Optimize max VersionVector in ApplyChanges to improve memory efficiency #1164
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
WalkthroughThe pull request modifies the handling of change IDs and version vectors across multiple components. The Changes
Sequence Diagram(s)sequenceDiagram
participant Caller
participant Converter
participant IDFactory
Caller->>Converter: Call fromChangeID(pbChange)
alt Extraction succeeds
Converter->>Caller: Return valid change.ID
else Extraction fails
Converter->>IDFactory: Construct new change.ID with initial values
IDFactory-->>Converter: Return detailed change.ID
Converter->>Caller: Return detailed change.ID
end
Possibly related PRs
Suggested reviewers
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
⏰ Context from checks skipped due to timeout of 90000ms (3)
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
There was a problem hiding this comment.
Go Benchmark Analysis 📊
This is a comparison result between the previous(e687d61) and the current commit(7bbe9e5).
Significant Changes (≥20% difference)
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| BenchmarkVersionVector/clients_1000/ (B/op) | 22.07 GB | 6.58 GB | 🟢 -70.16% |
| BenchmarkVersionVector/clients_1000/ (4_attach(ms)) | 249.00 ms | 104.00 ms | 🟢 -58.23% |
| BenchmarkSync/memory_sync_10000_test/ (ns/op) | 7.47 ms | 10.05 ms | 🔴 +34.52% |
| BenchmarkVersionVector/clients_1000/ (ns/op) | 60.97 s | 48.76 s | 🟢 -20.03% |
Key Observations 🔍
- Significant improvements were observed in the
BenchmarkVersionVector/clients_1000/suite, with a notable decrease in memory usage (B/op) by 70.16% and a significant improvement in attachment speed (4_attach(ms)) by 58.23%. - The
BenchmarkSync/memory_sync_10000_test/suite showed a significant increase in operation time (ns/op) by 34.52%, indicating a performance degradation in memory synchronization. - Overall, several benchmarks across different suites showcased slight performance improvements or stability, with some minor fluctuations in speed and memory usage.
Since no other significant changes (≥20% difference) were observed in the remaining benchmark suites, the focus should be on optimizing memory synchronization to reverse the performance degradation trend noted.
Clock Analysis
Lamport (v0.5.2)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 84.96 ms | 793.94 ms | 34,794.80 ms |
| Memory Allocations | 35.11 MB | 219.92 MB | 4.91 GB |
| Number of Allocations (allocs/op) | 69,271 | 1,246,728 | 81,485,288 |
| ChangePack Size | 138.0 B | 137.0 B | 141.0 B |
| Snapshot Size | 379.0 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 2.0 ms | 1.5 ms | 4.0 ms |
| Attach Time | 4.5 ms | 11.0 ms | 31.0 ms |
| ChangePack After Detach | 138.0 B | 140.0 B | 141.0 B |
| Snapshot After Detach | 136.0 B | 137.0 B | 139.0 B |
| Push-Pull After Detach | 2.5 ms | 5.0 ms | 9.5 ms |
VV (current)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 171.98 ms | 1.50 s | 48.76 s |
| Memory Allocations | 20.94 MB | 217.05 MB | 6.58 GB |
| Number of Allocations (allocs/op) | 83,378 | 1,484,440 | 93,477,305 |
| ChangePack Size | 745.00 B | 6.14 KB | 60.16 KB |
| Snapshot Size | 379.00 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 8.00 ms | 12.00 ms | 96.00 ms |
| Attach Time | 6.00 ms | 10.00 ms | 104.00 ms |
| ChangePack After Detach | 805.00 B | 6.21 KB | 60.22 KB |
| Snapshot After Detach | 136.00 B | 137.00 B | 139.00 B |
| Push-Pull After Detach | 8.00 ms | 10.00 ms | 24.00 ms |
Summary
- Total operation time increases significantly with Version Vector compared to Lamport across all client scenarios.
- Version Vector requires more memory allocations for all client scenarios than Lamport.
- The ChangePack size and Snapshot size are larger in Version Vector compared to Lamport.
- Push-Pull Time is higher for Version Vector as the number of clients increase, indicating potential scalability issues.
- Version Vector shows faster Attach Time for 1000 clients compared to Lamport.
- Version Vector shows improvements in ChangePack After Detach, Snapshot After Detach, and Push-Pull After Detach timings compared to Lamport, especially for 1000 clients, showcasing potential efficiency gains.
Detailed Test Results
BenchmarkDocument
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| constructor_test/ (ns/op) | 1439.00 ns | 1486.00 ns | 🔴 +3.27% |
| constructor_test/ (B/op) | 1.39 KB | 1.43 KB | 🔴 +3.47% |
| constructor_test/ (allocs/op) | 24 allocs | 25 allocs | 🔴 +4.17% |
| status_test/ (ns/op) | 1028.00 ns | 1103.00 ns | 🔴 +7.30% |
| status_test/ (B/op) | 1.35 KB | 1.40 KB | 🔴 +3.55% |
| status_test/ (allocs/op) | 22 allocs | 23 allocs | 🔴 +4.55% |
| equals_test/ (ns/op) | 7864.00 ns | 7973.00 ns | 🔴 +1.39% |
| equals_test/ (B/op) | 7.56 KB | 7.71 KB | 🔴 +1.90% |
| equals_test/ (allocs/op) | 129 allocs | 132 allocs | 🔴 +2.33% |
| nested_update_test/ (ns/op) | 17079.00 ns | 17149.00 ns | 🔴 +0.41% |
| nested_update_test/ (B/op) | 12.31 KB | 12.36 KB | 🔴 +0.39% |
| nested_update_test/ (allocs/op) | 258 allocs | 259 allocs | 🔴 +0.39% |
| delete_test/ (ns/op) | 27313.00 ns | 27473.00 ns | 🔴 +0.59% |
| delete_test/ (B/op) | 15.79 KB | 15.84 KB | 🔴 +0.30% |
| delete_test/ (allocs/op) | 339 allocs | 340 allocs | 🔴 +0.29% |
| object_test/ (ns/op) | 8546.00 ns | 8773.00 ns | 🔴 +2.66% |
| object_test/ (B/op) | 7.03 KB | 7.08 KB | 🔴 +0.68% |
