bitbake: Rework hash equivalence

Reworks the hash equivalence server to address performance issues that
were encountered with the REST mechanism used previously, particularly
during the heavy request load encountered during signature generation.
Notable changes are:

1) The server protocol is no longer HTTP based. Instead, it uses a
   simpler JSON over a streaming protocol link. This protocol has much
   lower overhead than HTTP since it eliminates the HTTP headers.
2) The hash equivalence server can either bind to a TCP port, or a Unix
   domain socket. Unix domain sockets are more efficient for local
   communication, and so are preferred if the user enables hash
   equivalence only for the local build. The arguments to the
   'bitbake-hashserve' command have been updated accordingly.
3) The value to which BB_HASHSERVE should be set to enable a local hash
   equivalence server is changed to "auto" instead of "localhost:0". The
   latter didn't make sense when the local server was using a Unix
   domain socket.
4) Clients are expected to keep a persistent connection to the server
   instead of creating a new connection each time a request is made for
   optimal performance.
5) Most of the client logic has been moved to the hashserve module in
   bitbake. This makes it easier to share the client code.
6) A new bitbake command has been added called 'bitbake-hashclient'.
   This command can be used to query a hash equivalence server, including
   fetching the statistics and running a performance stress test.
7) The table indexes in the SQLite database have been updated to
   optimize hash lookups. This change is backward compatible, as the
   database will delete the old indexes first if they exist.
8) The server has been reworked to use python async to maximize
   performance with persistently connected clients. This requires Python
   3.5 or later.

Signed-off-by: Joshua Watt <JPEWhacker@gmail.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

1 files changed, 26 insertions, 48 deletions

diff --git a/lib/bb/siggen.py b/lib/bb/siggen.py
index 8b593a348..e047c217e 100644
--- a/lib/bb/siggen.py
+++ b/lib/bb/siggen.py
@@ -13,6 +13,7 @@ import difflib
 import simplediff
 from bb.checksum import FileChecksumCache
 from bb import runqueue
+import hashserv
 
 logger = logging.getLogger('BitBake.SigGen')
 
@@ -375,6 +376,11 @@ class SignatureGeneratorUniHashMixIn(object):
         self.server, self.method = data[:2]
         super().set_taskdata(data[2:])
 
+    def client(self):
+        if getattr(self, '_client', None) is None:
+            self._client = hashserv.create_client(self.server)
+        return self._client
+
     def __get_task_unihash_key(self, tid):
         # TODO: The key only *needs* to be the taskhash, the tid is just
         # convenient
@@ -395,9 +401,6 @@ class SignatureGeneratorUniHashMixIn(object):
         self.unitaskhashes[self.__get_task_unihash_key(tid)] = unihash
 
     def get_unihash(self, tid):
-        import urllib
-        import json
-
         taskhash = self.taskhash[tid]
 
         # If its not a setscene task we can return
@@ -428,36 +431,22 @@ class SignatureGeneratorUniHashMixIn(object):
         unihash = taskhash
 
         try:
-            url = '%s/v1/equivalent?%s' % (self.server,
-                    urllib.parse.urlencode({'method': self.method, 'taskhash': self.taskhash[tid]}))
-
-            request = urllib.request.Request(url)
-            response = urllib.request.urlopen(request)
-            data = response.read().decode('utf-8')
-
-            json_data = json.loads(data)
-
-            if json_data:
-                unihash = json_data['unihash']
+            data = self.client().get_unihash(self.method, self.taskhash[tid])
+            if data:
+                unihash = data
                 # A unique hash equal to the taskhash is not very interesting,
                 # so it is reported it at debug level 2. If they differ, that
                 # is much more interesting, so it is reported at debug level 1
                 bb.debug((1, 2)[unihash == taskhash], 'Found unihash %s in place of %s for %s from %s' % (unihash, taskhash, tid, self.server))
             else:
                 bb.debug(2, 'No reported unihash for %s:%s from %s' % (tid, taskhash, self.server))
-        except urllib.error.URLError as e:
-            bb.warn('Failure contacting Hash Equivalence Server %s: %s' % (self.server, str(e)))
-        except (KeyError, json.JSONDecodeError) as e:
-            bb.warn('Poorly formatted response from %s: %s' % (self.server, str(e)))
+        except hashserv.HashConnectionError as e:
+            bb.warn('Error contacting Hash Equivalence Server %s: %s' % (self.server, str(e)))
 
