Commit graph

1667 commits

Author SHA1 Message Date
Anna Shaleva
7da394fd3f core: check MPT node is not requested twice by StateSync module
This check prevents infinite loop if something goes wrong with MPT nodes
restore process.
2021-10-12 14:08:56 +03:00
Anna Shaleva
01143da621 rpc: add getstate RPC handler 2021-10-11 16:43:44 +03:00
Anna Shaleva
c8120a139d core: add MaxKeyLength restrictions to MPT's operations 2021-10-06 16:37:23 +03:00
Evgeniy Stratonikov
e6aa9b76ee mempool: reword ErrConflict message, fix #2197
Make it more user-friendly.

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-09-28 09:57:42 +03:00
Anna Shaleva
b3ea7504cb subscriptions: add container hash to notification event
External users make use of it. Close #2190.
2021-09-24 17:42:02 +03:00
Roman Khimov
c009356b73 core: simplify component flushing in storeBlock
Instead of flushing everything to `cache` and then to `bc.dao`, wrap `bc.dao`
directly for block/tx data and AERs and then flush to it. Block/transactions
are usually processed more quickly than other components, so they easily end
up in `cache` where they directly affect Seek performance for any executing
transaction.

Simple as it is this change improves voter NEO transfer benchmark with 1000
accounts by more than 25%, from ~18500 TPS to ~23500 TPS. It doesn't affect
much other cases.
2021-09-22 17:15:12 +03:00
Roman Khimov
b66bc33cf9 native: short-circuit successive GAS distributions
GAS can only be distributed once in a block for particular address, so it
makes little sense trying to calculate it again and again. This fixes
neo-bench for NEO voter, because without it we get ~2500 TPS for
single-address test and with it it jumps 13-fold to normal values like
~33500.
2021-09-22 17:13:55 +03:00
Anna Shaleva
06d3c21e3f core: remove unused interopnames 2021-09-21 16:43:09 +03:00
Roman Khimov
4743d5aacf
Merge pull request #2181 from nspcc-dev/states-diff_testnet_289026
core: fix NEO balance state handler
2021-09-21 15:39:37 +03:00
Anna Shaleva
c113d682bd core: fix NEO balance state handler
We need to store NEO balance's LastUpdateHeight before GAS mint,
because mint can call onNEP17Payment and onNEP17Payment can call NEO
transfer which also calls GAS mint. Storing balance height allows to
avoid recursion.
2021-09-20 19:23:35 +03:00
Roman Khimov
56dd7b7364
Merge pull request #2177 from nspcc-dev/fix-lint
Replace golint with revive
2021-09-15 17:59:04 +03:00
Roman Khimov
1480e29548
Merge pull request #2178 from nspcc-dev/fix-oracle-unsupported-code
transaction: fix ContentTypeNotSupported oracle code processing
2021-09-14 18:01:40 +03:00
Roman Khimov
24a3cce1ca
Merge pull request #2169 from nspcc-dev/states-diff_mainnet_131795
core: allow transfer 0 GAS/NEO with zero balance
2021-09-14 17:30:41 +03:00
Roman Khimov
8a440a4016 transaction: fix ContentTypeNotSupported oracle code processing
Fix testnet block 311487 block processing and synchronization errors:
  2021-09-14T15:18:53.611+0300    WARN    peer disconnected       {"addr": "20.198.226.132:20333", "reason": "invalid oracle response code", "peerCount": 10}

Fix 8e9302f40b.
2021-09-14 15:18:38 +03:00
Evgeniy Stratonikov
176b61e317 *: fix linter issues
Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-09-14 14:39:39 +03:00
Roman Khimov
63e00ac128
Merge pull request #2166 from nspcc-dev/fix-nns-compat
Fix NNS compatibility
2021-09-10 18:10:17 +03:00
Anna Shaleva
7fc57c9d58 core: allow transfer 0 GAS/NEO with zero balance
This commit fixes states diff at 131795 block of mainnet.

Transaction:
```
NEO-GO-VM > loadbase64 DAAQDBSPsxdYh6cITC3gUKI4oWmYxJs49gwUj7MXWIenCEwt4FCiOKFpmMSbOPYUwB8MCHRyYW5zZmVyDBT1Y+pAvCg9TQ4FxI6jBbPyoHNA70FifVtSOQwAEQwUj7MXWIenCEwt4FCiOKFpmMSbOPYMFL1Mb4Fqp6gHiEwzM6xSc8fLS+RpFMAfDAh0cmFuc2ZlcgwU9WPqQLwoPU0OBcSOowWz8qBzQO9BYn1bUjk=
READY: loaded 176 instructions
NEO-GO-VM 0 > ops
INDEX    OPCODE       PARAMETER
0        PUSHDATA1     ("")                                       <<
2        PUSH0
3        PUSHDATA1    8fb3175887a7084c2de050a238a16998c49b38f6
25       PUSHDATA1    8fb3175887a7084c2de050a238a16998c49b38f6
47       PUSH4
48       PACK
49       PUSH15
50       PUSHDATA1    7472616e73666572 ("transfer")
60       PUSHDATA1    f563ea40bc283d4d0e05c48ea305b3f2a07340ef    // NEO token
82       SYSCALL      System.Contract.Call (627d5b52)
87       ASSERT
88       PUSHDATA1     ("")
90       PUSH1
91       PUSHDATA1    8fb3175887a7084c2de050a238a16998c49b38f6
113      PUSHDATA1    bd4c6f816aa7a807884c3333ac5273c7cb4be469
135      PUSH4
136      PACK
137      PUSH15
138      PUSHDATA1    7472616e73666572 ("transfer")
148      PUSHDATA1    f563ea40bc283d4d0e05c48ea305b3f2a07340ef    // NEO token
170      SYSCALL      System.Contract.Call (627d5b52)
175      ASSERT

```

Go's applog:
```
{
   "id" : 1,
   "result" : {
      "txid" : "0x97d2ccb01467b22c73a2cb95f7af298f3a5bd8c849d7044371898b8efecdaabd",
      "executions" : [
         {
            "exception" : "at instruction 87 (ASSERT): ASSERT failed",
            "stack" : [],
            "gasconsumed" : "4988995",
            "notifications" : [],
            "trigger" : "Application",
            "vmstate" : "FAULT"
         }
      ]
   },
   "jsonrpc" : "2.0"
}
```

C#'s applog:
```
{
   "jsonrpc" : "2.0",
   "result" : {
      "executions" : [
         {
            "stack" : [],
            "notifications" : [
               {
                  "contract" : "0xef4073a0f2b305a38ec4050e4d3d28bc40ea63f5",
                  "state" : {
                     "type" : "Array",
                     "value" : [
                        {
                           "type" : "ByteString",
                           "value" : "j7MXWIenCEwt4FCiOKFpmMSbOPY="
                        },
                        {
                           "type" : "ByteString",
                           "value" : "j7MXWIenCEwt4FCiOKFpmMSbOPY="
                        },
                        {
                           "value" : "0",
                           "type" : "Integer"
                        }
                     ]
                  },
                  "eventname" : "Transfer"
               },
               {
                  "contract" : "0xd2a4cff31913016155e38e474a2c06d08be276cf",
                  "state" : {
                     "value" : [
                        {
                           "type" : "Any"
                        },
                        {
                           "type" : "ByteString",
                           "value" : "vUxvgWqnqAeITDMzrFJzx8tL5Gk="
                        },
                        {
                           "value" : "2490",
                           "type" : "Integer"
                        }
                     ],
                     "type" : "Array"
                  },
                  "eventname" : "Transfer"
               },
               {
                  "contract" : "0xef4073a0f2b305a38ec4050e4d3d28bc40ea63f5",
                  "state" : {
                     "value" : [
                        {
                           "value" : "vUxvgWqnqAeITDMzrFJzx8tL5Gk=",
                           "type" : "ByteString"
                        },
                        {
                           "value" : "j7MXWIenCEwt4FCiOKFpmMSbOPY=",
                           "type" : "ByteString"
                        },
                        {
                           "value" : "1",
                           "type" : "Integer"
                        }
                     ],
                     "type" : "Array"
                  },
                  "eventname" : "Transfer"
               }
            ],
            "vmstate" : "HALT",
            "gasconsumed" : "9977990",
            "trigger" : "Application",
            "exception" : null
         }
      ],
      "txid" : "0x97d2ccb01467b22c73a2cb95f7af298f3a5bd8c849d7044371898b8efecdaabd"
   },
   "id" : 1
}