| object_test/ (allocs/op) | 118 allocs | 119 allocs | 🔴 +0.85% |
| array_test/ (ns/op) | 28984.00 ns | 29377.00 ns | 🔴 +1.36% |
| array_test/ (B/op) | 12.14 KB | 12.19 KB | 🔴 +0.40% |
| array_test/ (allocs/op) | 273 allocs | 274 allocs | 🔴 +0.37% |
| text_test/ (ns/op) | 32155.00 ns | 32734.00 ns | 🔴 +1.80% |
| text_test/ (B/op) | 15.19 KB | 15.24 KB | 🔴 +0.32% |
| text_test/ (allocs/op) | 484 allocs | 485 allocs | 🔴 +0.21% |
| text_composition_test/ (ns/op) | 31674.00 ns | 32376.00 ns | 🔴 +2.22% |
| text_composition_test/ (B/op) | 18.70 KB | 18.75 KB | 🔴 +0.26% |
| text_composition_test/ (allocs/op) | 501 allocs | 502 allocs | 🔴 +0.20% |
| rich_text_test/ (ns/op) | 87424.00 ns | 88340.00 ns | 🔴 +1.05% |
| rich_text_test/ (B/op) | 39.36 KB | 39.41 KB | 🔴 +0.13% |
| rich_text_test/ (allocs/op) | 1,146 allocs | 1,147 allocs | 🔴 +0.09% |
| counter_test/ (ns/op) | 18201.00 ns | 18406.00 ns | 🔴 +1.13% |
| counter_test/ (B/op) | 11.81 KB | 11.86 KB | 🔴 +0.40% |
| counter_test/ (allocs/op) | 253 allocs | 254 allocs | 🔴 +0.40% |
| text_edit_gc_100/ (ns/op) | 1.39 ms | 1.44 ms | 🔴 +3.29% |
| text_edit_gc_100/ (B/op) | 864.90 KB | 864.95 KB | ⚪ 0% |
| text_edit_gc_100/ (allocs/op) | 17,281 allocs | 17,283 allocs | 🔴 +0.01% |
| text_edit_gc_1000/ (ns/op) | 53.39 ms | 55.60 ms | 🔴 +4.14% |
| text_edit_gc_1000/ (B/op) | 46.84 MB | 46.84 MB | ⚪ 0% |
| text_edit_gc_1000/ (allocs/op) | 185,598 allocs | 185,598 allocs | ⚪ 0% |
| text_split_gc_100/ (ns/op) | 2.12 ms | 2.21 ms | 🔴 +4.12% |
| text_split_gc_100/ (B/op) | 1.58 MB | 1.58 MB | ⚪ 0% |
| text_split_gc_100/ (allocs/op) | 15,950 allocs | 15,952 allocs | 🔴 +0.01% |
| text_split_gc_1000/ (ns/op) | 128.25 ms | 134.42 ms | 🔴 +4.82% |
| text_split_gc_1000/ (B/op) | 137.79 MB | 137.79 MB | ⚪ 0% |
| text_split_gc_1000/ (allocs/op) | 185,000 allocs | 184,999 allocs | ⚪ 0% |
| text_delete_all_10000/ (ns/op) | 18.43 ms | 20.27 ms | 🔴 +9.99% |
| text_delete_all_10000/ (B/op) | 10.58 MB | 10.58 MB | ⚪ 0% |
| text_delete_all_10000/ (allocs/op) | 56,134 allocs | 56,133 allocs | ⚪ 0% |
| text_delete_all_100000/ (ns/op) | 312.31 ms | 308.88 ms | 🟢 -1.10% |
| text_delete_all_100000/ (B/op) | 105.54 MB | 105.56 MB | 🔴 +0.02% |
| text_delete_all_100000/ (allocs/op) | 566,133 allocs | 566,179 allocs | ⚪ 0% |
| text_100/ (ns/op) | 234634.00 ns | 233173.00 ns | 🟢 -0.62% |
| text_100/ (B/op) | 120.94 KB | 120.99 KB | 🔴 +0.04% |
| text_100/ (allocs/op) | 5,181 allocs | 5,182 allocs | 🔴 +0.02% |
| text_1000/ (ns/op) | 2.46 ms | 2.49 ms | 🔴 +0.93% |
| text_1000/ (B/op) | 1.16 MB | 1.16 MB | ⚪ 0% |
| text_1000/ (allocs/op) | 51,084 allocs | 51,085 allocs | ⚪ 0% |
| array_1000/ (ns/op) | 1.24 ms | 1.25 ms | 🔴 +0.92% |
| array_1000/ (B/op) | 1.09 MB | 1.09 MB | ⚪ 0% |
| array_1000/ (allocs/op) | 11,879 allocs | 11,880 allocs | ⚪ 0% |
| array_10000/ (ns/op) | 13.33 ms | 13.78 ms | 🔴 +3.33% |
| array_10000/ (B/op) | 9.89 MB | 9.89 MB | 🟢 -0.01% |
| array_10000/ (allocs/op) | 120,735 allocs | 120,731 allocs | ⚪ 0% |
| array_gc_100/ (ns/op) | 131750.00 ns | 133656.00 ns | 🔴 +1.45% |
| array_gc_100/ (B/op) | 99.89 KB | 99.93 KB | 🔴 +0.04% |
| array_gc_100/ (allocs/op) | 1,266 allocs | 1,267 allocs | 🔴 +0.08% |
| array_gc_1000/ (ns/op) | 1.42 ms | 1.45 ms | 🔴 +1.93% |
| array_gc_1000/ (B/op) | 1.14 MB | 1.14 MB | ⚪ 0% |
| array_gc_1000/ (allocs/op) | 12,926 allocs | 12,927 allocs | ⚪ 0% |
| counter_1000/ (ns/op) | 202098.00 ns | 203733.00 ns | 🔴 +0.81% |
| counter_1000/ (B/op) | 178.13 KB | 178.19 KB | 🔴 +0.03% |
| counter_1000/ (allocs/op) | 5,771 allocs | 5,772 allocs | 🔴 +0.02% |
| counter_10000/ (ns/op) | 2.17 ms | 2.18 ms | 🔴 +0.51% |
| counter_10000/ (B/op) | 2.07 MB | 2.07 MB | ⚪ 0% |
| counter_10000/ (allocs/op) | 59,778 allocs | 59,779 allocs | ⚪ 0% |
| object_1000/ (ns/op) | 1.39 ms | 1.43 ms | 🔴 +2.61% |
| object_1000/ (B/op) | 1.44 MB | 1.44 MB | 🔴 +0.02% |
| object_1000/ (allocs/op) | 9,925 allocs | 9,926 allocs | 🔴 +0.01% |
| object_10000/ (ns/op) | 14.82 ms | 15.40 ms | 🔴 +3.91% |
| object_10000/ (B/op) | 12.35 MB | 12.35 MB | 🟢 -0.02% |
| object_10000/ (allocs/op) | 101,232 allocs | 101,225 allocs | ⚪ 0% |
| tree_100/ (ns/op) | 1.02 ms | 1.06 ms | 🔴 +3.35% |
| tree_100/ (B/op) | 951.02 KB | 951.08 KB | ⚪ 0% |
| tree_100/ (allocs/op) | 6,102 allocs | 6,103 allocs | 🔴 +0.02% |
| tree_1000/ (ns/op) | 74.23 ms | 78.64 ms | 🔴 +5.94% |
| tree_1000/ (B/op) | 86.58 MB | 86.58 MB | ⚪ 0% |
| tree_1000/ (allocs/op) | 60,111 allocs | 60,113 allocs | ⚪ 0% |
| tree_10000/ (ns/op) | 9.68 s | 10.14 s | 🔴 +4.80% |
| tree_10000/ (B/op) | 8.58 GB | 8.58 GB | ⚪ 0% |
| tree_10000/ (allocs/op) | 600,173 allocs | 600,182 allocs | ⚪ 0% |
| tree_delete_all_1000/ (ns/op) | 78.41 ms | 80.94 ms | 🔴 +3.24% |
| tree_delete_all_1000/ (B/op) | 87.57 MB | 87.57 MB | ⚪ 0% |
| tree_delete_all_1000/ (allocs/op) | 75,289 allocs | 75,288 allocs | ⚪ 0% |
| tree_edit_gc_100/ (ns/op) | 3.96 ms | 3.91 ms | 🟢 -1.30% |
| tree_edit_gc_100/ (B/op) | 4.15 MB | 4.15 MB | ⚪ 0% |
| tree_edit_gc_100/ (allocs/op) | 15,147 allocs | 15,148 allocs | ⚪ 0% |
| tree_edit_gc_1000/ (ns/op) | 332.75 ms | 327.94 ms | 🟢 -1.44% |
| tree_edit_gc_1000/ (B/op) | 384.04 MB | 384.04 MB | ⚪ 0% |
| tree_edit_gc_1000/ (allocs/op) | 154,952 allocs | 154,952 allocs | ⚪ 0% |
| tree_split_gc_100/ (ns/op) | 2.67 ms | 2.68 ms | 🔴 +0.29% |
| tree_split_gc_100/ (B/op) | 2.41 MB | 2.41 MB | ⚪ 0% |
