ipld-eth-state-snapshot/cmd/stateSnapshot.go

106 lines
4.8 KiB
Go
Raw Normal View History

2020-06-30 16:54:10 +00:00
// Copyright © 2020 Vulcanize, Inc
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
package cmd
import (
"fmt"
2020-07-01 18:44:59 +00:00
"github.com/sirupsen/logrus"
2020-06-30 16:54:10 +00:00
"github.com/spf13/cobra"
2020-07-01 18:44:59 +00:00
"github.com/spf13/viper"
2021-12-14 06:50:19 +00:00
"github.com/vulcanize/ipld-eth-state-snapshot/pkg/snapshot"
2020-06-30 16:54:10 +00:00
)
// stateSnapshotCmd represents the stateSnapshot command
var stateSnapshotCmd = &cobra.Command{
Use: "stateSnapshot",
2020-07-01 18:44:59 +00:00
Short: "Extract the entire Ethereum state from leveldb and publish into PG-IPFS",
2020-07-15 04:43:11 +00:00
Long: `Usage
2020-06-30 16:54:10 +00:00
./ipld-eth-state-snapshot stateSnapshot --config={path to toml config file}`,
2020-06-30 16:54:10 +00:00
Run: func(cmd *cobra.Command, args []string) {
2020-07-01 18:44:59 +00:00
subCommand = cmd.CalledAs()
logWithCommand = *logrus.WithField("SubCommand", subCommand)
stateSnapshot()
2020-06-30 16:54:10 +00:00
},
}
2020-07-01 18:44:59 +00:00
func stateSnapshot() {
2022-05-18 03:23:38 +00:00
modeStr := viper.GetString(snapshot.SNAPSHOT_MODE_TOML)
mode := snapshot.SnapshotMode(modeStr)
config, err := snapshot.NewConfig(mode)
if err != nil {
2022-05-26 10:20:42 +00:00
logWithCommand.Fatalf("unable to initialize config: %v", err)
}
logWithCommand.Infof("opening levelDB and ancient data at %s and %s",
config.Eth.LevelDBPath, config.Eth.AncientDBPath)
edb, err := snapshot.NewLevelDB(config.Eth)
2022-01-11 00:59:26 +00:00
if err != nil {
logWithCommand.Fatal(err)
}
2022-05-18 03:23:38 +00:00
height := viper.GetInt64(snapshot.SNAPSHOT_BLOCK_HEIGHT_TOML)
recoveryFile := viper.GetString(snapshot.SNAPSHOT_RECOVERY_FILE_TOML)
if recoveryFile == "" {
recoveryFile = fmt.Sprintf("./%d_snapshot_recovery", height)
2022-06-08 12:08:17 +00:00
logWithCommand.Infof("no recovery file set, using default: %s", recoveryFile)
}
pub, err := snapshot.NewPublisher(mode, config)
2022-01-11 05:37:27 +00:00
if err != nil {
logWithCommand.Fatal(err)
}
snapshotService, err := snapshot.NewSnapshotService(edb, pub, recoveryFile)
2020-07-01 18:44:59 +00:00
if err != nil {
logWithCommand.Fatal(err)
}
2022-05-18 03:23:38 +00:00
workers := viper.GetUint(snapshot.SNAPSHOT_WORKERS_TOML)
if height < 0 {
Account selective snapshot (#46) * snapshotter ignores nodes not along a path along those derived from a list of account addresses if one is provided * config and env updates * cmd update * Encode watched address path bytes to hex for comparison * actually ignore the subtries that are not along the paths of interest * Fixes for account selective snapshot * Use non-concurrent iterator when having a single worker * Only index root node when starting path of an iterator is nil * Upgrade deps * Avoid tracking iterators and skip recovery test * Fix recovery mechanism, use sync Map instead of buffered channels * Add test for account selective snapshot * Continue traversal with concurrent iterators with starting path nil * Use errgroup to simplify error handling with concurrent iterators * Check if all the nodes are indexed in the recovery test * Use concurrency safe sync Map in account selective snapshot test * Only track concurrent iterators and refactor code * Fix node and recovered path comparison * Revert back to using buffered channels for tracking iterators * Add a metric to monitor number of active iterators * Update docs * Update seeked path after node is processed * Return error on context cancellation from subtrie iteration * Add tests for account selective snapshot recovery * Explicity enforce concurrent iterator bounds to avoid duplicate nodes * Update full snapshot test to check nodes being indexed * Refactor code to simplify snapshot logic * Remove unnecessary function argument * Use ctx cancellation for handling signals * Add descriptive comments Co-authored-by: prathamesh0 <prathamesh.musale0@gmail.com>