```
2021-09-10 17:18:09 +03:00
Roman Khimov
aaccf748ac nft-nd-nns: add getAllRecords method
See neo-project/non-native-contracts#5.
2021-09-10 16:30:45 +03:00
Anna Shaleva
61fd7bd6ba core: avoid nil values during natives manifest marshalling 2021-09-10 11:38:59 +03:00
Anna Shaleva
db13362e86 core: marshal Block.Nonce in upper-case hex 2021-09-09 15:52:51 +03:00
Anna Shaleva
51c8c0d82b core: add tests for StateSync module 2021-09-07 19:43:27 +03:00
Anna Shaleva
0aedfd0038 core: fix bug in MPT pool during Update
We need to copy the result of `TryGet` method, otherwice the slice can
be modified inside `Add` or `Update` methods, which leads to
inconsistent MPT pool state.
2021-09-07 19:43:27 +03:00
Anna Shaleva
36808b8904 core: clone MPT node while restoring it multiple times
We need this to avoid collapse collisions. Example of such collapse
described in
https://github.com/nspcc-dev/neo-go/pull/2019#discussion_r689629704.
2021-09-07 19:43:27 +03:00
Anna Shaleva
5cd78c31af core: allow to recover after state jump interruption
We need several stages to manage state jump process in order not to mess
up old and new contract storage items and to be sure about genesis state data
are properly removed from the storage. Other operations do not require
separate stage and can be performed each time `jumpToStateInternal` is
called.
2021-09-07 19:43:27 +03:00
Anna Shaleva
5cda24b3af core: initialize headers before current block 2021-09-07 19:43:27 +03:00
Anna Shaleva
0e0b55350a core: convert (*Blockchain).JumpToState to a callback
We don't need this method to be exposed, the only its user is the
StateSync module. At the same time StateSync module manages its state by
itself which guarantees that (*Blockchain).jumpToState will be called
with proper StateSync stage.
2021-09-07 19:43:27 +03:00
Anna Shaleva
6381173293 core: store statesync-related storage items under temp prefix
State jump should be an atomic operation, we can't modify contract
storage items state on-the-fly. Thus, store fresh items under temp
prefix and replase the outdated ones after state sync is completed.
Related
https://github.com/nspcc-dev/neo-go/pull/2019#discussion_r693350460.
2021-09-07 19:43:27 +03:00
Anna Shaleva
51f405471e core: remove outdated blocks/txs/AERs/MPT nodes during state sync
Before state sync process can be started, outdated MPT nodes
should be removed from storage. After state sync is completed,
outdated blocks/transactions/AERs should also be removed.
2021-09-07 19:43:27 +03:00
Anna Shaleva
a276a85b72 core: unify code of state sync module initialization 2021-09-07 19:43:27 +03:00
Anna Shaleva
3b7807e897 network: request unknown MPT nodes
In this commit:

1. Request unknown MPT nodes from peers. Note, that StateSync module itself
shouldn't be responsible for nodes requests, that's a server duty.
2. Do not request the same node twice, check if it is in storage
already. If so, then the only thing remaining is to update refcounter.
2021-09-07 19:43:27 +03:00
Anna Shaleva
6a04880b49 core: collapse completed parts of Billet
Some kind of marker is needed to check whether node has been collapsed
or not. So introduce (HashNode).Collapsed
2021-09-07 19:43:27 +03:00
Anna Shaleva
74f1848d19 core: adjust LastUpdatedBlock calculation for NEP17 balances
...wrt P2PStateExchange setting.
2021-09-07 19:43:27 +03:00
Anna Shaleva
d67ff30704 core: implement statesync module
And support GetMPTData and MPTData P2P commands.
2021-09-07 19:43:27 +03:00
Anna Shaleva
a22b1caa3e core: implement MPT Billet structure for MPT restore
MPT restore process is much simpler then regular MPT maintaining: trie
has a fixed structure, we don't need to remove or rebuild MPT nodes. The
only thing we should do is to replace Hash nodes to their unhashed
counterparts and increment refcount. It's better not to touch the
regular MPT code and create a separate structure for this.
2021-09-07 19:43:27 +03:00
Roman Khimov
c9e62769a6
Merge pull request #2143 from nspcc-dev/mpt/add_empty_values
core: allow empty MPT Leaf values
2021-09-07 09:18:48 +03:00
Anna Shaleva
c95f2079d5 core: adjust comments on behaviour defferences for MPT TestCompatibility
C# node does not return empty proof enymore in case if path is bad. C#
node also throws an exception on bad Put.

Our node does not return an error on delete if the key is empty.
2021-09-03 13:46:52 +03:00
Anna Shaleva
f721384ead core: allow empty MPT Leaf values
Allow it for (*Trie).Put. And distinguish empty value and nil value for
(*Trie).PutBatch, because batch is already capable of handling both nil
and empty value. For (*Trie).PutBatch putting nil value means deletion,
while putting empty value means just putting LeafNode with an empty
value.
2021-09-03 13:46:48 +03:00
Evgeniy Stratonikov
7371593bdc native/policy: disallow blocking native contracts
Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-09-03 11:11:06 +03:00
Roman Khimov
b07347e602 core: reuse PushItem for interops
Probably less critical here, but still let's push things faster.
2021-08-30 23:43:58 +03:00
Roman Khimov
7b9558d756
Merge pull request #2142 from nspcc-dev/fix-customgroups-witness-scope
runtime: fix CustomGroups witness
2021-08-26 18:13:08 +03:00
Roman Khimov
734eef3290
Merge pull request #2147 from nspcc-dev/drop-go-1.14
Drop Go 1.14, use 1.17
2021-08-26 17:59:21 +03:00
Roman Khimov
6d074a96e9 *: make tests use TempDir(), fix #1319
Simplify things, drop TempFile at the same time (refs. #1764)
2021-08-26 17:29:40 +03:00
Roman Khimov
40c6c065d2
Merge pull request #2140 from nspcc-dev/vm-optimize-stack
Optimize VM stack
2021-08-26 10:31:31 +03:00
Roman Khimov
de4ed7d020 runtime: fix CustomGroups witness
See neo-project/neo#2586.
2021-08-24 15:50:24 +03:00
Roman Khimov
930653418d vm: rework stack as a simple slice
Double-linked list is quite expensive to manage especially given that it
requires microallocations for each Element. It can be replaced by simple slice
which is much more effective for simple push/pop operations that are very
typical in a VM. I've worried a little about more complex operations like
XDROP/1024 or REVERSEN/1024 because these require copying quite substantial
number of elements, but turns out these work fine too.

At the moment Element is kept as a convenient wrapper for Bytes/BigInt/Bool/etc
methods, but it can be changed in future. Many other potential optimizations
are also possible now.

Complex scripts:
name                    old time/op    new time/op    delta
ScriptFibonacci-8         1.11ms ± 2%    0.85ms ± 2%  -23.40%  (p=0.000 n=10+10)
ScriptNestedRefCount-8    1.46ms ± 2%    1.16ms ± 1%  -20.65%  (p=0.000 n=10+10)
ScriptPushPop/4-8         1.81µs ± 1%    1.54µs ± 4%  -14.96%  (p=0.000 n=8+10)
ScriptPushPop/16-8        4.88µs ± 2%    3.91µs ± 2%  -19.87%  (p=0.000 n=9+9)
ScriptPushPop/128-8       31.9µs ± 9%    26.7µs ± 3%  -16.28%  (p=0.000 n=9+8)
ScriptPushPop/1024-8       235µs ± 1%     192µs ± 3%  -18.31%  (p=0.000 n=9+10)

name                    old alloc/op   new alloc/op   delta
ScriptFibonacci-8          392kB ± 0%     123kB ± 0%  -68.68%  (p=0.000 n=8+8)
ScriptNestedRefCount-8     535kB ± 0%     266kB ± 0%  -50.38%  (p=0.000 n=6+10)
ScriptPushPop/4-8           352B ± 0%      160B ± 0%  -54.55%  (p=0.000 n=10+10)
ScriptPushPop/16-8        1.41kB ± 0%    0.64kB ± 0%  -54.55%  (p=0.000 n=10+10)
ScriptPushPop/128-8       11.3kB ± 0%     8.7kB ± 0%  -22.73%  (p=0.000 n=10+10)
ScriptPushPop/1024-8      90.1kB ± 0%    73.2kB ± 0%  -18.75%  (p=0.000 n=10+10)

name                    old allocs/op  new allocs/op  delta
ScriptFibonacci-8          9.14k ± 0%     3.53k ± 0%  -61.41%  (p=0.000 n=10+10)
ScriptNestedRefCount-8     17.4k ± 0%     11.8k ± 0%  -32.35%  (p=0.000 n=10+10)
ScriptPushPop/4-8           12.0 ± 0%       8.0 ± 0%  -33.33%  (p=0.000 n=10+10)
ScriptPushPop/16-8          48.0 ± 0%      32.0 ± 0%  -33.33%  (p=0.000 n=10+10)
ScriptPushPop/128-8          384 ± 0%       259 ± 0%  -32.55%  (p=0.000 n=10+10)
ScriptPushPop/1024-8       3.07k ± 0%     2.05k ± 0%  -33.14%  (p=0.000 n=10+10)

