review comments

.github/workflows/benchmark.yml

@@ -1,4 +1,5 @@
----   # Proof generation benchmarking workflow
+---
+# Proof generation benchmarking workflow
 
 name: Benchmark proving
 

.github/workflows/cron_jerigon_zero_testing.yml

@@ -1,10 +1,14 @@
+---
+# Cron running every sunday at 12PM UTC which will run the integration and benchmarking tests for Jerigon Zero
+
 name: Jerigon Zero Testing
 
 on:
-  # Uncomment when ready to run on a schedule
+  # TODO - Change this before merge
+  # # Uncomment when ready to run on a schedule
   # schedule:
-  #   # Run every Sunday at 12:00 AM (UTC)
-  #   - cron: "0 0 * * 0"
+  #   # Run every Sunday at 12:00 PM (UTC)
+  #   - cron: "0 12 * * SUN"
   push:
     branches: [develop]
   pull_request:
@@ -21,22 +25,18 @@ env:
 jobs:
   jerigon_zero_testing:
     name: Jerigon Zero Testing - Integration and Benchmarking
-    runs-on: zero-ci
+    runs-on: zero-reg
+    concurrency:
+      group: jerigon_zero_testing
+      cancel-in-progress: true
     steps:
-      - name: Checkout zk_evm code
-        uses: actions/checkout@v4
-
-      - name: Setup Rust Toolchain
-        uses: actions-rust-lang/setup-rust-toolchain@v1
-
-      - name: Set up Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          cache-on-failure: true
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/rust
 
+      # Build optimized for the native CPU with `lld` linker and allow detailed performance profiling.
       - name: Build the project
         run: |
-          RUSTFLAGS='-C target-cpu=native -Zlinker-features=-lld -Copt-level=3' cargo build --release
+          RUSTFLAGS='-C target-cpu=native -Zlinker-features=-lld' cargo build --release
           sudo sysctl kernel.perf_event_paranoid=0
 
       - name: Set up QEMU
@@ -52,9 +52,10 @@ jobs:
       - name: Run Erigon Network
         run: |
           cd ..
-          tar xf "$(pwd)/zk_evm/test_data/erigon-data.tar.gz" || {
-            echo "Failed to extract erigon-data.tar.gz"; exit 1;
-          }
+          curl -o erigon-test-data.tar.gz \
+          https://224d54070bdacdb423e0b7594ebdc231.ipfscdn.io/ipfs/bafybeigpm34mzhebd24uljuntmhulo6dpniqf75xtxcviztemb2fi5q74i \
+          || { echo "Failed to download erigon.tar.gz"; exit 1; }
+          tar xf ./erigon-test-data.tar.gz
           docker pull ghcr.io/0xpolygonzero/erigon:feat-zero
           docker run -d --name erigon \
             -p 8545:8545 \
@@ -73,30 +74,29 @@ jobs:
         run: |
           export ETH_RPC_URL="http://localhost:8545"
           rm -rf proofs/* circuits/* ./proofs.json test.out verify.out leader.out
-          random_numbers=($(shuf -i 1-500 -n 5))
-          for number in "${random_numbers[@]}"; do
-            hex_number="0x$(echo "obase=16; $number" | bc)"
-            OUTPUT_TO_TERMINAL=true RUN_VERIFICATION=true ./scripts/prove_rpc.sh $hex_number $hex_number $ETH_RPC_URL jerigon true 3000 100
-          done
+          # TODO - Change block number and checkpoint before merge use 1000 to 1100
+          OUTPUT_TO_TERMINAL=true ./scripts/prove_rpc.sh 1 1 $ETH_RPC_URL jerigon 0 3000 100 test_only
 
       - name: Download Previous Results
         uses: dawidd6/action-download-artifact@v6
         with:
           workflow: cron_jerigon_zero_testing.yml
           workflow_conclusion: success
-          name: jerigon_zero_benchmark
+          name: jerigon_zero_testing
           path: ./
           if_no_artifact_found: ignore
 
       - name: Run the Benchmark Script
         run: |
           export ETH_RPC_URL="http://localhost:8545"
-          ./scripts/jerigon_zero_benchmark.sh
+          ./scripts/jerigon_zero_benchmark.bash
 
       - name: Upload New Results
         uses: actions/upload-artifact@v4
         with:
-          name: jerigon_zero_benchmark
-          path: ./jerigon_zero_output.log
+          name: jerigon_zero_testing
+          path: |
+            ./jerigon_zero_benchmark.log
+            ./jerigon_zero_error.log
           retention-days: 90
           overwrite: true

