2021-10-15 03:28:03 +00:00
|
|
|
use crate::{errors::BeaconChainError as Error, metrics, BeaconChain, BeaconChainTypes};
|
2021-09-22 00:37:28 +00:00
|
|
|
use itertools::Itertools;
|
|
|
|
use slog::debug;
|
|
|
|
use state_processing::{
|
|
|
|
per_block_processing::ParallelSignatureSets,
|
|
|
|
signature_sets::{block_proposal_signature_set_from_parts, Error as SignatureSetError},
|
|
|
|
};
|
|
|
|
use std::borrow::Cow;
|
|
|
|
use std::iter;
|
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
|
|
|
use std::sync::Arc;
|
2021-09-22 00:37:28 +00:00
|
|
|
use std::time::Duration;
|
|
|
|
use store::{chunked_vector::BlockRoots, AnchorInfo, ChunkWriter, KeyValueStore};
|
Separate execution payloads in the DB (#3157)
## Proposed Changes
Reduce post-merge disk usage by not storing finalized execution payloads in Lighthouse's database.
:warning: **This is achieved in a backwards-incompatible way for networks that have already merged** :warning:. Kiln users and shadow fork enjoyers will be unable to downgrade after running the code from this PR. The upgrade migration may take several minutes to run, and can't be aborted after it begins.
The main changes are:
- New column in the database called `ExecPayload`, keyed by beacon block root.
- The `BeaconBlock` column now stores blinded blocks only.
- Lots of places that previously used full blocks now use blinded blocks, e.g. analytics APIs, block replay in the DB, etc.
- On finalization:
- `prune_abanonded_forks` deletes non-canonical payloads whilst deleting non-canonical blocks.
- `migrate_db` deletes finalized canonical payloads whilst deleting finalized states.
- Conversions between blinded and full blocks are implemented in a compositional way, duplicating some work from Sean's PR #3134.
- The execution layer has a new `get_payload_by_block_hash` method that reconstructs a payload using the EE's `eth_getBlockByHash` call.
- I've tested manually that it works on Kiln, using Geth and Nethermind.
- This isn't necessarily the most efficient method, and new engine APIs are being discussed to improve this: https://github.com/ethereum/execution-apis/pull/146.
- We're depending on the `ethers` master branch, due to lots of recent changes. We're also using a workaround for https://github.com/gakonst/ethers-rs/issues/1134.
- Payload reconstruction is used in the HTTP API via `BeaconChain::get_block`, which is now `async`. Due to the `async` fn, the `blocking_json` wrapper has been removed.
- Payload reconstruction is used in network RPC to serve blocks-by-{root,range} responses. Here the `async` adjustment is messier, although I think I've managed to come up with a reasonable compromise: the handlers take the `SendOnDrop` by value so that they can drop it on _task completion_ (after the `fn` returns). Still, this is introducing disk reads onto core executor threads, which may have a negative performance impact (thoughts appreciated).
## Additional Info
- [x] For performance it would be great to remove the cloning of full blocks when converting them to blinded blocks to write to disk. I'm going to experiment with a `put_block` API that takes the block by value, breaks it into a blinded block and a payload, stores the blinded block, and then re-assembles the full block for the caller.
- [x] We should measure the latency of blocks-by-root and blocks-by-range responses.
- [x] We should add integration tests that stress the payload reconstruction (basic tests done, issue for more extensive tests: https://github.com/sigp/lighthouse/issues/3159)
- [x] We should (manually) test the schema v9 migration from several prior versions, particularly as blocks have changed on disk and some migrations rely on being able to load blocks.
Co-authored-by: Paul Hauner <paul@paulhauner.com>
2022-05-12 00:42:17 +00:00
|
|
|
use types::{Hash256, SignedBlindedBeaconBlock, Slot};
|
2021-09-22 00:37:28 +00:00
|
|
|
|
|
|
|
/// Use a longer timeout on the pubkey cache.
|
|
|
|
///
|
|
|
|
/// It's ok if historical sync is stalled due to writes from forwards block processing.
|
|
|
|
const PUBKEY_CACHE_LOCK_TIMEOUT: Duration = Duration::from_secs(30);
|
|
|
|
|
|
|
|
#[derive(Debug)]
|
|
|
|
pub enum HistoricalBlockError {
|
|
|
|
/// Block is not available (only returned when fetching historic blocks).
|
|
|
|
BlockOutOfRange { slot: Slot, oldest_block_slot: Slot },
|
|
|
|
/// Block root mismatch, caller should retry with different blocks.
