hashserv: Fix diverging report race condition

Fixes the hashequivalence server to resolve the diverging report race
error. This error occurs when the same task(hash) is run simultaneous on
two different builders, and then the results are reported back but the
hashes diverge (e.g. have different outhashes), and one outhash is
equivalent to a hash and another is not. If taskhash was not originally
in the database, the client will fallback to using the taskhash as the
suggested unihash and the server will see reports come in like:

    taskhash: A
    unihash: A
    outhash: B

    taskhash: C
    unihash: C
    outhash: B

    taskhash: C
    unihash: C
    outhash: D

Note that the second and third reports are the same taskhash, with
diverging outhashes.

Taskhash C should be equivalent to taskhash (and unihash) A because they
share an outhash B, but the server would not do this when tasks were
reported in the order shown.

It became clear while trying to fix this that single large table to
store all reported hashes was going to make these updates difficult
since updating the unihash of all entries would be complex and time
consuming. Instead, it makes more sense to split apart the database into
two tables: One that maps taskhashes to unihashes and one that maps
outhashes to taskhashes. This should hopefully improve the parsing query
times as well since they only care about the taskhashes to unihashes
table, at the cost of more complex INNER JOIN queries on the lesser used
API.

Note this change does delete existing hash equivlance data and starts a
new database table rather than converting existing data.

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

1 files changed, 48 insertions, 12 deletions

diff --git a/lib/hashserv/tests.py b/lib/hashserv/tests.py
index 1fcfb6b92..efaf3bdf4 100644
--- a/lib/hashserv/tests.py
+++ b/lib/hashserv/tests.py
@@ -19,10 +19,10 @@ import time
 import signal
 
 def server_prefunc(server, idx):
-    logging.basicConfig(level=logging.DEBUG, filename='bbhashserv.log', filemode='w',
+    logging.basicConfig(level=logging.DEBUG, filename='bbhashserv-%d.log' % idx, filemode='w',
                         format='%(levelname)s %(filename)s:%(lineno)d %(message)s')
     server.logger.debug("Running server %d" % idx)
-    sys.stdout = open('bbhashserv-%d.log' % idx, 'w')
+    sys.stdout = open('bbhashserv-stdout-%d.log' % idx, 'w')
     sys.stderr = sys.stdout
 
 class HashEquivalenceTestSetup(object):
@@ -140,12 +140,17 @@ class HashEquivalenceCommonTests(object):
         })
         self.assertEqual(result['unihash'], unihash, 'Server returned bad unihash')
 
-        result = self.client.get_taskhash(self.METHOD, taskhash, True)
-        self.assertEqual(result['taskhash'], taskhash)
-        self.assertEqual(result['unihash'], unihash)
-        self.assertEqual(result['method'], self.METHOD)
-        self.assertEqual(result['outhash'], outhash)
-        self.assertEqual(result['outhash_siginfo'], siginfo)
+        result_unihash = self.client.get_taskhash(self.METHOD, taskhash, True)
+        self.assertEqual(result_unihash['taskhash'], taskhash)
+        self.assertEqual(result_unihash['unihash'], unihash)
+        self.assertEqual(result_unihash['method'], self.METHOD)
+
+        result_outhash = self.client.get_outhash(self.METHOD, outhash, taskhash)
+        self.assertEqual(result_outhash['taskhash'], taskhash)
+        self.assertEqual(result_outhash['method'], self.METHOD)
+        self.assertEqual(result_outhash['unihash'], unihash)
+        self.assertEqual(result_outhash['outhash'], outhash)
+        self.assertEqual(result_outhash['outhash_siginfo'], siginfo)
 
     def test_stress(self):
         def query_server(failures):
@@ -260,6 +265,39 @@ class HashEquivalenceCommonTests(object):
         result = down_client.report_unihash(taskhash6, self.METHOD, outhash5, unihash6)
         self.assertEqual(result['unihash'], unihash5, 'Server failed to copy unihash from upstream')
 
+        # Tests read through from server with
+        taskhash7 = '9d81d76242cc7cfaf7bf74b94b9cd2e29324ed74'
+        outhash7 = '8470d56547eea6236d7c81a644ce74670ca0bbda998e13c629ef6bb3f0d60b69'
+        unihash7 = '05d2a63c81e32f0a36542ca677e8ad852365c538'
+        self.client.report_unihash(taskhash7, self.METHOD, outhash7, unihash7)
+
+        result = down_client.get_taskhash(self.METHOD, taskhash7, True)
+        self.assertEqual(result['unihash'], unihash7, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['outhash'], outhash7, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['taskhash'], taskhash7, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['method'], self.METHOD)
+
+        taskhash8 = '86978a4c8c71b9b487330b0152aade10c1ee58aa'
+        outhash8 = 'ca8c128e9d9e4a28ef24d0508aa20b5cf880604eacd8f65c0e366f7e0cc5fbcf'
+        unihash8 = 'd8bcf25369d40590ad7d08c84d538982f2023e01'
+        self.client.report_unihash(taskhash8, self.METHOD, outhash8, unihash8)
+
+        result = down_client.get_outhash(self.METHOD, outhash8, taskhash8)
+        self.assertEqual(result['unihash'], unihash8, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['outhash'], outhash8, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['taskhash'], taskhash8, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['method'], self.METHOD)
+
+        taskhash9 = 'ae6339531895ddf5b67e663e6a374ad8ec71d81c'
+        outhash9 = 'afc78172c81880ae10a1fec994b5b4ee33d196a001a1b66212a15ebe573e00b5'
+        unihash9 = '6662e699d6e3d894b24408ff9a4031ef9b038ee8'
+        self.client.report_unihash(taskhash9, self.METHOD, outhash9, unihash9)
+
+        result = down_client.get_taskhash(self.METHOD, taskhash9, False)
+        self.assertEqual(result['unihash'], unihash9, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['taskhash'], taskhash9, 'Server failed to copy unihash from upstream')
+        self.assertEqual(result['method'], self.METHOD)
+
     def test_ro_server(self):
         (ro_client, ro_server) = self.start_server(dbpath=self.server.dbpath, read_only=True)
 
@@ -287,10 +325,8 @@ class HashEquivalenceCommonTests(object):
 
 
     def test_slow_server_start(self):
-        """
-        Ensures that the server will exit correctly even if it gets a SIGTERM
-        before entering the main loop
-        """
+        # Ensures that the server will exit correctly even if it gets a SIGTERM
+        # before entering the main loop
 
         event = multiprocessing.Event()