Add a cassandra-backed storage option

MODULE.bazel

@@ -49,6 +49,7 @@ use_repo(
     "com_github_buildbarn_go_sha256tree",
     "com_github_fxtlabs_primes",
     "com_github_go_jose_go_jose_v3",
+    "com_github_gocql_gocql",
     "com_github_google_uuid",
     "com_github_gorilla_mux",
     "com_github_grpc_ecosystem_go_grpc_middleware",

go.mod

@@ -16,6 +16,7 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/sts v1.33.14
 	github.com/bazelbuild/buildtools v0.0.0-20250204160707-ad48c76ab9b5
 	github.com/bazelbuild/remote-apis v0.0.0-20250211041012-7f922028fcfa
+	github.com/bazelbuild/rules_go v0.53.0
 	github.com/buildbarn/go-sha256tree v0.0.0-20250310211320-0f70f20e855b
 	github.com/fxtlabs/primes v0.0.0-20150821004651-dad82d10a449
 	github.com/go-jose/go-jose/v3 v3.0.3
@@ -54,14 +55,20 @@ require (
 	mvdan.cc/gofumpt v0.7.0
 )
 
+require (
+	github.com/gogo/protobuf v1.3.2 // indirect
+	github.com/golang/mock v1.7.0-rc.1 // indirect
+	google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.5.1 // indirect
+)
+
 require (
 	cel.dev/expr v0.19.0 // indirect
-	cloud.google.com/go v0.116.0 // indirect
+	cloud.google.com/go v0.118.0 // indirect
 	cloud.google.com/go/auth v0.14.1 // indirect
 	cloud.google.com/go/auth/oauth2adapt v0.2.7 // indirect
 	cloud.google.com/go/compute/metadata v0.6.0 // indirect
-	cloud.google.com/go/iam v1.2.2 // indirect
-	cloud.google.com/go/monitoring v1.21.2 // indirect
+	cloud.google.com/go/iam v1.3.1 // indirect
+	cloud.google.com/go/monitoring v1.22.1 // indirect
 	github.com/GoogleCloudPlatform/opentelemetry-operations-go/detectors/gcp v1.25.0 // indirect
 	github.com/GoogleCloudPlatform/opentelemetry-operations-go/exporter/metric v0.48.1 // indirect
 	github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapping v0.48.1 // indirect
@@ -88,31 +95,33 @@ require (
 	github.com/fsnotify/fsnotify v1.6.0 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
-	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
+	github.com/gocql/gocql v1.7.0
 	github.com/golang/protobuf v1.5.4 // indirect
+	github.com/golang/snappy v0.0.4 // indirect
 	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/google/s2a-go v0.1.9 // indirect
 	github.com/googleapis/enterprise-certificate-proxy v0.3.4 // indirect
 	github.com/googleapis/gax-go/v2 v2.14.1 // indirect
 	github.com/grpc-ecosystem/grpc-gateway/v2 v2.25.1 // indirect
+	github.com/hailocab/go-hostpool v0.0.0-20160125115350-e80d13ce29ed // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/prometheus/procfs v0.15.1 // indirect
-	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/contrib/detectors/gcp v1.32.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.58.0 // indirect
 	go.opentelemetry.io/otel/metric v1.34.0 // indirect
 	go.opentelemetry.io/otel/sdk/metric v1.32.0 // indirect
 	golang.org/x/crypto v0.33.0 // indirect
-	golang.org/x/mod v0.17.0 // indirect
+	golang.org/x/mod v0.23.0 // indirect
 	golang.org/x/net v0.35.0 // indirect
 	golang.org/x/text v0.22.0 // indirect
 	golang.org/x/time v0.10.0 // indirect
-	golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d // indirect
-	google.golang.org/genproto v0.0.0-20241118233622-e639e219e697 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20250102185135-69823020774d // indirect
+	golang.org/x/tools v0.30.0 // indirect
+	google.golang.org/genproto v0.0.0-20250115164207-1a7da9e5054f // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20250106144421-5f5ef82da422 // indirect
+	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	sigs.k8s.io/yaml v1.1.0 // indirect

