Merge pull request #14381 from MinaProtocol/merge-back-to-develop-2023-10-18

Merge back to develop

Author: mrmr1993

automation/terraform/modules/testnet-alerts/templates/testnet-alert-rules.yml.tpl

@@ -255,6 +255,24 @@ groups:
       description: "{{ $value }} blocks have been validated on network {{ $labels.testnet }} in the last hour (according to some node)."
       runbook: "https://www.notion.so/minaprotocol/FewBlocksPerHour-47a6356f093242d988b0d9527ce23478"
 
+  - alert: StuckInBootstrap
+    expr: count by (testnet) (increase(Coda_Runtime_process_uptime_ms_total{syncStatus = "BOOTSTRAP"}[2h]) >= 7200000) > 0
+    for: ${alert_evaluation_duration}
+    labels:
+      testnet: "{{ $labels.testnet }}"
+      severity: critical 
+    annotations:
+      summary: "One or more {{ $labels.testnet }} nodes are stuck at bootstrap for more than 2 hours"
+
+  - alert: StuckInCatchup 
+    expr: count by (testnet) (increase(Coda_Runtime_process_uptime_ms_total{syncStatus = "CATCHUP"}[2h]) >= 7200000) > 0
+    for: ${alert_evaluation_duration}
+    labels:
+      testnet: "{{ $labels.testnet }}"
+      severity: critical 
+    annotations:
+      summary: "One or more {{ $labels.testnet }} nodes are stuck at catchup for more than 2 hours"
+
 
 - name: Warnings
   rules:

buildkite/scripts/rosetta-integration-tests.sh

@@ -93,7 +93,7 @@ ROSETTA_CLI_CONFIG_FILES=${ROSETTA_CLI_CONFIG_FILES:="config.json mina.ros"}
 ROSETTA_CLI_MAIN_CONFIG_FILE=${ROSETTA_CLI_MAIN_CONFIG_FILE:="config.json"}
 
 # Frequency (in seconds) at which payment operations will be sent
-TRANSACTION_FREQUENCY=60
+TRANSACTION_FREQUENCY=10
 
 # Fetch zkApps
 curl -Ls https://github.com/MinaProtocol/rosetta-integration-test-zkapps/tarball/$ROSETTA_INT_TEST_ZKAPPS_VERSION | tar xz -C /tmp
@@ -122,8 +122,8 @@ cat <<EOF >"$MINA_CONFIG_FILE"
   "ledger": {
     "name": "${MINA_NETWORK}",
     "accounts": [
-      { "pk": "${BLOCK_PRODUCER_PK}", "balance": "1000", "delegate": null, "sk": null },
-      { "pk": "${SNARK_PRODUCER_PK}", "balance": "2000", "delegate": "${BLOCK_PRODUCER_PK}", "sk": null }
+      { "pk": "${BLOCK_PRODUCER_PK}", "balance": "1000000", "delegate": null, "sk": null },
+      { "pk": "${SNARK_PRODUCER_PK}", "balance": "2000000", "delegate": "${BLOCK_PRODUCER_PK}", "sk": null }
     ]
   }
 }

buildkite/scripts/run-snark-transaction-profiler.sh

@@ -8,13 +8,7 @@ export DEBIAN_FRONTEND=noninteractive
 apt-get update
 apt-get install -y git apt-transport-https ca-certificates tzdata curl python3
 
-case "$BUILDKITE_PULL_REQUEST_BASE_BRANCH" in
-  rampup|berkeley|release/2.0.0|develop)
-    TESTNET_NAME="berkeley"
-  ;;
-  *)
-    TESTNET_NAME="mainnet"
-esac
+TESTNET_NAME="berkeley"
 
 git config --global --add safe.directory /workdir
 
@@ -30,4 +24,4 @@ MAX_NUM_UPDATES=4
 MIN_NUM_UPDATES=2   
 
 echo "--- Run Snark Transaction Profiler with parameters: --zkapps --k ${K} --max-num-updates ${MAX_NUM_UPDATES} --min-num-updates ${MIN_NUM_UPDATES}"
-python3 ./scripts/snark_transaction_profiler.py ${K} ${MAX_NUM_UPDATES} ${MIN_NUM_UPDATES}
+python3 ./scripts/snark_transaction_profiler.py ${K} ${MAX_NUM_UPDATES} ${MIN_NUM_UPDATES}