Some stack-management opcodes:

name                                 old time/op    new time/op    delta
Opcodes/XDROP/0/1-8                     255ns ± 9%     273ns ±11%    +6.92%  (p=0.016 n=11+10)
Opcodes/XDROP/0/1024-8                  362ns ± 2%     365ns ± 8%      ~     (p=0.849 n=10+11)
Opcodes/XDROP/1024/1024-8              3.20µs ± 2%    1.99µs ±12%   -37.69%  (p=0.000 n=11+11)
Opcodes/XDROP/2047/2048-8              6.55µs ± 3%    1.75µs ± 5%   -73.26%  (p=0.000 n=10+11)
Opcodes/DUP/null-8                      414ns ± 6%     245ns ±12%   -40.88%  (p=0.000 n=11+11)
Opcodes/DUP/boolean-8                   411ns ± 8%     245ns ± 6%   -40.31%  (p=0.000 n=11+11)
Opcodes/DUP/integer/small-8             684ns ± 8%     574ns ± 3%   -16.02%  (p=0.000 n=11+10)
Opcodes/DUP/integer/big-8               675ns ± 6%     601ns ±10%   -10.98%  (p=0.000 n=11+11)
Opcodes/DUP/bytearray/small-8           675ns ±10%     566ns ±10%   -16.22%  (p=0.000 n=11+11)
Opcodes/DUP/bytearray/big-8            6.39µs ±11%    6.13µs ± 3%      ~     (p=0.148 n=10+10)
Opcodes/DUP/buffer/small-8              412ns ± 5%     261ns ± 8%   -36.55%  (p=0.000 n=9+11)
Opcodes/DUP/buffer/big-8                586ns ±10%     337ns ± 7%   -42.53%  (p=0.000 n=11+11)
Opcodes/DUP/struct/small-8              458ns ±12%     256ns ±12%   -44.09%  (p=0.000 n=11+11)
Opcodes/DUP/struct/big-8                489ns ± 7%     274ns ± 5%   -44.06%  (p=0.000 n=10+10)
Opcodes/DUP/pointer-8                   586ns ± 7%     494ns ± 7%   -15.67%  (p=0.000 n=11+11)
Opcodes/OVER/null-8                     450ns ±14%     264ns ±10%   -41.30%  (p=0.000 n=11+11)
Opcodes/OVER/boolean-8                  450ns ±14%     264ns ±10%   -41.31%  (p=0.000 n=11+11)
Opcodes/OVER/integer/small-8            716ns ± 9%     604ns ± 6%   -15.65%  (p=0.000 n=11+11)
Opcodes/OVER/integer/big-8              696ns ± 5%     634ns ± 6%    -8.89%  (p=0.000 n=10+11)
Opcodes/OVER/bytearray/small-8          693ns ± 1%     539ns ± 9%   -22.18%  (p=0.000 n=9+10)
Opcodes/OVER/bytearray/big-8           6.33µs ± 2%    6.16µs ± 4%    -2.79%  (p=0.004 n=8+10)
Opcodes/OVER/buffer/small-8             415ns ± 4%     263ns ± 8%   -36.76%  (p=0.000 n=9+11)
Opcodes/OVER/buffer/big-8               587ns ± 5%     342ns ± 7%   -41.70%  (p=0.000 n=11+11)
Opcodes/OVER/struct/small-8             446ns ±14%     257ns ± 8%   -42.42%  (p=0.000 n=11+11)
Opcodes/OVER/struct/big-8               607ns ±26%     278ns ± 7%   -54.25%  (p=0.000 n=11+11)
Opcodes/OVER/pointer-8                  645ns ±12%     476ns ±10%   -26.21%  (p=0.000 n=11+11)
Opcodes/PICK/2/null-8                   460ns ±11%     264ns ± 9%   -42.68%  (p=0.000 n=11+11)
Opcodes/PICK/2/boolean-8                460ns ± 4%     260ns ± 4%   -43.37%  (p=0.000 n=8+11)
Opcodes/PICK/2/integer/small-8          725ns ± 7%     557ns ± 4%   -23.19%  (p=0.000 n=11+10)
Opcodes/PICK/2/integer/big-8            722ns ±12%     582ns ± 6%   -19.51%  (p=0.000 n=11+11)
Opcodes/PICK/2/bytearray/small-8        705ns ± 6%     545ns ± 4%   -22.69%  (p=0.000 n=11+11)
Opcodes/PICK/2/bytearray/big-8         7.17µs ±36%    6.37µs ± 8%      ~     (p=0.065 n=11+11)
Opcodes/PICK/2/buffer/small-8           427ns ± 8%     253ns ± 8%   -40.82%  (p=0.000 n=11+11)
Opcodes/PICK/2/buffer/big-8             590ns ± 3%     331ns ± 6%   -43.83%  (p=0.000 n=11+11)
Opcodes/PICK/2/struct/small-8           428ns ± 8%     254ns ± 7%   -40.64%  (p=0.000 n=11+11)
Opcodes/PICK/2/struct/big-8             489ns ±15%     283ns ± 7%   -42.11%  (p=0.000 n=11+11)
Opcodes/PICK/2/pointer-8                553ns ± 7%     414ns ± 8%   -25.18%  (p=0.000 n=11+11)
Opcodes/PICK/1024/null-8                531ns ± 4%     327ns ± 6%   -38.49%  (p=0.000 n=10+10)
Opcodes/PICK/1024/boolean-8             527ns ± 5%     318ns ± 5%   -39.78%  (p=0.000 n=11+9)
Opcodes/PICK/1024/integer/small-8       861ns ± 4%     683ns ± 4%   -20.66%  (p=0.000 n=11+11)
Opcodes/PICK/1024/integer/big-8         882ns ± 4%    1060ns ±47%      ~     (p=0.748 n=11+11)
Opcodes/PICK/1024/bytearray/small-8     850ns ± 4%     671ns ± 5%   -21.12%  (p=0.000 n=10+11)
Opcodes/PICK/1024/bytearray/big-8      6.32µs ±26%    6.75µs ± 4%    +6.86%  (p=0.019 n=10+11)
Opcodes/PICK/1024/buffer/small-8        530ns ± 6%     324ns ± 5%   -38.86%  (p=0.000 n=10+11)
Opcodes/PICK/1024/buffer/big-8          570ns ± 4%     417ns ±45%   -26.82%  (p=0.001 n=11+10)
Opcodes/PICK/1024/struct/small-8      1.11µs ±122%    0.34µs ±11%   -69.38%  (p=0.000 n=11+10)
Opcodes/PICK/1024/pointer-8             693ns ± 5%     568ns ±31%   -18.10%  (p=0.002 n=10+10)
Opcodes/TUCK/null-8                     450ns ±10%     275ns ± 8%   -38.93%  (p=0.000 n=11+11)
Opcodes/TUCK/boolean-8                  449ns ±13%     268ns ± 9%   -40.16%  (p=0.000 n=11+10)
Opcodes/TUCK/integer/small-8            716ns ± 7%     599ns ± 7%   -16.30%  (p=0.000 n=11+11)
Opcodes/TUCK/integer/big-8              718ns ± 8%     613ns ±11%   -14.55%  (p=0.000 n=11+11)
Opcodes/TUCK/bytearray/small-8          700ns ±12%     558ns ± 7%   -20.39%  (p=0.000 n=11+11)
Opcodes/TUCK/bytearray/big-8           5.88µs ± 7%    6.37µs ± 3%    +8.31%  (p=0.000 n=10+11)
Opcodes/TUCK/buffer/small-8             425ns ± 6%     258ns ±12%   -39.28%  (p=0.000 n=11+11)
Opcodes/TUCK/buffer/big-8               553ns ±19%     334ns ± 6%   -39.57%  (p=0.000 n=11+11)
Opcodes/TUCK/struct/small-8             474ns ± 3%     263ns ±12%   -44.51%  (p=0.000 n=10+11)
Opcodes/TUCK/struct/big-8               641ns ±24%     284ns ± 8%   -55.63%  (p=0.000 n=11+11)
Opcodes/TUCK/pointer-8                  635ns ±13%     468ns ±16%   -26.31%  (p=0.000 n=11+11)
Opcodes/SWAP/null-8                     227ns ±31%     212ns ±11%      ~     (p=0.847 n=11+11)
Opcodes/SWAP/integer-8                  233ns ±32%     210ns ±14%      ~     (p=0.072 n=10+11)
Opcodes/SWAP/big_bytes-8                263ns ±39%     211ns ±11%      ~     (p=0.056 n=11+11)
Opcodes/ROT/null-8                      308ns ±68%     223ns ±12%      ~     (p=0.519 n=11+11)
Opcodes/ROT/integer-8                   226ns ±25%     228ns ± 9%      ~     (p=0.705 n=10+11)
Opcodes/ROT/big_bytes-8                 215ns ±18%     218ns ± 7%      ~     (p=0.756 n=10+11)
Opcodes/ROLL/4/null-8                   269ns ±10%     295ns ± 9%    +9.42%  (p=0.002 n=10+11)
Opcodes/ROLL/4/integer-8                344ns ±48%     280ns ± 2%      ~     (p=0.882 n=11+9)
Opcodes/ROLL/4/big_bytes-8              276ns ±13%     288ns ± 4%    +4.38%  (p=0.046 n=9+11)
Opcodes/ROLL/1024/null-8               4.21µs ±70%    1.01µs ± 9%   -76.15%  (p=0.000 n=11+11)
Opcodes/ROLL/1024/integer-8            4.78µs ±82%    0.71µs ± 3%   -85.06%  (p=0.000 n=11+11)
Opcodes/ROLL/1024/big_bytes-8          3.28µs ± 5%    1.35µs ±36%   -58.91%  (p=0.000 n=9+11)
Opcodes/REVERSE3/null-8                 219ns ± 9%     224ns ± 9%      ~     (p=0.401 n=11+11)
Opcodes/REVERSE3/integer-8              261ns ±28%     220ns ± 6%   -15.67%  (p=0.015 n=11+11)
Opcodes/REVERSE3/big_bytes-8            245ns ±31%     218ns ± 7%      ~     (p=0.051 n=10+11)
Opcodes/REVERSE4/null-8                 223ns ±10%     218ns ± 6%      ~     (p=0.300 n=11+11)
Opcodes/REVERSE4/integer-8              233ns ±10%     220ns ± 7%    -5.74%  (p=0.016 n=11+11)
Opcodes/REVERSE4/big_bytes-8            225ns ±10%     220ns ± 7%      ~     (p=0.157 n=10+11)
Opcodes/REVERSEN/5/null-8               281ns ±12%     277ns ± 4%      ~     (p=0.847 n=11+11)
Opcodes/REVERSEN/5/integer-8            280ns ±11%     275ns ± 5%      ~     (p=0.243 n=11+11)
Opcodes/REVERSEN/5/big_bytes-8          283ns ± 9%     276ns ± 7%      ~     (p=0.133 n=11+11)
Opcodes/REVERSEN/1024/null-8           4.85µs ± 6%    1.94µs ± 6%   -60.07%  (p=0.000 n=10+11)
Opcodes/REVERSEN/1024/integer-8        4.97µs ± 7%    1.99µs ±22%   -59.88%  (p=0.000 n=11+11)
Opcodes/REVERSEN/1024/big_bytes-8      5.11µs ±10%    2.00µs ± 4%   -60.87%  (p=0.000 n=10+9)
Opcodes/PACK/1-8                       1.22µs ± 7%    0.95µs ± 6%   -22.17%  (p=0.000 n=10+11)
Opcodes/PACK/255-8                     11.1µs ± 4%    10.2µs ± 6%    -7.96%  (p=0.000 n=11+11)
Opcodes/PACK/1024-8                    38.9µs ± 4%    37.4µs ± 9%      ~     (p=0.173 n=10+11)
Opcodes/UNPACK/1-8                     1.32µs ±34%    0.96µs ± 6%   -27.57%  (p=0.000 n=10+11)
Opcodes/UNPACK/255-8                   27.2µs ±14%    16.0µs ±13%   -41.04%  (p=0.000 n=11+11)
Opcodes/UNPACK/1024-8                   102µs ±10%      64µs ±16%   -37.33%  (p=0.000 n=10+11)

