vtorc

vtorc #

VTOrc is the automated fault detection and repair tool in Vitess.

vtorc [flags]

Examples #

vtorc \
	--topo_implementation etcd2 \
	--topo_global_server_address localhost:2379 \
	--topo_global_root /vitess/global \
	--log_dir $VTDATAROOT/tmp \
	--port 15000 \
	--instance-poll-time "1s" \
	--topo-information-refresh-duration "30s" \
	--alsologtostderr

Options #

      --allow-emergency-reparent                                    Whether VTOrc should be allowed to run emergency reparent operation when it detects a dead primary (default true)
      --alsologtostderr                                             log to standard error as well as files
      --audit-file-location string                                  File location where the audit logs are to be stored
      --audit-purge-duration duration                               Duration for which audit logs are held before being purged. Should be in multiples of days (default 168h0m0s)
      --audit-to-backend                                            Whether to store the audit log in the VTOrc database
      --audit-to-syslog                                             Whether to store the audit log in the syslog
      --bind-address string                                         Bind address for the server. If empty, the server will listen on all available unicast and anycast IP addresses of the local system.
      --catch-sigpipe                                               catch and ignore SIGPIPE on stdout and stderr if specified
      --change-tablets-with-errant-gtid-to-drained                  Whether VTOrc should be changing the type of tablets with errant GTIDs to DRAINED
      --clusters_to_watch strings                                   Comma-separated list of keyspaces or keyspace/shards that this instance will monitor and repair. Defaults to all clusters in the topology. Example: "ks1,ks2/-80"
      --config string                                               config file name
      --config-file string                                          Full path of the config file (with extension) to use. If set, --config-path, --config-type, and --config-name are ignored.
      --config-file-not-found-handling ConfigFileNotFoundHandling   Behavior when a config file is not found. (Options: error, exit, ignore, warn) (default warn)
      --config-name string                                          Name of the config file (without extension) to search for. (default "vtconfig")
      --config-path strings                                         Paths to search for config files in. (default [<WORKDIR>])
      --config-persistence-min-interval duration                    minimum interval between persisting dynamic config changes back to disk (if no change has occurred, nothing is done). (default 1s)
      --config-type string                                          Config file type (omit to infer config type from file extension).
      --consul_auth_static_file string                              JSON File to read the topos/tokens from.
      --emit_stats                                                  If set, emit stats to push-based monitoring and stats backends
      --grpc_auth_static_client_creds string                        When using grpc_static_auth in the server, this file provides the credentials to use to authenticate with server.
      --grpc_compression string                                     Which protocol to use for compressing gRPC. Default: nothing. Supported: snappy
      --grpc_enable_tracing                                         Enable gRPC tracing.
      --grpc_initial_conn_window_size int                           gRPC initial connection window size
      --grpc_initial_window_size int                                gRPC initial window size
      --grpc_keepalive_time duration                                After a duration of this time, if the client doesn't see any activity, it pings the server to see if the transport is still alive. (default 10s)
      --grpc_keepalive_timeout duration                             After having pinged for keepalive check, the client waits for a duration of Timeout and if no activity is seen even after that the connection is closed. (default 10s)
      --grpc_max_message_size int                                   Maximum allowed RPC message size. Larger messages will be rejected by gRPC with the error 'exceeding the max size'. (default 16777216)
      --grpc_prometheus                                             Enable gRPC monitoring with Prometheus.
  -h, --help                                                        help for vtorc
      --instance-poll-time duration                                 Timer duration on which VTOrc refreshes MySQL information (default 5s)
      --keep_logs duration                                          keep logs for this long (using ctime) (zero to keep forever)
      --keep_logs_by_mtime duration                                 keep logs for this long (using mtime) (zero to keep forever)
      --lameduck-period duration                                    keep running at least this long after SIGTERM before stopping (default 50ms)
      --lock-timeout duration                                       Maximum time for which a shard/keyspace lock can be acquired for (default 45s)
      --log_backtrace_at traceLocations                             when logging hits line file:N, emit a stack trace
      --log_dir string                                              If non-empty, write log files in this directory
      --log_err_stacks                                              log stack traces for errors
      --log_rotate_max_size uint                                    size in bytes at which logs are rotated (glog.MaxSize) (default 1887436800)
      --logtostderr                                                 log to standard error instead of files
      --max-stack-size int                                          configure the maximum stack size in bytes (default 67108864)
      --onclose_timeout duration                                    wait no more than this for OnClose handlers before stopping (default 10s)
      --onterm_timeout duration                                     wait no more than this for OnTermSync handlers before stopping (default 10s)
      --pid_file string                                             If set, the process will write its pid to the named file, and delete it on graceful shutdown.
      --port int                                                    port for the server
      --pprof strings                                               enable profiling
      --pprof-http                                                  enable pprof http endpoints