| tree_split_gc_100/ (allocs/op) | 11,131 allocs | 11,132 allocs | ⚪ 0% |
| tree_split_gc_1000/ (ns/op) | 197.74 ms | 198.46 ms | 🔴 +0.36% |
| tree_split_gc_1000/ (B/op) | 222.50 MB | 222.50 MB | ⚪ 0% |
| tree_split_gc_1000/ (allocs/op) | 122,053 allocs | 122,068 allocs | 🔴 +0.01% |
BenchmarkRPC
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| client_to_server/ (ns/op) | 431.85 ms | 426.93 ms | 🟢 -1.14% |
| client_to_server/ (B/op) | 16.13 MB | 16.11 MB | 🟢 -0.15% |
| client_to_server/ (allocs/op) | 223,674 allocs | 223,151 allocs | 🟢 -0.23% |
| client_to_client_via_server/ (ns/op) | 788.62 ms | 809.03 ms | 🔴 +2.59% |
| client_to_client_via_server/ (B/op) | 37.20 MB | 38.12 MB | 🔴 +2.48% |
| client_to_client_via_server/ (allocs/op) | 478,656 allocs | 484,535 allocs | 🔴 +1.23% |
| attach_large_document/ (ns/op) | 1.32 s | 1.23 s | 🟢 -7.13% |
| attach_large_document/ (B/op) | 1.89 GB | 1.90 GB | 🔴 +0.44% |
| attach_large_document/ (allocs/op) | 12,321 allocs | 12,418 allocs | 🔴 +0.79% |
| adminCli_to_server/ (ns/op) | 542.08 ms | 541.25 ms | 🟢 -0.15% |
| adminCli_to_server/ (B/op) | 21.76 MB | 20.38 MB | 🟢 -6.33% |
| adminCli_to_server/ (allocs/op) | 291,952 allocs | 291,953 allocs | ⚪ 0% |
BenchmarkLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 82.86 ns | 82.48 ns | 🟢 -0.46% |
| (B/op) | 32.00 B | 32.00 B | ⚪ 0% |
| (allocs/op) | 1 allocs | 1 allocs | ⚪ 0% |
BenchmarkLockerParallel
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 45.80 ns | 45.15 ns | 🟢 -1.42% |
| (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkLockerMoreKeys
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 180.50 ns | 177.10 ns | 🟢 -1.88% |
| (B/op) | 31.00 B | 31.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkRWLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| RWLock_rate_2/ (ns/op) | 50.25 ns | 49.43 ns | 🟢 -1.63% |
| RWLock_rate_2/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_2/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_10/ (ns/op) | 44.88 ns | 44.25 ns | 🟢 -1.40% |
| RWLock_rate_10/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_10/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_100/ (ns/op) | 63.08 ns | 59.33 ns | 🟢 -5.94% |
| RWLock_rate_100/ (B/op) | 2.00 B | 2.00 B | ⚪ 0% |
| RWLock_rate_100/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_1000/ (ns/op) | 91.91 ns | 88.96 ns | 🟢 -3.21% |
| RWLock_rate_1000/ (B/op) | 8.00 B | 8.00 B | ⚪ 0% |
| RWLock_rate_1000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkChange
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_10_Changes/ (ns/op) | 4.54 ms | 4.59 ms | 🔴 +1.21% |
| Push_10_Changes/ (B/op) | 150.42 KB | 150.21 KB | 🟢 -0.14% |
| Push_10_Changes/ (allocs/op) | 1,623 allocs | 1,616 allocs | 🟢 -0.43% |
| Push_100_Changes/ (ns/op) | 16.52 ms | 16.71 ms | 🔴 +1.15% |
| Push_100_Changes/ (B/op) | 770.59 KB | 776.69 KB | 🔴 +0.79% |
| Push_100_Changes/ (allocs/op) | 8,509 allocs | 8,504 allocs | 🟢 -0.06% |
| Push_1000_Changes/ (ns/op) | 129.20 ms | 132.48 ms | 🔴 +2.54% |
| Push_1000_Changes/ (B/op) | 7.22 MB | 7.30 MB | 🔴 +1.07% |
| Push_1000_Changes/ (allocs/op) | 79,325 allocs | 79,323 allocs | ⚪ 0% |
| Pull_10_Changes/ (ns/op) | 3.70 ms | 3.79 ms | 🔴 +2.26% |
| Pull_10_Changes/ (B/op) | 124.59 KB | 124.01 KB | 🟢 -0.46% |
| Pull_10_Changes/ (allocs/op) | 1,456 allocs | 1,456 allocs | ⚪ 0% |
| Pull_100_Changes/ (ns/op) | 5.32 ms | 5.49 ms | 🔴 +3.09% |
| Pull_100_Changes/ (B/op) | 354.61 KB | 353.01 KB | 🟢 -0.45% |
| Pull_100_Changes/ (allocs/op) | 5,182 allocs | 5,181 allocs | 🟢 -0.02% |
| Pull_1000_Changes/ (ns/op) | 10.88 ms | 11.58 ms | 🔴 +6.45% |
| Pull_1000_Changes/ (B/op) | 2.20 MB | 2.20 MB | 🟢 -0.10% |
| Pull_1000_Changes/ (allocs/op) | 44,681 allocs | 44,681 allocs | ⚪ 0% |
BenchmarkSnapshot
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_3KB_snapshot/ (ns/op) | 19.55 ms | 19.21 ms | 🟢 -1.78% |
| Push_3KB_snapshot/ (B/op) | 905.58 KB | 903.03 KB | 🟢 -0.28% |
| Push_3KB_snapshot/ (allocs/op) | 8,516 allocs | 8,515 allocs | 🟢 -0.01% |
| Push_30KB_snapshot/ (ns/op) | 132.18 ms | 135.90 ms | 🔴 +2.82% |
| Push_30KB_snapshot/ (B/op) | 8.24 MB | 8.10 MB | 🟢 -1.73% |
| Push_30KB_snapshot/ (allocs/op) | 89,008 allocs | 89,229 allocs | 🔴 +0.25% |
| Pull_3KB_snapshot/ (ns/op) | 7.80 ms | 7.61 ms | 🟢 -2.44% |
| Pull_3KB_snapshot/ (B/op) | 1.12 MB | 1.06 MB | 🟢 -5.06% |
| Pull_3KB_snapshot/ (allocs/op) | 20,064 allocs | 19,257 allocs | 🟢 -4.02% |
| Pull_30KB_snapshot/ (ns/op) | 19.91 ms | 20.44 ms | 🔴 +2.64% |
| Pull_30KB_snapshot/ (B/op) | 9.31 MB | 8.77 MB | 🟢 -5.83% |
| Pull_30KB_snapshot/ (allocs/op) | 193,610 allocs | 185,677 allocs | 🟢 -4.10% |
BenchmarkSplayTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| stress_test_100000/ (ns/op) | 0.19 ns | 0.19 ns | 🟢 -3.15% |
| stress_test_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_200000/ (ns/op) | 0.40 ns | 0.38 ns | 🟢 -3.75% |
| stress_test_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_300000/ (ns/op) | 0.57 ns | 0.58 ns | 🔴 +1.50% |
| stress_test_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_100000/ (ns/op) | 0.01 ns | 0.01 ns | 🔴 +5.51% |
| random_access_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_200000/ (ns/op) | 0.03 ns | 0.03 ns | 🔴 +5.75% |
| random_access_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_300000/ (ns/op) | 0.04 ns | 0.05 ns | 🔴 +7.78% |