2022-08-03 11:35:04 +00:00
if err := snapshotService.CreateLatestSnapshot(workers, config.Service.AllowedAccounts); err != nil {
logWithCommand.Fatal(err)
}
} else {
Account selective snapshot (#46) * snapshotter ignores nodes not along a path along those derived from a list of account addresses if one is provided * config and env updates * cmd update * Encode watched address path bytes to hex for comparison * actually ignore the subtries that are not along the paths of interest * Fixes for account selective snapshot * Use non-concurrent iterator when having a single worker * Only index root node when starting path of an iterator is nil * Upgrade deps * Avoid tracking iterators and skip recovery test * Fix recovery mechanism, use sync Map instead of buffered channels * Add test for account selective snapshot * Continue traversal with concurrent iterators with starting path nil * Use errgroup to simplify error handling with concurrent iterators * Check if all the nodes are indexed in the recovery test * Use concurrency safe sync Map in account selective snapshot test * Only track concurrent iterators and refactor code * Fix node and recovered path comparison * Revert back to using buffered channels for tracking iterators * Add a metric to monitor number of active iterators * Update docs * Update seeked path after node is processed * Return error on context cancellation from subtrie iteration * Add tests for account selective snapshot recovery * Explicity enforce concurrent iterator bounds to avoid duplicate nodes * Update full snapshot test to check nodes being indexed * Refactor code to simplify snapshot logic * Remove unnecessary function argument * Use ctx cancellation for handling signals * Add descriptive comments Co-authored-by: prathamesh0 <prathamesh.musale0@gmail.com>
2022-08-03 11:35:04 +00:00
params := snapshot.SnapshotParams{Workers: workers, Height: uint64(height), WatchedAddresses: config.Service.AllowedAccounts}
2020-08-20 10:23:36 +00:00
if err := snapshotService.CreateSnapshot(params); err != nil {
logWithCommand.Fatal(err)
}
2020-07-01 18:44:59 +00:00
}
2020-07-15 04:43:11 +00:00
logWithCommand.Infof("state snapshot at height %d is complete", height)
2020-07-01 18:44:59 +00:00
}
2020-06-30 16:54:10 +00:00
func init() {
rootCmd.AddCommand(stateSnapshotCmd)
2022-05-18 03:23:38 +00:00
stateSnapshotCmd.PersistentFlags().String(snapshot.LVL_DB_PATH_CLI, "", "path to primary datastore")
stateSnapshotCmd.PersistentFlags().String(snapshot.ANCIENT_DB_PATH_CLI, "", "path to ancient datastore")
stateSnapshotCmd.PersistentFlags().String(snapshot.SNAPSHOT_BLOCK_HEIGHT_CLI, "", "block height to extract state at")
stateSnapshotCmd.PersistentFlags().Int(snapshot.SNAPSHOT_WORKERS_CLI, 1, "number of concurrent workers to use")
stateSnapshotCmd.PersistentFlags().String(snapshot.SNAPSHOT_RECOVERY_FILE_CLI, "", "file to recover from a previous iteration")
stateSnapshotCmd.PersistentFlags().String(snapshot.SNAPSHOT_MODE_CLI, "postgres", "output mode for snapshot ('file' or 'postgres')")
stateSnapshotCmd.PersistentFlags().String(snapshot.FILE_OUTPUT_DIR_CLI, "", "directory for writing ouput to while operating in 'file' mode")
Account selective snapshot (#46) * snapshotter ignores nodes not along a path along those derived from a list of account addresses if one is provided * config and env updates * cmd update * Encode watched address path bytes to hex for comparison * actually ignore the subtries that are not along the paths of interest * Fixes for account selective snapshot * Use non-concurrent iterator when having a single worker * Only index root node when starting path of an iterator is nil * Upgrade deps * Avoid tracking iterators and skip recovery test * Fix recovery mechanism, use sync Map instead of buffered