feat(auth.apikeys.sqlserver): zbauth schema v1 + concurrent-boot-safe migrator (retry on 1205/2714/1913/2627, newer-version fail-closed); live tests gated on AUTH_SQLSERVER_CONNSTR

Claude-Session: https://claude.ai/code/session_013L3XdmVii9i5sY4FChU8pB
This commit is contained in:
Joseph Doherty
2026-09-02 14:22:25 -04:00
parent 2969805e4e
commit c1e34c307e
7 changed files with 712 additions and 2 deletions
@@ -28,9 +28,38 @@ public sealed class SqlServerApiKeyOptions
{
if (string.IsNullOrWhiteSpace(ConnectionString))
throw new InvalidOperationException("SQL Server API-key store requires a ConnectionString.");
if (string.IsNullOrEmpty(Schema) || !Schema.All(c => char.IsAsciiLetterOrDigit(c) || c == '_') || Schema.Length > 64)
throw new InvalidOperationException($"SQL Server API-key store schema name '{Schema}' is not a safe identifier.");
ValidateIdentifier(Schema);
if (CommandTimeout <= TimeSpan.Zero)
throw new InvalidOperationException($"SQL Server API-key store CommandTimeout must be positive (was {CommandTimeout}).");
}
/// <summary>
/// Strict allow-list for a SQL identifier that will be interpolated into DDL or query text.
/// Rejects everything that is not <c>[A-Za-z_][A-Za-z0-9_]{0,63}</c> — no brackets, quotes, dots
/// or spaces — so no bracket-escape (<c>]]</c>) trick can break out of the quoting applied at the
/// use site. Uses the ASCII-only character tests deliberately, so homoglyph and full-width
/// look-alikes are rejected rather than accepted as "letters".
/// </summary>
/// <param name="schemaName">The candidate identifier.</param>
/// <returns>The same value, once validated.</returns>
/// <exception cref="InvalidOperationException">The value is not a plain identifier.</exception>
/// <remarks>
/// Public because <see cref="SqlServerAuthSchema.CreateSchemaDdl(string)"/> is public and must
/// defend itself rather than trust that every caller routed through <see cref="Validate"/>.
/// </remarks>
public static string ValidateIdentifier(string schemaName)
{
if (string.IsNullOrEmpty(schemaName)
|| schemaName.Length > 64
|| (!char.IsAsciiLetter(schemaName[0]) && schemaName[0] != '_')
|| !schemaName.All(c => char.IsAsciiLetterOrDigit(c) || c == '_'))
{
throw new InvalidOperationException(
$"SQL Server API-key store schema name '{schemaName}' is not a safe identifier.");
}
return schemaName;
}
}
@@ -0,0 +1,207 @@
using System.Data;
using System.Globalization;
using Microsoft.Data.SqlClient;
using ZB.MOM.WW.Auth.Abstractions.ApiKeys;
using ZB.MOM.WW.Auth.ApiKeys.Sqlite;
namespace ZB.MOM.WW.Auth.ApiKeys.SqlServer;
/// <summary>
/// Creates the shared SQL Server API-key schema and records the applied version. Idempotent: safe
/// to run on every node at every startup, including concurrently — lost provisioning races surface
/// as retryable <see cref="SqlException"/>s (see <see cref="IsRetryableMigrationErrorNumber"/>) and
/// the retry re-runs the <c>IF NOT EXISTS</c> path against the objects the winner just created.
/// Refuses to run against a database whose recorded version is newer than this build supports.
/// </summary>
/// <param name="connectionFactory">Factory for connections to the shared API-key database.</param>
public sealed class SqlServerApiKeyStoreMigrator(AuthSqlServerConnectionFactory connectionFactory)
: IApiKeyStoreMigrator
{
// Every node runs this at every startup, so a virgin database being provisioned by N nodes at
// once is the NORMAL case, not a rare race — and an unretried failure aborts that node's whole
// host at startup. Two failure shapes come out of that race, and retrying is correct for both
// precisely because the migration is idempotent:
//
// - Deadlock victim (1205): concurrent Serializable DDL against the system catalogs can pick
// a victim even though the IF NOT EXISTS guards make the logic itself safe.
// - Lost CREATE / lost INSERT (2714, 1913, 2627): Serializable range locks do NOT serialize
// the metadata existence checks against another session's in-flight CREATE — observed live
// on the sibling shared secret store (ScadaBridge central-pair first boot, 2026-08-07):
// both nodes passed the sys.schemas IF NOT EXISTS probe, the loser's CREATE SCHEMA then
// died with 2714 "There is already an object named 'zbsecrets'". The object the loser tried
// to create now exists, which is the desired end state — the retry's IF NOT EXISTS pass
// skips it and proceeds.