         self.unitaskhashes[key] = unihash
         return unihash
 
     def report_unihash(self, path, task, d):
-        import urllib
-        import json
-        import tempfile
-        import base64
         import importlib
 
         taskhash = d.getVar('BB_TASKHASH')
@@ -492,42 +481,31 @@ class SignatureGeneratorUniHashMixIn(object):
                 outhash = bb.utils.better_eval(self.method + '(path, sigfile, task, d)', locs)
 
             try:
-                url = '%s/v1/equivalent' % self.server
-                task_data = {
-                    'taskhash': taskhash,
-                    'method': self.method,
-                    'outhash': outhash,
-                    'unihash': unihash,
-                    'owner': d.getVar('SSTATE_HASHEQUIV_OWNER')
-                    }
+                extra_data = {}
+
+                owner = d.getVar('SSTATE_HASHEQUIV_OWNER')
+                if owner:
+                    extra_data['owner'] = owner
 
                 if report_taskdata:
                     sigfile.seek(0)
 
-                    task_data['PN'] = d.getVar('PN')
-                    task_data['PV'] = d.getVar('PV')
-                    task_data['PR'] = d.getVar('PR')
-                    task_data['task'] = task
-                    task_data['outhash_siginfo'] = sigfile.read().decode('utf-8')
-
-                headers = {'content-type': 'application/json'}
-
-                request = urllib.request.Request(url, json.dumps(task_data).encode('utf-8'), headers)
-                response = urllib.request.urlopen(request)
-                data = response.read().decode('utf-8')
+                    extra_data['PN'] = d.getVar('PN')
+                    extra_data['PV'] = d.getVar('PV')
+                    extra_data['PR'] = d.getVar('PR')
+                    extra_data['task'] = task
+                    extra_data['outhash_siginfo'] = sigfile.read().decode('utf-8')
 
-                json_data = json.loads(data)
-                new_unihash = json_data['unihash']
+                data = self.client().report_unihash(taskhash, self.method, outhash, unihash, extra_data)
+                new_unihash = data['unihash']
 
                 if new_unihash != unihash:
                     bb.debug(1, 'Task %s unihash changed %s -> %s by server %s' % (taskhash, unihash, new_unihash, self.server))
                     bb.event.fire(bb.runqueue.taskUniHashUpdate(fn + ':do_' + task, new_unihash), d)
                 else:
                     bb.debug(1, 'Reported task %s as unihash %s to %s' % (taskhash, unihash, self.server))
-            except urllib.error.URLError as e:
-                bb.warn('Failure contacting Hash Equivalence Server %s: %s' % (self.server, str(e)))
-            except (KeyError, json.JSONDecodeError) as e:
-                bb.warn('Poorly formatted response from %s: %s' % (self.server, str(e)))
+            except hashserv.HashConnectionError as e:
+                bb.warn('Error contacting Hash Equivalence Server %s: %s' % (self.server, str(e)))
         finally:
             if sigfile:
                 sigfile.close()
@@ -548,7 +526,7 @@ class SignatureGeneratorTestEquivHash(SignatureGeneratorUniHashMixIn, SignatureG
     name = "TestEquivHash"
     def init_rundepcheck(self, data):
         super().init_rundepcheck(data)
-        self.server = "http://" + data.getVar('BB_HASHSERVE')
+        self.server = data.getVar('BB_HASHSERVE')
         self.method = "sstate_output_hash"