| random_access_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| editing_trace_bench/ (ns/op) | 0.00 ns | 0.00 ns | 🔴 +19.08% |
| editing_trace_bench/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| editing_trace_bench/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkSync
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| memory_sync_10_test/ (ns/op) | 7288.00 ns | 7332.00 ns | 🔴 +0.60% |
| memory_sync_10_test/ (B/op) | 1.34 KB | 1.34 KB | ⚪ 0% |
| memory_sync_10_test/ (allocs/op) | 35 allocs | 35 allocs | ⚪ 0% |
| memory_sync_100_test/ (ns/op) | 55353.00 ns | 57178.00 ns | 🔴 +3.30% |
| memory_sync_100_test/ (B/op) | 9.51 KB | 9.50 KB | 🟢 -0.04% |
| memory_sync_100_test/ (allocs/op) | 268 allocs | 268 allocs | ⚪ 0% |
| memory_sync_1000_test/ (ns/op) | 616285.00 ns | 628491.00 ns | 🔴 +1.98% |
| memory_sync_1000_test/ (B/op) | 75.92 KB | 75.70 KB | 🟢 -0.29% |
| memory_sync_1000_test/ (allocs/op) | 2,111 allocs | 2,105 allocs | 🟢 -0.28% |
| memory_sync_10000_test/ (ns/op) | 7.47 ms | 10.05 ms | 🔴 +34.52% |
| memory_sync_10000_test/ (B/op) | 761.49 KB | 762.59 KB | 🔴 +0.14% |
| memory_sync_10000_test/ (allocs/op) | 20,475 allocs | 20,515 allocs | 🔴 +0.20% |
BenchmarkTextEditing
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 5.18 s | 5.39 s | 🔴 +3.97% |
| (B/op) | 3.92 GB | 3.92 GB | ⚪ 0% |
| (allocs/op) | 20,619,777 allocs | 20,619,832 allocs | ⚪ 0% |
BenchmarkTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| 10000_vertices_to_protobuf/ (ns/op) | 4.17 ms | 4.68 ms | 🔴 +12.19% |
| 10000_vertices_to_protobuf/ (B/op) | 6.36 MB | 6.36 MB | ⚪ 0% |
| 10000_vertices_to_protobuf/ (allocs/op) | 70,025 allocs | 70,025 allocs | ⚪ 0% |
| 10000_vertices_from_protobuf/ (ns/op) | 217.30 ms | 239.31 ms | 🔴 +10.13% |
| 10000_vertices_from_protobuf/ (B/op) | 442.30 MB | 442.31 MB | ⚪ 0% |
| 10000_vertices_from_protobuf/ (allocs/op) | 290,038 allocs | 290,039 allocs | ⚪ 0% |
| 20000_vertices_to_protobuf/ (ns/op) | 8.84 ms | 9.45 ms | 🔴 +6.91% |
| 20000_vertices_to_protobuf/ (B/op) | 12.89 MB | 12.89 MB | ⚪ 0% |
| 20000_vertices_to_protobuf/ (allocs/op) | 140,028 allocs | 140,028 allocs | ⚪ 0% |
| 20000_vertices_from_protobuf/ (ns/op) | 884.61 ms | 903.91 ms | 🔴 +2.18% |
| 20000_vertices_from_protobuf/ (B/op) | 1.70 GB | 1.70 GB | ⚪ 0% |
| 20000_vertices_from_protobuf/ (allocs/op) | 580,043 allocs | 580,050 allocs | ⚪ 0% |
| 30000_vertices_to_protobuf/ (ns/op) | 14.26 ms | 14.76 ms | 🔴 +3.50% |
| 30000_vertices_to_protobuf/ (B/op) | 18.98 MB | 18.98 MB | ⚪ 0% |
| 30000_vertices_to_protobuf/ (allocs/op) | 210,029 allocs | 210,030 allocs | ⚪ 0% |
| 30000_vertices_from_protobuf/ (ns/op) | 2.00 s | 2.05 s | 🔴 +2.63% |
| 30000_vertices_from_protobuf/ (B/op) | 3.75 GB | 3.75 GB | ⚪ 0% |
| 30000_vertices_from_protobuf/ (allocs/op) | 870,147 allocs | 870,053 allocs | 🟢 -0.01% |
BenchmarkVersionVector
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| clients_10/ (ns/op) | 160.21 ms | 171.98 ms | 🔴 +7.34% |
| clients_10/ (1_changepack(bytes)) | 745.00 B | 745.00 B | ⚪ 0% |
| clients_10/ (2_snapshot(bytes)) | 379.00 B | 379.00 B | ⚪ 0% |
| clients_10/ (3_pushpull(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (4_attach(ms)) | 6.00 ms | 6.00 ms | ⚪ 0% |
| clients_10/ (5_changepack_after_detach(bytes)) | 805.00 B | 805.00 B | ⚪ 0% |
| clients_10/ (6_snapshot_after_detach(bytes)) | 136.00 B | 136.00 B | ⚪ 0% |
| clients_10/ (7_pushpull_after_detach(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (B/op) | 19.93 MB | 20.94 MB | 🔴 +5.05% |
| clients_10/ (allocs/op) | 83,762 allocs | 83,378 allocs | 🟢 -0.46% |
| clients_100/ (ns/op) | 1.41 s | 1.50 s | 🔴 +6.33% |
| clients_100/ (1_changepack(bytes)) | 6.14 KB | 6.14 KB | ⚪ 0% |
| clients_100/ (2_snapshot(bytes)) | 3.08 KB | 3.08 KB | ⚪ 0% |
| clients_100/ (3_pushpull(ms)) | 11.00 ms | 12.00 ms | 🔴 +9.09% |
| clients_100/ (4_attach(ms)) | 11.00 ms | 10.00 ms | 🟢 -9.09% |
| clients_100/ (5_changepack_after_detach(bytes)) | 6.21 KB | 6.21 KB | ⚪ 0% |
| clients_100/ (6_snapshot_after_detach(bytes)) | 137.00 B | 137.00 B | ⚪ 0% |
| clients_100/ (7_pushpull_after_detach(ms)) | 9.00 ms | 10.00 ms | 🔴 +11.11% |
| clients_100/ (B/op) | 230.31 MB | 217.05 MB | 🟢 -5.76% |
| clients_100/ (allocs/op) | 1,539,768 allocs | 1,484,440 allocs | 🟢 -3.59% |
| clients_1000/ (ns/op) | 60.97 s | 48.76 s | 🟢 -20.03% |
| clients_1000/ (1_changepack(bytes)) | 60.16 KB | 60.16 KB | ⚪ 0% |
| clients_1000/ (2_snapshot(bytes)) | 30.08 KB | 30.08 KB | ⚪ 0% |
| clients_1000/ (3_pushpull(ms)) | 95.00 ms | 96.00 ms | 🔴 +1.05% |
| clients_1000/ (4_attach(ms)) | 249.00 ms | 104.00 ms | 🟢 -58.23% |
| clients_1000/ (5_changepack_after_detach(bytes)) | 60.22 KB | 60.22 KB | ⚪ 0% |
| clients_1000/ (6_snapshot_after_detach(bytes)) | 139.00 B | 139.00 B | ⚪ 0% |
| clients_1000/ (7_pushpull_after_detach(ms)) | 26.00 ms | 24.00 ms | 🟢 -7.69% |
| clients_1000/ (B/op) | 22.07 GB | 6.58 GB | 🟢 -70.16% |
| clients_1000/ (allocs/op) | 111,762,106 allocs | 93,477,305 allocs | 🟢 -16.36% |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #1164 +/- ##
==========================================
- Coverage 38.56% 38.32% -0.24%
==========================================
Files 170 172 +2
Lines 25441 25803 +362
==========================================
+ Hits 9812 9890 +78
- Misses 14808 15079 +271
- Partials 821 834 +13 ☔ View full report in Codecov by Sentry. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