//
// The retry cap keeps this from masking a GENUINE conflict (e.g. an unrelated pre-existing
// object colliding with the schema name): that reproduces on every attempt, so after
// MaxMigrationRetries the real SqlException propagates and the node fails closed.
private const int MaxMigrationRetries = 5;
/// <summary>Deadlock victim.</summary>
private const int SqlDeadlockVictimErrorNumber = 1205;
/// <summary>"There is already an object named '%ls'" — lost CREATE SCHEMA / CREATE TABLE race.</summary>
private const int SqlObjectAlreadyExistsErrorNumber = 2714;
/// <summary>"An index or statistics with name '%ls' already exists" — lost CREATE INDEX race.</summary>
private const int SqlIndexAlreadyExistsErrorNumber = 1913;
/// <summary>Primary-key violation — lost version-row MERGE-insert race.</summary>
private const int SqlPrimaryKeyViolationErrorNumber = 2627;
/// <inheritdoc />
/// <exception cref="AuthStoreMigrationException">
/// The recorded schema version is newer than <see cref="SqlServerAuthSchema.CurrentVersion"/>.
/// </exception>
public async Task MigrateAsync(CancellationToken cancellationToken)
{
for (int attempt = 1; ; attempt++)
{
try
{
await MigrateOnceAsync(cancellationToken).ConfigureAwait(false);
return;
}
catch (SqlException ex)
when (IsRetryableMigrationError(ex) && attempt < MaxMigrationRetries)
{
await Task.Delay(BackoffFor(attempt), cancellationToken).ConfigureAwait(false);
}
}
}
/// <summary>
/// Back-off before retry attempt <paramref name="attempt"/> + 1: a growing base plus RANDOM
/// jitter. The jitter is the load-bearing half. The sibling secret-store migrator this is ported
/// from delays a flat <c>100 * attempt</c>, which is the SAME value for every victim of the same
/// round — so N deadlock victims wake together and re-collide, exactly the lockstep its comment
/// claims to prevent. Measured here against a live SQL Server with eight concurrent migrators on
/// a virgin schema, the unjittered form exhausted the five-attempt budget on repeated 1205s in
/// roughly 1 run in 60; with jitter it did not.
/// </summary>
/// <param name="attempt">The 1-based attempt that just failed.</param>
/// <returns>How long to wait before the next attempt.</returns>
private static TimeSpan BackoffFor(int attempt) =>
TimeSpan.FromMilliseconds((100 * attempt) + Random.Shared.Next(0, 100 * attempt));
/// <summary>
/// Whether any error carried by <paramref name="exception"/> is a retryable provisioning-race
/// outcome. Scans the whole <see cref="SqlException.Errors"/> collection rather than only
/// <see cref="SqlException.Number"/> because a failed DDL batch stacks follow-on errors (e.g.
/// 2714 arrives with 2759 "CREATE SCHEMA failed due to previous errors") and the retryable one
/// is not guaranteed to be first.
/// </summary>
/// <param name="exception">The exception the migration attempt failed with.</param>
/// <returns><see langword="true"/> when a retry may succeed.</returns>
internal static bool IsRetryableMigrationError(SqlException exception)
{
foreach (SqlError error in exception.Errors)
{
if (IsRetryableMigrationErrorNumber(error.Number))
{
return true;
}
}
return IsRetryableMigrationErrorNumber(exception.Number);
}
/// <summary>
/// Classifies a SQL Server error number as a retryable outcome of N nodes provisioning the same
/// (possibly virgin) database at once. Everything here is a race whose retry re-runs the
/// idempotent <c>IF NOT EXISTS</c> path; anything else (login failures, missing database,
/// permissions, syntax) reproduces identically on retry and must propagate. 2705 (duplicate
/// column) is deliberately absent: every column lives inside a single <c>CREATE TABLE</c>
/// statement, so no cross-session race can produce it.
/// </summary>
/// <param name="errorNumber">The <see cref="SqlError.Number"/> to classify.</param>
/// <returns><see langword="true"/> when the number is a known provisioning-race outcome.</returns>
internal static bool IsRetryableMigrationErrorNumber(int errorNumber) => errorNumber
is SqlDeadlockVictimErrorNumber
or SqlObjectAlreadyExistsErrorNumber
or SqlIndexAlreadyExistsErrorNumber
or SqlPrimaryKeyViolationErrorNumber;
private async Task MigrateOnceAsync(CancellationToken cancellationToken)
{
string schema = connectionFactory.Schema;
await using SqlConnection connection =
await connectionFactory.OpenConnectionAsync(cancellationToken).ConfigureAwait(false);
// Serializable: unlike the single-writer SQLite store, EVERY node in the cluster runs this
// migration at startup, so concurrent first-boots are the normal case rather than a rare
// race. The isolation level narrows the race window but does NOT close it — the IF NOT
// EXISTS metadata probes are not serialized against another session's in-flight CREATE, so
// a loser can still fail with "object exists" (2714/1913) or a deadlock (1205). The retry
// filter in MigrateAsync is what makes simultaneous provision converge: by the time the
// loser retries, the winner's objects exist and every guard here skips them.
