reth_db/tables/mod.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462
//! Tables and data models.
//!
//! # Overview
//!
//! This module defines the tables in reth, as well as some table-related abstractions:
//!
//! - [`codecs`] integrates different codecs into [`Encode`] and [`Decode`]
//! - [`models`](reth_db_api::models) defines the values written to tables
//!
//! # Database Tour
//!
//! TODO(onbjerg): Find appropriate format for this...
pub mod codecs;
mod raw;
pub use raw::{RawDupSort, RawKey, RawTable, RawValue, TableRawRow};
#[cfg(feature = "mdbx")]
pub(crate) mod utils;
use alloy_primitives::{Address, BlockHash, BlockNumber, TxHash, TxNumber, B256};
use reth_db_api::{
models::{
accounts::BlockNumberAddress,
blocks::{HeaderHash, StoredBlockOmmers},
storage_sharded_key::StorageShardedKey,
AccountBeforeTx, ClientVersion, CompactU256, ShardedKey, StoredBlockBodyIndices,
StoredBlockWithdrawals,
},
table::{Decode, DupSort, Encode, Table},
};
use reth_primitives::{
Account, Bytecode, Header, Receipt, Requests, StorageEntry, TransactionSignedNoHash,
};
use reth_primitives_traits::IntegerList;
use reth_prune_types::{PruneCheckpoint, PruneSegment};
use reth_stages_types::StageCheckpoint;
use reth_trie_common::{BranchNodeCompact, StorageTrieEntry, StoredNibbles, StoredNibblesSubKey};
use serde::{Deserialize, Serialize};
use std::fmt;
/// Enum for the types of tables present in libmdbx.
#[derive(Debug, PartialEq, Eq, Copy, Clone)]
pub enum TableType {
/// key value table
Table,
/// Duplicate key value table
DupSort,
}
/// The general purpose of this is to use with a combination of Tables enum,
/// by implementing a `TableViewer` trait you can operate on db tables in an abstract way.
///
/// # Example
///
/// ```
/// use reth_db::{TableViewer, Tables};
/// use reth_db_api::table::{DupSort, Table};
///
/// struct MyTableViewer;
///
/// impl TableViewer<()> for MyTableViewer {
/// type Error = &'static str;
///
/// fn view<T: Table>(&self) -> Result<(), Self::Error> {
/// // operate on table in a generic way
/// Ok(())
/// }
///
/// fn view_dupsort<T: DupSort>(&self) -> Result<(), Self::Error> {
/// // operate on a dupsort table in a generic way
/// Ok(())
/// }
/// }
///
/// let viewer = MyTableViewer {};
///
/// let _ = Tables::Headers.view(&viewer);
/// let _ = Tables::Transactions.view(&viewer);
/// ```
pub trait TableViewer<R> {
/// The error type returned by the viewer.
type Error;
/// Calls `view` with the correct table type.
fn view_rt(&self, table: Tables) -> Result<R, Self::Error> {
table.view(self)
}
/// Operate on the table in a generic way.
fn view<T: Table>(&self) -> Result<R, Self::Error>;
/// Operate on the dupsort table in a generic way.
///
/// By default, the `view` function is invoked unless overridden.
fn view_dupsort<T: DupSort>(&self) -> Result<R, Self::Error> {
self.view::<T>()
}
}
/// Defines all the tables in the database.
#[macro_export]
macro_rules! tables {
(@bool) => { false };
(@bool $($t:tt)+) => { true };
(@view $name:ident $v:ident) => { $v.view::<$name>() };
(@view $name:ident $v:ident $_subkey:ty) => { $v.view_dupsort::<$name>() };
($( $(#[$attr:meta])* table $name:ident<Key = $key:ty, Value = $value:ty $(, SubKey = $subkey:ty)? $(,)?>; )*) => {
// Table marker types.
$(
$(#[$attr])*
///
#[doc = concat!("Marker type representing a database table mapping [`", stringify!($key), "`] to [`", stringify!($value), "`].")]
$(
#[doc = concat!("\n\nThis table's `DUPSORT` subkey is [`", stringify!($subkey), "`].")]
)?
pub struct $name {
_private: (),
}
// Ideally this implementation wouldn't exist, but it is necessary to derive `Debug`
// when a type is generic over `T: Table`. See: https://github.com/rust-lang/rust/issues/26925
impl fmt::Debug for $name {
fn fmt(&self, _: &mut fmt::Formatter<'_>) -> fmt::Result {
unreachable!("this type cannot be instantiated")
}
}
impl reth_db_api::table::Table for $name {
const NAME: &'static str = table_names::$name;
type Key = $key;
type Value = $value;
}
$(
impl DupSort for $name {
type SubKey = $subkey;
}
)?
)*
// Tables enum.
// NOTE: the ordering of the enum does not matter, but it is assumed that the discriminants
// start at 0 and increment by 1 for each variant (the default behavior).
// See for example `reth_db::implementation::mdbx::tx::Tx::db_handles`.
/// A table in the database.