api/converter/from_pb.go (1)
154-184: Memory optimization achieved through improved error handling.The changes successfully optimize memory efficiency by:
- Avoiding unnecessary version vector copies during error handling
- Using initial values instead of default copies
- Maintaining consistent error handling patterns
This aligns well with the PR's objective of improving memory efficiency.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
api/converter/from_pb.go(1 hunks)pkg/document/change/id.go(2 hunks)pkg/document/internal_document.go(2 hunks)pkg/document/time/version_vector.go(1 hunks)test/helper/helper.go(1 hunks)
🔇 Additional comments (9)
pkg/document/time/version_vector.go (1)
159-183: LGTM! The optimization improves memory efficiency.The changes effectively optimize memory usage by:
- Modifying the vector in place instead of creating a new one.
- Using pointer parameter to avoid unnecessary copies.
Note: The implementation correctly handles the nil case and properly dereferences the pointer when accessing elements.
pkg/document/change/id.go (2)
116-116: LGTM! Correctly adapted to the new Max method signature.The call to
Maxhas been updated to pass a pointer tootherVV, aligning with the optimized implementation.
138-138: LGTM! Correctly adapted to the new Max method signature.The call to
Maxhas been updated to pass a pointer tovector, aligning with the optimized implementation.pkg/document/internal_document.go (2)
100-105: LGTM! Improved initialization with explicit parameters.The initialization now uses
change.NewIDwith explicit parameters, making the code more maintainable and easier to understand.
124-130: LGTM! Consistent initialization pattern.The initialization follows the same pattern as in
NewInternalDocument, maintaining consistency across the codebase.test/helper/helper.go (1)
120-125: LGTM! Consistent with the new initialization pattern.The test helper has been updated to use
change.NewIDwith explicit parameters, maintaining consistency with the changes in the main codebase.api/converter/from_pb.go (3)
157-164: LGTM: Consistent error handling with initial values.The error handling for
actorIDconversion now returns a new change ID with initial values, which is more informative than returning a default ID.
168-175: LGTM: Consistent error handling pattern.The error handling for version vector conversion follows the same pattern, maintaining consistency in the codebase.
177-183: LGTM: Proper initialization of change ID.The successful case properly initializes a new change ID with all required parameters.
raararaara
force-pushed
the
in-place-vv
branch
from
a596d99 to
f219d23
Compare
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
pkg/document/internal_document.go (1)
100-100: Improve readability by breaking down the long line.The line exceeds the maximum length of 120 characters. Consider reformatting for better readability.
- changeID: change.NewID(change.InitialClientSeq, change.InitialServerSeq, change.InitialLamport, time.InitialActorID, time.NewVersionVector()), + changeID: change.NewID( + change.InitialClientSeq, + change.InitialServerSeq, + change.InitialLamport, + time.InitialActorID, + time.NewVersionVector(), + ),🧰 Tools
🪛 golangci-lint (1.62.2)
100-100: the line is 149 characters long, which exceeds the maximum of 120 characters.
(lll)
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
api/converter/from_pb.go(1 hunks)pkg/document/internal_document.go(2 hunks)test/helper/helper.go(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (2)
- api/converter/from_pb.go
- test/helper/helper.go
🧰 Additional context used
🪛 golangci-lint (1.62.2)
pkg/document/internal_document.go
100-100: the line is 149 characters long, which exceeds the maximum of 120 characters.
(lll)
⏰ Context from checks skipped due to timeout of 90000ms (3)
- GitHub Check: complex-test
- GitHub Check: bench
- GitHub Check: build
🔇 Additional comments (2)
pkg/document/internal_document.go (2)
119-126: LGTM! Well-structured initialization.The code is well-organized with each parameter on a new line, making it easy to read and maintain. The use of
SetClocksafter initialization properly sets the lamport and vector values.
134-134: LGTM! Simple and clear assignment.The assignment of the constructed
changeIDis straightforward and clear.
raararaara
force-pushed
the
in-place-vv
branch
from
f219d23 to
75ddf38
Compare
There was a problem hiding this comment.
Go Benchmark Analysis 📊
This is a comparison result between the previous(e687d61) and the current commit(b42eab4).
Significant Changes (≥20% difference)
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| BenchmarkVersionVector/clients_1000/ (B/op) | 22.07 GB | 6.59 GB | 🟢 -70.14% |
| BenchmarkVersionVector/clients_1000/ (4_attach(ms)) | 249.00 ms | 102.00 ms | 🟢 -59.04% |
| BenchmarkVersionVector/clients_100/ (3_pushpull(ms)) | 11.00 ms | 15.00 ms | 🔴 +36.36% |
| BenchmarkVersionVector/clients_1000/ (ns/op) | 60.97 s | 47.44 s | 🟢 -22.20% |
Key Observations 🔍
-
BenchmarkVersionVector:
- For the suite
BenchmarkVersionVector/clients_1000/, significant improvements were seen:- There was a remarkable decrease in memory usage by approximately 70.14%.
- The
4_attachoperation time reduced significantly by about 59.04%.
- Notably, the
3_pushpulloperation time forclients_100/increased by approximately 36.36%.
