0
0
Fork 0
mirror of https://github.com/bitcoin/bitcoin.git synced 2025-02-13 11:25:02 -05:00
bitcoin-bitcoin-core/src/addrdb.cpp
Andrew Chow ba3d32715f
Merge bitcoin/bitcoin#26847: p2p: track AddrMan totals by network and table, improve precision of adding fixed seeds
80f39c99ef addrman, refactor: combine two size functions (Amiti Uttarwar)
4885d6f197 addrman, refactor: move count increment into Create() (Martin Zumsande)
c77c877a8e net: Load fixed seeds from reachable networks for which we don't have addresses (Martin Zumsande)
d35595a78a addrman: add function to return size by network and table (Martin Zumsande)

Pull request description:

  AddrMan currently doesn't track the number of its entries by network, it only knows the total number of addresses. This PR makes AddrMan keep track of these numbers, which would be helpful for multiple things:

  1. Allow to specifically add fixed seeds to AddrMan of networks where we don't have any addresses yet - even if AddrMan as a whole is not empty (partly fixing #26035). This is in particular helpful if the user abruptly changes `-onlynet` settings (such that addrs that used to be reachable are no longer and vice versa), in which case they currently could get stuck and not find any outbound peers. The second commit of this PR implements this.
  1. (Future work): Add logic for automatic connection management with respect to networks - such as making attempts to have at least one connection to each reachable network as suggested [here](https://github.com/bitcoin/bitcoin/issues/26035#issuecomment-1249420209). This would involve requesting an address from a particular network from AddrMan, and expanding its corresponding function `AddrMan::Select()`  to do this requires internal knowledge of the current number of addresses for each network and table to avoid getting stuck in endless loops.
  1. (Future work): Perhaps display the totals to users. At least I would find this helpful to debug, the existing option (`./bitcoin-cli -addrinfo`) is rather indirect by doing the aggregation itself in each call, doesn't distinguish between new and tried, and being based on `AddrMan::GetAddr()` it's also subject to a quality filter which we probably don't want in this spot.

ACKs for top commit:
  naumenkogs:
    utACK 80f39c9
  stratospher:
    ACK 80f39c9
  achow101:
    ACK 80f39c99ef
  vasild:
    ACK 80f39c99ef

Tree-SHA512: 6359f2e3f4db7c120c0789d92d74cb7d87a2ceedb7d6a34b5eff20c7f55c5c81092d10ed94efe29afc1c66947820a0d9c14876ee0c8d1f8e068a6df4e1131927
2023-01-31 16:08:44 -05:00

