+
         h = hashlib.sha256(data.encode("utf-8")).hexdigest()
         self.taskhash[tid] = h
         #d.setVar("BB_TASKHASH_task-%s" % task, taskhash[task])