|
|
|
|
MismatchedBlockRoot {
|
|
|
|
block_root: Hash256,
|
|
|
|
expected_block_root: Hash256,
|
|
|
|
},
|
|
|
|
/// Bad signature, caller should retry with different blocks.
|
|
|
|
SignatureSet(SignatureSetError),
|
|
|
|
/// Bad signature, caller should retry with different blocks.
|
|
|
|
InvalidSignature,
|
|
|
|
/// Transitory error, caller should retry with the same blocks.
|
|
|
|
ValidatorPubkeyCacheTimeout,
|
|
|
|
/// No historical sync needed.
|
|
|
|
NoAnchorInfo,
|
|
|
|
/// Logic error: should never occur.
|
|
|
|
IndexOutOfBounds,
|
|
|
|
}
|
|
|
|
|
|
|
|
impl<T: BeaconChainTypes> BeaconChain<T> {
|
|
|
|
/// Store a batch of historical blocks in the database.
|
|
|
|
///
|
|
|
|
/// The `blocks` should be given in slot-ascending order. One of the blocks should have a block
|
|
|
|
/// root corresponding to the `oldest_block_parent` from the store's `AnchorInfo`.
|
|
|
|
///
|
|
|
|
/// The block roots and proposer signatures are verified. If any block doesn't match the parent
|
|
|
|
/// root listed in its successor, then the whole batch will be discarded and
|
|
|
|
/// `MismatchedBlockRoot` will be returned. If any proposer signature is invalid then
|
|
|
|
/// `SignatureSetError` or `InvalidSignature` will be returned.
|
|
|
|
///
|
|
|
|
/// To align with sync we allow some excess blocks with slots greater than or equal to
|
|
|
|
/// `oldest_block_slot` to be provided. They will be ignored without being checked.
|
|
|
|
///
|
|
|
|
/// This function should not be called concurrently with any other function that mutates
|
|
|
|
/// the anchor info (including this function itself). If a concurrent mutation occurs that
|
|
|
|
/// would violate consistency then an `AnchorInfoConcurrentMutation` error will be returned.
|
|
|
|
///
|
|
|
|
/// Return the number of blocks successfully imported.
|
|
|
|
pub fn import_historical_block_batch(
|
|
|
|
&self,
|
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
|
|
|
blocks: Vec<Arc<SignedBlindedBeaconBlock<T::EthSpec>>>,
|
2021-09-22 00:37:28 +00:00
|
|
|
) -> Result<usize, Error> {
|
|
|
|
let anchor_info = self
|
|
|
|
.store
|
|
|
|
.get_anchor_info()
|
|
|
|
.ok_or(HistoricalBlockError::NoAnchorInfo)?;
|
|
|
|
|
|
|
|
// Take all blocks with slots less than the oldest block slot.
|
|
|
|
let num_relevant =
|
|
|
|
blocks.partition_point(|block| block.slot() < anchor_info.oldest_block_slot);
|
|
|
|
let blocks_to_import = &blocks
|
|
|
|
.get(..num_relevant)
|
|
|
|
.ok_or(HistoricalBlockError::IndexOutOfBounds)?;
|
|
|
|
|
|
|
|
if blocks_to_import.len() != blocks.len() {
|
|
|
|
debug!(
|
|
|
|
self.log,
|
|
|
|
"Ignoring some historic blocks";
|
|
|
|
"oldest_block_slot" => anchor_info.oldest_block_slot,
|
|
|
|
"total_blocks" => blocks.len(),
|
|
|
|
"ignored" => blocks.len().saturating_sub(blocks_to_import.len()),
|
|
|
|
);
|
|
|
|
}
|
|
|
|
|
|
|
|
if blocks_to_import.is_empty() {
|
|
|
|
return Ok(0);
|
|
|
|
}
|
|
|
|
|
|
|
|
let mut expected_block_root = anchor_info.oldest_block_parent;
|
|
|
|
let mut prev_block_slot = anchor_info.oldest_block_slot;
|
|
|
|
let mut chunk_writer =
|
|
|
|
ChunkWriter::<BlockRoots, _, _>::new(&self.store.cold_db, prev_block_slot.as_usize())?;
|
|
|
|
|
|
|
|
let mut cold_batch = Vec::with_capacity(blocks.len());
|
|
|
|
let mut hot_batch = Vec::with_capacity(blocks.len());
|
|
|
|
|
|
|
|
for block in blocks_to_import.iter().rev() {
|
|
|
|
// Check chain integrity.
|
|
|
|
let block_root = block.canonical_root();
|
|
|
|
|
|
|
|
if block_root != expected_block_root {
|
|
|
|
return Err(HistoricalBlockError::MismatchedBlockRoot {
|
|
|
|
block_root,
|
|
|
|
expected_block_root,
|
|
|
|
}
|
|
|
|
.into());
|
|
|
|
}
|
|
|
|
|
Separate execution payloads in the DB (#3157)
## Proposed Changes
Reduce post-merge disk usage by not storing finalized execution payloads in Lighthouse's database.