234 lines
8 KiB
C++

// Copyright (c) 2009-2010 Satoshi Nakamoto
// Copyright (c) 2009-2022 The Bitcoin Core developers
// Distributed under the MIT software license, see the accompanying
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
#include <addrdb.h>
#include <addrman.h>
#include <chainparams.h>
#include <clientversion.h>
#include <cstdint>
#include <fs.h>
#include <hash.h>
#include <logging/timer.h>
#include <netbase.h>
#include <netgroup.h>
#include <random.h>
#include <streams.h>
#include <tinyformat.h>
#include <univalue.h>
#include <util/settings.h>
#include <util/system.h>
#include <util/translation.h>
namespace {
class DbNotFoundError : public std::exception
{
using std::exception::exception;
};
template <typename Stream, typename Data>
bool SerializeDB(Stream& stream, const Data& data)
{
// Write and commit header, data
try {
HashedSourceWriter hashwriter{stream};
hashwriter << Params().MessageStart() << data;
stream << hashwriter.GetHash();
} catch (const std::exception& e) {
return error("%s: Serialize or I/O error - %s", __func__, e.what());
}
return true;
}
template <typename Data>
bool SerializeFileDB(const std::string& prefix, const fs::path& path, const Data& data, int version)
{
// Generate random temporary filename
const uint16_t randv{GetRand<uint16_t>()};
std::string tmpfn = strprintf("%s.%04x", prefix, randv);
// open temp output file, and associate with CAutoFile
fs::path pathTmp = gArgs.GetDataDirNet() / fs::u8path(tmpfn);
FILE *file = fsbridge::fopen(pathTmp, "wb");
CAutoFile fileout(file, SER_DISK, version);
if (fileout.IsNull()) {
fileout.fclose();
remove(pathTmp);
return error("%s: Failed to open file %s", __func__, fs::PathToString(pathTmp));
}
// Serialize
if (!SerializeDB(fileout, data)) {
fileout.fclose();
remove(pathTmp);
return false;
}
if (!FileCommit(fileout.Get())) {
fileout.fclose();
remove(pathTmp);
return error("%s: Failed to flush file %s", __func__, fs::PathToString(pathTmp));
}
fileout.fclose();
// replace existing file, if any, with new file
if (!RenameOver(pathTmp, path)) {
remove(pathTmp);
return error("%s: Rename-into-place failed", __func__);
}
return true;
}
template <typename Stream, typename Data>
void DeserializeDB(Stream& stream, Data& data, bool fCheckSum = true)
{
CHashVerifier<Stream> verifier(&stream);
// de-serialize file header (network specific magic number) and ..
unsigned char pchMsgTmp[4];
verifier >> pchMsgTmp;
// ... verify the network matches ours
if (memcmp(pchMsgTmp, Params().MessageStart(), sizeof(pchMsgTmp))) {
throw std::runtime_error{"Invalid network magic number"};
}
// de-serialize data
verifier >> data;
// verify checksum
if (fCheckSum) {
uint256 hashTmp;
stream >> hashTmp;
if (hashTmp != verifier.GetHash()) {
throw std::runtime_error{"Checksum mismatch, data corrupted"};
}
}
}
template <typename Data>
void DeserializeFileDB(const fs::path& path, Data& data, int version)
{
// open input file, and associate with CAutoFile
FILE* file = fsbridge::fopen(path, "rb");
CAutoFile filein(file, SER_DISK, version);
if (filein.IsNull()) {
throw DbNotFoundError{};
}
DeserializeDB(filein, data);
}
} // namespace
CBanDB::CBanDB(fs::path ban_list_path)
: m_banlist_dat(ban_list_path + ".dat"),
m_banlist_json(ban_list_path + ".json")
{
}
bool CBanDB::Write(const banmap_t& banSet)
{
std::vector<std::string> errors;
if (util::WriteSettings(m_banlist_json, {{JSON_KEY, BanMapToJson(banSet)}}, errors)) {
return true;
}
for (const auto& err : errors) {
error("%s", err);
}
return false;
}
bool CBanDB::Read(banmap_t& banSet)
{
if (fs::exists(m_banlist_dat)) {
LogPrintf("banlist.dat ignored because it can only be read by " PACKAGE_NAME " version 22.x. Remove %s to silence this warning.\n", fs::quoted(fs::PathToString(m_banlist_dat)));
}
// If the JSON banlist does not exist, then recreate it
if (!fs::exists(m_banlist_json)) {
return false;
}
std::map<std::string, util::SettingsValue> settings;
std::vector<std::string> errors;
if (!util::ReadSettings(m_banlist_json, settings, errors)) {
for (const auto& err : errors) {
LogPrintf("Cannot load banlist %s: %s\n", fs::PathToString(m_banlist_json), err);
}
return false;
}
try {
BanMapFromJson(settings[JSON_KEY], banSet);
} catch (const std::runtime_error& e) {
LogPrintf("Cannot parse banlist %s: %s\n", fs::PathToString(m_banlist_json), e.what());
return false;
}
return true;
}
bool DumpPeerAddresses(const ArgsManager& args, const AddrMan& addr)
{
const auto pathAddr = args.GetDataDirNet() / "peers.dat";
return SerializeFileDB("peers", pathAddr, addr, CLIENT_VERSION);
}
void ReadFromStream(AddrMan& addr, CDataStream& ssPeers)
{
DeserializeDB(ssPeers, addr, false);
}
std::optional<bilingual_str> LoadAddrman(const NetGroupManager& netgroupman, const ArgsManager& args, std::unique_ptr<AddrMan>& addrman)
{
auto check_addrman = std::clamp<int32_t>(args.GetIntArg("-checkaddrman", DEFAULT_ADDRMAN_CONSISTENCY_CHECKS), 0, 1000000);
addrman = std::make_unique<AddrMan>(netgroupman, /*deterministic=*/false, /*consistency_check_ratio=*/check_addrman);
const auto start{SteadyClock::now()};
const auto path_addr{args.GetDataDirNet() / "peers.dat"};
try {
DeserializeFileDB(path_addr, *addrman, CLIENT_VERSION);
LogPrintf("Loaded %i addresses from peers.dat %dms\n", addrman->Size(), Ticks<std::chrono::milliseconds>(SteadyClock::now() - start));
} catch (const DbNotFoundError&) {
// Addrman can be in an inconsistent state after failure, reset it
addrman = std::make_unique<AddrMan>(netgroupman, /*deterministic=*/false, /*consistency_check_ratio=*/check_addrman);
LogPrintf("Creating peers.dat because the file was not found (%s)\n", fs::quoted(fs::PathToString(path_addr)));
DumpPeerAddresses(args, *addrman);
} catch (const InvalidAddrManVersionError&) {
if (!RenameOver(path_addr, (fs::path)path_addr + ".bak")) {
addrman = nullptr;
return strprintf(_("Failed to rename invalid peers.dat file. Please move or delete it and try again."));
}
// Addrman can be in an inconsistent state after failure, reset it
addrman = std::make_unique<AddrMan>(netgroupman, /*deterministic=*/false, /*consistency_check_ratio=*/check_addrman);
LogPrintf("Creating new peers.dat because the file version was not compatible (%s). Original backed up to peers.dat.bak\n", fs::quoted(fs::PathToString(path_addr)));
DumpPeerAddresses(args, *addrman);
} catch (const std::exception& e) {
addrman = nullptr;
return strprintf(_("Invalid or corrupt peers.dat (%s). If you believe this is a bug, please report it to %s. As a workaround, you can move the file (%s) out of the way (rename, move, or delete) to have a new one created on the next start."),
e.what(), PACKAGE_BUGREPORT, fs::quoted(fs::PathToString(path_addr)));
}
return std::nullopt;
}
void DumpAnchors(const fs::path& anchors_db_path, const std::vector<CAddress>& anchors)
{
LOG_TIME_SECONDS(strprintf("Flush %d outbound block-relay-only peer addresses to anchors.dat", anchors.size()));
SerializeFileDB("anchors", anchors_db_path, anchors, CLIENT_VERSION | ADDRV2_FORMAT);
}
std::vector<CAddress> ReadAnchors(const fs::path& anchors_db_path)
{
std::vector<CAddress> anchors;
try {
DeserializeFileDB(anchors_db_path, anchors, CLIENT_VERSION | ADDRV2_FORMAT);
LogPrintf("Loaded %i addresses from %s\n", anchors.size(), fs::quoted(fs::PathToString(anchors_db_path.filename())));
} catch (const std::exception&) {
anchors.clear();
}
fs::remove(anchors_db_path);
return anchors;
}