pkg/blobstore/cassandra/BUILD.bazel

@@ -0,0 +1,38 @@
+load("@rules_go//go:def.bzl", "go_library", "go_test")
+
+go_library(
+    name = "cassandra",
+    srcs = [
+        "cassandra_blob_access.go",
+        "format.go",
+    ],
+    importpath = "github.com/buildbarn/bb-storage/pkg/blobstore/cassandra",
+    visibility = ["//visibility:public"],
+    deps = [
+        "//pkg/blobstore",
+        "//pkg/blobstore/buffer",
+        "//pkg/blobstore/slicing",
+        "//pkg/capabilities",
+        "//pkg/digest",
+        "//pkg/util",
+        "@bazel_remote_apis//build/bazel/remote/execution/v2:remote_execution_go_proto",
+        "@com_github_gocql_gocql//:gocql",
+        "@com_github_prometheus_client_golang//prometheus",
+        "@org_golang_google_grpc//codes",
+        "@org_golang_google_grpc//status",
+        "@org_golang_x_sync//errgroup",
+    ],
+)
+
+go_test(
+    name = "cassandra_test",
+    srcs = [
+        "cassandra_blob_access_test.go",
+        "format_test.go",
+    ],
+    embed = [":cassandra"],
+    deps = [
+        "@com_github_gocql_gocql//:gocql",
+        "@com_github_stretchr_testify//require",
+    ],
+)

pkg/blobstore/cassandra/README.md

@@ -0,0 +1,104 @@
+# Cassandra
+
+## Required setup
+
+`bb-storage` should not be configured to use the admin user by default in
+production. Instead, you should be using a regular user which cannot create
+tables or keyspaces.
+
+The tables that are required can be set up using command similar to the
+below in a `cqlsh` session:
+
+```sql
+CREATE KEYSPACE IF NOT EXISTS buildbarn_storage WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor': 3 };
+
+USE buildbarn_storage;
+
+CREATE TABLE IF NOT EXISTS prod_metadata (
+    digest_function TEXT,
+    digest_hash BLOB,
+    digest_size_bytes BIGINT,
+    digest_instance_name TEXT,
+    blob_id ASCII,
+    last_access TIMESTAMP,
+    segment_count INT,
+    segment_size INT,
+    PRIMARY KEY ((digest_function, digest_hash, digest_size_bytes, digest_instance_name)))
+    WITH gc_grace_seconds = 86400;
+
+CREATE TABLE IF NOT EXISTS prod_content (
+    blob_id ASCII,
+    segment INT,
+    content BLOB,
+    PRIMARY KEY ((blob_id, segment)))
+    WITH gc_grace_seconds = 86400;
+
+CREATE TABLE IF NOT EXISTS prod_orphaned_content (
+    blob_id ASCII,
+    digest_instance_name TEXT,
+    digest_function TEXT,
+    digest_hash BLOB,
+    digest_size_bytes BIGINT,
+    segment_count INT,
+    timestamp DATE,
+PRIMARY KEY (blob_id, digest_instance_name))
+WITH WITH gc_grace_seconds = 86400;
+```
+
+Note that you will need a table prefix (`prod` in this case), which allow
+multiple different environments to run in the same keyspace.
+
+The `prod_orphaned_content` table is used to track items that may have been
+orphaned. Essentially, as blobs begin to be streamed into cassandra, a note
+is taken of the blob and the estimated number of segments it will require.
+Users are expected to have their own processes in place for using this data
+to "reap" orphan content from the table.
+
+The `prod_orphaned_content` table will contain many Cassandra tombstones
+(most rows are deleted soon after they are inserted). For that reason, you
+should reduce the `gc_grace_seconds` to 1 day. This reduces the minimum
+amount of time tombstones will be kept around. This can cause some rows to
+resurrect if a Cassandra node is down for more than a day, but it is not a
+problem at the application level: they will just need to be reaped again.
+
+In the long term, this might still create many tombstones, causing non-critical
+errors when reaping old orphan rows. Consider setting a scheduled compaction
+(e.g. every 2h) to help ensure that tombstones are regularly reviewed for
+garbage collection.
+
+The `prod_metadata` and `prod_content` tables also contain many tombstones
+so the `gc_grace_seconds` attribute is also set to 1 day (86400s).
+
+### Configuring `bb-storage`
+
+An example snippet of jsonnet config for setting up Cassandra is:
+
+```jsonnet
+{
+  cassandra: {
+    hosts: ["cassandra.mycorp.com:1234"],
+    context: "example/bazel",
+    keyspace: "buildbarn_storage",
+    tablePrefix: "prod",
+    segmentSize: 524288,
+    username: "cassandra_user",
+    password: "hunter2",
+  }
+}
+```
+
+The segment size is the size in bytes before a new segment should be created.
+It is a balancing act between being able to store as many items as possible
+in a single segment and the maximum row size allowed in Cassandra (1MB). In
+this example, 512kb was chosen, which should allow the majority of writes
+seen by Buildbarn to be written in a single row.
+
+### Using the nearest DC
+
+To minimise latency, you can set a `preferredDC` in the `cassandra`
+configuration. This works on the assumption that physical proximity will
+lead to lower latencies, so the preferred DC is the one that is closest to the
+particular cluster the Buildbarn is installed in. To find the nearest data
+centre, talk to someone familiar with your network topology, and select from
+the datacenters listed in your `NetworkTopologyStrategy` (if you're using
+one) when creating the Cassandra keyspace.