await using SqlTransaction transaction = (SqlTransaction)
await connection.BeginTransactionAsync(IsolationLevel.Serializable, cancellationToken)
.ConfigureAwait(false);
int existingVersion =
await ReadExistingSchemaVersionAsync(connection, transaction, schema, cancellationToken)
.ConfigureAwait(false);
if (existingVersion > SqlServerAuthSchema.CurrentVersion)
{
throw new AuthStoreMigrationException(
$"Shared API-key database schema version {existingVersion} is newer than supported version " +
$"{SqlServerAuthSchema.CurrentVersion}. Upgrade this node before it writes to the shared store.");
}
await using (SqlCommand ddl = connectionFactory.CreateCommand(
connection, SqlServerAuthSchema.CreateSchemaDdl(schema), transaction))
{
await ddl.ExecuteNonQueryAsync(cancellationToken).ConfigureAwait(false);
}
// MERGE rather than insert-if-missing: WHEN MATCHED re-stamps the row, so a future schema
// version actually lands in the table instead of leaving the first-ever value behind.
await using (SqlCommand version = connectionFactory.CreateCommand(
connection,
$"""
MERGE [{schema}].[{SqlServerAuthSchema.SchemaVersionTable}] AS target
USING (SELECT 1 AS id, @version AS version, @applied_utc AS applied_utc) AS source
ON target.id = source.id
WHEN MATCHED THEN
UPDATE SET version = source.version, applied_utc = source.applied_utc
WHEN NOT MATCHED THEN
INSERT (id, version, applied_utc) VALUES (1, source.version, source.applied_utc);
""",
transaction))
{
version.Parameters.Add("@version", SqlDbType.Int).Value = SqlServerAuthSchema.CurrentVersion;
version.Parameters.Add("@applied_utc", SqlDbType.DateTimeOffset).Value = DateTimeOffset.UtcNow;
await version.ExecuteNonQueryAsync(cancellationToken).ConfigureAwait(false);
}
await transaction.CommitAsync(cancellationToken).ConfigureAwait(false);
}
private async Task<int> ReadExistingSchemaVersionAsync(
SqlConnection connection,
SqlTransaction transaction,
string schema,
CancellationToken cancellationToken)
{
// OBJECT_ID returns NULL for an absent table, so this reads 0 on a virgin database without
// needing the table to exist first.
await using SqlCommand command = connectionFactory.CreateCommand(
connection,
$"""
IF OBJECT_ID(N'[{schema}].[{SqlServerAuthSchema.SchemaVersionTable}]', N'U') IS NULL
SELECT 0;
ELSE
SELECT ISNULL((SELECT version FROM [{schema}].[{SqlServerAuthSchema.SchemaVersionTable}] WHERE id = 1), 0);
""",
transaction);
object? version = await command.ExecuteScalarAsync(cancellationToken).ConfigureAwait(false);
return version is null || version == DBNull.Value
? 0
: Convert.ToInt32(version, CultureInfo.InvariantCulture);
}
}
@@ -0,0 +1,116 @@
namespace ZB.MOM.WW.Auth.ApiKeys.SqlServer;
/// <summary>
/// Schema constants and DDL for the shared SQL Server API-key store. Mirrors
/// <c>ZB.MOM.WW.Auth.ApiKeys.Sqlite.SqliteAuthSchema</c> column-for-column so a row means exactly
/// the same thing in either store.
/// </summary>
/// <remarks>
/// <para>
/// <b>Timestamps are <c>DATETIMEOFFSET(7)</c>, not ISO-8601 text.</b> The sibling
/// <c>ZB.MOM.WW.Secrets</c> SQL Server store deliberately stores its timestamps as
/// <c>nvarchar</c> because its rows <em>replicate</em> with a SQLite store and last-writer-wins
/// compares those timestamps for equality, where a sub-tick round-trip difference would turn a tie
/// into a spurious "newer". No such rationale applies here: this store never replicates with the
/// SQLite one — a host picks exactly one provider, and the one-shot SQLite import is a copy, not an
/// ongoing sync — so the native type is used, which sorts and range-scans correctly and keeps the
/// tables readable to a DBA.
/// </para>
/// <para>
/// <c>SqliteAuthSchema.CurrentVersion</c> is 3 only because that store carries the donor
/// MxAccessGateway's version history (v1/v2 were byte-identical; v3 added <c>expires_utc</c>). This
/// schema is created whole, with <c>expires_utc</c> present from the start, so its own version line
/// starts at 1.