channels * Add test for account selective snapshot * Continue traversal with concurrent iterators with starting path nil * Use errgroup to simplify error handling with concurrent iterators * Check if all the nodes are indexed in the recovery test * Use concurrency safe sync Map in account selective snapshot test * Only track concurrent iterators and refactor code * Fix node and recovered path comparison * Revert back to using buffered channels for tracking iterators * Add a metric to monitor number of active iterators * Update docs * Update seeked path after node is processed * Return error on context cancellation from subtrie iteration * Add tests for account selective snapshot recovery * Explicity enforce concurrent iterator bounds to avoid duplicate nodes * Update full snapshot test to check nodes being indexed * Refactor code to simplify snapshot logic * Remove unnecessary function argument * Use ctx cancellation for handling signals * Add descriptive comments Co-authored-by: prathamesh0 <prathamesh.musale0@gmail.com>
2022-08-03 11:35:04 +00:00
stateSnapshotCmd.PersistentFlags().StringArray(snapshot.SNAPSHOT_ACCOUNTS_CLI, nil, "list of account addresses to limit snapshot to")
2020-06-30 16:54:10 +00:00
2022-05-18 03:23:38 +00:00
viper.BindPFlag(snapshot.LVL_DB_PATH_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.LVL_DB_PATH_CLI))
viper.BindPFlag(snapshot.ANCIENT_DB_PATH_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.ANCIENT_DB_PATH_CLI))
viper.BindPFlag(snapshot.SNAPSHOT_BLOCK_HEIGHT_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.SNAPSHOT_BLOCK_HEIGHT_CLI))
viper.BindPFlag(snapshot.SNAPSHOT_WORKERS_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.SNAPSHOT_WORKERS_CLI))
viper.BindPFlag(snapshot.SNAPSHOT_RECOVERY_FILE_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.SNAPSHOT_RECOVERY_FILE_CLI))
viper.BindPFlag(snapshot.SNAPSHOT_MODE_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.SNAPSHOT_MODE_CLI))
viper.BindPFlag(snapshot.FILE_OUTPUT_DIR_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.FILE_OUTPUT_DIR_CLI))
Account selective snapshot (#46) * snapshotter ignores nodes not along a path along those derived from a list of account addresses if one is provided * config and env updates * cmd update * Encode watched address path bytes to hex for comparison * actually ignore the subtries that are not along the paths of interest * Fixes for account selective snapshot * Use non-concurrent iterator when having a single worker * Only index root node when starting path of an iterator is nil * Upgrade deps * Avoid tracking iterators and skip recovery test * Fix recovery mechanism, use sync Map instead of buffered channels * Add test for account selective snapshot * Continue traversal with concurrent iterators with starting path nil * Use errgroup to simplify error handling with concurrent iterators * Check if all the nodes are indexed in the recovery test * Use concurrency safe sync Map in account selective snapshot test * Only track concurrent iterators and refactor code * Fix node and recovered path comparison * Revert back to using buffered channels for tracking iterators * Add a metric to monitor number of active iterators * Update docs * Update seeked path after node is processed * Return error on context cancellation from subtrie iteration * Add tests for account selective snapshot recovery * Explicity enforce concurrent iterator bounds to avoid duplicate nodes * Update full snapshot test to check nodes being indexed * Refactor code to simplify snapshot logic * Remove unnecessary function argument * Use ctx cancellation for handling signals * Add descriptive comments Co-authored-by: prathamesh0 <prathamesh.musale0@gmail.com>
2022-08-03 11:35:04 +00:00
viper.BindPFlag(snapshot.SNAPSHOT_ACCOUNTS_TOML, stateSnapshotCmd.PersistentFlags().Lookup(snapshot.SNAPSHOT_ACCOUNTS_CLI))
2020-06-30 16:54:10 +00:00
}