name                                 old alloc/op   new alloc/op   delta
Opcodes/XDROP/0/1-8                     0.00B          0.00B           ~     (all equal)
Opcodes/XDROP/0/1024-8                  0.00B          0.00B           ~     (all equal)
Opcodes/XDROP/1024/1024-8               0.00B          0.00B           ~     (all equal)
Opcodes/XDROP/2047/2048-8               0.00B          0.00B           ~     (all equal)
Opcodes/DUP/null-8                      48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/boolean-8                   48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/integer/small-8             96.0B ± 0%     48.0B ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/DUP/integer/big-8                104B ± 0%       56B ± 0%   -46.15%  (p=0.000 n=11+11)
Opcodes/DUP/bytearray/small-8           88.0B ± 0%     40.0B ± 0%   -54.55%  (p=0.000 n=11+11)
Opcodes/DUP/bytearray/big-8            65.6kB ± 0%    65.6kB ± 0%    -0.07%  (p=0.000 n=10+9)
Opcodes/DUP/buffer/small-8              48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/buffer/big-8                48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/struct/small-8              48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/struct/big-8                48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/pointer-8                    112B ± 0%       64B ± 0%   -42.86%  (p=0.000 n=11+11)
Opcodes/OVER/null-8                     48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/boolean-8                  48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/integer/small-8            96.0B ± 0%     48.0B ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/OVER/integer/big-8               104B ± 0%       56B ± 0%   -46.15%  (p=0.000 n=11+11)
Opcodes/OVER/bytearray/small-8          88.0B ± 0%     40.0B ± 0%   -54.55%  (p=0.000 n=11+11)
Opcodes/OVER/bytearray/big-8           65.6kB ± 0%    65.6kB ± 0%    -0.07%  (p=0.000 n=9+11)
Opcodes/OVER/buffer/small-8             48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/buffer/big-8               48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/struct/small-8             48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/struct/big-8               48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/pointer-8                   112B ± 0%       64B ± 0%   -42.86%  (p=0.000 n=11+11)
Opcodes/PICK/2/null-8                   48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/boolean-8                48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/integer/small-8          96.0B ± 0%     48.0B ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/integer/big-8             104B ± 0%       56B ± 0%   -46.15%  (p=0.000 n=11+11)
Opcodes/PICK/2/bytearray/small-8        88.0B ± 0%     40.0B ± 0%   -54.55%  (p=0.000 n=11+11)
Opcodes/PICK/2/bytearray/big-8         65.6kB ± 0%    65.6kB ± 0%    -0.07%  (p=0.001 n=9+11)
Opcodes/PICK/2/buffer/small-8           48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/buffer/big-8             48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/struct/small-8           48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/struct/big-8             48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/pointer-8                 112B ± 0%       64B ± 0%   -42.86%  (p=0.000 n=11+11)
Opcodes/PICK/1024/null-8                48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/boolean-8             48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/integer/small-8       96.0B ± 0%     48.0B ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/integer/big-8          104B ± 0%       56B ± 0%   -46.15%  (p=0.000 n=11+11)
Opcodes/PICK/1024/bytearray/small-8     88.0B ± 0%     40.0B ± 0%   -54.55%  (p=0.000 n=11+11)
Opcodes/PICK/1024/bytearray/big-8      65.6kB ± 0%    65.6kB ± 0%    -0.07%  (p=0.000 n=11+11)
Opcodes/PICK/1024/buffer/small-8        48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/buffer/big-8          48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/struct/small-8        48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/pointer-8              112B ± 0%       64B ± 0%   -42.86%  (p=0.000 n=11+11)
Opcodes/TUCK/null-8                     48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/boolean-8                  48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/integer/small-8            96.0B ± 0%     48.0B ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/TUCK/integer/big-8               104B ± 0%       56B ± 0%   -46.15%  (p=0.000 n=11+11)
Opcodes/TUCK/bytearray/small-8          88.0B ± 0%     40.0B ± 0%   -54.55%  (p=0.000 n=11+11)
Opcodes/TUCK/bytearray/big-8           65.6kB ± 0%    65.6kB ± 0%    -0.07%  (p=0.000 n=10+11)
Opcodes/TUCK/buffer/small-8             48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/buffer/big-8               48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/struct/small-8             48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/struct/big-8               48.0B ± 0%      0.0B       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/pointer-8                   112B ± 0%       64B ± 0%   -42.86%  (p=0.000 n=11+11)
Opcodes/SWAP/null-8                     0.00B          0.00B           ~     (all equal)
Opcodes/SWAP/integer-8                  0.00B          0.00B           ~     (all equal)
Opcodes/SWAP/big_bytes-8                0.00B          0.00B           ~     (all equal)
Opcodes/ROT/null-8                      0.00B          0.00B           ~     (all equal)
Opcodes/ROT/integer-8                   0.00B          0.00B           ~     (all equal)
Opcodes/ROT/big_bytes-8                 0.00B          0.00B           ~     (all equal)
Opcodes/ROLL/4/null-8                   0.00B          0.00B           ~     (all equal)
Opcodes/ROLL/4/integer-8                0.00B          0.00B           ~     (all equal)
Opcodes/ROLL/4/big_bytes-8              0.00B          0.00B           ~     (all equal)
Opcodes/ROLL/1024/null-8                0.00B          0.00B           ~     (all equal)
Opcodes/ROLL/1024/integer-8             0.00B          0.00B           ~     (all equal)
Opcodes/ROLL/1024/big_bytes-8           0.00B          0.00B           ~     (all equal)
Opcodes/REVERSE3/null-8                 0.00B          0.00B           ~     (all equal)
Opcodes/REVERSE3/integer-8              0.00B          0.00B           ~     (all equal)
Opcodes/REVERSE3/big_bytes-8            0.00B          0.00B           ~     (all equal)
Opcodes/REVERSE4/null-8                 0.00B          0.00B           ~     (all equal)
Opcodes/REVERSE4/integer-8              0.00B          0.00B           ~     (all equal)
Opcodes/REVERSE4/big_bytes-8            0.00B          0.00B           ~     (all equal)
Opcodes/REVERSEN/5/null-8               0.00B          0.00B           ~     (all equal)
Opcodes/REVERSEN/5/integer-8            0.00B          0.00B           ~     (all equal)
Opcodes/REVERSEN/5/big_bytes-8          0.00B          0.00B           ~     (all equal)
Opcodes/REVERSEN/1024/null-8            0.00B          0.00B           ~     (all equal)
Opcodes/REVERSEN/1024/integer-8         0.00B          0.00B           ~     (all equal)
Opcodes/REVERSEN/1024/big_bytes-8       0.00B          0.00B           ~     (all equal)
Opcodes/PACK/1-8                         144B ± 0%       96B ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PACK/255-8                     4.22kB ± 0%    4.18kB ± 0%    -1.14%  (p=0.000 n=11+11)
Opcodes/PACK/1024-8                    16.5kB ± 0%    16.5kB ± 0%    -0.29%  (p=0.000 n=11+11)
Opcodes/UNPACK/1-8                       168B ± 0%       72B ± 0%   -57.14%  (p=0.000 n=11+11)
Opcodes/UNPACK/255-8                   12.4kB ± 0%     7.8kB ± 0%   -37.28%  (p=0.000 n=11+11)
Opcodes/UNPACK/1024-8                  49.3kB ± 0%    52.8kB ± 0%    +7.18%  (p=0.000 n=11+11)