- For the suite
-
BenchmarkSnapshot:
- In the suite
BenchmarkSnapshot, the data showed fluctuations in performance:- The operation time for
Pull_30KB_snapshotslightly increased by 0.33%. - However, for
Push_30KB_snapshot, the operation time increased by 5.22%.
- The operation time for
- In the suite
-
BenchmarkRPC:
- Suite
BenchmarkRPChighlighted improvements as well as minor setbacks:client_to_serveroperation time increased slightly by 0.07%.- Notably, memory usage decreased for
client_to_serverandadminCli_to_serveroperations by 0.12% and 6.07% respectively.
- Suite
-
Overall Trends:
- Across various benchmark suites, there were instances of both improvements and declines in performance metrics.
- Generally, there seemed to be more instances of performance enhancements (🟢) than deteriorations (🔴).
- Memory optimizations were observed in several benchmarks, suggesting efficiency gains in resource management.
- Operation times fluctuated, with some operations showing considerable variations in performance.
Overall, the benchmark data reflects a mix of improvements and declines in different performance aspects, showcasing the dynamic nature of optimizations and regressions in the tested scenarios.
Clock Analysis
Lamport (v0.5.2)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 84.96 ms | 793.94 ms | 34.79 s |
| Memory Allocations | 35.11 MB | 219.92 MB | 4.91 GB |
| Number of Allocations (allocs/op) | 69,271 | 1,246,728 | 81,485,288 |
| ChangePack Size | 138.0 B | 137.0 B | 141.0 B |
| Snapshot Size | 379.0 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 2.0 ms | 1.5 ms | 4.0 ms |
| Attach Time | 4.5 ms | 11.0 ms | 31.0 ms |
| ChangePack After Detach | 138.0 B | 140.0 B | 141.0 B |
| Snapshot After Detach | 136.0 B | 137.0 B | 139.0 B |
| Push-Pull After Detach | 2.5 ms | 5.0 ms | 9.5 ms |
VV (current)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 163.10 ms | 1.46 s | 47.44 s |
| Memory Allocations | 20.28 MB | 215.40 MB | 6.59 GB |
| Number of Allocations (allocs/op) | 83,354 | 1,484,696 | 93,478,838 |
| ChangePack Size | 745.00 B | 6.14 KB | 60.16 KB |
| Snapshot Size | 379.00 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 8.00 ms | 15.00 ms | 95.00 ms |
| Attach Time | 6.00 ms | 10.00 ms | 102.00 ms |
| ChangePack After Detach | 805.00 B | 6.21 KB | 60.22 KB |
| Snapshot After Detach | 136.00 B | 137.00 B | 139.00 B |
| Push-Pull After Detach | 8.00 ms | 9.00 ms | 23.00 ms |
Summary
- Lamport clock generally performs better in terms of total operation time across all client loads compared to the Version Vector.
- Version Vector has higher memory allocations and number of allocations as the number of clients increases, indicating a more resource-intensive operation.
- Push-Pull time for Version Vector drastically increases with 1000 clients, suggesting potential scalability challenges.
- Attach times for Lamport are generally lower than Version Vector, indicating faster processing of operations.
- ChangePack and Snapshot sizes are smaller for Lamport across all client loads, showing better efficiency in data representation.
- The Version Vector shows significant improvements in total operation time and memory usage with 1000 clients compared to Lamport clock.
Detailed Test Results
BenchmarkDocument
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| constructor_test/ (ns/op) | 1439.00 ns | 1475.00 ns | 🔴 +2.50% |
| constructor_test/ (B/op) | 1.39 KB | 1.43 KB | 🔴 +3.47% |
| constructor_test/ (allocs/op) | 24 allocs | 25 allocs | 🔴 +4.17% |
| status_test/ (ns/op) | 1028.00 ns | 1078.00 ns | 🔴 +4.86% |
| status_test/ (B/op) | 1.35 KB | 1.40 KB | 🔴 +3.55% |
| status_test/ (allocs/op) | 22 allocs | 23 allocs | 🔴 +4.55% |
| equals_test/ (ns/op) | 7864.00 ns | 8013.00 ns | 🔴 +1.89% |
| equals_test/ (B/op) | 7.56 KB | 7.71 KB | 🔴 +1.90% |
| equals_test/ (allocs/op) | 129 allocs | 132 allocs | 🔴 +2.33% |
| nested_update_test/ (ns/op) | 17079.00 ns | 17841.00 ns | 🔴 +4.46% |
| nested_update_test/ (B/op) | 12.31 KB | 12.36 KB | 🔴 +0.39% |
| nested_update_test/ (allocs/op) | 258 allocs | 259 allocs | 🔴 +0.39% |
| delete_test/ (ns/op) | 27313.00 ns | 26273.00 ns | 🟢 -3.81% |
| delete_test/ (B/op) | 15.79 KB | 15.84 KB | 🔴 +0.30% |
| delete_test/ (allocs/op) | 339 allocs | 340 allocs | 🔴 +0.29% |
| object_test/ (ns/op) | 8546.00 ns | 8628.00 ns | 🔴 +0.96% |
| object_test/ (B/op) | 7.03 KB | 7.08 KB | 🔴 +0.70% |
| object_test/ (allocs/op) | 118 allocs | 119 allocs | 🔴 +0.85% |
| array_test/ (ns/op) | 28984.00 ns | 28377.00 ns | 🟢 -2.09% |
| array_test/ (B/op) | 12.14 KB | 12.19 KB | 🔴 +0.40% |
| array_test/ (allocs/op) | 273 allocs | 274 allocs | 🔴 +0.37% |
| text_test/ (ns/op) | 32155.00 ns | 32560.00 ns | 🔴 +1.26% |
| text_test/ (B/op) | 15.19 KB | 15.24 KB | 🔴 +0.32% |
| text_test/ (allocs/op) | 484 allocs | 485 allocs | 🔴 +0.21% |
| text_composition_test/ (ns/op) | 31674.00 ns | 32523.00 ns | 🔴 +2.68% |
| text_composition_test/ (B/op) | 18.70 KB | 18.75 KB | 🔴 +0.26% |