      --prevent-cross-cell-failover                                 Prevent VTOrc from promoting a primary in a different cell than the current primary in case of a failover
      --purge_logs_interval duration                                how often try to remove old logs (default 1h0m0s)
      --reasonable-replication-lag duration                         Maximum replication lag on replicas which is deemed to be acceptable (default 10s)
      --recovery-poll-duration duration                             Timer duration on which VTOrc polls its database to run a recovery (default 1s)
      --remote_operation_timeout duration                           time to wait for a remote operation (default 15s)
      --security_policy string                                      the name of a registered security policy to use for controlling access to URLs - empty means allow all for anyone (built-in policies: deny-all, read-only)
      --shutdown_wait_time duration                                 Maximum time to wait for VTOrc to release all the locks that it is holding before shutting down on SIGTERM (default 30s)
      --snapshot-topology-interval duration                         Timer duration on which VTOrc takes a snapshot of the current MySQL information it has in the database. Should be in multiple of hours
      --sqlite-data-file string                                     SQLite Datafile to use as VTOrc's database (default "file::memory:?mode=memory&cache=shared")
      --stats_backend string                                        The name of the registered push-based monitoring/stats backend to use
      --stats_combine_dimensions string                             List of dimensions to be combined into a single "all" value in exported stats vars
      --stats_common_tags strings                                   Comma-separated list of common tags for the stats backend. It provides both label and values. Example: label1:value1,label2:value2
      --stats_drop_variables string                                 Variables to be dropped from the list of exported variables.
      --stats_emit_period duration                                  Interval between emitting stats to all registered backends (default 1m0s)
      --stderrthreshold severityFlag                                logs at or above this threshold go to stderr (default 1)
      --table-refresh-interval int                                  interval in milliseconds to refresh tables in status page with refreshRequired class
      --tablet_manager_grpc_ca string                               the server ca to use to validate servers when connecting
      --tablet_manager_grpc_cert string                             the cert to use to connect
      --tablet_manager_grpc_concurrency int                         concurrency to use to talk to a vttablet server for performance-sensitive RPCs (like ExecuteFetchAs{Dba,App}, CheckThrottler and FullStatus) (default 8)
      --tablet_manager_grpc_connpool_size int                       number of tablets to keep tmclient connections open to (default 100)
      --tablet_manager_grpc_crl string                              the server crl to use to validate server certificates when connecting
      --tablet_manager_grpc_key string                              the key to use to connect
      --tablet_manager_grpc_server_name string                      the server name to use to validate server certificate
      --tablet_manager_protocol string                              Protocol to use to make tabletmanager RPCs to vttablets. (default "grpc")
      --tolerable-replication-lag duration                          Amount of replication lag that is considered acceptable for a tablet to be eligible for promotion when Vitess makes the choice of a new primary in PRS
      --topo-information-refresh-duration duration                  Timer duration on which VTOrc refreshes the keyspace and vttablet records from the topology server (default 15s)
      --topo_consul_lock_delay duration                             LockDelay for consul session. (default 15s)
      --topo_consul_lock_session_checks string                      List of checks for consul session. (default "serfHealth")
      --topo_consul_lock_session_ttl string                         TTL for consul session.
      --topo_consul_watch_poll_duration duration                    time of the long poll for watch queries. (default 30s)
      --topo_etcd_lease_ttl int                                     Lease TTL for locks and leader election. The client will use KeepAlive to keep the lease going. (default 30)
      --topo_etcd_tls_ca string                                     path to the ca to use to validate the server cert when connecting to the etcd topo server
      --topo_etcd_tls_cert string                                   path to the client cert to use to connect to the etcd topo server, requires topo_etcd_tls_key, enables TLS
      --topo_etcd_tls_key string                                    path to the client key to use to connect to the etcd topo server, enables TLS
      --topo_global_root string                                     the path of the global topology data in the global topology server
      --topo_global_server_address string                           the address of the global topology server
      --topo_implementation string                                  the topology implementation to use
      --topo_zk_auth_file string                                    auth to use when connecting to the zk topo server, file contents should be <scheme>:<auth>, e.g., digest:user:pass
      --topo_zk_base_timeout duration                               zk base timeout (see zk.Connect) (default 30s)
      --topo_zk_max_concurrency int                                 maximum number of pending requests to send to a Zookeeper server. (default 64)
      --topo_zk_tls_ca string                                       the server ca to use to validate servers when connecting to the zk topo server
      --topo_zk_tls_cert string                                     the cert to use to connect to the zk topo server, requires topo_zk_tls_key, enables TLS
      --topo_zk_tls_key string                                      the key to use to connect to the zk topo server, enables TLS
      --v Level                                                     log level for V logs
  -v, --version                                                     print binary version
      --vmodule vModuleFlag                                         comma-separated list of pattern=N settings for file-filtered logging
      --wait-replicas-timeout duration                              Duration for which to wait for replica's to respond when issuing RPCs (default 30s)