#[derive(Clone, Copy, PartialEq, Eq, Hash)]
pub enum Tables {
$(
#[doc = concat!("The [`", stringify!($name), "`] database table.")]
$name,
)*
}
impl Tables {
/// All the tables in the database.
pub const ALL: &'static [Self] = &[$(Self::$name,)*];
/// The number of tables in the database.
pub const COUNT: usize = Self::ALL.len();
/// Returns the name of the table as a string.
pub const fn name(&self) -> &'static str {
match self {
$(
Self::$name => table_names::$name,
)*
}
}
/// Returns `true` if the table is a `DUPSORT` table.
pub const fn is_dupsort(&self) -> bool {
match self {
$(
Self::$name => tables!(@bool $($subkey)?),
)*
}
}
/// The type of the given table in database.
pub const fn table_type(&self) -> TableType {
if self.is_dupsort() {
TableType::DupSort
} else {
TableType::Table
}
}
/// Allows to operate on specific table type
pub fn view<T, R>(&self, visitor: &T) -> Result<R, T::Error>
where
T: ?Sized + TableViewer<R>,
{
match self {
$(
Self::$name => tables!(@view $name visitor $($subkey)?),
)*
}
}
}
impl fmt::Debug for Tables {
#[inline]
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.write_str(self.name())
}
}
impl fmt::Display for Tables {
#[inline]
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
self.name().fmt(f)
}
}
impl std::str::FromStr for Tables {
type Err = String;
fn from_str(s: &str) -> Result<Self, Self::Err> {
match s {
$(
table_names::$name => Ok(Self::$name),
)*
s => Err(format!("unknown table: {s:?}")),
}
}
}
// Need constants to match on in the `FromStr` implementation.
#[allow(non_upper_case_globals)]
mod table_names {
$(
pub(super) const $name: &'static str = stringify!($name);
)*
}
/// Maps a run-time [`Tables`] enum value to its corresponding compile-time [`Table`] type.
///
/// This is a simpler alternative to [`TableViewer`].
///
/// # Examples
///
/// ```
/// use reth_db::{Tables, tables_to_generic};
/// use reth_db_api::table::Table;
///
/// let table = Tables::Headers;
/// let result = tables_to_generic!(table, |GenericTable| GenericTable::NAME);
/// assert_eq!(result, table.name());
/// ```
#[macro_export]
macro_rules! tables_to_generic {
($table:expr, |$generic_name:ident| $e:expr) => {
match $table {
$(
Tables::$name => {
use $crate::tables::$name as $generic_name;
$e
},
)*
}
};
}
};
}
tables! {
/// Stores the header hashes belonging to the canonical chain.
table CanonicalHeaders<Key = BlockNumber, Value = HeaderHash>;
/// Stores the total difficulty from a block header.
table HeaderTerminalDifficulties<Key = BlockNumber, Value = CompactU256>;
/// Stores the block number corresponding to a header.
table HeaderNumbers<Key = BlockHash, Value = BlockNumber>;
/// Stores header bodies.
table Headers<Key = BlockNumber, Value = Header>;
/// Stores block indices that contains indexes of transaction and the count of them.
///
/// More information about stored indices can be found in the [`StoredBlockBodyIndices`] struct.
table BlockBodyIndices<Key = BlockNumber, Value = StoredBlockBodyIndices>;
/// Stores the uncles/ommers of the block.
table BlockOmmers<Key = BlockNumber, Value = StoredBlockOmmers>;
/// Stores the block withdrawals.
table BlockWithdrawals<Key = BlockNumber, Value = StoredBlockWithdrawals>;
/// Canonical only Stores the transaction body for canonical transactions.
table Transactions<Key = TxNumber, Value = TransactionSignedNoHash>;
/// Stores the mapping of the transaction hash to the transaction number.
table TransactionHashNumbers<Key = TxHash, Value = TxNumber>;
/// Stores the mapping of transaction number to the blocks number.
///
/// The key is the highest transaction ID in the block.
table TransactionBlocks<Key = TxNumber, Value = BlockNumber>;
/// Canonical only Stores transaction receipts.
table Receipts<Key = TxNumber, Value = Receipt>;
/// Stores all smart contract bytecodes.
/// There will be multiple accounts that have same bytecode
/// So we would need to introduce reference counter.
/// This will be small optimization on state.
table Bytecodes<Key = B256, Value = Bytecode>;
/// Stores the current state of an [`Account`].
table PlainAccountState<Key = Address, Value = Account>;
/// Stores the current value of a storage key.
table PlainStorageState<Key = Address, Value = StorageEntry, SubKey = B256>;
/// Stores pointers to block changeset with changes for each account key.
///
/// Last shard key of the storage will contain `u64::MAX` `BlockNumber`,
/// this would allows us small optimization on db access when change is in plain state.
///
/// Imagine having shards as:
/// * `Address | 100`
/// * `Address | u64::MAX`
///
/// What we need to find is number that is one greater than N. Db `seek` function allows us to fetch
/// the shard that equal or more than asked. For example:
/// * For N=50 we would get first shard.
/// * for N=150 we would get second shard.
