Files
prysm/beacon-chain/sync/custody.go
james-prysm 74c8a25354 adding semi-supernode feature (#16029)
<!-- Thanks for sending a PR! Before submitting:

1. If this is your first PR, check out our contribution guide here
https://docs.prylabs.network/docs/contribute/contribution-guidelines
You will then need to sign our Contributor License Agreement (CLA),
which will show up as a comment from a bot in this pull request after
you open it. We cannot review code without a signed CLA.
2. Please file an associated tracking issue if this pull request is
non-trivial and requires context for our team to understand. All
features and most bug fixes should have
an associated issue with a design discussed and decided upon. Small bug
   fixes and documentation improvements don't need issues.
3. New features and bug fixes must have tests. Documentation may need to
be updated. If you're unsure what to update, send the PR, and we'll
discuss
   in review.
4. Note that PRs updating dependencies and new Go versions are not
accepted.
   Please file an issue instead.
5. A changelog entry is required for user facing issues.
-->

**What type of PR is this?**

Feature


**What does this PR do? Why is it needed?**

| Feature | Semi-Supernode | Supernode |
| ----------------------- | ------------------------- |
------------------------ |
| **Custody Groups** | 64 | 128 |
| **Data Columns** | 64 | 128 |
| **Storage** | ~50% | ~100% |
| **Blob Reconstruction** | Yes (via Reed-Solomon) | No reconstruction
needed |
| **Flag** | `--semi-supernode` | `--supernode` |
| **Can serve all blobs** | Yes (with reconstruction) | Yes (directly) |

**note** if your validator total effective balance results in more
custody than the semi-supernode it will override those those
requirements.

cgc=64 from @nalepae 
Pro:
- We are useful to the network
- Less disconnection likelihood
- Straight forward to implement

Con:
- We cannot revert to a full node
- We have to serve incoming RPC requests corresponding to 64 columns

Tested the following using this kurtosis setup

```
participants:
  # Super-nodes
  - el_type: geth
    el_image: ethpandaops/geth:master
    cl_type: prysm
    vc_image: gcr.io/offchainlabs/prysm/validator:latest
    cl_image: gcr.io/offchainlabs/prysm/beacon-chain:latest
    count: 2
    cl_extra_params:
      - --supernode
    vc_extra_params:
      - --verbosity=debug
  # Full-nodes
  - el_type: geth
    el_image: ethpandaops/geth:master
    cl_type: prysm
    vc_image: gcr.io/offchainlabs/prysm/validator:latest
    cl_image: gcr.io/offchainlabs/prysm/beacon-chain:latest
    count: 2
    validator_count: 1
    cl_extra_params:
      - --semi-supernode
    vc_extra_params:
      - --verbosity=debug

additional_services:
  - dora
  - spamoor

spamoor_params:
  image: ethpandaops/spamoor:master
  max_mem: 4000
  spammers:
    - scenario: eoatx
      config:
        throughput: 200
    - scenario: blobs
      config:
        throughput: 20

network_params:
  fulu_fork_epoch: 0
  withdrawal_type: "0x02"
  preset: mainnet

global_log_level: debug
```

```
curl -H "Accept: application/json" http://127.0.0.1:32961/eth/v1/node/identity
{"data":{"peer_id":"16Uiu2HAm7xzhnGwea8gkcxRSC6fzUkvryP6d9HdWNkoeTkj6RSqw","enr":"enr:-Ni4QIH5u2NQz17_pTe9DcCfUyG8TidDJJjIeBpJRRm4ACQzGBpCJdyUP9eGZzwwZ2HS1TnB9ACxFMQ5LP5njnMDLm-GAZqZEXjih2F0dG5ldHOIAAAAAAAwAACDY2djQIRldGgykLZy_whwAAA4__________-CaWSCdjSCaXCErBAAE4NuZmSEAAAAAIRxdWljgjLIiXNlY3AyNTZrMaECulJrXpSOBmCsQWcGYzQsst7r3-Owlc9iZbEcJTDkB6qIc3luY25ldHMFg3RjcIIyyIN1ZHCCLuA","p2p_addresses":["/ip4/172.16.0.19/tcp/13000/p2p/16Uiu2HAm7xzhnGwea8gkcxRSC6fzUkvryP6d9HdWNkoeTkj6RSqw","/ip4/172.16.0.19/udp/13000/quic-v1/p2p/16Uiu2HAm7xzhnGwea8gkcxRSC6fzUkvryP6d9HdWNkoeTkj6RSqw"],"discovery_addresses":["/ip4/172.16.0.19/udp/12000/p2p/16Uiu2HAm7xzhnGwea8gkcxRSC6fzUkvryP6d9HdWNkoeTkj6RSqw"],"metadata":{"seq_number":"3","attnets":"0x0000000000300000","syncnets":"0x05","custody_group_count":"64"}}}
```

```
curl -s http://127.0.0.1:32961/eth/v1/debug/beacon/data_column_sidecars/head | jq '.data | length'
64
```

```
curl -X 'GET' \
  'http://127.0.0.1:32961/eth/v1/beacon/blobs/head' \
  -H 'accept: application/json'
  ```

**Which issues(s) does this PR fix?**

Fixes #

**Other notes for review**

**Acknowledgements**

- [x] I have read [CONTRIBUTING.md](https://github.com/prysmaticlabs/prysm/blob/develop/CONTRIBUTING.md).
- [x] I have included a uniquely named [changelog fragment file](https://github.com/prysmaticlabs/prysm/blob/develop/CONTRIBUTING.md#maintaining-changelogmd).
- [x] I have added a description to this PR with sufficient context for reviewers to understand this PR.

