# Conflicts: # .github/CODEOWNERS # .travis.yml # README.md # VERSION # accounts/abi/argument.go # accounts/abi/bind/backends/simulated.go # accounts/abi/bind/bind_test.go # accounts/abi/event_test.go # accounts/abi/numbers.go # accounts/abi/numbers_test.go # accounts/abi/reflect.go # accounts/accounts.go # accounts/keystore/keystore.go # accounts/keystore/keystore_wallet.go # accounts/usbwallet/internal/trezor/trezor.go # accounts/usbwallet/ledger.go # accounts/usbwallet/wallet.go # appveyor.yml # build/ci.go # build/goimports.sh # cmd/ethkey/generate.go # cmd/ethkey/inspect.go # cmd/ethkey/main.go # cmd/ethkey/message.go # cmd/ethkey/utils.go # cmd/faucet/faucet.go # cmd/geth/chaincmd.go # cmd/geth/config.go # cmd/geth/main.go # cmd/geth/misccmd.go # cmd/geth/usage.go # cmd/p2psim/main.go # cmd/puppeth/genesis.go # cmd/puppeth/module_dashboard.go # cmd/puppeth/wizard_faucet.go # cmd/puppeth/wizard_genesis.go # cmd/puppeth/wizard_netstats.go # cmd/puppeth/wizard_node.go # cmd/puppeth/wizard_wallet.go # cmd/swarm/config.go # cmd/swarm/config_test.go # cmd/swarm/db.go # cmd/swarm/hash.go # cmd/swarm/main.go # cmd/swarm/manifest.go # cmd/swarm/run_test.go # cmd/swarm/upload.go # cmd/swarm/upload_test.go # cmd/utils/flags.go # cmd/wnode/main.go # common/bytes.go # common/compiler/solidity.go # common/hexutil/hexutil.go # common/math/big.go # common/math/integer.go # common/mclock/mclock.go # common/types.go # common/types_template.go # consensus/clique/clique.go # consensus/consensus.go # consensus/ethash/algorithm.go # consensus/ethash/consensus.go # consensus/ethash/ethash.go # containers/vagrant/Vagrantfile # contracts/ens/ens_test.go # core/asm/compiler.go # core/asm/lexer.go # core/block_validator.go # core/blockchain.go # core/blockchain_test.go # core/chain_makers.go # core/database_util.go # core/database_util_test.go # core/events.go # core/genesis.go # core/genesis_alloc.go # core/genesis_test.go # core/headerchain.go # core/rawdb/accessors_chain.go # core/rawdb/accessors_indexes.go # core/rawdb/accessors_metadata.go # core/rawdb/schema.go # core/state/state_test.go # core/state/statedb.go # core/state/sync.go # core/state_processor.go # core/state_transition.go # core/tx_journal.go # core/tx_list.go # core/tx_pool.go # core/tx_pool_test.go # core/types.go # core/types/block.go # core/types/block_test.go # core/types/gen_receipt_json.go # core/types/log.go # core/types/receipt.go # core/types/transaction.go # core/types/transaction_signing.go # core/types/transaction_signing_test.go # core/types/transaction_test.go # core/vm/errors.go # core/vm/evm.go # core/vm/gas.go # core/vm/gas_table.go # core/vm/instructions.go # core/vm/instructions_test.go # core/vm/interface.go # core/vm/interpreter.go # core/vm/intpool.go # core/vm/jump_table.go # core/vm/logger.go # core/vm/logger_test.go # core/vm/memory_table.go # core/vm/opcodes.go # core/vm/runtime/env.go # core/vm/runtime/runtime.go # crypto/crypto.go # crypto/crypto_test.go # eth/api.go # eth/api_backend.go # eth/api_tracer.go # eth/backend.go # eth/config.go # eth/downloader/downloader.go # eth/downloader/queue.go # eth/downloader/statesync.go # eth/filters/filter.go # eth/filters/filter_system.go # eth/filters/filter_system_test.go # eth/gen_config.go # eth/handler.go # eth/handler_test.go # eth/helper_test.go # eth/protocol.go # eth/sync.go # eth/tracers/internal/tracers/4byte_tracer.js # eth/tracers/internal/tracers/assets.go # eth/tracers/tracer_test.go # eth/tracers/tracers_test.go # ethclient/ethclient.go # ethdb/database.go # ethdb/interface.go # ethdb/memory_database.go # ethstats/ethstats.go # event/feed.go # internal/ethapi/api.go # internal/ethapi/backend.go # internal/guide/guide_test.go # internal/web3ext/web3ext.go # les/api_backend.go # les/backend.go # les/fetcher.go # les/handler.go # les/helper_test.go # les/odr_requests.go # les/odr_test.go # les/retrieve.go # les/server.go # les/serverpool.go # light/lightchain.go # light/odr_test.go # light/postprocess.go # light/txpool.go # log/README.md # log/doc.go # log/format.go # log/handler.go # log/logger.go # log/root.go # metrics/exp/exp.go # metrics/influxdb/influxdb.go # metrics/metrics.go # metrics/resetting_timer.go # metrics/resetting_timer_test.go # metrics/timer_test.go # miner/worker.go # mobile/accounts.go # mobile/ethereum.go # mobile/geth.go # node/config.go # node/doc.go # p2p/discover/database.go # p2p/discover/database_test.go # p2p/discover/table.go # p2p/discover/table_test.go # p2p/discover/udp.go # p2p/discover/udp_test.go # p2p/discv5/udp.go # p2p/enr/enr.go # p2p/enr/enr_test.go # p2p/enr/entries.go # p2p/protocols/protocol.go # p2p/protocols/protocol_test.go # p2p/rlpx_test.go # p2p/server.go # p2p/simulations/adapters/docker.go # p2p/simulations/adapters/exec.go # p2p/simulations/adapters/inproc.go # p2p/simulations/adapters/types.go # p2p/simulations/http.go # p2p/simulations/http_test.go # p2p/simulations/mocker.go # p2p/simulations/network.go # p2p/simulations/network_test.go # p2p/testing/protocolsession.go # params/bootnodes.go # params/config.go # params/denomination.go # params/gas_table.go # params/protocol_params.go # params/version.go # rpc/http.go # rpc/json.go # rpc/utils.go # signer/core/api.go # swarm/api/api.go # swarm/api/api_test.go # swarm/api/client/client.go # swarm/api/client/client_test.go # swarm/api/config.go # swarm/api/config_test.go # swarm/api/filesystem.go # swarm/api/filesystem_test.go # swarm/api/http/error.go # swarm/api/http/error_templates.go # swarm/api/http/error_test.go # swarm/api/http/roundtripper.go # swarm/api/http/server.go # swarm/api/http/server_test.go # swarm/api/http/templates.go # swarm/api/manifest.go # swarm/api/manifest_test.go # swarm/api/storage.go # swarm/api/storage_test.go # swarm/api/uri.go # swarm/api/uri_test.go # swarm/fuse/fuse_dir.go # swarm/fuse/fuse_file.go # swarm/fuse/swarmfs.go # swarm/fuse/swarmfs_test.go # swarm/fuse/swarmfs_unix.go # swarm/fuse/swarmfs_util.go # swarm/metrics/flags.go # swarm/network/depo.go # swarm/network/forwarding.go # swarm/network/hive.go # swarm/network/kademlia/address.go # swarm/network/kademlia/kaddb.go # swarm/network/kademlia/kademlia.go # swarm/network/kademlia/kademlia_test.go # swarm/network/messages.go # swarm/network/protocol.go # swarm/network/syncdb.go # swarm/network/syncdb_test.go # swarm/network/syncer.go # swarm/services/swap/swap.go # swarm/services/swap/swap/swap.go # swarm/storage/chunker.go # swarm/storage/chunker_test.go # swarm/storage/common_test.go # swarm/storage/database.go # swarm/storage/dbstore.go # swarm/storage/dbstore_test.go # swarm/storage/dpa.go # swarm/storage/dpa_test.go # swarm/storage/localstore.go # swarm/storage/memstore.go # swarm/storage/netstore.go # swarm/storage/pyramid.go # swarm/storage/swarmhasher.go # swarm/storage/types.go # swarm/swarm.go # swarm/swarm_test.go # swarm/testutil/http.go # tests/block_test_util.go # tests/difficulty_test.go # tests/init.go # tests/state_test_util.go # tests/transaction_test.go # tests/util.go # tests/vm_test_util.go # trie/database.go # trie/encoding.go # trie/hasher.go # trie/iterator.go # trie/proof.go # trie/proof_test.go # trie/secure_trie.go # trie/sync.go # trie/sync_test.go # trie/trie.go # vendor/github.com/docker/docker/pkg/reexec/command_linux.go # vendor/github.com/docker/docker/pkg/reexec/command_unix.go # vendor/github.com/docker/docker/pkg/reexec/command_unsupported.go # vendor/github.com/docker/docker/pkg/reexec/command_windows.go # vendor/github.com/docker/docker/pkg/reexec/reexec.go # vendor/github.com/eapache/channels/.gitignore # vendor/github.com/eapache/queue/.gitignore # vendor/github.com/naoina/toml/encode.go # vendor/github.com/naoina/toml/parse.go # vendor/github.com/naoina/toml/parse.peg # vendor/github.com/naoina/toml/parse.peg.go # vendor/github.com/rcrowley/go-metrics/.gitignore # vendor/github.com/rcrowley/go-metrics/.travis.yml # vendor/github.com/rcrowley/go-metrics/README.md # vendor/github.com/rcrowley/go-metrics/counter.go # vendor/github.com/rcrowley/go-metrics/debug.go # vendor/github.com/rcrowley/go-metrics/ewma.go # vendor/github.com/rcrowley/go-metrics/exp/exp.go # vendor/github.com/rcrowley/go-metrics/gauge.go # vendor/github.com/rcrowley/go-metrics/gauge_float64.go # vendor/github.com/rcrowley/go-metrics/graphite.go # vendor/github.com/rcrowley/go-metrics/healthcheck.go # vendor/github.com/rcrowley/go-metrics/histogram.go # vendor/github.com/rcrowley/go-metrics/json.go # vendor/github.com/rcrowley/go-metrics/log.go # vendor/github.com/rcrowley/go-metrics/meter.go # vendor/github.com/rcrowley/go-metrics/metrics.go # vendor/github.com/rcrowley/go-metrics/opentsdb.go # vendor/github.com/rcrowley/go-metrics/registry.go # vendor/github.com/rcrowley/go-metrics/runtime.go # vendor/github.com/rcrowley/go-metrics/sample.go # vendor/github.com/rcrowley/go-metrics/syslog.go # vendor/github.com/rcrowley/go-metrics/timer.go # vendor/github.com/rcrowley/go-metrics/writer.go # vendor/github.com/syndtr/goleveldb/leveldb/db.go # vendor/golang.org/x/sys/unix/mksysnum_linux.pl # vendor/golang.org/x/sys/unix/types_linux.go # vendor/vendor.json # whisper/shhclient/client.go # whisper/whisperv5/api.go # whisper/whisperv5/peer_test.go # whisper/whisperv5/whisper.go # whisper/whisperv6/api.go # whisper/whisperv6/peer_test.go # whisper/whisperv6/whisper.go |
||
---|---|---|
.. | ||
bitvector | ||
priorityqueue | ||
simulations | ||
stream | ||
README.md | ||
common.go | ||
discovery.go | ||
discovery_test.go | ||
hive.go | ||
hive_test.go | ||
kademlia.go | ||
kademlia_test.go | ||
protocol.go | ||
protocol_test.go |
README.md
Streaming
Streaming is a new protocol of the swarm bzz bundle of protocols. This protocol provides the basic logic for chunk-based data flow. It implements simple retrieve requests and delivery using priority queue. A data exchange stream is a directional flow of chunks between peers. The source of datachunks is the upstream, the receiver is called the downstream peer. Each streaming protocol defines an outgoing streamer and an incoming streamer, the former installing on the upstream, the latter on the downstream peer.
