bitbake: hashserv: Add `gc-mark-stream` command for batch hash marking

Implements the `gc-mark-stream` command to allow for marking equivalence entries
in batch, by  making use of stream mode communication to the server.

The aim of this is to improve efficiency by reducing the impact of latency when
marking a high volume of hash entries.

Example usage of the new `gc-mark-stream` command:

```
$ cat << HASHES | \
./bin/bitbake-hashclient --address "ws://localhost:8688/ws" gc-mark-stream "alive"
unihash f37918cc02eb5a520b1aff86faacbc0a38124646
unihash af36b199320e611fbb16f1f277d3ee1d619ca58b
taskhash a1117c1f5a7c9ab2f5a39cc6fe5e6152169d09c0 method oe.sstatesig.OEOuthashBasic
HASHES
```

(Bitbake rev: c84715f28cd36666ea07a179d91b8c32ea0df8e7)

Signed-off-by: Alexander Marques <c137.marques@gmail.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

1 files changed, 42 insertions, 0 deletions

diff --git a/bitbake/lib/hashserv/tests.py b/bitbake/lib/hashserv/tests.py
index 13ccb20ebf..da3f8e0884 100644
--- a/bitbake/lib/hashserv/tests.py
+++ b/bitbake/lib/hashserv/tests.py
@@ -969,6 +969,48 @@ class HashEquivalenceCommonTests(object):
         # First hash is still present
         self.assertClientGetHash(self.client, taskhash, unihash)
 
+    def test_gc_stream(self):
+        taskhash = '53b8dce672cb6d0c73170be43f540460bfc347b4'
+        outhash = '5a9cb1649625f0bf41fc7791b635cd9c2d7118c7f021ba87dcd03f72b67ce7a8'
+        unihash = 'f37918cc02eb5a520b1aff86faacbc0a38124646'
+
+        result = self.client.report_unihash(taskhash, self.METHOD, outhash, unihash)
+        self.assertEqual(result['unihash'], unihash, 'Server returned bad unihash')
+
+        taskhash2 = '3bf6f1e89d26205aec90da04854fbdbf73afe6b4'
+        outhash2 = '77623a549b5b1a31e3732dfa8fe61d7ce5d44b3370f253c5360e136b852967b4'
+        unihash2 = 'af36b199320e611fbb16f1f277d3ee1d619ca58b'
+
+        result = self.client.report_unihash(taskhash2, self.METHOD, outhash2, unihash2)
+        self.assertClientGetHash(self.client, taskhash2, unihash2)
+
+        taskhash3 = 'a1117c1f5a7c9ab2f5a39cc6fe5e6152169d09c0'
+        outhash3 = '7289c414905303700a1117c1f5a7c9ab2f5a39cc6fe5e6152169d09c04f9a53c'
+        unihash3 = '905303700a1117c1f5a7c9ab2f5a39cc6fe5e615'
+
+        result = self.client.report_unihash(taskhash3, self.METHOD, outhash3, unihash3)
+        self.assertClientGetHash(self.client, taskhash3, unihash3)
+
+        # Mark the first unihash to be kept
+        ret = self.client.gc_mark_stream("ABC", (f"unihash {h}" for h in [unihash, unihash2]))
+        self.assertEqual(ret, {"count": 2})
+
+        ret = self.client.gc_status()
+        self.assertEqual(ret, {"mark": "ABC", "keep": 2, "remove": 1})
+
+        # Third hash is still there; mark doesn't delete hashes
+        self.assertClientGetHash(self.client, taskhash3, unihash3)
+
+        ret = self.client.gc_sweep("ABC")
+        self.assertEqual(ret, {"count": 1})
+
+        # Hash is gone. Taskhash is returned for second hash
+        self.assertClientGetHash(self.client, taskhash3, None)
+        # First hash is still present
+        self.assertClientGetHash(self.client, taskhash, unihash)
+        # Second hash is still present
+        self.assertClientGetHash(self.client, taskhash2, unihash2)
+
     def test_gc_switch_mark(self):
         taskhash = '53b8dce672cb6d0c73170be43f540460bfc347b4'
         outhash = '5a9cb1649625f0bf41fc7791b635cd9c2d7118c7f021ba87dcd03f72b67ce7a8'