2020-03-05 06:19:35 +00:00
|
|
|
use crate::metrics;
|
|
|
|
use lru::LruCache;
|
2021-02-15 07:17:52 +00:00
|
|
|
use types::{beacon_state::CommitteeCache, AttestationShufflingId, Epoch, Hash256};
|
2020-03-05 06:19:35 +00:00
|
|
|
|
|
|
|
/// The size of the LRU cache that stores committee caches for quicker verification.
|
|
|
|
///
|
|
|
|
/// Each entry should be `8 + 800,000 = 800,008` bytes in size with 100k validators. (8-byte hash +
|
|
|
|
/// 100k indices). Therefore, this cache should be approx `16 * 800,008 = 12.8 MB`. (Note: this
|
|
|
|
/// ignores a few extra bytes in the caches that should be insignificant compared to the indices).
|
|
|
|
const CACHE_SIZE: usize = 16;
|
|
|
|
|
|
|
|
/// Provides an LRU cache for `CommitteeCache`.
|
|
|
|
///
|
|
|
|
/// It has been named `ShufflingCache` because `CommitteeCacheCache` is a bit weird and looks like
|
|
|
|
/// a find/replace error.
|
|
|
|
pub struct ShufflingCache {
|
2021-02-15 07:17:52 +00:00
|
|
|
cache: LruCache<AttestationShufflingId, CommitteeCache>,
|
2020-03-05 06:19:35 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
impl ShufflingCache {
|
|
|
|
pub fn new() -> Self {
|
|
|
|
Self {
|
|
|
|
cache: LruCache::new(CACHE_SIZE),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-02-15 07:17:52 +00:00
|
|
|
pub fn get(&mut self, key: &AttestationShufflingId) -> Option<&CommitteeCache> {
|
2020-09-29 03:46:54 +00:00
|
|
|
let opt = self.cache.get(key);
|
2020-03-05 06:19:35 +00:00
|
|
|
|
|
|
|
if opt.is_some() {
|
|
|
|
metrics::inc_counter(&metrics::SHUFFLING_CACHE_HITS);
|
|
|
|
} else {
|
|
|
|
metrics::inc_counter(&metrics::SHUFFLING_CACHE_MISSES);
|
|
|
|
}
|
|
|
|
|
|
|
|
opt
|
|
|
|
}
|
|
|
|
|
2021-02-15 07:17:52 +00:00
|
|
|
pub fn contains(&self, key: &AttestationShufflingId) -> bool {
|
2020-09-29 03:46:54 +00:00
|
|
|
self.cache.contains(key)
|
|
|
|
}
|
2020-03-05 06:19:35 +00:00
|
|
|
|
2021-02-15 07:17:52 +00:00
|
|
|
pub fn insert(&mut self, key: AttestationShufflingId, committee_cache: &CommitteeCache) {
|
2020-03-05 06:19:35 +00:00
|
|
|
if !self.cache.contains(&key) {
|
|
|
|
self.cache.put(key, committee_cache.clone());
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2020-09-29 03:46:54 +00:00
|
|
|
|
Use async code when interacting with EL (#3244)
## Overview
This rather extensive PR achieves two primary goals:
1. Uses the finalized/justified checkpoints of fork choice (FC), rather than that of the head state.
2. Refactors fork choice, block production and block processing to `async` functions.
Additionally, it achieves:
- Concurrent forkchoice updates to the EL and cache pruning after a new head is selected.
- Concurrent "block packing" (attestations, etc) and execution payload retrieval during block production.
- Concurrent per-block-processing and execution payload verification during block processing.
- The `Arc`-ification of `SignedBeaconBlock` during block processing (it's never mutated, so why not?):
- I had to do this to deal with sending blocks into spawned tasks.
- Previously we were cloning the beacon block at least 2 times during each block processing, these clones are either removed or turned into cheaper `Arc` clones.
- We were also `Box`-ing and un-`Box`-ing beacon blocks as they moved throughout the networking crate. This is not a big deal, but it's nice to avoid shifting things between the stack and heap.
- Avoids cloning *all the blocks* in *every chain segment* during sync.
- It also has the potential to clean up our code where we need to pass an *owned* block around so we can send it back in the case of an error (I didn't do much of this, my PR is already big enough :sweat_smile:)
- The `BeaconChain::HeadSafetyStatus` struct was removed. It was an old relic from prior merge specs.
For motivation for this change, see https://github.com/sigp/lighthouse/pull/3244#issuecomment-1160963273
## Changes to `canonical_head` and `fork_choice`
Previously, the `BeaconChain` had two separate fields:
```
canonical_head: RwLock<Snapshot>,
fork_choice: RwLock<BeaconForkChoice>
```
Now, we have grouped these values under a single struct:
```
canonical_head: CanonicalHead {
cached_head: RwLock<Arc<Snapshot>>,
fork_choice: RwLock<BeaconForkChoice>
}
```
Apart from ergonomics, the only *actual* change here is wrapping the canonical head snapshot in an `Arc`. This means that we no longer need to hold the `cached_head` (`canonical_head`, in old terms) lock when we want to pull some values from it. This was done to avoid deadlock risks by preventing functions from acquiring (and holding) the `cached_head` and `fork_choice` locks simultaneously.