.github/workflows/yamllint.yml

@@ -1,14 +1,15 @@
----  # Run yamllint on all YAML files in the repository
+---
+# Run yamllint on all YAML files in the repository
 
 name: Yamllint
-'on':
+"on":
   pull_request:
     paths:
-      - '**/*.yml'
-      - '.github/**'
+      - "**/*.yml"
+      - ".github/**"
   workflow_dispatch:
     branches:
-      - '**'
+      - "**"
 
 jobs:
   yamllint-check:
@@ -22,5 +23,5 @@ jobs:
         run: >
           yamllint
           --format github
-          -d "{extends: default, rules: {line-length: {max: 120}, truthy: {check-keys: false}}}"
+          -d "{extends: default, rules: {line-length: {max: 130}, truthy: {check-keys: false}}}"
           .github scripts

resp.json

@@ -0,0 +1 @@
+{"jsonrpc":"2.0","id":1,"result":{"trie_pre_images":{"combined":{"compact":"0x"}},"code_db":{},"txn_info":[{"traces":{"0xf39fd6e51aad88f6f4ce6ab8827279cfffb92266":{"balance":"0xd3c21bce8022181a02cd","nonce":"0x3"},"0x0000000000000000000000000000000000000000":{"balance":"0x3bbc3b274218","nonce":"0x0"},"0x852da15b70a3e197d1d668a9a481b1f4c2168a5d":{"balance":"0x3","nonce":"0x0"}},"meta":{"byte_code":"0xf86602843b9aca07830186a094852da15b70a3e197d1d668a9a481b1f4c2168a5d0180820a95a0d5081ac0967a518e50ccdcb92d9eed98b71d5dfa9b38ccf3c63adc429d9d13a6a058c166e24381b70ceff2cbe22786a686e62a004ac82aecf0516c91dd53ef2e25","new_receipt_trie_node_byte":"0xf9010801825208b9010000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000c0","gas_used":21000}}]}}

scripts/jerigon_zero_benchmark.sh → scripts/jerigon_zero_benchmark.bash

@@ -1,9 +1,5 @@
-#!/bin/bash
-# ------------------------------------------------------------------------------
-set -exo pipefail
-
-# Args:
-# 1 --> Output file (Not used in the current script)
+#!/usr/bin/env bash
+set -euxo pipefail
 
 # Get the number of processors for parallelism
 if [[ "$OSTYPE" == "darwin"* ]]; then
@@ -18,8 +14,9 @@ PROOF_OUTPUT_DIR="${REPO_ROOT}/proofs"
 BLOCK_BATCH_SIZE="${BLOCK_BATCH_SIZE:-8}"
 
 # Logging setup
-OUTPUT_LOG="jerigon_zero_output.log"
+OUTPUT_LOG="jerigon_zero_benchmark.log"
 BLOCK_OUTPUT_LOG="jerigon_zero_block_output.log"
+ERROR_LOG="jerigon_zero_error.log"
 PROOFS_FILE_LIST="${PROOF_OUTPUT_DIR}/proof_files.json"
 
 # Ensure necessary directories exist
@@ -33,57 +30,58 @@ export RUST_BACKTRACE=full
 export RUST_LOG=info
 
 # Log the current date and time
-echo "$(date +"%Y-%m-%d %H:%M:%S")" &>> "$OUTPUT_LOG"
-
-# Define the blocks to process
-blocks=(100 200 300 400 500)
+date +"%Y-%m-%d %H:%M:%S" &>> "$OUTPUT_LOG"
+date +"%Y-%m-%d %H:%M:%S" &>> "$ERROR_LOG"
 
 # Function to process each block
 process_block() {
-    local block=$1
-
-    echo "Processing block: $block" &>> "$OUTPUT_LOG"
+    local block start_time end_time duration_sec PERF_TIME PERF_USER_TIME PERF_SYS_TIME
+    block=$1
 
     # Fetch block data
-    if ! ./target/release/rpc --rpc-url "$ETH_RPC_URL" fetch --start-block "$block" --end-block "$block" > "output_${block}.json"; then
-        echo "Failed to fetch block data for block: $block" &>> "$OUTPUT_LOG"
-        exit 1
+    if ! ./target/release/rpc --rpc-url "$ETH_RPC_URL" fetch --start-block "$block" --end-block "$block" > "witness_${block}.json"; then
+        echo "Failed to fetch block data for block: $block" &>> "$ERROR_LOG"
+        return
     fi
 
-    local start_time=$(date +%s%N)
+    start_time=$(date +%s%N)
 
     # Run performance stats
-    if ! perf stat -e cycles ./target/release/leader --runtime in-memory --load-strategy monolithic --block-batch-size "$BLOCK_BATCH_SIZE" --proof-output-dir "$PROOF_OUTPUT_DIR" stdio < "output_${block}.json" &> "$BLOCK_OUTPUT_LOG"; then
+    if ! perf stat -e cycles ./target/release/leader --runtime in-memory --use-test-config --load-strategy on-demand --block-batch-size "$BLOCK_BATCH_SIZE" --proof-output-dir "$PROOF_OUTPUT_DIR" stdio < "witness_${block}.json" &> "$BLOCK_OUTPUT_LOG"; then
         echo "Performance command failed for block: $block" &>> "$OUTPUT_LOG"
-        cat "$BLOCK_OUTPUT_LOG" &>> "$OUTPUT_LOG"
-        exit 1
+        cat "$BLOCK_OUTPUT_LOG" &>> "$ERROR_LOG"
+        return
     fi
 