Subscribe on StreamerPeer launches an incoming streamer that sends a subscribe msg upstream. The streamer on the upstream peer handles the subscribe msg by installing the relevant outgoing streamer . The modules now engage in a process of upstream sending a sequence of hashes of chunks downstream (OfferedHashesMsg). The downstream peer evaluates which hashes are needed and get it delivered by sending back a msg (WantedHashesMsg).
Historical syncing is supported - currently not the right abstraction -- state kept across sessions by saving a series of intervals after their last batch actually arrived.
Live streaming is also supported, by starting session from the first item after the subscription.
Provable data exchange. In case a stream represents a swarm document's data layer or higher level chunks, streaming up to a certain index is always provable. It saves on sending intermediate chunks.
Using the streamer logic, various stream types are easy to implement:
- light node requests:
- url lookup with offset
- document download
- document upload
- syncing
- live session syncing
- historical syncing
- simple retrieve requests and deliveries
- mutable resource updates streams
- receipting for finger pointing
Syncing
Syncing is the process that makes sure storer nodes end up storing all and only the chunks that are requested from them.
Requirements
- eventual consistency: so each chunk historical should be syncable
- since the same chunk can and will arrive from many peers, (network traffic should be optimised, only one transfer of data per chunk)
- explicit request deliveries should be prioritised higher than recent chunks received during the ongoing session which in turn should be higher than historical chunks.
- insured chunks should get receipted for finger pointing litigation, the receipts storage should be organised efficiently, upstream peer should also be able to find these receipts for a deleted chunk easily to refute their challenge.
- syncing should be resilient to cut connections, metadata should be persisted that keep track of syncing state across sessions, historical syncing state should survive restart
- extra data structures to support syncing should be kept at minimum
- syncing is organized separately for chunk types (resource update v content chunk)
- various types of streams should have common logic abstracted
Syncing is now entirely mediated by the localstore, ie., no processes or memory leaks due to network contention. When a new chunk is stored, its chunk hash is index by proximity bin
peers syncronise by getting the chunks closer to the downstream peer than to the upstream one. Consequently peers just sync all stored items for the kad bin the receiving peer falls into. The special case of nearest neighbour sets is handled by the downstream peer indicating they want to sync all kademlia bins with proximity equal to or higher than their depth.
This sync state represents the initial state of a sync connection session. Retrieval is dictated by downstream peers simply using a special streamer protocol.
Syncing chunks created during the session by the upstream peer is called live session syncing while syncing of earlier chunks is historical syncing.
Once the relevant chunk is retrieved, downstream peer looks up all hash segments in its localstore
and sends to the upstream peer a message with a a bitvector to indicate
missing chunks (e.g., for chunk k
, hash with chunk internal index which case )
new items. In turn upstream peer sends the relevant chunk data alongside their index.
On sending chunks there is a priority queue system. If during looking up hashes in its localstore, downstream peer hits on an open request then a retrieve request is sent immediately to the upstream peer indicating that no extra round of checks is needed. If another peers syncer hits the same open request, it is slightly unsafe to not ask that peer too: if the first one disconnects before delivering or fails to deliver and therefore gets disconnected, we should still be able to continue with the other. The minimum redundant traffic coming from such simultaneous eventualities should be sufficiently rare not to warrant more complex treatment.