:warning: **This is achieved in a backwards-incompatible way for networks that have already merged** :warning:. Kiln users and shadow fork enjoyers will be unable to downgrade after running the code from this PR. The upgrade migration may take several minutes to run, and can't be aborted after it begins.
The main changes are:
- New column in the database called `ExecPayload`, keyed by beacon block root.
- The `BeaconBlock` column now stores blinded blocks only.
- Lots of places that previously used full blocks now use blinded blocks, e.g. analytics APIs, block replay in the DB, etc.
- On finalization:
- `prune_abanonded_forks` deletes non-canonical payloads whilst deleting non-canonical blocks.
- `migrate_db` deletes finalized canonical payloads whilst deleting finalized states.
- Conversions between blinded and full blocks are implemented in a compositional way, duplicating some work from Sean's PR #3134.
- The execution layer has a new `get_payload_by_block_hash` method that reconstructs a payload using the EE's `eth_getBlockByHash` call.
- I've tested manually that it works on Kiln, using Geth and Nethermind.
- This isn't necessarily the most efficient method, and new engine APIs are being discussed to improve this: https://github.com/ethereum/execution-apis/pull/146.
- We're depending on the `ethers` master branch, due to lots of recent changes. We're also using a workaround for https://github.com/gakonst/ethers-rs/issues/1134.
- Payload reconstruction is used in the HTTP API via `BeaconChain::get_block`, which is now `async`. Due to the `async` fn, the `blocking_json` wrapper has been removed.
- Payload reconstruction is used in network RPC to serve blocks-by-{root,range} responses. Here the `async` adjustment is messier, although I think I've managed to come up with a reasonable compromise: the handlers take the `SendOnDrop` by value so that they can drop it on _task completion_ (after the `fn` returns). Still, this is introducing disk reads onto core executor threads, which may have a negative performance impact (thoughts appreciated).
## Additional Info
- [x] For performance it would be great to remove the cloning of full blocks when converting them to blinded blocks to write to disk. I'm going to experiment with a `put_block` API that takes the block by value, breaks it into a blinded block and a payload, stores the blinded block, and then re-assembles the full block for the caller.
- [x] We should measure the latency of blocks-by-root and blocks-by-range responses.
- [x] We should add integration tests that stress the payload reconstruction (basic tests done, issue for more extensive tests: https://github.com/sigp/lighthouse/issues/3159)
- [x] We should (manually) test the schema v9 migration from several prior versions, particularly as blocks have changed on disk and some migrations rely on being able to load blocks.
Co-authored-by: Paul Hauner <paul@paulhauner.com>
2022-05-12 00:42:17 +00:00
|
|
|
// Store block in the hot database without payload.
|
|
|
|
self.store
|
|
|
|
.blinded_block_as_kv_store_ops(&block_root, block, &mut hot_batch);
|
2021-09-22 00:37:28 +00:00
|
|
|
|
|
|
|
// Store block roots, including at all skip slots in the freezer DB.
|
|
|
|
for slot in (block.slot().as_usize()..prev_block_slot.as_usize()).rev() {
|
|
|
|
chunk_writer.set(slot, block_root, &mut cold_batch)?;
|
|
|
|
}
|
|
|
|
|
|
|
|
prev_block_slot = block.slot();
|
|
|
|
expected_block_root = block.message().parent_root();
|
|
|
|
|
|
|
|
// If we've reached genesis, add the genesis block root to the batch and set the
|
|
|
|
// anchor slot to 0 to indicate completion.
|
|
|
|
if expected_block_root == self.genesis_block_root {
|
|
|
|
let genesis_slot = self.spec.genesis_slot;
|
|
|
|
chunk_writer.set(
|
|
|
|
genesis_slot.as_usize(),
|
|
|
|
self.genesis_block_root,
|
|
|
|
&mut cold_batch,
|
|
|
|
)?;
|
|
|
|
prev_block_slot = genesis_slot;
|
|
|
|
expected_block_root = Hash256::zero();
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
chunk_writer.write(&mut cold_batch)?;
|
|
|
|
|
|
|
|
// Verify signatures in one batch, holding the pubkey cache lock for the shortest duration
|
|
|
|
// possible. For each block fetch the parent root from its successor. Slicing from index 1
|
|
|
|
// is safe because we've already checked that `blocks_to_import` is non-empty.