buildkite/src/Constants/DebianVersions.dhall

@@ -66,7 +66,11 @@ let minimalDirtyWhen = [
   S.strictlyStart (S.contains "dockerfiles/stages"),
   S.exactly "scripts/rebuild-deb" "sh",
   S.exactly "scripts/release-docker" "sh",
-  S.exactly "buildkite/scripts/build-artifact" "sh"
+  S.exactly "buildkite/scripts/build-artifact" "sh",
+  -- Snark profiler dirtyWhen
+  S.exactly "buildkite/src/Jobs/Test/RunSnarkProfiler" "dhall",
+  S.exactly "buildkite/scripts/run-snark-transaction-profiler" "sh",
+  S.exactly "scripts/snark_transaction_profiler" "py"
 ]
 
 -- The default debian version (Bullseye) is used in all downstream CI jobs

buildkite/src/Jobs/Test/FuzzyZkappTest.dhall

@@ -51,6 +51,6 @@ Pipeline.build
         mode = PipelineMode.Type.Stable
       },
     steps = [
-      buildTestCmd "dev" "src/lib/transaction_snark/test/zkapp_fuzzy/zkapp_fuzzy.exe" 3600 150 Size.Small
+      buildTestCmd "dev" "src/lib/transaction_snark/test/zkapp_fuzzy/zkapp_fuzzy.exe" 4200 150 Size.Small
     ]
   }

scripts/version-linter.py

@@ -2,6 +2,30 @@
 
 # version-linter.py -- makes sure serializations of versioned types don't change
 
+"""
+For the PR branch, PR base branch, and release branch, download the
+type shapes file from Google storage There should be a type shape file
+available for every commit in a PR branch.
+
+For each branch, store the type shape information in a Python dictionary, truncating
+the shapes at a maximum depth.
+
+For each type, compare the type shapes of each branch. If the shapes don't match, print an
+error message. The exact comparison rules are given in RFC 0047 (with some embellishments
+mentioned below).
+
+The maximum depth should be set high enough so that all differences are caught
+(no false negatives).
+
+There may be some false positives, where a difference is reported for
+type t1 due to a change to a type t2 contained in t1. The
+difference will always also be reported for t2 directly.  The maximum
+depth should be set low enough to minimize such false positives.
+
+There are some special rules for the types associated with signed commands and zkApp commands.
+See `check_command_types` below.
+"""
+
 import subprocess
 import os
 import io

src/app/archive/create_schema.sql

@@ -135,7 +135,7 @@ CREATE TABLE protocol_versions
 , transaction      int    NOT NULL
 , network          int    NOT NULL
 , patch            int    NOT NULL
-, UNIQUE (transaction,network)
+, UNIQUE (transaction,network,patch)
 );
 
 CREATE TYPE chain_status_type AS ENUM ('canonical', 'orphaned', 'pending');

src/app/archive/lib/load_data.ml

@@ -1,5 +1,9 @@
 (* load_data.ml -- load archive db data to "native" OCaml data *)
 
+(* these functions are used by the replayer and `extract_blocks` to load particular pieces
+   of archive db data
+*)
+
 open Core_kernel
 open Async
 open Mina_base

src/app/archive/lib/processor.ml

@@ -1,5 +1,23 @@
 (* processor.ml -- database processing for archive node *)
 
+(* For each table in the archive database schema, a
+   corresponding module contains code to read from and write to
+   that table. The module defines a type `t`, a record with fields
+   corresponding to columns in the table; typically, the `id` column
+   that does not have an associated field.
+
+   The more recently written modules use the Mina_caqti library to
+   construct the SQL for those queries. For consistency and
+   simplicity, the older modules should probably be refactored to use
+   Mina_caqti.
+
+   Module `Account_identifiers` is a good example of how Mina_caqti
+   can be used.
+
+   After these table-related modules, there are functions related to
+   running the archive process and archive-related apps.
+*)
+
 module Archive_rpc = Rpc
 open Async
 open Core
@@ -51,6 +69,7 @@ module Public_key = struct
           public_key
 end
 
