mirror of
https://github.com/monero-project/monero.git
synced 2024-11-18 00:37:43 +00:00
e5d2680094
Bockchain:
1. Optim: Multi-thread long-hash computation when encountering groups of blocks.
2. Optim: Cache verified txs and return result from cache instead of re-checking whenever possible.
3. Optim: Preload output-keys when encoutering groups of blocks. Sort by amount and global-index before bulk querying database and multi-thread when possible.
4. Optim: Disable double spend check on block verification, double spend is already detected when trying to add blocks.
5. Optim: Multi-thread signature computation whenever possible.
6. Patch: Disable locking (recursive mutex) on called functions from check_tx_inputs which causes slowdowns (only seems to happen on ubuntu/VMs??? Reason: TBD)
7. Optim: Removed looped full-tx hash computation when retrieving transactions from pool (???).
8. Optim: Cache difficulty/timestamps (735 blocks) for next-difficulty calculations so that only 2 db reads per new block is needed when a new block arrives (instead of 1470 reads).
Berkeley-DB:
1. Fix: 32-bit data errors causing wrong output global indices and failure to send blocks to peers (etc).
2. Fix: Unable to pop blocks on reorganize due to transaction errors.
3. Patch: Large number of transaction aborts when running multi-threaded bulk queries.
4. Patch: Insufficient locks error when running full sync.
5. Patch: Incorrect db stats when returning from an immediate exit from "pop block" operation.
6. Optim: Add bulk queries to get output global indices.
7. Optim: Modified output_keys table to store public_key+unlock_time+height for single transaction lookup (vs 3)
8. Optim: Used output_keys table retrieve public_keys instead of going through output_amounts->output_txs+output_indices->txs->output:public_key
9. Optim: Added thread-safe buffers used when multi-threading bulk queries.
10. Optim: Added support for nosync/write_nosync options for improved performance (*see --db-sync-mode option for details)
11. Mod: Added checkpoint thread and auto-remove-logs option.
12. *Now usable on 32-bit systems like RPI2.
LMDB:
1. Optim: Added custom comparison for 256-bit key tables (minor speed-up, TBD: get actual effect)
2. Optim: Modified output_keys table to store public_key+unlock_time+height for single transaction lookup (vs 3)
3. Optim: Used output_keys table retrieve public_keys instead of going through output_amounts->output_txs+output_indices->txs->output:public_key
4. Optim: Added support for sync/writemap options for improved performance (*see --db-sync-mode option for details)
5. Mod: Auto resize to +1GB instead of multiplier x1.5
ETC:
1. Minor optimizations for slow-hash for ARM (RPI2). Incomplete.
2. Fix: 32-bit saturation bug when computing next difficulty on large blocks.
[PENDING ISSUES]
1. Berkely db has a very slow "pop-block" operation. This is very noticeable on the RPI2 as it sometimes takes > 10 MINUTES to pop a block during reorganization.
This does not happen very often however, most reorgs seem to take a few seconds but it possibly depends on the number of outputs present. TBD.
2. Berkeley db, possible bug "unable to allocate memory". TBD.
[NEW OPTIONS] (*Currently all enabled for testing purposes)
1. --fast-block-sync arg=[0:1] (default: 1)
a. 0 = Compute long hash per block (may take a while depending on CPU)
b. 1 = Skip long-hash and verify blocks based on embedded known good block hashes (faster, minimal CPU dependence)
2. --db-sync-mode arg=[[safe|fast|fastest]:[sync|async]:[nblocks_per_sync]] (default: fastest:async:1000)
a. safe = fdatasync/fsync (or equivalent) per stored block. Very slow, but safest option to protect against power-out/crash conditions.
b. fast/fastest = Enables asynchronous fdatasync/fsync (or equivalent). Useful for battery operated devices or STABLE systems with UPS and/or systems with battery backed write cache/solid state cache.
Fast - Write meta-data but defer data flush.
Fastest - Defer meta-data and data flush.
Sync - Flush data after nblocks_per_sync and wait.