-    local end_time=$(date +%s%N)
+    end_time=$(date +%s%N)
 
     set +o pipefail
-    if ! cat "$BLOCK_OUTPUT_LOG" | grep "Successfully wrote to disk proof file " | awk '{print $NF}' | tee "$PROOFS_FILE_LIST"; then
+    if ! grep "Successfully wrote to disk proof file " "$BLOCK_OUTPUT_LOG" | awk '{print $NF}' | tee "$PROOFS_FILE_LIST"; then
         echo "Proof list not generated for block: $block. Check the log for details." &>> "$OUTPUT_LOG"
-        cat "$BLOCK_OUTPUT_LOG" &>> "$OUTPUT_LOG"
-        exit 1
+        cat "$BLOCK_OUTPUT_LOG" &>> "$ERROR_LOG"
+        return
     fi
 
-    local duration_sec=$(echo "scale=3; ($end_time - $start_time) / 1000000000" | bc -l)
+    duration_sec=$(echo "scale=3; ($end_time - $start_time) / 1000000000" | bc -l)
 
     # Extract performance timings
-    local PERF_TIME=$(grep "seconds time elapsed" "$BLOCK_OUTPUT_LOG" | tail -1 | awk '{ print ($1)}')
-    local PERF_USER_TIME=$(grep "seconds user" "$BLOCK_OUTPUT_LOG" | tail -1 | awk '{ print ($1)}')
-    local PERF_SYS_TIME=$(grep "seconds sys" "$BLOCK_OUTPUT_LOG" | tail -1 | awk '{ print ($1)}')
+    PERF_TIME=$(grep "seconds time elapsed" "$BLOCK_OUTPUT_LOG" | tail -1 | awk '{ print ($1)}')
+    PERF_USER_TIME=$(grep "seconds user" "$BLOCK_OUTPUT_LOG" | tail -1 | awk '{ print ($1)}')
+    PERF_SYS_TIME=$(grep "seconds sys" "$BLOCK_OUTPUT_LOG" | tail -1 | awk '{ print ($1)}')
 
     echo "Success for block: $block!"
     echo "Proving duration for block $block: $duration_sec seconds, performance time: $PERF_TIME, performance user time: $PERF_USER_TIME, performance system time: $PERF_SYS_TIME" &>> "$OUTPUT_LOG"
 }
 
 # Process each block
-for block in "${blocks[@]}"; do
-    process_block "$block"
+# TODO - Change block numbers before merge use 700 to 1000
+for i in $(seq 1 2); do
+    process_block "$i"
 done
 
 # Finalize logging
 echo "Processing completed at: $(date +"%Y-%m-%d %H:%M:%S")" &>> "$OUTPUT_LOG"
 echo "" &>> "$OUTPUT_LOG"
+
+echo "Processing completed at: $(date +"%Y-%m-%d %H:%M:%S")" &>> "$ERROR_LOG"
+echo "" &>> "$ERROR_LOG"

zero/src/rpc/zeth.rs

@@ -0,0 +1,42 @@
+use alloy::{
+    primitives::B256, providers::Provider, rpc::types::eth::BlockId, transports::Transport,
+};
+use trace_decoder::BlockTrace;
+
+use super::{fetch_other_block_data, CachedProvider};
+use crate::prover::BlockProverInput;
+
+pub async fn block_prover_input<ProviderT, TransportT>(
+    cached_provider: std::sync::Arc<CachedProvider<ProviderT, TransportT>>,
+    target_block_id: BlockId,
+    checkpoint_block_number: u64,
+) -> anyhow::Result<BlockProverInput>
+where
+    ProviderT: Provider<TransportT>,
+    TransportT: Transport + Clone,
+{
+    let block_number = match target_block_id {
+        BlockId::Number(block_number) => block_number,
+        _ => return Err(anyhow::anyhow!("block number expected")),
+    };
+
+    println!("Fetching block trace for block number: {}", block_number);
+
+    let block_trace: BlockTrace = cached_provider
+        .get_provider()
+        .await?
+        .raw_request("zero_getBlockTraceByNumber".into(), vec![block_number])
+        .await?;
+
+    println!("trace: {:?}", block_trace);
+
+    let other_data =
+        fetch_other_block_data(cached_provider, target_block_id, checkpoint_block_number).await?;
+    println!("other_data: {:?}", other_data);
+
+    // Assemble
+    Ok(BlockProverInput {
+        block_trace,
+        other_data,
+    })
+}