Jordan Hrycaj 8c7d91512b
Prep for full sync after snap mark2 (#1263)
* Rename `LeafRange` => `NodeTagRange`

* Replacing storage slot partition point by interval

why:
  The partition point only allows to describe slots `[point,high(Uint256)]`
  for fetching interval slot ranges. This has been generalised for any
  interval.

* Replacing `SnapAccountRanges` by `SnapTrieRangeBatch`

why:
  Generalised healing status for accounts, and later for storage slots.

* Improve accounts healing loop

* Split `snap_db` into accounts and storage modules

why:
  It is cleaner to have separate session descriptors for accounts and
  storage slots (based on a common base descriptor.)

  Also, persistent storage handling might be changed in future which
  requires the storage slot implementation disentangled from the accounts
  handling.

* Re-model worker queues for storage slots

why:
  There is a dynamic list of storage sub-tries, each one has to be
  treated similar to the accounts database. This applied to slot
  interval downloads as well as to healing

* Compress some return value report lists for snapdb methods

why:
  No need to report all handling details for work items that are filteres
  out and discarded, anyway.

* Remove inner loop frame from healing function

why:
  The healing function runs as a loop body already.
2022-10-14 17:40:32 +01:00

105 lines
2.8 KiB
Nim

# Nimbus
# Copyright (c) 2021 Status Research & Development GmbH
# Licensed under either of
# * Apache License, version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or
# http://www.apache.org/licenses/LICENSE-2.0)
# * MIT license ([LICENSE-MIT](LICENSE-MIT) or
# http://opensource.org/licenses/MIT)
# at your option. This file may not be copied, modified, or distributed
# except according to those terms.
import
chronos,
../../../sync_desc
const
comErrorsTimeoutMax* = 2
## Maximal number of non-resonses accepted in a row. If there are more than
## `comErrorsTimeoutMax` consecutive errors, the worker will be degraded
## as zombie.
type
ComErrorStatsRef* = ref object
## particular error counters so connections will not be cut immediately
## after a particular error.
nTimeouts*: uint
nNetwork*: uint
ComError* = enum
ComNothingSerious
ComAccountsMaxTooLarge
ComAccountsMinTooSmall
ComEmptyAccountsArguments
ComEmptyPartialRange
ComEmptyRequestArguments
ComMissingProof
ComNetworkProblem
ComNoAccountsForStateRoot
ComNoByteCodesAvailable
ComNoDataForProof
ComNoHeaderAvailable
ComNoStorageForAccounts
ComNoTrieNodesAvailable
ComResponseTimeout
ComTooManyByteCodes
ComTooManyHeaders
ComTooManyStorageSlots
ComTooManyTrieNodes
# Other errors not directly related to communication
ComInspectDbFailed
ComImportAccountsFailed
proc stopAfterSeriousComError*(
ctrl: BuddyCtrlRef;
error: ComError;
stats: ComErrorStatsRef;
): Future[bool]
{.async.} =
## Error handling after data protocol failed.
case error:
of ComResponseTimeout:
stats.nTimeouts.inc
if comErrorsTimeoutMax < stats.nTimeouts:
# Mark this peer dead, i.e. avoid fetching from this peer for a while
ctrl.zombie = true
else:
# Otherwise try again some time later. Nevertheless, stop the
# current action.
await sleepAsync(5.seconds)
return true
of ComNetworkProblem,
ComMissingProof,
ComAccountsMinTooSmall,
ComAccountsMaxTooLarge:
stats.nNetwork.inc
# Mark this peer dead, i.e. avoid fetching from this peer for a while
ctrl.zombie = true
return true
of ComEmptyAccountsArguments,
ComEmptyRequestArguments,
ComEmptyPartialRange,
ComInspectDbFailed,
ComImportAccountsFailed,
ComNoDataForProof,
ComNothingSerious:
discard
of ComNoAccountsForStateRoot,
ComNoStorageForAccounts,
ComNoByteCodesAvailable,
ComNoHeaderAvailable,
ComNoTrieNodesAvailable,
ComTooManyByteCodes,
ComTooManyHeaders,
ComTooManyStorageSlots,
ComTooManyTrieNodes:
# Mark this peer dead, i.e. avoid fetching from this peer for a while
ctrl.zombie = true
return true
# End