name                                 old allocs/op  new allocs/op  delta
Opcodes/XDROP/0/1-8                      0.00           0.00           ~     (all equal)
Opcodes/XDROP/0/1024-8                   0.00           0.00           ~     (all equal)
Opcodes/XDROP/1024/1024-8                0.00           0.00           ~     (all equal)
Opcodes/XDROP/2047/2048-8                0.00           0.00           ~     (all equal)
Opcodes/DUP/null-8                       1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/boolean-8                    1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/integer/small-8              3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/DUP/integer/big-8                3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/DUP/bytearray/small-8            3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/DUP/bytearray/big-8              3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/DUP/buffer/small-8               1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/buffer/big-8                 1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/struct/small-8               1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/struct/big-8                 1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/DUP/pointer-8                    2.00 ± 0%      1.00 ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/OVER/null-8                      1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/boolean-8                   1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/integer/small-8             3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/OVER/integer/big-8               3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/OVER/bytearray/small-8           3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/OVER/bytearray/big-8             3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/OVER/buffer/small-8              1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/buffer/big-8                1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/struct/small-8              1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/struct/big-8                1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/OVER/pointer-8                   2.00 ± 0%      1.00 ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/null-8                    1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/boolean-8                 1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/integer/small-8           3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/2/integer/big-8             3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/2/bytearray/small-8         3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/2/bytearray/big-8           3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/2/buffer/small-8            1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/buffer/big-8              1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/struct/small-8            1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/struct/big-8              1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/2/pointer-8                 2.00 ± 0%      1.00 ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/null-8                 1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/boolean-8              1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/integer/small-8        3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/1024/integer/big-8          3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/1024/bytearray/small-8      3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/1024/bytearray/big-8        3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/PICK/1024/buffer/small-8         1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/buffer/big-8           1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/struct/small-8         1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/PICK/1024/pointer-8              2.00 ± 0%      1.00 ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/TUCK/null-8                      1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/boolean-8                   1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/integer/small-8             3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/TUCK/integer/big-8               3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/TUCK/bytearray/small-8           3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/TUCK/bytearray/big-8             3.00 ± 0%      2.00 ± 0%   -33.33%  (p=0.000 n=11+11)
Opcodes/TUCK/buffer/small-8              1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/buffer/big-8                1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/struct/small-8              1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/struct/big-8                1.00 ± 0%      0.00       -100.00%  (p=0.000 n=11+11)
Opcodes/TUCK/pointer-8                   2.00 ± 0%      1.00 ± 0%   -50.00%  (p=0.000 n=11+11)
Opcodes/SWAP/null-8                      0.00           0.00           ~     (all equal)
Opcodes/SWAP/integer-8                   0.00           0.00           ~     (all equal)
Opcodes/SWAP/big_bytes-8                 0.00           0.00           ~     (all equal)
Opcodes/ROT/null-8                       0.00           0.00           ~     (all equal)
Opcodes/ROT/integer-8                    0.00           0.00           ~     (all equal)
Opcodes/ROT/big_bytes-8                  0.00           0.00           ~     (all equal)
Opcodes/ROLL/4/null-8                    0.00           0.00           ~     (all equal)
Opcodes/ROLL/4/integer-8                 0.00           0.00           ~     (all equal)
Opcodes/ROLL/4/big_bytes-8               0.00           0.00           ~     (all equal)
Opcodes/ROLL/1024/null-8                 0.00           0.00           ~     (all equal)
Opcodes/ROLL/1024/integer-8              0.00           0.00           ~     (all equal)
Opcodes/ROLL/1024/big_bytes-8            0.00           0.00           ~     (all equal)
Opcodes/REVERSE3/null-8                  0.00           0.00           ~     (all equal)
Opcodes/REVERSE3/integer-8               0.00           0.00           ~     (all equal)
Opcodes/REVERSE3/big_bytes-8             0.00           0.00           ~     (all equal)
Opcodes/REVERSE4/null-8                  0.00           0.00           ~     (all equal)
Opcodes/REVERSE4/integer-8               0.00           0.00           ~     (all equal)
Opcodes/REVERSE4/big_bytes-8             0.00           0.00           ~     (all equal)
Opcodes/REVERSEN/5/null-8                0.00           0.00           ~     (all equal)
Opcodes/REVERSEN/5/integer-8             0.00           0.00           ~     (all equal)
Opcodes/REVERSEN/5/big_bytes-8           0.00           0.00           ~     (all equal)
Opcodes/REVERSEN/1024/null-8             0.00           0.00           ~     (all equal)
Opcodes/REVERSEN/1024/integer-8          0.00           0.00           ~     (all equal)
Opcodes/REVERSEN/1024/big_bytes-8        0.00           0.00           ~     (all equal)
Opcodes/PACK/1-8                         5.00 ± 0%      4.00 ± 0%   -20.00%  (p=0.000 n=11+11)
Opcodes/PACK/255-8                       5.00 ± 0%      4.00 ± 0%   -20.00%  (p=0.000 n=11+11)
Opcodes/PACK/1024-8                      5.00 ± 0%      4.00 ± 0%   -20.00%  (p=0.000 n=11+11)
Opcodes/UNPACK/1-8                       5.00 ± 0%      3.00 ± 0%   -40.00%  (p=0.000 n=11+11)
Opcodes/UNPACK/255-8                      259 ± 0%         7 ± 0%   -97.30%  (p=0.000 n=11+11)
Opcodes/UNPACK/1024-8                   1.03k ± 0%     0.01k ± 0%   -98.93%  (p=0.000 n=11+11)
2021-08-24 15:28:14 +03:00
Roman Khimov
7808762ba0 transaction: avoid reencoding and reading what can't be read
name               old time/op    new time/op    delta
DecodeFromBytes-8    1.79µs ± 2%    1.46µs ± 4%  -18.44%  (p=0.000 n=10+10)

name               old alloc/op   new alloc/op   delta
DecodeFromBytes-8      800B ± 0%      624B ± 0%  -22.00%  (p=0.000 n=10+10)

name               old allocs/op  new allocs/op  delta
DecodeFromBytes-8      10.0 ± 0%       8.0 ± 0%  -20.00%  (p=0.000 n=10+10)
2021-08-23 21:41:38 +03:00
Roman Khimov
2808f6857d interop: don't allocate for Functions and Notifications in New
Functions are usually immediately replaced (and it's OK for them to be nil,
searching through an array with length of zero is fine), Notifications are
usually appended to (and are absolutely useless in verification contexts).
2021-08-20 11:56:28 +03:00
Roman Khimov
a68a8aa8fc core: simplify and correct notification handling
* both 'to' and 'from' are either Null or Hash160, there is no other
   possibility for valid NEP-17. So returning util.Uint160{} in case of
   parsing error is wrong.
 * but this is what allowed burns/mints to work at the expense of error
   allocation inside of util.Uint160DecodeBytesBE()
 * Uint160 can technically fit into regular VM integer, so even though it'd be
   quite surprising to see it there, TryBytes() is more correct (and easier!)
   to use
 * same thing with `amount`, we have `TryInteger()` that easily covers all
   possible cases and does appropriate error checking inside
2021-08-20 11:26:16 +03:00
Roman Khimov
abc48229a3 block: Grow buffer on Trim, avoid reallocations 2021-08-20 11:05:46 +03:00
Anna Shaleva
5f9d38f640 core: refactor (*DAO).StoreAsTransaction
Squash (*DAO).StoreAsTransaction and
(*DAO).StoreConflictingTransactions. It's better to keep them this way,
because StoreAsTransaction is always followed by
StoreConflictingTransactions, so it's an atomic operation.

The logic wasn't changed.
2021-08-18 13:39:28 +03:00
Anna Shaleva
4b35a1cf92 core: remove conflicting transactions wrt MaxTraceableBlocks 2021-08-18 13:31:47 +03:00
Roman Khimov
f477a48758 contract: block calls to contracts via Policy contract
See neo-project/neo#2567.
2021-08-17 15:24:06 +03:00
Roman Khimov
adc660c3e0
Merge pull request #2123 from nspcc-dev/store-better
Store better
2021-08-13 12:50:24 +03:00
Roman Khimov
ae071d4542 storage: introduce PutChangeSet and use it for Persist
We're using batches in wrong way during persist, we already have all changes
accumulated in two maps and then we move them to batch and then this is
applied. For some DBs like BoltDB this batch is just another MemoryStore, so
we essentially just shuffle the changeset from one map to another, for others
like LevelDB batch is just a serialized set of KV pairs, it doesn't help much
on subsequent PutBatch, we just duplicate the changeset again.