| text_composition_test/ (allocs/op) | 501 allocs | 502 allocs | 🔴 +0.20% |
| rich_text_test/ (ns/op) | 87424.00 ns | 85796.00 ns | 🟢 -1.86% |
| rich_text_test/ (B/op) | 39.36 KB | 39.40 KB | 🔴 +0.12% |
| rich_text_test/ (allocs/op) | 1,146 allocs | 1,147 allocs | 🔴 +0.09% |
| counter_test/ (ns/op) | 18201.00 ns | 18619.00 ns | 🔴 +2.30% |
| counter_test/ (B/op) | 11.81 KB | 11.86 KB | 🔴 +0.41% |
| counter_test/ (allocs/op) | 253 allocs | 254 allocs | 🔴 +0.40% |
| text_edit_gc_100/ (ns/op) | 1.39 ms | 1.40 ms | 🔴 +0.62% |
| text_edit_gc_100/ (B/op) | 864.90 KB | 864.91 KB | ⚪ 0% |
| text_edit_gc_100/ (allocs/op) | 17,281 allocs | 17,282 allocs | ⚪ 0% |
| text_edit_gc_1000/ (ns/op) | 53.39 ms | 53.93 ms | 🔴 +1.01% |
| text_edit_gc_1000/ (B/op) | 46.84 MB | 46.84 MB | ⚪ 0% |
| text_edit_gc_1000/ (allocs/op) | 185,598 allocs | 185,590 allocs | ⚪ 0% |
| text_split_gc_100/ (ns/op) | 2.12 ms | 2.13 ms | 🔴 +0.21% |
| text_split_gc_100/ (B/op) | 1.58 MB | 1.58 MB | ⚪ 0% |
| text_split_gc_100/ (allocs/op) | 15,950 allocs | 15,952 allocs | 🔴 +0.01% |
| text_split_gc_1000/ (ns/op) | 128.25 ms | 131.55 ms | 🔴 +2.58% |
| text_split_gc_1000/ (B/op) | 137.79 MB | 137.79 MB | ⚪ 0% |
| text_split_gc_1000/ (allocs/op) | 185,000 allocs | 184,991 allocs | ⚪ 0% |
| text_delete_all_10000/ (ns/op) | 18.43 ms | 17.48 ms | 🟢 -5.16% |
| text_delete_all_10000/ (B/op) | 10.58 MB | 10.58 MB | ⚪ 0% |
| text_delete_all_10000/ (allocs/op) | 56,134 allocs | 56,135 allocs | ⚪ 0% |
| text_delete_all_100000/ (ns/op) | 312.31 ms | 271.82 ms | 🟢 -12.96% |
| text_delete_all_100000/ (B/op) | 105.54 MB | 105.52 MB | 🟢 -0.02% |
| text_delete_all_100000/ (allocs/op) | 566,133 allocs | 566,112 allocs | ⚪ 0% |
| text_100/ (ns/op) | 234634.00 ns | 238225.00 ns | 🔴 +1.53% |
| text_100/ (B/op) | 120.94 KB | 120.96 KB | 🔴 +0.01% |
| text_100/ (allocs/op) | 5,181 allocs | 5,182 allocs | 🔴 +0.02% |
| text_1000/ (ns/op) | 2.46 ms | 2.52 ms | 🔴 +2.06% |
| text_1000/ (B/op) | 1.16 MB | 1.16 MB | ⚪ 0% |
| text_1000/ (allocs/op) | 51,084 allocs | 51,085 allocs | ⚪ 0% |
| array_1000/ (ns/op) | 1.24 ms | 1.29 ms | 🔴 +3.72% |
| array_1000/ (B/op) | 1.09 MB | 1.09 MB | ⚪ 0% |
| array_1000/ (allocs/op) | 11,879 allocs | 11,880 allocs | ⚪ 0% |
| array_10000/ (ns/op) | 13.33 ms | 13.83 ms | 🔴 +3.68% |
| array_10000/ (B/op) | 9.89 MB | 9.89 MB | ⚪ 0% |
| array_10000/ (allocs/op) | 120,735 allocs | 120,738 allocs | ⚪ 0% |
| array_gc_100/ (ns/op) | 131750.00 ns | 138209.00 ns | 🔴 +4.90% |
| array_gc_100/ (B/op) | 99.89 KB | 99.94 KB | 🔴 +0.05% |
| array_gc_100/ (allocs/op) | 1,266 allocs | 1,267 allocs | 🔴 +0.08% |
| array_gc_1000/ (ns/op) | 1.42 ms | 1.48 ms | 🔴 +3.99% |
| array_gc_1000/ (B/op) | 1.14 MB | 1.14 MB | ⚪ 0% |
| array_gc_1000/ (allocs/op) | 12,926 allocs | 12,927 allocs | ⚪ 0% |
| counter_1000/ (ns/op) | 202098.00 ns | 207995.00 ns | 🔴 +2.92% |
| counter_1000/ (B/op) | 178.13 KB | 178.19 KB | 🔴 +0.03% |
| counter_1000/ (allocs/op) | 5,771 allocs | 5,772 allocs | 🔴 +0.02% |
| counter_10000/ (ns/op) | 2.17 ms | 2.17 ms | 🔴 +0.22% |
| counter_10000/ (B/op) | 2.07 MB | 2.07 MB | ⚪ 0% |
| counter_10000/ (allocs/op) | 59,778 allocs | 59,779 allocs | ⚪ 0% |
| object_1000/ (ns/op) | 1.39 ms | 1.47 ms | 🔴 +6.02% |
| object_1000/ (B/op) | 1.44 MB | 1.44 MB | 🔴 +0.02% |
| object_1000/ (allocs/op) | 9,925 allocs | 9,926 allocs | 🔴 +0.01% |
| object_10000/ (ns/op) | 14.82 ms | 15.26 ms | 🔴 +2.98% |
| object_10000/ (B/op) | 12.35 MB | 12.35 MB | 🟢 -0.01% |
| object_10000/ (allocs/op) | 101,232 allocs | 101,227 allocs | ⚪ 0% |
| tree_100/ (ns/op) | 1.02 ms | 1.08 ms | 🔴 +5.24% |
| tree_100/ (B/op) | 951.02 KB | 951.08 KB | ⚪ 0% |
| tree_100/ (allocs/op) | 6,102 allocs | 6,103 allocs | 🔴 +0.02% |
| tree_1000/ (ns/op) | 74.23 ms | 80.32 ms | 🔴 +8.20% |
| tree_1000/ (B/op) | 86.58 MB | 86.58 MB | ⚪ 0% |
| tree_1000/ (allocs/op) | 60,111 allocs | 60,112 allocs | ⚪ 0% |
| tree_10000/ (ns/op) | 9.68 s | 9.83 s | 🔴 +1.58% |
| tree_10000/ (B/op) | 8.58 GB | 8.58 GB | ⚪ 0% |
| tree_10000/ (allocs/op) | 600,173 allocs | 600,184 allocs | ⚪ 0% |
| tree_delete_all_1000/ (ns/op) | 78.41 ms | 79.86 ms | 🔴 +1.85% |
| tree_delete_all_1000/ (B/op) | 87.57 MB | 87.57 MB | ⚪ 0% |
| tree_delete_all_1000/ (allocs/op) | 75,289 allocs | 75,290 allocs | ⚪ 0% |
| tree_edit_gc_100/ (ns/op) | 3.96 ms | 3.95 ms | 🟢 -0.37% |
| tree_edit_gc_100/ (B/op) | 4.15 MB | 4.15 MB | ⚪ 0% |
| tree_edit_gc_100/ (allocs/op) | 15,147 allocs | 15,147 allocs | ⚪ 0% |
| tree_edit_gc_1000/ (ns/op) | 332.75 ms | 327.34 ms | 🟢 -1.62% |
| tree_edit_gc_1000/ (B/op) | 384.04 MB | 384.05 MB | ⚪ 0% |
| tree_edit_gc_1000/ (allocs/op) | 154,952 allocs | 154,955 allocs | ⚪ 0% |
| tree_split_gc_100/ (ns/op) | 2.67 ms | 2.70 ms | 🔴 +1.21% |
| tree_split_gc_100/ (B/op) | 2.41 MB | 2.41 MB | ⚪ 0% |
| tree_split_gc_100/ (allocs/op) | 11,131 allocs | 11,132 allocs | ⚪ 0% |
| tree_split_gc_1000/ (ns/op) | 197.74 ms | 202.90 ms | 🔴 +2.61% |