|
2021-10-15 03:28:03 +00:00
|
|
|
let sig_timer = metrics::start_timer(&metrics::BACKFILL_SIGNATURE_TOTAL_TIMES);
|
|
|
|
let setup_timer = metrics::start_timer(&metrics::BACKFILL_SIGNATURE_SETUP_TIMES);
|
2021-09-22 00:37:28 +00:00
|
|
|
let pubkey_cache = self
|
|
|
|
.validator_pubkey_cache
|
|
|
|
.try_read_for(PUBKEY_CACHE_LOCK_TIMEOUT)
|
|
|
|
.ok_or(HistoricalBlockError::ValidatorPubkeyCacheTimeout)?;
|
|
|
|
let block_roots = blocks_to_import
|
|
|
|
.get(1..)
|
|
|
|
.ok_or(HistoricalBlockError::IndexOutOfBounds)?
|
|
|
|
.iter()
|
|
|
|
.map(|block| block.parent_root())
|
|
|
|
.chain(iter::once(anchor_info.oldest_block_parent));
|
|
|
|
let signature_set = blocks_to_import
|
|
|
|
.iter()
|
|
|
|
.zip_eq(block_roots)
|
|
|
|
.map(|(block, block_root)| {
|
|
|
|
block_proposal_signature_set_from_parts(
|
|
|
|
block,
|
|
|
|
Some(block_root),
|
|
|
|
block.message().proposer_index(),
|
|
|
|
&self.spec.fork_at_epoch(block.message().epoch()),
|
|
|
|
self.genesis_validators_root,
|
2021-10-15 03:28:03 +00:00
|
|
|
|validator_index| pubkey_cache.get(validator_index).cloned().map(Cow::Owned),
|
2021-09-22 00:37:28 +00:00
|
|
|
&self.spec,
|
|
|
|
)
|
|
|
|
})
|
|
|
|
.collect::<Result<Vec<_>, _>>()
|
|
|
|
.map_err(HistoricalBlockError::SignatureSet)
|
|
|
|
.map(ParallelSignatureSets::from)?;
|
2021-10-15 03:28:03 +00:00
|
|
|
drop(pubkey_cache);
|
|
|
|
drop(setup_timer);
|
|
|
|
|
|
|
|
let verify_timer = metrics::start_timer(&metrics::BACKFILL_SIGNATURE_VERIFY_TIMES);
|
2021-09-22 00:37:28 +00:00
|
|
|
if !signature_set.verify() {
|
|
|
|
return Err(HistoricalBlockError::InvalidSignature.into());
|
|
|
|
}
|
2021-10-15 03:28:03 +00:00
|
|
|
drop(verify_timer);
|
|
|
|
drop(sig_timer);
|
2021-09-22 00:37:28 +00:00
|
|
|
|
|
|
|
// Write the I/O batches to disk, writing the blocks themselves first, as it's better
|
|
|
|
// for the hot DB to contain extra blocks than for the cold DB to point to blocks that
|
|
|
|
// do not exist.
|
|
|
|
self.store.hot_db.do_atomically(hot_batch)?;
|
|
|
|
self.store.cold_db.do_atomically(cold_batch)?;
|
|
|
|
|
|
|
|
// Update the anchor.
|
|
|
|
let new_anchor = AnchorInfo {
|
|
|
|
oldest_block_slot: prev_block_slot,
|
|
|
|
oldest_block_parent: expected_block_root,
|
|
|
|
..anchor_info
|
|
|
|
};
|
|
|
|
let backfill_complete = new_anchor.block_backfill_complete();
|
|
|
|
self.store
|
2021-10-05 03:53:17 +00:00
|
|
|
.compare_and_set_anchor_info_with_write(Some(anchor_info), Some(new_anchor))?;
|
2021-09-22 00:37:28 +00:00
|
|
|
|
|
|
|
// If backfill has completed and the chain is configured to reconstruct historic states,
|
|
|
|
// send a message to the background migrator instructing it to begin reconstruction.
|
|
|
|
if backfill_complete && self.config.reconstruct_historic_states {
|
|
|
|
self.store_migrator.process_reconstruction();
|
|
|
|
}
|
|
|
|
|
|
|
|
Ok(blocks_to_import.len())
|
|
|
|
}
|
|
|
|
}
|