+(* Unlike other modules here, `Token_owners` does not correspond with a database table *)
 module Token_owners = struct
   (* hash table of token owners, updated for each block *)
   let owner_tbl : Account_id.t Token_id.Table.t = Token_id.Table.create ()
@@ -3755,6 +3774,7 @@ let add_block_aux ?(retries = 3) ~logger ~pool ~add_block ~hash
   in
   retry ~f:add ~logger ~error_str:"add_block_aux" retries
 
+(* used by `archive_blocks` app *)
 let add_block_aux_precomputed ~constraint_constants ~logger ?retries ~pool
     ~delete_older_than block =
   add_block_aux ~logger ?retries ~pool ~delete_older_than
@@ -3765,6 +3785,7 @@ let add_block_aux_precomputed ~constraint_constants ~logger ?retries ~pool
     ~accounts_created:block.Precomputed.accounts_created
     ~tokens_used:block.Precomputed.tokens_used block
 
+(* used by `archive_blocks` app *)
 let add_block_aux_extensional ~logger ?retries ~pool ~delete_older_than block =
   add_block_aux ~logger ?retries ~pool ~delete_older_than
     ~add_block:Block.add_from_extensional
@@ -3773,6 +3794,7 @@ let add_block_aux_extensional ~logger ?retries ~pool ~delete_older_than block =
     ~accounts_created:block.Extensional.Block.accounts_created
     ~tokens_used:block.Extensional.Block.tokens_used block
 
+(* receive blocks from a daemon, write them to the database *)
 let run pool reader ~constraint_constants ~logger ~delete_older_than :
     unit Deferred.t =
   Strict_pipe.Reader.iter reader ~f:(function
@@ -3799,6 +3821,7 @@ let run pool reader ~constraint_constants ~logger ~delete_older_than :
     | Transition_frontier _ ->
         Deferred.unit )
 
+(* [add_genesis_accounts] is called when starting the archive process *)
 let add_genesis_accounts ~logger ~(runtime_config_opt : Runtime_config.t option)
     pool =
   match runtime_config_opt with
@@ -3976,6 +3999,7 @@ let create_metrics_server ~logger ~metrics_server_port ~missing_blocks_width
       in
       go ()
 
+(* for running the archive process *)
 let setup_server ~metrics_server_port ~constraint_constants ~logger
     ~postgres_address ~server_port ~delete_older_than ~runtime_config_opt
     ~missing_blocks_width =

src/lib/mina_lib/mina_lib.ml

@@ -462,6 +462,13 @@ let create_sync_status_observer ~logger ~is_seed ~demo_mode ~net
   let open Mina_incremental.Status in
   let restart_delay = Time.Span.of_min 5. in
   let offline_shutdown_delay = Time.Span.of_min 25. in
+  let after_genesis =
+    let genesis_timestamp =
+      Genesis_constants.(
+        genesis_timestamp_of_string genesis_state_timestamp_string)
+    in
+    fun () -> Time.(( >= ) (now ())) genesis_timestamp
+  in
   let incremental_status =
     map4 online_status_incr transition_frontier_and_catchup_signal_incr
       first_connection_incr first_message_incr
@@ -471,29 +478,31 @@ let create_sync_status_observer ~logger ~is_seed ~demo_mode ~net
         else
           match online_status with
           | `Offline ->
-              ( match !next_helper_restart with
-              | None ->
-                  next_helper_restart :=
-                    Some
-                      (Async.Clock.Event.run_after restart_delay
-                         (fun () ->
-                           [%log info]
-                             "Offline for too long; restarting libp2p_helper" ;
-                           Mina_networking.restart_helper net ;
-                           next_helper_restart := None ;
-                           match !offline_shutdown with
-                           | None ->
-                               offline_shutdown :=
-                                 Some
-                                   (Async.Clock.Event.run_after
-                                      offline_shutdown_delay
-                                      (fun () -> raise Offline_shutdown)
-                                      () )
-                           | Some _ ->
-                               () )
-                         () )
-              | Some _ ->
-                  () ) ;
+              (* nothing to do if offline before genesis *)
+              ( if after_genesis () then
+                match !next_helper_restart with
+                | None ->
+                    next_helper_restart :=
+                      Some
+                        (Async.Clock.Event.run_after restart_delay
+                           (fun () ->
+                             [%log info]
+                               "Offline for too long; restarting libp2p_helper" ;
+                             Mina_networking.restart_helper net ;
+                             next_helper_restart := None ;
+                             match !offline_shutdown with
+                             | None ->
+                                 offline_shutdown :=
+                                   Some
+                                     (Async.Clock.Event.run_after
+                                        offline_shutdown_delay
+                                        (fun () -> raise Offline_shutdown)
+                                        () )
+                             | Some _ ->
+                                 () )
+                           () )
+                | Some _ ->
+                    () ) ;
               let is_empty = function `Empty -> true | _ -> false in
               if is_empty first_connection then (
                 [%str_log info] Connecting ;
@@ -572,10 +581,12 @@ let create_sync_status_observer ~logger ~is_seed ~demo_mode ~net
       | Some _ ->
           ()
       | None ->
-          bootstrap_timeout :=
-            Some
-              (Timeout.create () bootstrap_timeout_duration
-                 ~f:log_bootstrap_error_and_restart )
+          (* don't check bootstrap timeout before genesis *)
+          if after_genesis () then
+            bootstrap_timeout :=
+              Some
+                (Timeout.create () bootstrap_timeout_duration
+                   ~f:log_bootstrap_error_and_restart )
     in
     let stop_bootstrap_timeout () =
       match !bootstrap_timeout with
@@ -585,7 +596,7 @@ let create_sync_status_observer ~logger ~is_seed ~demo_mode ~net
       | None ->
           ()
     in
-    let handle_status_change sync_status =
+    let handle_status_change (sync_status : Sync_status.t) =
       ( match sync_status with
       | `Offline ->
           start_offline_timeout ()