So introduce PutChangeSet that allows to take two maps with sets and deletes
directly. It also allows to simplify MemCachedStore logic.

neo-bench for single node with 10 workers, LevelDB:

  Reference:

  RPS    30189.132 30556.448 30390.482 ≈ 30379    ±  0.61%
  TPS    29427.344 29418.687 29434.273 ≈ 29427    ±  0.03%
  CPU %     33.304    27.179    33.860 ≈    31.45 ± 11.79%
  Mem MB   800.677   798.389   715.042 ≈   771    ±  6.33%

  Patched:

  RPS    30264.326 30386.364 30166.231 ≈ 30272    ± 0.36% ⇅
  TPS    29444.673 29407.440 29452.478 ≈ 29435    ± 0.08% ⇅
  CPU %     34.012    32.597    33.467 ≈   33.36  ± 2.14% ⇅
  Mem MB   549.126   523.656   517.684 ≈  530     ± 3.15% ↓ 31.26%

BoltDB:

  Reference:

  RPS    31937.647 31551.684 31850.408 ≈ 31780    ±  0.64%
  TPS    31292.049 30368.368 31307.724 ≈ 30989    ±  1.74%
  CPU %     33.792    22.339    35.887 ≈    30.67 ± 23.78%
  Mem MB  1271.687  1254.472  1215.639 ≈  1247    ±  2.30%

  Patched:

  RPS    31746.818 30859.485 31689.761 ≈ 31432    ± 1.58% ⇅
  TPS    31271.499 30340.726 30342.568 ≈ 30652    ± 1.75% ⇅
  CPU %     34.611    34.414    31.553 ≈    33.53 ± 5.11% ⇅
  Mem MB  1262.960  1231.389  1335.569 ≈  1277    ± 4.18% ⇅
2021-08-12 17:42:16 +03:00
Roman Khimov
5aff82aef4
Merge pull request #2119 from nspcc-dev/states-exchange/insole
core, network: prepare basis for Insole module
2021-08-12 10:35:02 +03:00
Roman Khimov
47f0f4c45f dao: completely drop Cached
It was very useful in 2.0 days, but today it only serves one purpose that
could easily (and more effectively!) be solved in another way.
2021-08-11 23:06:17 +03:00
Roman Khimov
3e60771175 core: deduplicate and simplify processNEP17Transfer a bit
Just refactoring, no functional changes.
2021-08-11 22:36:26 +03:00
Roman Khimov
50ee1a1f91 *: don't use dao.Cached in tests
There is no need to use it.
2021-08-11 21:02:50 +03:00
Roman Khimov
18682f2409 storage: don't use locks for memory batches
They're inherently single-threaded, so locking makes no sense for them.
2021-08-11 18:55:07 +03:00
Roman Khimov
13da1b62fb interop: fetch baseExecFee once and keep it in the Context
It never changes during single execution, so we can cache it and avoid going
to Policer via Chain for every instruction.
2021-08-11 15:42:23 +03:00
Anna Shaleva
0e3b9c48a2 core: add API to store StateSyncPoint and StateSyncCurrentBlockHeight
We need it in order not to mess up the blockchain which has its own
CurrentBlockHeight.
2021-08-10 14:06:28 +03:00
Anna Shaleva
cb01f533c0 core: store conflicting transactions in a separate method
(DAO).StoreConflictingTransactions will be reused from the state sync
module.
2021-08-10 13:47:13 +03:00
Anna Shaleva
72e654332e core: refactor block queue
It requires only two methods from Blockchainer: AddBlock and
BlockHeight. New interface will allow to easily reuse the block queue
for state exchange purposes.
2021-08-10 13:47:13 +03:00
Anna Shaleva
35501a281a core: remove untraceable blocks wrt StateSyncInterval 2021-08-10 13:47:10 +03:00
Anna Shaleva
76c687aaa1 config: add P2PStateExchangeExtensions and StateSyncInterval settings 2021-08-10 11:00:32 +03:00
Roman Khimov
1e0c70ecb0
Merge pull request #2117 from nspcc-dev/io-grow
Some io package improvements
2021-08-10 09:57:31 +03:00
Evgeniy Stratonikov
73e4040628 mpt: use BinWriter.Grow() instead of custom buffer
Also add benchmarks.

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-10 09:34:05 +03:00
Evgeniy Stratonikov
620295efe3 transaction: add benchmark for transaction serialization
Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-09 12:01:38 +03:00
Evgeniy Stratonikov
23adb1e2fc state: optimize NEP17TransferLog.Append
Do not allocate a separate buffer for the transfer.
```
name                       old time/op    new time/op    delta
NEP17TransferLog_Append-8    58.8µs ± 3%    32.1µs ± 1%  -45.40%  (p=0.000 n=10+9)

name                       old alloc/op   new alloc/op   delta
NEP17TransferLog_Append-8     118kB ± 1%      44kB ± 3%  -63.00%  (p=0.000 n=9+10)

name                       old allocs/op  new allocs/op  delta
NEP17TransferLog_Append-8       901 ± 1%       513 ± 3%  -43.08%  (p=0.000 n=9+8)
```

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-09 11:09:49 +03:00
Evgeniy Stratonikov
403a4b75de state/test: add benchmark for NEP17TransferLog.Append
Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-09 11:09:49 +03:00
Evgeniy Stratonikov
b210a34b1e state: optimize NEP17Balance deserialization
```
BenchmarkNEP17BalanceFromBytes/stackitem-8         	 2402318	       503.3 ns/op	     208 B/op	      10 allocs/op
BenchmarkNEP17BalanceFromBytes/from_bytes-8        	 7623139	       160.7 ns/op	      72 B/op	       3 allocs/op
```

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-09 11:09:49 +03:00
Evgeniy Stratonikov
3218b74ea5 state: optimize NEP17Balance serialization
Put to slice directly and allow to provide pre-allocated buffer.
```
BenchmarkNEP17BalanceBytes/stackitem-8         	 1712475	       673.4 ns/op	     448 B/op	       9 allocs/op
BenchmarkNEP17BalanceBytes/bytes-8             	13422715	        75.80 ns/op	      32 B/op	       2 allocs/op
BenchmarkNEP17BalanceBytes/bytes,_prealloc-8   	25990371	        46.46 ns/op	      16 B/op	       1 allocs/op
```

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-09 11:09:06 +03:00
Roman Khimov
b989504d74
Merge pull request #2108 from nspcc-dev/optimize-mpt
Some allocation optimizations
2021-08-06 14:51:10 +03:00
Evgeniy Stratonikov
bd2b1a0521 mpt: add Size method to trie nodes
Knowing serialized size of the node is useful for
preallocating byte-slice in advance.

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-06 12:01:16 +03:00
Evgeniy Stratonikov
db80ef28df mpt: move empty hash node in a separate type
We use them quite frequently (consider children for a new branch
node) and it is better to get rid of unneeded allocations.

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-06 12:01:16 +03:00
Evgeniy Stratonikov
291a29af1e *: do not use WriteArray for frequently used items
`WriteArray` involves reflection, it makes sense to optimize
serialization of transactions and application logs which are serialized
constantly. Adding case in a type switch in `WriteArray` is not an
option because we don't want new dependencies for `io` package.

```
name                          old time/op    new time/op    delta
AppExecResult_EncodeBinary-8     852ns ± 3%     656ns ± 2%  -22.94%  (p=0.000 n=10+9)

name                          old alloc/op   new alloc/op   delta
AppExecResult_EncodeBinary-8      448B ± 0%      376B ± 0%  -16.07%  (p=0.000 n=10+10)

name                          old allocs/op  new allocs/op  delta
AppExecResult_EncodeBinary-8      7.00 ± 0%      5.00 ± 0%  -28.57%  (p=0.000 n=10+10)
```

```
name                 old time/op    new time/op    delta
Transaction_Bytes-8    1.29µs ± 3%    0.76µs ± 5%  -41.52%  (p=0.000 n=9+10)

name                 old alloc/op   new alloc/op   delta
Transaction_Bytes-8    1.21kB ± 0%    1.01kB ± 0%  -16.56%  (p=0.000 n=10+10)

name                 old allocs/op  new allocs/op  delta
Transaction_Bytes-8      12.0 ± 0%       7.0 ± 0%  -41.67%  (p=0.000 n=10+10)
```

Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-06 11:59:20 +03:00
Roman Khimov
39f874d03f core: don't recalculate witness script hash
We know it already, but with current loading code VM will hash it once
more. It doesn't help a lot and still it costs nothing to avoid this
overhead.

name             old time/op    new time/op    delta
VerifyWitness-8    93.4µs ± 3%    92.7µs ± 2%    ~     (p=0.353 n=10+10)

name             old alloc/op   new alloc/op   delta
VerifyWitness-8    3.43kB ± 0%    3.40kB ± 0%  -0.70%  (p=0.000 n=9+9)

name             old allocs/op  new allocs/op  delta
VerifyWitness-8      67.0 ± 0%      66.0 ± 0%  -1.49%  (p=0.000 n=10+10)
2021-08-06 11:25:09 +03:00
Evgeniy Stratonikov
43ee671f36 mpt: do not allocate NodeObject for serialization
Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-06 10:28:19 +03:00
Roman Khimov
e41fc2fd1b
Merge pull request #2111 from nspcc-dev/drop-refuel
native: drop Refuel method from GAS
2021-08-05 16:42:29 +03:00
Roman Khimov
d6bd6b6888 native: drop Refuel method from GAS
It can be used to attack the network (amplifying DOS), so it's broken
beyond repair. This reverts ac601601c1.

