nimbus-eth1/scripts
Jacek Sieka b4b4d16729
speed up key computation (#2642)
* batch database key writes during `computeKey` calls
* log progress when there are many keys to update
* avoid evicting the vertex cache when traversing the trie for key
computation purposes
* avoid storing trivial leaf hashes that directly can be loaded from the
vertex
2024-09-20 07:43:53 +02:00
..
.gitignore eth: bump (#2308) 2024-06-06 23:39:09 +00:00
README.md Script for comparing csv outputs from block import 2024-06-06 14:33:49 +02:00
block-import-stats.py stats: interpolate, remove some broken stats 2024-06-29 06:36:35 +02:00
check_copyright_year.sh Cleanup stateless and block witness code. (#2295) 2024-06-08 15:05:00 +07:00
make_dist.sh
make_states.sh speed up key computation (#2642) 2024-09-20 07:43:53 +02:00
print_version.nims Add check copyright year linter to CI 2023-11-01 10:41:20 +07:00
requirements.in Script for comparing csv outputs from block import 2024-06-06 14:33:49 +02:00
requirements.txt increase Python dependencies to address urllib3 vuln and certifi root cert (#2605) 2024-09-10 06:36:28 +00:00

README.md

Utility scripts

block-import-stats.py

This script compares outputs from two nimbus import --debug-csv-stats, a baseline and a contender.

To use it, set up a virtual environment:

# Create a venv for the tool
python -m venv stats
. stats/bin/activate
pip install -r requirements.txt

python block-import-stats.py
  • Generate a baseline version by processing a long range of blocks using nimbus import
  • Modify your code and commit to git (to generate a unique identifier for the code)
  • Re-run the same import over the range of blocks of interest, saving the import statistics to a new CSV
  • Pass the two CSV files to the script

By default, the script will skip block numbers below 500k since these are mostly unintersting.

See -h for help text on running the script.

Testing a particular range of blocks

As long as block import is run on similar hardware, each run can be saved for future reference using the git hash.

The block import can be run repeatedly with --max-blocks to stop after processing a number of blocks - by copying the state at that point, one can resume or replay the import of a particular block range

See make_states.sh for such an example.