src/lib/pickles/proof_cache.ml

@@ -250,3 +250,10 @@ let set_wrap_proof t ~keypair ~public_input proof =
   in
   let proof_json = Backend.Tock.Proof.to_yojson proof in
   set_proof t ~verification_key ~public_input proof_json
+
+let is_env_var_set_requesting_error_for_proofs () =
+  match Sys.getenv_opt "ERROR_ON_PROOF" with
+  | Some ("true" | "t" (* insert whatever value is okay here *)) ->
+      true
+  | None | Some _ ->
+      false

src/lib/pickles/proof_cache.mli

@@ -52,3 +52,5 @@ val set_wrap_proof :
   -> public_input:Kimchi_bindings.FieldVectors.Fq.t
   -> Backend.Tock.Proof.t
   -> unit
+
+val is_env_var_set_requesting_error_for_proofs : unit -> bool

src/lib/pickles/step.ml

@@ -827,6 +827,10 @@ struct
                               ~public_input:public_inputs
                           with
                           | None ->
+                              if
+                                Proof_cache
+                                .is_env_var_set_requesting_error_for_proofs ()
+                              then failwith "Regenerated proof" ;
                               let%map.Promise proof = create_proof () in
                               Proof_cache.set_step_proof proof_cache ~keypair:pk
                                 ~public_input:public_inputs proof.proof ;

src/lib/pickles/wrap.ml

@@ -876,6 +876,10 @@ let wrap
                       ~public_input:public_inputs
                   with
                   | None ->
+                      if
+                        Proof_cache.is_env_var_set_requesting_error_for_proofs
+                          ()
+                      then failwith "Regenerated proof" ;
                       let%map.Promise proof = create_proof () in
                       Proof_cache.set_wrap_proof proof_cache ~keypair:pk
                         ~public_input:public_inputs proof.proof ;

src/lib/sync_status/sync_status.ml

@@ -1,13 +1,14 @@
 open Core_kernel
 
-(** Sync_status represent states interacting with peers in the coda protocol.
+(** Sync_status represent states interacting with peers in the Mina protocol.
     When the protocol is starting, the node should be in the CONNECT state
     trying to connect to a peer. Once it connects to a peer, the node should be
     in the LISTENING state waiting for peers to send a message to them. When
     the node receives a constant flow of messages, its state should be SYNCED.
     However, when the node is bootstrapping, its state is BOOTSTRAPPING. If it
-    hasn’t received messages for some time
-    (Mina_compile_config.inactivity_secs), then it is OFFLINE. *)
+    hasn’t received messages for some time (see [Mina_lib.offline_time]), then
+    it is OFFLINE.
+*)
 let to_string = function
   | `Connecting ->
       "Connecting"