See also neo-project/neo#2560 and neo-project/neo#2561.
2021-08-05 10:27:13 +03:00
Roman Khimov
892c9785ad transaction: don't allocate new buffer to calculate hash
We can write directly to hash.Hash.

name               old time/op    new time/op    delta
DecodeBinary-8       2.89µs ± 3%    2.82µs ± 5%     ~     (p=0.052 n=10+10)
DecodeJSON-8         13.0µs ± 1%    12.8µs ± 1%   -1.54%  (p=0.002 n=10+8)
DecodeFromBytes-8    2.37µs ± 1%    2.25µs ± 5%   -5.25%  (p=0.000 n=9+10)

name               old alloc/op   new alloc/op   delta
DecodeBinary-8       1.75kB ± 0%    1.53kB ± 0%  -12.79%  (p=0.000 n=10+10)
DecodeJSON-8         3.49kB ± 0%    3.26kB ± 0%   -6.42%  (p=0.000 n=10+10)
DecodeFromBytes-8    1.37kB ± 0%    1.14kB ± 0%  -16.37%  (p=0.000 n=10+10)

name               old allocs/op  new allocs/op  delta
DecodeBinary-8         26.0 ± 0%      23.0 ± 0%  -11.54%  (p=0.000 n=10+10)
DecodeJSON-8           58.0 ± 0%      55.0 ± 0%   -5.17%  (p=0.000 n=10+10)
DecodeFromBytes-8      18.0 ± 0%      15.0 ± 0%  -16.67%  (p=0.000 n=10+10)
2021-08-04 23:43:20 +03:00
Roman Khimov
6d10cdc2f6 transaction: avoid ReadArray()
Reflection adds some real cost to it:

name               old time/op    new time/op    delta
DecodeBinary-8       3.14µs ± 5%    2.89µs ± 3%   -8.19%  (p=0.000 n=10+10)
DecodeJSON-8         12.6µs ± 3%    13.0µs ± 1%   +3.77%  (p=0.000 n=10+10)
DecodeFromBytes-8    2.73µs ± 2%    2.37µs ± 1%  -13.12%  (p=0.000 n=9+9)

name               old alloc/op   new alloc/op   delta
DecodeBinary-8       1.82kB ± 0%    1.75kB ± 0%   -3.95%  (p=0.000 n=10+10)
DecodeJSON-8         3.49kB ± 0%    3.49kB ± 0%     ~     (all equal)
DecodeFromBytes-8    1.44kB ± 0%    1.37kB ± 0%   -5.00%  (p=0.000 n=10+10)

name               old allocs/op  new allocs/op  delta
DecodeBinary-8         29.0 ± 0%      26.0 ± 0%  -10.34%  (p=0.000 n=10+10)
DecodeJSON-8           58.0 ± 0%      58.0 ± 0%     ~     (all equal)
DecodeFromBytes-8      21.0 ± 0%      18.0 ± 0%  -14.29%  (p=0.000 n=10+10)
2021-08-04 23:34:57 +03:00
Roman Khimov
d2732a71d8 transaction: don't overwrite error and witnesses length check
ReadArray() can return some error and we shouldn't overwrite it. At the same
time limiting ReadArray() to the number of Signers can make it return wrong
error if the number of witnesses actually is bigger than the number of
signers, so use MaxAttributes.
2021-08-04 23:17:50 +03:00
Roman Khimov
d487b54612 transaction: don't recalculate size when decoding from buffer
name               old time/op    new time/op    delta
DecodeBinary-8       3.17µs ± 6%    3.14µs ± 5%     ~     (p=0.579 n=10+10)
DecodeJSON-8         12.8µs ± 3%    12.6µs ± 3%     ~     (p=0.105 n=10+10)
DecodeFromBytes-8    3.45µs ± 4%    2.73µs ± 2%  -20.70%  (p=0.000 n=10+9)

name               old alloc/op   new alloc/op   delta
DecodeBinary-8       1.82kB ± 0%    1.82kB ± 0%     ~     (all equal)
DecodeJSON-8         3.49kB ± 0%    3.49kB ± 0%     ~     (all equal)
DecodeFromBytes-8    1.82kB ± 0%    1.44kB ± 0%  -21.05%  (p=0.000 n=10+10)

name               old allocs/op  new allocs/op  delta
DecodeBinary-8         29.0 ± 0%      29.0 ± 0%     ~     (all equal)
DecodeJSON-8           58.0 ± 0%      58.0 ± 0%     ~     (all equal)
DecodeFromBytes-8      29.0 ± 0%      21.0 ± 0%  -27.59%  (p=0.000 n=10+10)
2021-08-04 23:13:58 +03:00
Roman Khimov
64c780ad7a native: optimize totalSupply operations during token burn/mint
We burn GAS in OnPersist for every transaction so some buffer reuse here is
quite natural.

This also doesn't change a lot in the overall TPS picture, maybe adding some
1%.
2021-08-03 17:59:38 +03:00
Roman Khimov
dede4fa7b1 state: convert NEO balance to stack item directly
Avoid calling Append() that will reallocate the slice, we know the length of
the slice exactly.
2021-08-03 17:59:38 +03:00
Roman Khimov
5c65d33439 native: move required balance check to token contracts
Which duplicates the check, but deduplicates error path. This check forced
double balance deserialization which is quite costly operation, so we better
do it once.

It's hardly noticeable as of TPS metrics though, maybe some 1-2%%.
2021-08-03 17:59:38 +03:00
Roman Khimov
3c1325035e fee: use array for opcodes
Use less memory and have faster access.

name       old time/op  new time/op  delta
Opcode1-8  22.4ns ± 6%   3.0ns ± 6%  -86.63%  (p=0.000 n=10+10)
2021-08-02 20:18:33 +03:00
Roman Khimov
dfc514eda0
Merge pull request #2102 from nspcc-dev/store4
Improve (*MemCachedStore).Persist
2021-08-02 20:10:05 +03:00
Roman Khimov
82f481e143
Merge pull request #2105 from nspcc-dev/json-restrict
native/std: restrint amount of items in JSON deserialization
2021-08-02 19:41:54 +03:00
Evgeniy Stratonikov
bdb9748c1b native/std: restrict amount of items in JSON deserialization
Signed-off-by: Evgeniy Stratonikov <evgeniy@nspcc.ru>
2021-08-02 18:57:47 +03:00
Roman Khimov
f8174ca64c core: ensure data logged is from persistent store
Using bc.dao here is wrong, it can contain unpersisted data.
2021-08-02 16:33:09 +03:00
Roman Khimov
8277b7a19a core: don't spawn goroutine for persist function
It doesn't make any sense, in some situations it leads to a number of
goroutines created that will Persist one after another (as we can't Persist
concurrently). We can manage it better in a single thread.

This doesn't change performance in any way, but somewhat reduces resource
consumption. It was tested neo-bench (single node, 10 workers, LevelDB) on two
machines and block dump processing (RC4 testnet up to 62800 with VerifyBlocks
set to false) on i7-8565U.

Reference (b9be892bf9):

Ryzen 9 5950X:
RPS     27747.349 27407.726 27520.210  ≈ 27558   ± 0.63%
TPS     26992.010 26993.468 27010.966  ≈ 26999   ± 0.04%
CPU %      28.928    28.096    29.105  ≈    28.7 ± 1.88%
Mem MB    760.385   726.320   756.118  ≈   748   ± 2.48%

Core i7-8565U:
RPS     7783.229 7628.409 7542.340  ≈ 7651   ± 1.60%
TPS     7708.436 7607.397 7489.459  ≈ 7602   ± 1.44%
CPU %     74.899   71.020   72.697  ≈   72.9 ± 2.67%
Mem MB   438.047  436.967  416.350  ≈  430   ± 2.84%

DB restore:
real    0m20.838s 0m21.895s 0m21.794s  ≈ 21.51 ± 2.71%
user    0m39.091s 0m40.565s 0m41.493s  ≈ 40.38 ± 3.00%
sys      0m3.184s  0m2.923s  0m3.062s  ≈  3.06 ± 4.27%

Patched:

Ryzen 9 5950X:
RPS     27636.957 27246.911 27462.036  ≈ 27449   ±  0.71%  ↓ 0.40%
TPS     27003.672 26993.468 27011.696  ≈ 27003   ±  0.03%  ↑ 0.01%
CPU %      28.562    28.475    28.012  ≈    28.3 ±  1.04%  ↓ 1.39%
Mem MB    627.007   648.110   794.895  ≈   690   ± 13.25%  ↓ 7.75%

Core i7-8565U:
RPS     7497.210 7527.797 7897.532  ≈ 7641   ±  2.92%  ↓ 0.13%
TPS     7461.128 7482.678 7841.723  ≈ 7595   ±  2.81%  ↓ 0.09%
CPU %     71.559   73.423   69.005  ≈   71.3 ±  3.11%  ↓ 2.19%
Mem MB   393.090  395.899  482.264  ≈  424   ± 11.96%  ↓ 1.40%

DB restore:
real    0m20.773s 0m21.583s 0m20.522s  ≈ 20.96 ±  2.65%  ↓ 2.56%
user    0m39.322s 0m42.268s 0m38.626s  ≈ 40.07 ±  4.82%  ↓ 0.77%
sys      0m3.006s  0m3.597s  0m3.042s  ≈  3.22 ± 10.31%  ↑ 5.23%
2021-08-02 16:33:00 +03:00
Roman Khimov
b9be892bf9 storage: allow accessing MemCachedStore during Persist
Persist by its definition doesn't change MemCachedStore visible state, all KV
pairs that were acessible via it before Persist remain accessible after
Persist. The only thing it does is flushing of the current set of KV pairs
from memory to peristent store. To do that it needs read-only access to the
current KV pair set, but technically it then replaces maps, so we have to use
full write lock which makes MemCachedStore inaccessible for the duration of
Persist. And Persist can take a lot of time, it's about disk access for
regular DBs.

