From e5d2680094ee15889934fe28901e4e133cda56f2 Mon Sep 17 00:00:00 2001 From: NoodleDoodleNoodleDoodleNoodleDoodleNoo Date: Fri, 10 Jul 2015 13:09:32 -0700 Subject: ** CHANGES ARE EXPERIMENTAL (FOR TESTING ONLY) 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 (0f4a036437fd41a5498ee5e74e2422ea6177aa3e) 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). --- src/p2p/net_node.inl | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) (limited to 'src/p2p/net_node.inl') diff --git a/src/p2p/net_node.inl b/src/p2p/net_node.inl index 66ee5cb53..bce3ab5af 100644 --- a/src/p2p/net_node.inl +++ b/src/p2p/net_node.inl @@ -67,6 +67,8 @@ namespace nodetool { namespace { + const int64_t default_limit_up = 2048; + const int64_t default_limit_down = 8192; const command_line::arg_descriptor arg_p2p_bind_ip = {"p2p-bind-ip", "Interface for p2p network protocol", "0.0.0.0"}; const command_line::arg_descriptor arg_p2p_bind_port = { "p2p-bind-port" @@ -93,7 +95,7 @@ namespace nodetool const command_line::arg_descriptor arg_limit_rate_up = {"limit-rate-up", "set limit-rate-up [kB/s]", -1}; const command_line::arg_descriptor arg_limit_rate_down = {"limit-rate-down", "set limit-rate-down [kB/s]", -1}; - const command_line::arg_descriptor arg_limit_rate = {"limit-rate", "set limit-rate [kB/s]", 128}; + const command_line::arg_descriptor arg_limit_rate = {"limit-rate", "set limit-rate [kB/s]", -1}; const command_line::arg_descriptor arg_save_graph = {"save-graph", "Save data for dr monero", false}; } @@ -1446,7 +1448,7 @@ namespace nodetool this->islimitup=true; if (limit==-1) { - limit=128; + limit=default_limit_up; this->islimitup=false; } @@ -1461,7 +1463,7 @@ namespace nodetool { this->islimitdown=true; if(limit==-1) { - limit=128; + limit=default_limit_down; this->islimitdown=false; } limit *= 1024; @@ -1471,19 +1473,31 @@ namespace nodetool } template - bool node_server::set_rate_limit(const boost::program_options::variables_map& vm, uint64_t limit) + bool node_server::set_rate_limit(const boost::program_options::variables_map& vm, int64_t limit) { + int64_t limit_up = 0; + int64_t limit_down = 0; + + if(limit == -1) + { + limit_up = default_limit_up * 1024; + limit_down = default_limit_down * 1024; + } + else + { + limit_up = limit * 1024; + limit_down = limit * 1024; + } limit *= 1024; if(this->islimitdown==false && this->islimitup==false) { - epee::net_utils::connection >::set_rate_up_limit( limit ); - epee::net_utils::connection >::set_rate_down_limit( limit ); - LOG_PRINT_L0("Set limit to " << limit/1024 << " kB/s"); + epee::net_utils::connection >::set_rate_up_limit(limit_up); + epee::net_utils::connection >::set_rate_down_limit(limit_down); } else if(this->islimitdown==false && this->islimitup==true ) { - epee::net_utils::connection >::set_rate_down_limit( limit ); + epee::net_utils::connection >::set_rate_down_limit(limit_down); } else if(this->islimitdown==true && this->islimitup==false ) { - epee::net_utils::connection >::set_rate_up_limit( limit ); + epee::net_utils::connection >::set_rate_up_limit(limit_up); } return true; -- cgit v1.2.3