/// * If max block number is 200 and we ask for N=250 we would fetch last shard and
/// know that needed entry is in `AccountPlainState`.
/// * If there were no shard we would get `None` entry or entry of different storage key.
///
/// Code example can be found in `reth_provider::HistoricalStateProviderRef`
table AccountsHistory<Key = ShardedKey<Address>, Value = BlockNumberList>;
/// Stores pointers to block number changeset with changes for each storage key.
///
/// Last shard key of the storage will contain `u64::MAX` `BlockNumber`,
/// this would allows us small optimization on db access when change is in plain state.
///
/// Imagine having shards as:
/// * `Address | StorageKey | 100`
/// * `Address | StorageKey | u64::MAX`
///
/// What we need to find is number that is one greater than N. Db `seek` function allows us to fetch
/// the shard that equal or more than asked. For example:
/// * For N=50 we would get first shard.
/// * for N=150 we would get second shard.
/// * If max block number is 200 and we ask for N=250 we would fetch last shard and
/// know that needed entry is in `StoragePlainState`.
/// * If there were no shard we would get `None` entry or entry of different storage key.
///
/// Code example can be found in `reth_provider::HistoricalStateProviderRef`
table StoragesHistory<Key = StorageShardedKey, Value = BlockNumberList>;
/// Stores the state of an account before a certain transaction changed it.
/// Change on state can be: account is created, selfdestructed, touched while empty
/// or changed balance,nonce.
table AccountChangeSets<Key = BlockNumber, Value = AccountBeforeTx, SubKey = Address>;
/// Stores the state of a storage key before a certain transaction changed it.
/// If [`StorageEntry::value`] is zero, this means storage was not existing
/// and needs to be removed.
table StorageChangeSets<Key = BlockNumberAddress, Value = StorageEntry, SubKey = B256>;
/// Stores the current state of an [`Account`] indexed with `keccak256Address`
/// This table is in preparation for merklization and calculation of state root.
/// We are saving whole account data as it is needed for partial update when
/// part of storage is changed. Benefit for merklization is that hashed addresses are sorted.
table HashedAccounts<Key = B256, Value = Account>;
/// Stores the current storage values indexed with `keccak256Address` and
/// hash of storage key `keccak256key`.
/// This table is in preparation for merklization and calculation of state root.
/// Benefit for merklization is that hashed addresses/keys are sorted.
table HashedStorages<Key = B256, Value = StorageEntry, SubKey = B256>;
/// Stores the current state's Merkle Patricia Tree.
table AccountsTrie<Key = StoredNibbles, Value = BranchNodeCompact>;
/// From HashedAddress => NibblesSubKey => Intermediate value
table StoragesTrie<Key = B256, Value = StorageTrieEntry, SubKey = StoredNibblesSubKey>;
/// Stores the transaction sender for each canonical transaction.
/// It is needed to speed up execution stage and allows fetching signer without doing
/// transaction signed recovery
table TransactionSenders<Key = TxNumber, Value = Address>;
/// Stores the highest synced block number and stage-specific checkpoint of each stage.
table StageCheckpoints<Key = StageId, Value = StageCheckpoint>;
/// Stores arbitrary data to keep track of a stage first-sync progress.
table StageCheckpointProgresses<Key = StageId, Value = Vec<u8>>;
/// Stores the highest pruned block number and prune mode of each prune segment.
table PruneCheckpoints<Key = PruneSegment, Value = PruneCheckpoint>;
/// Stores the history of client versions that have accessed the database with write privileges by unix timestamp in seconds.
table VersionHistory<Key = u64, Value = ClientVersion>;
/// Stores EIP-7685 EL -> CL requests, indexed by block number.
table BlockRequests<Key = BlockNumber, Value = Requests>;
/// Stores generic chain state info, like the last finalized block.
table ChainState<Key = ChainStateKey, Value = BlockNumber>;
}
/// Keys for the `ChainState` table.
#[derive(Ord, Clone, Eq, PartialOrd, PartialEq, Debug, Deserialize, Serialize, Hash)]
pub enum ChainStateKey {
/// Last finalized block key
LastFinalizedBlock,
}
impl Encode for ChainStateKey {
type Encoded = [u8; 1];
fn encode(self) -> Self::Encoded {
match self {
Self::LastFinalizedBlock => [0],
}
}
}
impl Decode for ChainStateKey {
fn decode(value: &[u8]) -> Result<Self, reth_db_api::DatabaseError> {
if value == [0] {
Ok(Self::LastFinalizedBlock)
} else {
Err(reth_db_api::DatabaseError::Decode)
}
}
}
// Alias types.
/// List with transaction numbers.
pub type BlockNumberList = IntegerList;
/// Encoded stage id.
pub type StageId = String;
#[cfg(test)]
mod tests {
use super::*;
use std::str::FromStr;
#[test]
fn parse_table_from_str() {
for table in Tables::ALL {
assert_eq!(format!("{table:?}"), table.name());
assert_eq!(table.to_string(), table.name());
assert_eq!(Tables::from_str(table.name()).unwrap(), *table);
}
}
}