What we do here is we create new in-memory maps for MemCachedStore before
flushing old ones to the persistent store. Then a fake persistent store is
created which actually is a MemCachedStore with old maps, so it has exactly
the same visible state. This Store is never accessed for writes, so we can
read it without taking any internal locks and at the same time we no longer
need write locks for original MemCachedStore, we're not using it. All of this
makes it possible to use MemCachedStore as normally reads are handled going
down to whatever level is needed and writes are handled by new maps. So while
Persist for (*Blockchain).dao does its most time-consuming work we can process
other blocks (reading data for transactions and persisting storeBlock caches
to (*Blockchain).dao).

The change was tested for performance with neo-bench (single node, 10 workers,
LevelDB) on two machines and block dump processing (RC4 testnet up to 62800
with VerifyBlocks set to false) on i7-8565U.

Reference results (bbe4e9cd7b):

Ryzen 9 5950X:
RPS     23616.969 22817.086 23222.378  ≈ 23218   ± 1.72%
TPS     23047.316 22608.578 22735.540  ≈ 22797   ± 0.99%
CPU %      23.434    25.553    23.848  ≈    24.3 ± 4.63%
Mem MB    600.636   503.060   582.043  ≈   562   ± 9.22%

Core i7-8565U:
RPS     6594.007 6499.501 6572.902  ≈ 6555   ± 0.76%
TPS     6561.680 6444.545 6510.120  ≈ 6505   ± 0.90%
CPU %     58.452   60.568   62.474    ≈ 60.5 ± 3.33%
Mem MB   234.893  285.067  269.081   ≈ 263   ± 9.75%

DB restore:
real    0m22.237s 0m23.471s 0m23.409s  ≈ 23.04 ± 3.02%
user    0m35.435s 0m38.943s 0m39.247s  ≈ 37.88 ± 5.59%
sys      0m3.085s  0m3.360s  0m3.144s  ≈  3.20 ± 4.53%

After the change:

Ryzen 9 5950X:
RPS     27747.349 27407.726 27520.210  ≈ 27558   ± 0.63%  ↑ 18.69%
TPS     26992.010 26993.468 27010.966  ≈ 26999   ± 0.04%  ↑ 18.43%
CPU %      28.928    28.096    29.105  ≈    28.7 ± 1.88%  ↑ 18.1%
Mem MB    760.385   726.320   756.118  ≈   748   ± 2.48%  ↑ 33.10%

Core i7-8565U:
RPS     7783.229 7628.409 7542.340  ≈ 7651   ± 1.60%  ↑ 16.72%
TPS     7708.436 7607.397 7489.459  ≈ 7602   ± 1.44%  ↑ 16.85%
CPU %     74.899   71.020   72.697  ≈   72.9 ± 2.67%  ↑ 20.50%
Mem MB   438.047  436.967  416.350  ≈  430   ± 2.84%  ↑ 63.50%

DB restore:
real    0m20.838s 0m21.895s 0m21.794s  ≈ 21.51 ± 2.71%  ↓ 6.64%
user    0m39.091s 0m40.565s 0m41.493s  ≈ 40.38 ± 3.00%  ↑ 6.60%
sys      0m3.184s  0m2.923s  0m3.062s  ≈  3.06 ± 4.27%  ↓ 4.38%

It obviously uses more memory now and utilizes CPU more aggressively, but at
the same time it allows to improve all relevant metrics and finally reach a
situation where we process 50K transactions in less than second on Ryzen 9
5950X (going higher than 25K TPS). The other observation is much more stable
block time, on Ryzen 9 it's as close to 1 second as it could be.
2021-08-02 16:33:00 +03:00
Roman Khimov
3cebd2b129 interop: use non-Cached wrapped DAO
Cached only caches NEP-17 tracking data now, it makes no sense here.
2021-07-30 15:45:17 +03:00
Roman Khimov
fa7314ea90 dao: drop dropNEP17Cache from Cached
It's not used now.
2021-07-30 15:45:17 +03:00
Roman Khimov
49be753850 core: spread storeBlock actions to three goroutines
Block processing consists of:
 * saving block/transactions to the DB
 * executing blocks/transactions
 * processing notifications/saving AERs
 * updating MPT
 * atomically updating Blockchain state

Of these the first one is completely independent of others, it can be done in
a separate routine easily. The third one technically depends on the second,
it just doesn't have data until something is executed. At the same time it
doesn't affect future executions in any way, so we can offload
AER/notification processing to separate goroutine (while the main thread
proceeds with other transactions).

MPT update depends on all executions, so it can't be offloaded, but it can be
done concurrently to AER processing. And only the last thing actually needs
all previous ones to be finished, so it's a natural synchronization point.

So we spawn two additional routines and let the main one execute transactions
and update MPT as fast as it can. While technically all of these routines
could share single DAO (they are working with different KV sets) benchmarking
shows that using separate DAOs and then persisting them to lower one actually
works about 7-8%% better. At the same time we can simplify DAOs used, Cached
one is only relevant for AER processing because it caches NEP-17 tracking
data, everything else can do just fine with Simple.

The change was tested for performance with neo-bench (single node, 10 workers,
LevelDB) on two machines and block dump processing (RC4 testnet up to 50825
with VerifyBlocks set to false) on i7-8565U. neo-bench creates huge blocks
with lots of transactions while RC4 dump mostly consists of empty blocks.

Reference results (06c3dda5d1):

Ryzen 9 5950X:
RPS ≈ 20059.569   21186.328   20158.983   ≈ 20468   ±  3.05%
TPS ≈ 19544.993   20585.450   19658.338   ≈ 19930   ±  2.86%
CPU ≈    18.682%     23.877%     22.852%  ≈    21.8 ± 12.62%
Mem ≈   618.981MB   559.246MB   541.539MB ≈   573   ±  7.08%

Core i7-8565U:
RPS ≈ 5927.082   6526.739   6372.115   ≈ 6275   ± 4.96%
TPS ≈ 5899.531   6477.187   6329.515   ≈ 6235   ± 4.81%
CPU ≈   56.346%    61.955%    58.125%  ≈   58.8 ± 4.87%
Mem ≈  212.191MB  224.974MB  205.479MB ≈  214   ± 4.62%

DB restore:
real    0m12.683s 0m13.222s 0m13.382s  ≈ 13.096 ±  2.80%
user    0m18.501s 0m19.163s 0m19.489s  ≈ 19.051 ±  2.64%
sys      0m1.404s  0m1.396s  0m1.666s  ≈  1.489 ± 10.32%

After the change:

Ryzen 9 5950X:
RPS ≈ 23056.899   22822.015   23006.543   ≈ 22962   ± 0.54%
TPS ≈ 22594.785   22292.071   22800.857   ≈ 22562   ± 1.13%
CPU ≈    24.262%     23.185%     25.921%  ≈    24.5 ± 5.65%
Mem ≈   614.254MB   613.204MB   555.491MB ≈   594   ± 5.66%

Core i7-8565U:
RPS ≈ 6378.702   6423.927   6363.788      ≈ 6389   ± 0.49%
TPS ≈ 6327.072   6372.552   6311.179      ≈ 6337   ± 0.50%
CPU ≈   57.599%    58.622%    59.737%     ≈   58.7 ± 1.82%
Mem ≈  198.697MB  188.746MB  200.235MB    ≈  196   ± 3.18%

DB restore:
real    0m13.576s 0m13.334s 0m12.757s  ≈  13.222 ±  3.18%
user    0m19.113s 0m19.490s 0m20.197s  ≈  19.600 ±  2.81%
sys      0m2.211s  0m1.558s  0m1.559s  ≈   1.776 ± 21.21%

On Ryzen 9 we've got 12% better RPS, 13% better TPS with 12% CPU and 3% RAM
more used. Core i7-8565U changes don't seem to be statistically significant:
1.8% more RPS, 1.6% more TPS with about the same CPU and 8.5% less RAM
used. It also is 1% worse in DB restore time.

The result is somewhat expected, on a powerful machine with lots of spare
cores we get 10%+ better results while on average resource-constrained laptop it
doesn't change much (the machine is already saturated). Overall, this seems to
be worthwhile.
2021-07-30 15:45:17 +03:00
Roman Khimov
06c3dda5d1
Merge pull request #2093 from nspcc-dev/states-exchange/drop-nep17-balance-state
core: implement dynamic NEP17 balances tracking
2021-07-29 19:08:42 +03:00
Anna Shaleva
a30e48ff90 core: increment the DB version
DB scheme has been changed.
2021-07-29 10:23:13 +03:00
Anna Shaleva
e8bed184d5 core: implement dynamic NEP17 balances tracking
Request NEP17 balances from a set of NEP17 contracts instead of getting
them from storage. LastUpdatedBlock tracking remains untouched, because
there's no way to retrieve it dynamically.
2021-07-29 10:23:01 +03:00