mesh-controller/internal/broker/declaration_files.go

package broker

import (
	"context"
	"fmt"
	"time"

	"git.novox.be/novox/mesh-sdk/go/declaration"
	"github.com/nats-io/nats.go/jetstream"
)

// The object buckets a declaration's large files travel in (novox/hq ADR 0486, issues 1696 and 1697): **one bucket for each
// node**, `declaration-files-<node>`.
//
// **The controller alone writes them, and a node-engine reads an object by its name from its own bucket** (ADR 0486 §2): its
// account may neither list the bucket nor write it, no account may touch another node's, and no other account has any access.
// Why a bucket each: a subject pattern cannot tell a name from a wildcard. A grant of `...M.*` matches a publish to the literal
// subject `...M.*` too (probed on nats-server 2.11.17 by the review of this issue: a node created a consumer filtered on
// `$O.<bucket>.C.*` and read every object of the bucket), so in one shared bucket a node could read every other node's files.
// With a bucket each, the same trick reads only the node's own files, which are the files of its own declaration.
//
// A bucket of the bus's object store is a stream, OBJ_<bucket>, whose messages are the objects' metadata
// (`$O.<bucket>.M.<base64 of the name>`) and chunks (`$O.<bucket>.C.<nuid>`).

// DeclarationFilesBucket is the prefix of the buckets' names, which mesh-sdk fixes for the node-engine and the controller alike.
const DeclarationFilesBucket = declaration.FileBucket

// DeclarationFilesBucketOf is the bucket a node's files are in. One function, so the name of a node's bucket is composed in one
// place.
func DeclarationFilesBucketOf(node string) string { return DeclarationFilesBucket + "-" + node }

// DeclarationFilesStreamOf is the stream under a node's bucket.
func DeclarationFilesStreamOf(node string) string { return "OBJ_" + DeclarationFilesBucketOf(node) }

// DeclarationFilesMaxBytes is a bucket's size: the objects are immutable and regenerable, and one node's hold well under a hundred
// megabytes.
const DeclarationFilesMaxBytes = 1 << 30

// DeclarationFilesKeptFor is how long an object stays after no node's latest declaration names it (ADR 0486 §3).
const DeclarationFilesKeptFor = 24 * time.Hour

// DeclarationFilesWrites is the one pattern the controller may publish to write a node's bucket: every object's metadata and
// chunks. The server's API for the stream is the controller's `$JS.API.>`.
func DeclarationFilesWrites(node string) string { return "$O." + DeclarationFilesBucketOf(node) + ".>" }

// DeclarationFilesReads is what a node-engine's account may publish to read an object of its own bucket by its name, and nothing
// more. The set is the one node-engine's own call (mesh-host internal/link FileObject) makes, for B the node's bucket and S its
// stream (issue 1697, notes 4 and 5):
//
//   - the object's metadata, by a direct get of the last message of the one subject that names it. **Only the suffixed
//     form**: the bare `$JS.API.DIRECT.GET.S` takes a sequence number and would read any message of the stream.
//   - the ordered consumer on that object's chunks: `$JS.API.CONSUMER.CREATE.S.<name>.$O.B.C.<nuid>`. **Not `S.>`**:
//     a consumer filtered on `$O.B.M.>` would read every object's name.
//   - the flow-control replies of that consumer, without which a large object stalls at the flow-control window.
//   - the consumer's deletion, best effort: the consumer's inactivity threshold removes it if this is refused.
//
// **Never granted:** STREAM.INFO (a `subjects_filter` of `>` lists every name), STREAM.MSG.GET (any message by its sequence), a
// publish to `$O.B.>` (a write), and any subject of another node's stream. A literal `*` in a subject matches the grant's `*`: it
// reaches the objects of this node's own bucket and no other (above).
func DeclarationFilesReads(node string) []string {
	stream, bucket := DeclarationFilesStreamOf(node), DeclarationFilesBucketOf(node)
	return []string{
		"$JS.API.DIRECT.GET." + stream + ".$O." + bucket + ".M.*",
		"$JS.API.CONSUMER.CREATE." + stream + ".*.$O." + bucket + ".C.*",
		"$JS.API.CONSUMER.DELETE." + stream + ".*",
		"$JS.FC." + stream + ".>",
	}
}

// EnsureDeclarationFiles creates the buckets of these nodes if absent and brings their options to match. A bucket exists whenever the
// bus does, so a node that is starting finds it (ADR 0486 §4). An update, never a delete.
func (j *JetStream) EnsureDeclarationFiles(nodes []string) error {
	js, err := jetstream.New(j.conn)
	if err != nil {
		return err
	}
	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
	defer cancel()
	return EnsureDeclarationFiles(ctx, js, nodes...)
}

// EnsureDeclarationFiles is the same on a JetStream the caller holds.
func EnsureDeclarationFiles(ctx context.Context, js jetstream.JetStream, nodes ...string) error {
	for _, node := range nodes {
		if _, err := js.CreateOrUpdateObjectStore(ctx, DeclarationFilesConfig(node)); err != nil {
			return fmt.Errorf("asserting the object bucket %s: %w", DeclarationFilesBucketOf(node), err)
		}
	}
	return nil
}

// DeclarationFilesConfig is a node's bucket as the controller asserts it.
func DeclarationFilesConfig(node string) jetstream.ObjectStoreConfig {
	return jetstream.ObjectStoreConfig{
		Bucket: DeclarationFilesBucketOf(node),
		Description: "the contents of the files over 64 KiB of the declaration of " + node + ", each under the hex of its sha256 " +
			"digest (novox/hq ADR 0486): written by the controller alone, read by the node-engine of that node by name, removed " +
			"a day after the node's latest declaration no longer names it",
		MaxBytes: DeclarationFilesMaxBytes,
		Storage:  jetstream.FileStorage,
	}
}