Session syncing involves downstream peer to request a new state on a bin from upstream. using the new state, the range (of chunks) between the previous state and the new one are retrieved and chunks are requested identical to the historical case. After receiving all the missing chunks from the new hashes, downstream peer will request a new range. If this happens before upstream peer updates a new state, we say that session syncing is live or the two peers are in sync. In general the time interval passed since downstream peer request up to the current session cursor is a good indication of a permanent (probably increasing) lag.
If there is no historical backlog, and downstream peer has an acceptable 'last synced' tag, then it is said to be fully synced with the upstream peer. If a peer is fully synced with all its storer peers, it can advertise itself as globally fully synced.
The downstream peer persists the record of the last synced offset. When the two peers disconnect and reconnect syncing can start from there. This situation however can also happen while historical syncing is not yet complete. Effectively this means that the peer needs to persist a record of an arbitrary array of offset ranges covered.
Delivery requests
once the appropriate ranges of the hashstream are retrieved and buffered, downstream peer just scans the hashes, looks them up in localstore, if not found, create a request entry. The range is referenced by the chunk index. Alongside the name (indicating the stream, e.g., content chunks for bin 6) and the range downstream peer sends a 128 long bitvector indicating which chunks are needed. Newly created requests are satisfied bound together in a waitgroup which when done, will promptt sending the next one. to be able to do check and storage concurrently, we keep a buffer of one, we start with two batches of hashes. If there is nothing to give, upstream peers SetNextBatch is blocking. Subscription ends with an unsubscribe. which removes the syncer from the map.
Canceling requests (for instance the late chunks of an erasure batch) should be a chan closed on the request
Simple request is also a subscribe different streaming protocols are different p2p protocols with same message types. the constructor is the Run function itself. which takes a streamerpeer as argument
provable streams
The swarm hash over the hash stream has many advantages. It implements a provable data transfer and provide efficient storage for receipts in the form of inclusion proofs useable for finger pointing litigation. When challenged on a missing chunk, upstream peer will provide an inclusion proof of a chunk hash against the state of the sync stream. In order to be able to generate such an inclusion proof, upstream peer needs to store the hash index (counting consecutive hash-size segments) alongside the chunk data and preserve it even when the chunk data is deleted until the chunk is no longer insured. if there is no valid insurance on the files the entry may be deleted. As long as the chunk is preserved, no takeover proof will be needed since the node can respond to any challenge. However, once the node needs to delete an insured chunk for capacity reasons, a receipt should be available to refute the challenge by finger pointing to a downstream peer. As part of the deletion protocol then, hashes of insured chunks to be removed are pushed to an infinite stream for every bin.
Downstream peer on the other hand needs to make sure that they can only be finger pointed about a chunk they did receive and store. For this the check of a state should be exhaustive. If historical syncing finishes on one state, all hashes before are covered, no surprises. In other words historical syncing this process is self verifying. With session syncing however, it is not enough to check going back covering the range from old offset to new. Continuity (i.e., that the new state is extension of the old) needs to be verified: after downstream peer reads the range into a buffer, it appends the buffer the last known state at the last known offset and verifies the resulting hash matches the latest state. Past intervals of historical syncing are checked via the the session root. Upstream peer signs the states, downstream peers can use as handover proofs. Downstream peers sign off on a state together with an initial offset.
Once historical syncing is complete and the session does not lag, downstream peer only preserves the latest upstream state and store the signed version.
Upstream peer needs to keep the latest takeover states: each deleted chunk's hash should be covered by takeover proof of at least one peer. If historical syncing is complete, upstream peer typically will store only the latest takeover proof from downstream peer. Crucially, the structure is totally independent of the number of peers in the bin, so it scales extremely well.
implementation
The simplest protocol just involves upstream peer to prefix the key with the kademlia proximity order (say 0-15 or 0-31) and simply iterate on index per bin when syncing with a peer.
priority queues are used for sending chunks so that user triggered requests should be responded to first, session syncing second, and historical with lower priority. The request on chunks remains implemented as a dataless entry in the memory store. The lifecycle of this object should be more carefully thought through, ie., when it fails to retrieve it should be removed.