/// </para>
/// </remarks>
public static class SqlServerAuthSchema
{
/// <summary>
/// The schema version this build creates and supports. The migrator refuses a database whose
/// recorded version is <em>newer</em> than this.
/// </summary>
public const int CurrentVersion = 1;
/// <summary>Default schema the API-key tables live in.</summary>
public const string DefaultSchemaName = "zbauth";
/// <summary>Name of the single-row table tracking the applied schema version.</summary>
public const string SchemaVersionTable = "schema_version";
/// <summary>Name of the table storing API-key records.</summary>
public const string ApiKeysTable = "api_keys";
/// <summary>Name of the append-only audit table.</summary>
public const string ApiKeyAuditTable = "api_key_audit";
/// <summary>
/// Returns the idempotent DDL that provisions the schema, the three tables and the two
/// supporting indexes in <paramref name="schemaName"/>.
/// </summary>
/// <param name="schemaName">The SQL schema name to create the objects in.</param>
/// <returns>The DDL batch.</returns>
/// <remarks>
/// <paramref name="schemaName"/> is interpolated, not parameterized — T-SQL has no parameter
/// form for an object name. It is re-validated here against the same strict identifier
/// allow-list <see cref="SqlServerApiKeyOptions.Validate"/> enforces, and bracket-quoted below.
/// The duplicate check is deliberate: this method is <c>public</c>, so it must defend itself
/// rather than trust that every caller routed through the options type. The version row is NOT
/// written here — <see cref="SqlServerApiKeyStoreMigrator"/> writes it with a MERGE that also
/// updates on match, so a future upgrade re-stamps the stored version.
/// </remarks>
/// <exception cref="InvalidOperationException"><paramref name="schemaName"/> is not a plain identifier.</exception>
public static string CreateSchemaDdl(string schemaName)
{
SqlServerApiKeyOptions.ValidateIdentifier(schemaName);
return $"""
IF NOT EXISTS (SELECT 1 FROM sys.schemas WHERE name = N'{schemaName}')
EXEC(N'CREATE SCHEMA [{schemaName}]');
IF OBJECT_ID(N'[{schemaName}].[{SchemaVersionTable}]', N'U') IS NULL
CREATE TABLE [{schemaName}].[{SchemaVersionTable}] (
id INT NOT NULL CONSTRAINT PK_{schemaName}_{SchemaVersionTable} PRIMARY KEY CHECK (id = 1),
version INT NOT NULL,
applied_utc DATETIMEOFFSET(7) NOT NULL
);
IF OBJECT_ID(N'[{schemaName}].[{ApiKeysTable}]', N'U') IS NULL
CREATE TABLE [{schemaName}].[{ApiKeysTable}] (
key_id NVARCHAR(64) NOT NULL CONSTRAINT PK_{schemaName}_{ApiKeysTable} PRIMARY KEY,
key_prefix NVARCHAR(16) NOT NULL,
secret_hash VARBINARY(64) NOT NULL,
display_name NVARCHAR(256) NOT NULL,
scopes NVARCHAR(MAX) NOT NULL,
constraints NVARCHAR(MAX) NULL,
created_utc DATETIMEOFFSET(7) NOT NULL,
last_used_utc DATETIMEOFFSET(7) NULL,
revoked_utc DATETIMEOFFSET(7) NULL,
expires_utc DATETIMEOFFSET(7) NULL
);
IF OBJECT_ID(N'[{schemaName}].[{ApiKeyAuditTable}]', N'U') IS NULL
CREATE TABLE [{schemaName}].[{ApiKeyAuditTable}] (
audit_id BIGINT IDENTITY(1,1) NOT NULL CONSTRAINT PK_{schemaName}_{ApiKeyAuditTable} PRIMARY KEY,
key_id NVARCHAR(64) NULL,
event_type NVARCHAR(64) NOT NULL,
remote_address NVARCHAR(64) NULL,
created_utc DATETIMEOFFSET(7) NOT NULL,
details NVARCHAR(MAX) NULL
);
IF NOT EXISTS (
SELECT 1 FROM sys.indexes
WHERE name = N'ix_api_keys_revoked_utc'
AND object_id = OBJECT_ID(N'[{schemaName}].[{ApiKeysTable}]'))
CREATE INDEX ix_api_keys_revoked_utc
ON [{schemaName}].[{ApiKeysTable}] (revoked_utc);
IF NOT EXISTS (
SELECT 1 FROM sys.indexes
WHERE name = N'ix_api_key_audit_key_id_created_utc'
AND object_id = OBJECT_ID(N'[{schemaName}].[{ApiKeyAuditTable}]'))
CREATE INDEX ix_api_key_audit_key_id_created_utc
ON [{schemaName}].[{ApiKeyAuditTable}] (key_id, created_utc);
""";
}
}