Async - Flush data after nblocks_per_sync but do not wait for the operation to finish.
3. --prep-blocks-threads arg=[n] (default: 4 or system max threads, whichever is lower)
Max number of threads to use when computing long-hash in groups.
4. --show-time-stats arg=[0:1] (default: 1)
Show benchmark related time stats.
5. --db-auto-remove-logs arg=[0:1] (default: 1)
For berkeley-db only. Auto remove logs if enabled.
**Note: lmdb and berkeley-db have changes to the tables and are not compatible with official git head version.
At the moment, you need a full resync to use this optimized version.
[PERFORMANCE COMPARISON]
**Some figures are approximations only.
Using a baseline machine of an i7-2600K+SSD+(with full pow computation):
1. The optimized lmdb/blockhain core can process blocks up to 585K for ~1.25 hours + download time, so it usually takes 2.5 hours to sync the full chain.
2. The current head with memory can process blocks up to 585K for ~4.2 hours + download time, so it usually takes 5.5 hours to sync the full chain.
3. The current head with lmdb can process blocks up to 585K for ~32 hours + download time and usually takes 36 hours to sync the full chain.
Averate procesing times (with full pow computation):
lmdb-optimized:
1. tx_ave = 2.5 ms / tx
2. block_ave = 5.87 ms / block
memory-official-repo:
1. tx_ave = 8.85 ms / tx
2. block_ave = 19.68 ms / block
lmdb-official-repo (0f4a036437
)
1. tx_ave = 47.8 ms / tx
2. block_ave = 64.2 ms / block
**Note: The following data denotes processing times only (does not include p2p download time)
lmdb-optimized processing times (with full pow computation):
1. Desktop, Quad-core / 8-threads 2600k (8Mb) - 1.25 hours processing time (--db-sync-mode=fastest:async:1000).
2. Laptop, Dual-core / 4-threads U4200 (3Mb) - 4.90 hours processing time (--db-sync-mode=fastest:async:1000).
3. Embedded, Quad-core / 4-threads Z3735F (2x1Mb) - 12.0 hours processing time (--db-sync-mode=fastest:async:1000).
lmdb-optimized processing times (with per-block-checkpoint)
1. Desktop, Quad-core / 8-threads 2600k (8Mb) - 10 minutes processing time (--db-sync-mode=fastest:async:1000).
berkeley-db optimized processing times (with full pow computation)
1. Desktop, Quad-core / 8-threads 2600k (8Mb) - 1.8 hours processing time (--db-sync-mode=fastest:async:1000).
2. RPI2. Improved from estimated 3 months(???) into 2.5 days (*Need 2AMP supply + Clock:1Ghz + [usb+ssd] to achieve this speed) (--db-sync-mode=fastest:async:1000).
berkeley-db optimized processing times (with per-block-checkpoint)
1. RPI2. 12-15 hours (*Need 2AMP supply + Clock:1Ghz + [usb+ssd] to achieve this speed) (--db-sync-mode=fastest:async:1000).
91 lines
4.7 KiB
C++
91 lines
4.7 KiB
C++
// Copyright (c) 2014-2015, The Monero Project
|
|
//
|
|
// All rights reserved.
|
|
//
|
|
// Redistribution and use in source and binary forms, with or without modification, are
|
|
// permitted provided that the following conditions are met:
|
|
//
|
|
// 1. Redistributions of source code must retain the above copyright notice, this list of
|
|
// conditions and the following disclaimer.
|
|
//
|
|
// 2. Redistributions in binary form must reproduce the above copyright notice, this list
|
|
// of conditions and the following disclaimer in the documentation and/or other
|
|
// materials provided with the distribution.
|
|
//
|
|
// 3. Neither the name of the copyright holder nor the names of its contributors may be
|
|
// used to endorse or promote products derived from this software without specific
|
|
// prior written permission.