## Breaking Changes
### The `state` (root) field in the `finalized_checkpoint` SSE event
Consider the scenario where epoch `n` is just finalized, but `start_slot(n)` is skipped. There are two state roots we might in the `finalized_checkpoint` SSE event:
1. The state root of the finalized block, which is `get_block(finalized_checkpoint.root).state_root`.
4. The state root at slot of `start_slot(n)`, which would be the state from (1), but "skipped forward" through any skip slots.
Previously, Lighthouse would choose (2). However, we can see that when [Teku generates that event](https://github.com/ConsenSys/teku/blob/de2b2801c89ef5abf983d6bf37867c37fc47121f/data/beaconrestapi/src/main/java/tech/pegasys/teku/beaconrestapi/handlers/v1/events/EventSubscriptionManager.java#L171-L182) it uses [`getStateRootFromBlockRoot`](https://github.com/ConsenSys/teku/blob/de2b2801c89ef5abf983d6bf37867c37fc47121f/data/provider/src/main/java/tech/pegasys/teku/api/ChainDataProvider.java#L336-L341) which uses (1).
I have switched Lighthouse from (2) to (1). I think it's a somewhat arbitrary choice between the two, where (1) is easier to compute and is consistent with Teku.
## Notes for Reviewers
I've renamed `BeaconChain::fork_choice` to `BeaconChain::recompute_head`. Doing this helped ensure I broke all previous uses of fork choice and I also find it more descriptive. It describes an action and can't be confused with trying to get a reference to the `ForkChoice` struct.
I've changed the ordering of SSE events when a block is received. It used to be `[block, finalized, head]` and now it's `[block, head, finalized]`. It was easier this way and I don't think we were making any promises about SSE event ordering so it's not "breaking".
I've made it so fork choice will run when it's first constructed. I did this because I wanted to have a cached version of the last call to `get_head`. Ensuring `get_head` has been run *at least once* means that the cached values doesn't need to wrapped in an `Option`. This was fairly simple, it just involved passing a `slot` to the constructor so it knows *when* it's being run. When loading a fork choice from the store and a slot clock isn't handy I've just used the `slot` that was saved in the `fork_choice_store`. That seems like it would be a faithful representation of the slot when we saved it.
I added the `genesis_time: u64` to the `BeaconChain`. It's small, constant and nice to have around.
Since we're using FC for the fin/just checkpoints, we no longer get the `0x00..00` roots at genesis. You can see I had to remove a work-around in `ef-tests` here: b56be3bc2. I can't find any reason why this would be an issue, if anything I think it'll be better since the genesis-alias has caught us out a few times (0x00..00 isn't actually a real root). Edit: I did find a case where the `network` expected the 0x00..00 alias and patched it here: 3f26ac3e2.
You'll notice a lot of changes in tests. Generally, tests should be functionally equivalent. Here are the things creating the most diff-noise in tests:
- Changing tests to be `tokio::async` tests.
- Adding `.await` to fork choice, block processing and block production functions.
- Refactor of the `canonical_head` "API" provided by the `BeaconChain`. E.g., `chain.canonical_head.cached_head()` instead of `chain.canonical_head.read()`.
- Wrapping `SignedBeaconBlock` in an `Arc`.
- In the `beacon_chain/tests/block_verification`, we can't use the `lazy_static` `CHAIN_SEGMENT` variable anymore since it's generated with an async function. We just generate it in each test, not so efficient but hopefully insignificant.
I had to disable `rayon` concurrent tests in the `fork_choice` tests. This is because the use of `rayon` and `block_on` was causing a panic.
Co-authored-by: Mac L <mjladson@pm.me>
2022-07-03 05:36:50 +00:00
|
|
|
impl Default for ShufflingCache {
|
|
|
|
fn default() -> Self {
|
|
|
|
Self::new()
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-09-29 03:46:54 +00:00
|
|
|
/// Contains the shuffling IDs for a beacon block.
|
|
|
|
pub struct BlockShufflingIds {
|
2021-02-15 07:17:52 +00:00
|
|
|
pub current: AttestationShufflingId,
|
|
|
|
pub next: AttestationShufflingId,
|
2020-09-29 03:46:54 +00:00
|
|
|
pub block_root: Hash256,
|
|
|
|
}
|
|
|
|
|
|
|
|
impl BlockShufflingIds {
|
|
|
|
/// Returns the shuffling ID for the given epoch.
|
|
|
|
///
|
|
|
|
/// Returns `None` if `epoch` is prior to `self.current.shuffling_epoch`.
|
2021-02-15 07:17:52 +00:00
|
|
|
pub fn id_for_epoch(&self, epoch: Epoch) -> Option<AttestationShufflingId> {
|
2020-09-29 03:46:54 +00:00
|
|
|
if epoch == self.current.shuffling_epoch {
|
|
|
|
Some(self.current.clone())
|
|
|
|
} else if epoch == self.next.shuffling_epoch {
|
|
|
|
Some(self.next.clone())
|
|
|
|
} else if epoch > self.next.shuffling_epoch {
|
2021-02-15 07:17:52 +00:00
|
|
|
Some(AttestationShufflingId::from_components(
|
|
|
|
epoch,
|
|
|
|
self.block_root,
|
|
|
|
))
|
2020-09-29 03:46:54 +00:00
|
|
|
} else {
|
|
|
|
None
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|