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, 29 insertions, 0 deletions

diff --git a/bitbake/lib/hashserv/server.py b/bitbake/lib/hashserv/server.py
index 68f64f983b..58f95c7bcd 100644
--- a/bitbake/lib/hashserv/server.py
+++ b/bitbake/lib/hashserv/server.py
@@ -10,6 +10,7 @@ import math
 import time
 import os
 import base64
+import json
 import hashlib
 from . import create_async_client
 import bb.asyncrpc
@@ -256,6 +257,7 @@ class ServerClient(bb.asyncrpc.AsyncServerConnection):
                     "backfill-wait": self.handle_backfill_wait,
                     "remove": self.handle_remove,
                     "gc-mark": self.handle_gc_mark,
+                    "gc-mark-stream": self.handle_gc_mark_stream,
                     "gc-sweep": self.handle_gc_sweep,
                     "gc-status": self.handle_gc_status,
                     "clean-unused": self.handle_clean_unused,
@@ -584,6 +586,33 @@ class ServerClient(bb.asyncrpc.AsyncServerConnection):
         return {"count": await self.db.gc_mark(mark, condition)}
 
     @permissions(DB_ADMIN_PERM)
+    async def handle_gc_mark_stream(self, request):
+        async def handler(line):
+            try:
+                decoded_line = json.loads(line)
+            except json.JSONDecodeError as exc:
+                raise bb.asyncrpc.InvokeError(
+                    "Could not decode JSONL input '%s'" % line
+                ) from exc
+
+            try:
+                mark = decoded_line["mark"]
+                condition = decoded_line["where"]
+                if not isinstance(mark, str):
+                    raise TypeError("Bad mark type %s" % type(mark))
+
+                if not isinstance(condition, dict):
+                    raise TypeError("Bad condition type %s" % type(condition))
+            except KeyError as exc:
+                raise bb.asyncrpc.InvokeError(
+                    "Input line is missing key '%s' " % exc
+                ) from exc
+
+            return json.dumps({"count": await self.db.gc_mark(mark, condition)})
+
+        return await self._stream_handler(handler)
+
+    @permissions(DB_ADMIN_PERM)
     async def handle_gc_sweep(self, request):
         mark = request["mark"]