itest: fix flakiness around/startup/reconnect

This commit is contained in:
Oliver Gugger 2020-07-27 14:15:36 +02:00
parent 5d5e6c369d
commit ecca1f9653
No known key found for this signature in database
GPG Key ID: 8E4256593F177720
3 changed files with 12 additions and 2 deletions

@ -403,7 +403,9 @@ func (n *NetworkHarness) connect(ctx context.Context,
tryconnect:
if _, err := a.ConnectPeer(ctx, req); err != nil {
// If the chain backend is still syncing, retry.
if err == lnd.ErrServerNotActive {
if strings.Contains(err.Error(), lnd.ErrServerNotActive.Error()) ||
strings.Contains(err.Error(), "i/o timeout") {
select {
case <-time.After(100 * time.Millisecond):
goto tryconnect

@ -2,6 +2,8 @@
<time> [ERR] BRAR: Unable to register for conf for txid(<hex>): TxNotifier is exiting
<time> [ERR] BTCN: Broadcast attempt failed: rejected by <ip>: replacement transaction <hex> has an insufficient absolute fee: needs <amt>, has <amt>
<time> [ERR] BTCN: Broadcast attempt failed: rejected by <ip>: replacement transaction <hex> has an insufficient fee rate: needs more than <amt>, has <amt>
<time> [ERR] BTCN: Can't accept connection: unable to accept connection from <ip>: EOF
<time> [ERR] BTCN: Can't accept connection: unable to accept connection from <ip>: read tcp <ip>-><ip>: i/o timeout
<time> [ERR] BTCN: Unable to process block connected (height=<height>, hash=<hex>): out of order block <hex>: expected PrevBlock <hex>, got <hex>
<time> [ERR] BTCN: Unknown connid=<id>
<time> [ERR] CHFT: Close channel <chan_point> unknown to store
@ -112,6 +114,7 @@
<time> [ERR] LNWL: ChannelPoint(<chan_point>): sync failed: remote's next commit height is <height>, while we believe it is <height>!
<time> [ERR] LNWL: Neutrino rescan ended with error: rescan exited
<time> [ERR] LNWL: Notifying unmined tx notification (<hex>) while creating notification for blocks
<time> [ERR] LNWL: Rescan for <num> addresses failed: the client has been shutdown
<time> [ERR] LTND: Unable to lookup witness: no witnesses
<time> [ERR] NANN: Unable to retrieve chan status for Channel(<chan_point>): edge not found
<time> [ERR] NANN: Unable to retrieve chan status for Channel(<chan_point>): unable to extract ChannelUpdate for channel <chan_point>
@ -138,6 +141,8 @@
<time> [ERR] RPCS: [/lnrpc.Lightning/CloseChannel]: cannot co-op close frozen channel as initiator until height=3059, (current_height=3055)
<time> [ERR] RPCS: [/lnrpc.Lightning/CloseChannel]: chain notifier shutting down
<time> [ERR] RPCS: [/lnrpc.Lightning/ConnectPeer]: already connected to peer: <hex>@<ip>
<time> [ERR] RPCS: [/lnrpc.Lightning/ConnectPeer]: read tcp <ip>-><ip>: i/o timeout
<time> [ERR] RPCS: [/lnrpc.Lightning/ConnectPeer]: server is still in the process of starting
<time> [ERR] RPCS: [/lnrpc.Lightning/FundingStateStep]: pendingChanID(<hex>) already has intent registered
<time> [ERR] RPCS: [/lnrpc.Lightning/GetChanInfo]: edge marked as zombie
<time> [ERR] RPCS: [/lnrpc.Lightning/OpenChannel]: channels cannot be created before the wallet is fully synced
@ -168,6 +173,7 @@
<time> [ERR] RPCS: [/routerrpc.Router/SubscribeHtlcEvents]: htlc event subscription terminated
<time> [ERR] RPCS: [closechannel] unable to close ChannelPoint(<chan_point>): chain notifier shutting down
<time> [ERR] RPCS: [connectpeer]: error connecting to peer: already connected to peer: <hex>@<ip>
<time> [ERR] RPCS: [connectpeer]: error connecting to peer: read tcp <ip>-><ip>: i/o timeout
<time> [ERR] RPCS: Failed receiving from stream: rpc error: code = Canceled desc = context canceled
<time> [ERR] RPCS: Failed receiving from stream: rpc error: code = DeadlineExceeded desc = context deadline exceeded
<time> [ERR] RPCS: Failed sending error response: rpc error: code = Canceled desc = context canceled
@ -178,6 +184,7 @@
<time> [ERR] RPCS: unable to open channel to NodeKey(<hex>): received funding error from <hex>: chan_id=<hex>, err=Synchronizing blockchain
<time> [ERR] RPCS: Websocket receive error from <ip>: read tcp4 <ip>-><ip>: use of closed network connection
<time> [ERR] RPCS: Websocket receive error from <ip>: websocket: close 1006 unexpected EOF
<time> [ERR] SRVR: Unable to connect to <hex>@<ip>: read tcp <ip>-><ip>: i/o timeout
<time> [ERR] SRVR: Unable to retrieve advertised address for node <hex>: no advertised addresses found
<time> [ERR] SRVR: Unable to retrieve advertised address for node <hex>: unable to find node
<time> [ERR] UTXN: error while graduating class at height=<height>: TxNotifier is exiting

@ -16,4 +16,5 @@ s/connid=[[:digit:]]+/connid=<id>/g
s/sync failed with local data loss: remote believes our tail height is [[:digit:]]+, while we have [[:digit:]]+/sync failed with local data loss: remote believes our tail height is <height>, while we have <height>/g
s/sync failed: remote believes our tail height is [[:digit:]]+, while we have [[:digit:]]+/sync failed: remote believes our tail height is <height>, while we have <height>/g
s/sync failed: remote's next commit height is [[:digit:]]+, while we believe it is [[:digit:]]+/sync failed: remote's next commit height is <height>, while we believe it is <height>/g
s/replacement transaction <hex> has an insufficient absolute fee: needs [[:digit:]]+, has [[:digit:]]+/replacement transaction <hex> has an insufficient absolute fee: needs <amt>, has <amt>/g
s/replacement transaction <hex> has an insufficient absolute fee: needs [[:digit:]]+, has [[:digit:]]+/replacement transaction <hex> has an insufficient absolute fee: needs <amt>, has <amt>/g
s/Rescan for [[:digit:]]+ addresses/Rescan for <num> addresses/g