From ba28e0a86a1747112e1216d1f602ca4254bdf1f7 Mon Sep 17 00:00:00 2001
From: Taras Madan <tarasmadan@google.com>
Date: Mon, 28 Jul 2025 10:54:22 +0200
Subject: pkg/coveragedb: document how to create the BQ table and data transfer

---
 pkg/coveragedb/README.md      |  61 +++++++++++++++++++++++++
 pkg/coveragedb/bq-schema.json | 104 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 165 insertions(+)
 create mode 100644 pkg/coveragedb/README.md
 create mode 100644 pkg/coveragedb/bq-schema.json

(limited to 'pkg/coveragedb')

diff --git a/pkg/coveragedb/README.md b/pkg/coveragedb/README.md
new file mode 100644
index 000000000..834ffca1d
--- /dev/null
+++ b/pkg/coveragedb/README.md
@@ -0,0 +1,61 @@
+# Prepare coverage aggregation pipeline
+
+Assuming you have the coverage `*.jsonl` files in some bucket:
+1. Create BigQuery table.
+2. Start data transfers from the bucket to BigQuery table.
+
+Coverage merger job is consuming data from BQ table and store aggregations
+in the Spanner DB.
+
+The dots in BQ table name are not supported, thus:
+1. For the namespace "upstream" the expected BQ table name is "upstream".
+2. For the namespace "android-6.12" the expected BQ table name is "android-6-12".
+
+
+### Create new BigQuery table for coverage data
+```bash
+bq mk \
+  --table \
+  --description "android 6.12"
+  --time_partitioning_field timestamp \
+  --time_partitioning_type DAY \
+  --require_partition_filter=true \
+  --clustering_fields file_path,kernel_commit,hit_count \
+  syzkaller:syzbot_coverage.android-6-12 \
+  ./pkg/coveragedb/bq-schema.json
+```
+
+### Add new data transfer
+```bash
+bq mk \
+  --transfer_config \
+  --display_name=ci-android-6-12-bucket-to-syzbot_coverage \
+  --params='{"destination_table_name_template":"android-6-12",
+  "data_path_template": "gs://$COVERAGE_STREAM_BUCKET/ci-android-6.12/*.jsonl",
+  "allow_jagged_rows": false,
+  "allow_quoted_newlines": false,
+  "delete_source_files": true,
+  "encoding": "UTF8",
+  "field_delimiter": ",",
+  "file_format": "JSON",
+  "ignore_unknown_values": false,
+  "max_bad_records": "0",
+  "parquet_enable_list_inference": false,
+  "parquet_enum_as_string": false,
+  "preserve_ascii_control_characters": false,
+  "skip_leading_rows": "0",
+  "use_avro_logical_types": false,
+  "write_disposition": "APPEND"
+  }' \
+  --project_id=syzkaller \
+  --data_source=google_cloud_storage \
+  --target_dataset=syzbot_coverage
+```
+
+### List BigQuery data transfers
+```bash
+bq ls \
+  --transfer_config \
+  --transfer_location=us-central1 \
+  --project_id=syzkaller
+```
\ No newline at end of file
diff --git a/pkg/coveragedb/bq-schema.json b/pkg/coveragedb/bq-schema.json
new file mode 100644
index 000000000..bb757a503
--- /dev/null
+++ b/pkg/coveragedb/bq-schema.json
@@ -0,0 +1,104 @@
+[
+  {
+    "name": "timestamp",
+    "type": "TIMESTAMP",
+    "mode": "REQUIRED",
+    "description": "the time following data was captured"
+  },
+  {
+    "name": "version",
+    "type": "INTEGER",
+    "mode": "REQUIRED",
+    "description": "the record version to simplify future changes"
+  },
+  {
+    "name": "fuzzing_minutes",
+    "type": "INTEGER",
+    "mode": "REQUIRED",
+    "description": "how many fuzzing hours are represented in the record"
+  },
+  {
+    "name": "arch",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "build_id",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "manager",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "kernel_repo",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "kernel_branch",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "kernel_commit",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "file_path",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "func_name",
+    "type": "STRING",
+    "mode": "REQUIRED"
+  },
+  {
+    "name": "sl",
+    "type": "INTEGER",
+    "mode": "REQUIRED",
+    "description": "Callback position frame StartLine."
+  },
+  {
+    "name": "sc",
+    "type": "INTEGER",
+    "mode": "REQUIRED",
+    "description": "Callback position frame StarCol."
+  },
+  {
+    "name": "el",
+    "type": "INTEGER",
+    "mode": "REQUIRED",
+    "description": "Callback position frame EndLine."
+  },
+  {
+    "name": "ec",
+    "type": "INTEGER",
+    "mode": "REQUIRED",
+    "description": "Callback position frame EndCol."
+  },
+  {
+    "name": "hit_count",
+    "type": "INTEGER",
+    "mode": "REQUIRED",
+    "description": "Coverage point hit count."
+  },
+  {
+    "name": "inline",
+    "type": "BOOLEAN",
+    "mode": "REQUIRED",
+    "description": "TRUE if the coverage signal was received from inline function"
+  },
+  {
+    "name": "pc",
+    "type": "NUMERIC",
+    "mode": "REQUIRED",
+    "description": "single callback generates many coverage signals if inlined",
+    "precision": "20",
+    "scale": "0"
+  }
+]
-- 
cgit mrf-deployment