|
|
//
|
|
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
|
|
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
|
// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
|
|
// THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
|
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
|
// STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF
|
|
// THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
//
|
|
// Parts of this file are originally copyright (c) 2012-2013 The Cryptonote developers
|
|
|
|
#pragma once
|
|
|
|
#include <boost/program_options/variables_map.hpp>
|
|
|
|
#include "cryptonote_core/cryptonote_basic_impl.h"
|
|
#include "cryptonote_core/verification_context.h"
|
|
#include "cryptonote_core/blockchain_storage.h"
|
|
#include <unordered_map>
|
|
|
|
namespace tests
|
|
{
|
|
struct block_index {
|
|
size_t height;
|
|
crypto::hash id;
|
|
crypto::hash longhash;
|
|
cryptonote::block blk;
|
|
cryptonote::blobdata blob;
|
|
std::list<cryptonote::transaction> txes;
|
|
|
|
block_index() : height(0), id(cryptonote::null_hash), longhash(cryptonote::null_hash) { }
|
|
block_index(size_t _height, const crypto::hash &_id, const crypto::hash &_longhash, const cryptonote::block &_blk, const cryptonote::blobdata &_blob, const std::list<cryptonote::transaction> &_txes)
|
|
: height(_height), id(_id), longhash(_longhash), blk(_blk), blob(_blob), txes(_txes) { }
|
|
};
|
|
|
|
class proxy_core
|
|
{
|
|
cryptonote::block m_genesis;
|
|
std::list<crypto::hash> m_known_block_list;
|
|
std::unordered_map<crypto::hash, block_index> m_hash2blkidx;
|
|
|
|
crypto::hash m_lastblk;
|
|
std::list<cryptonote::transaction> txes;
|
|
|
|
bool add_block(const crypto::hash &_id, const crypto::hash &_longhash, const cryptonote::block &_blk, const cryptonote::blobdata &_blob);
|
|
void build_short_history(std::list<crypto::hash> &m_history, const crypto::hash &m_start);
|
|
|
|
|
|
public:
|
|
void on_synchronized(){}
|
|
uint64_t get_current_blockchain_height(){return 1;}
|
|
void set_target_blockchain_height(uint64_t) {}
|
|
bool init(const boost::program_options::variables_map& vm);
|
|
bool deinit(){return true;}
|
|
bool get_short_chain_history(std::list<crypto::hash>& ids);
|
|
bool get_stat_info(cryptonote::core_stat_info& st_inf){return true;}
|
|
bool have_block(const crypto::hash& id);
|
|
bool get_blockchain_top(uint64_t& height, crypto::hash& top_id);
|
|
bool handle_incoming_tx(const cryptonote::blobdata& tx_blob, cryptonote::tx_verification_context& tvc, bool keeped_by_block);
|
|
bool handle_incoming_block(const cryptonote::blobdata& block_blob, cryptonote::block_verification_context& bvc, bool update_miner_blocktemplate = true);
|
|
void pause_mine(){}
|
|
void resume_mine(){}
|
|
bool on_idle(){return true;}
|
|
bool find_blockchain_supplement(const std::list<crypto::hash>& qblock_ids, cryptonote::NOTIFY_RESPONSE_CHAIN_ENTRY::request& resp){return true;}
|
|
bool handle_get_objects(cryptonote::NOTIFY_REQUEST_GET_OBJECTS::request& arg, cryptonote::NOTIFY_RESPONSE_GET_OBJECTS::request& rsp, cryptonote::cryptonote_connection_context& context){return true;}
|
|
cryptonote::blockchain_storage &get_blockchain_storage() { throw std::runtime_error("Called invalid member function: please never call get_blockchain_storage on the TESTING class proxy_core."); }
|
|
bool get_test_drop_download() {return true;}
|
|
bool get_test_drop_download_height() {return true;}
|
|
bool prepare_handle_incoming_blocks(const std::list<cryptonote::block_complete_entry> &blocks) { return true; }
|
|
bool cleanup_handle_incoming_blocks(bool force_sync = false) { return true; }
|
|
};
|
|
}
|