---------

Co-authored-by: Preston Van Loon <pvanloon@offchainlabs.com>
Co-authored-by: james-prysm <jhe@offchainlabs.com>
Co-authored-by: Manu NALEPA <enalepa@offchainlabs.com>
2025-11-26 15:31:15 +00:00

149 lines
4.5 KiB
Go

package sync
import (
"context"
"strings"
"time"
"github.com/OffchainLabs/prysm/v7/async"
"github.com/OffchainLabs/prysm/v7/beacon-chain/core/peerdas"
"github.com/OffchainLabs/prysm/v7/beacon-chain/p2p"
"github.com/OffchainLabs/prysm/v7/cmd/beacon-chain/flags"
"github.com/OffchainLabs/prysm/v7/config/params"
"github.com/pkg/errors"
"github.com/sirupsen/logrus"
)
var nilFinalizedStateError = errors.New("finalized state is nil")
func (s *Service) maintainCustodyInfo() {
const interval = 1 * time.Minute
async.RunEvery(s.ctx, interval, func() {
if err := s.updateCustodyInfoIfNeeded(); err != nil {
log.WithError(err).Error("Failed to update custody info")
}
})
}
func (s *Service) updateCustodyInfoIfNeeded() error {
const minimumPeerCount = 1
// Get our actual custody group count.
actualCustodyGrounpCount, err := s.cfg.p2p.CustodyGroupCount(s.ctx)
if err != nil {
return errors.Wrap(err, "p2p custody group count")
}
// Get our target custody group count.
targetCustodyGroupCount, err := s.custodyGroupCount(s.ctx)
if err != nil {
return errors.Wrap(err, "custody group count")
}
// If the actual custody group count is already equal to the target, skip the update.
if actualCustodyGrounpCount >= targetCustodyGroupCount {
return nil
}
// Check that all subscribed data column sidecars topics have at least `minimumPeerCount` peers.
topics := s.cfg.p2p.PubSub().GetTopics()
enoughPeers := true
for _, topic := range topics {
if !strings.Contains(topic, p2p.GossipDataColumnSidecarMessage) {
continue
}
if peers := s.cfg.p2p.PubSub().ListPeers(topic); len(peers) < minimumPeerCount {
// If a topic has fewer than the minimum required peers, log a warning.
log.WithFields(logrus.Fields{
"topic": topic,
"peerCount": len(peers),
"minimumPeerCount": minimumPeerCount,
}).Debug("Insufficient peers for data column sidecar topic to maintain custody count")
enoughPeers = false
}
}
if !enoughPeers {
return nil
}
headROBlock, err := s.cfg.chain.HeadBlock(s.ctx)
if err != nil {
return errors.Wrap(err, "head block")
}
headSlot := headROBlock.Block().Slot()
storedEarliestSlot, storedGroupCount, err := s.cfg.p2p.UpdateCustodyInfo(headSlot, targetCustodyGroupCount)
if err != nil {
return errors.Wrap(err, "p2p update custody info")
}
if _, _, err := s.cfg.beaconDB.UpdateCustodyInfo(s.ctx, storedEarliestSlot, storedGroupCount); err != nil {
return errors.Wrap(err, "beacon db update custody info")
}
return nil
}
// custodyGroupCount computes the custody group count based on the custody requirement,
// the validators custody requirement, and whether the node is subscribed to all data subnets.
func (s *Service) custodyGroupCount(context.Context) (uint64, error) {
cfg := params.BeaconConfig()
if flags.Get().Supernode {
return cfg.NumberOfCustodyGroups, nil
}
// Calculate validator custody requirements
validatorsCustodyRequirement, err := s.validatorsCustodyRequirement()
if err != nil {
return 0, errors.Wrap(err, "validators custody requirement")
}
effectiveCustodyRequirement := max(cfg.CustodyRequirement, validatorsCustodyRequirement)
// If we're not in semi-supernode mode, just use the effective requirement.
if !flags.Get().SemiSupernode {
return effectiveCustodyRequirement, nil
}
// Semi-supernode mode custodies the minimum custody groups required for reconstruction.
// This is future-proof and works correctly even if custody groups != columns.
semiSupernodeTarget, err := peerdas.MinimumCustodyGroupCountToReconstruct()
if err != nil {
return 0, errors.Wrap(err, "minimum custody group count")
}
return max(effectiveCustodyRequirement, semiSupernodeTarget), nil
}
// validatorsCustodyRequirements computes the custody requirements based on the
// finalized state and the tracked validators.
func (s *Service) validatorsCustodyRequirement() (uint64, error) {
if s.trackedValidatorsCache == nil {
return 0, nil
}
// Get the indices of the tracked validators.
indices := s.trackedValidatorsCache.Indices()
// Return early if no validators are tracked.
if len(indices) == 0 {
return 0, nil
}
// Retrieve the finalized state.
finalizedState := s.cfg.stateGen.FinalizedState()
if finalizedState == nil || finalizedState.IsNil() {
return 0, nilFinalizedStateError
}
// Compute the validators custody requirements.
result, err := peerdas.ValidatorsCustodyRequirement(finalizedState, indices)
if err != nil {
return 0, errors.Wrap(err, "validators custody requirements")
}
return result, nil
}