| tree_split_gc_1000/ (B/op) | 222.50 MB | 222.50 MB | ⚪ 0% |
| tree_split_gc_1000/ (allocs/op) | 122,053 allocs | 122,076 allocs | 🔴 +0.02% |
BenchmarkRPC
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| client_to_server/ (ns/op) | 431.85 ms | 432.17 ms | 🔴 +0.07% |
| client_to_server/ (B/op) | 16.13 MB | 16.11 MB | 🟢 -0.12% |
| client_to_server/ (allocs/op) | 223,674 allocs | 223,174 allocs | 🟢 -0.22% |
| client_to_client_via_server/ (ns/op) | 788.62 ms | 813.18 ms | 🔴 +3.11% |
| client_to_client_via_server/ (B/op) | 37.20 MB | 37.05 MB | 🟢 -0.42% |
| client_to_client_via_server/ (allocs/op) | 478,656 allocs | 481,677 allocs | 🔴 +0.63% |
| attach_large_document/ (ns/op) | 1.32 s | 1.32 s | 🟢 -0.26% |
| attach_large_document/ (B/op) | 1.89 GB | 1.90 GB | 🔴 +0.62% |
| attach_large_document/ (allocs/op) | 12,321 allocs | 12,507 allocs | 🔴 +1.51% |
| adminCli_to_server/ (ns/op) | 542.08 ms | 550.59 ms | 🔴 +1.57% |
| adminCli_to_server/ (B/op) | 21.76 MB | 20.44 MB | 🟢 -6.07% |
| adminCli_to_server/ (allocs/op) | 291,952 allocs | 291,920 allocs | 🟢 -0.01% |
BenchmarkLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 82.86 ns | 81.11 ns | 🟢 -2.11% |
| (B/op) | 32.00 B | 32.00 B | ⚪ 0% |
| (allocs/op) | 1 allocs | 1 allocs | ⚪ 0% |
BenchmarkLockerParallel
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 45.80 ns | 45.46 ns | 🟢 -0.74% |
| (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkLockerMoreKeys
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 180.50 ns | 181.60 ns | 🔴 +0.61% |
| (B/op) | 31.00 B | 30.00 B | 🟢 -3.23% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkRWLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| RWLock_rate_2/ (ns/op) | 50.25 ns | 49.86 ns | 🟢 -0.78% |
| RWLock_rate_2/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_2/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_10/ (ns/op) | 44.88 ns | 44.20 ns | 🟢 -1.52% |
| RWLock_rate_10/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_10/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_100/ (ns/op) | 63.08 ns | 62.20 ns | 🟢 -1.40% |
| RWLock_rate_100/ (B/op) | 2.00 B | 2.00 B | ⚪ 0% |
| RWLock_rate_100/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_1000/ (ns/op) | 91.91 ns | 100.90 ns | 🔴 +9.78% |
| RWLock_rate_1000/ (B/op) | 8.00 B | 8.00 B | ⚪ 0% |
| RWLock_rate_1000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkChange
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_10_Changes/ (ns/op) | 4.54 ms | 4.62 ms | 🔴 +1.73% |
| Push_10_Changes/ (B/op) | 150.42 KB | 149.92 KB | 🟢 -0.33% |
| Push_10_Changes/ (allocs/op) | 1,623 allocs | 1,623 allocs | ⚪ 0% |
| Push_100_Changes/ (ns/op) | 16.52 ms | 16.98 ms | 🔴 +2.83% |
| Push_100_Changes/ (B/op) | 770.59 KB | 778.21 KB | 🔴 +0.99% |
| Push_100_Changes/ (allocs/op) | 8,509 allocs | 8,510 allocs | 🔴 +0.01% |
| Push_1000_Changes/ (ns/op) | 129.20 ms | 135.59 ms | 🔴 +4.95% |
| Push_1000_Changes/ (B/op) | 7.22 MB | 7.24 MB | 🔴 +0.30% |
| Push_1000_Changes/ (allocs/op) | 79,325 allocs | 79,325 allocs | ⚪ 0% |
| Pull_10_Changes/ (ns/op) | 3.70 ms | 3.79 ms | 🔴 +2.26% |
| Pull_10_Changes/ (B/op) | 124.59 KB | 124.42 KB | 🟢 -0.14% |
| Pull_10_Changes/ (allocs/op) | 1,456 allocs | 1,457 allocs | 🔴 +0.07% |
| Pull_100_Changes/ (ns/op) | 5.32 ms | 5.48 ms | 🔴 +2.93% |
| Pull_100_Changes/ (B/op) | 354.61 KB | 353.56 KB | 🟢 -0.29% |
| Pull_100_Changes/ (allocs/op) | 5,182 allocs | 5,181 allocs | 🟢 -0.02% |
| Pull_1000_Changes/ (ns/op) | 10.88 ms | 11.10 ms | 🔴 +2.11% |
| Pull_1000_Changes/ (B/op) | 2.20 MB | 2.20 MB | 🟢 -0.20% |
| Pull_1000_Changes/ (allocs/op) | 44,681 allocs | 44,681 allocs | ⚪ 0% |
BenchmarkSnapshot
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_3KB_snapshot/ (ns/op) | 19.55 ms | 19.35 ms | 🟢 -1.04% |
| Push_3KB_snapshot/ (B/op) | 905.58 KB | 897.33 KB | 🟢 -0.91% |
| Push_3KB_snapshot/ (allocs/op) | 8,516 allocs | 8,511 allocs | 🟢 -0.06% |
| Push_30KB_snapshot/ (ns/op) | 132.18 ms | 139.08 ms | 🔴 +5.22% |
| Push_30KB_snapshot/ (B/op) | 8.24 MB | 8.07 MB | 🟢 -2.14% |
| Push_30KB_snapshot/ (allocs/op) | 89,008 allocs | 88,660 allocs | 🟢 -0.39% |
| Pull_3KB_snapshot/ (ns/op) | 7.80 ms | 7.53 ms | 🟢 -3.53% |
| Pull_3KB_snapshot/ (B/op) | 1.12 MB | 1.06 MB | 🟢 -5.10% |
| Pull_3KB_snapshot/ (allocs/op) | 20,064 allocs | 19,256 allocs | 🟢 -4.03% |
| Pull_30KB_snapshot/ (ns/op) | 19.91 ms | 19.98 ms | 🔴 +0.33% |
| Pull_30KB_snapshot/ (B/op) | 9.31 MB | 8.76 MB | 🟢 -5.90% |
| Pull_30KB_snapshot/ (allocs/op) | 193,610 allocs | 185,677 allocs | 🟢 -4.10% |
BenchmarkSplayTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| stress_test_100000/ (ns/op) | 0.19 ns | 0.19 ns | 🟢 -2.79% |
| stress_test_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_200000/ (ns/op) | 0.40 ns | 0.41 ns | 🔴 +2.76% |
| stress_test_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_300000/ (ns/op) | 0.57 ns | 0.59 ns | 🔴 +3.10% |
| stress_test_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_100000/ (ns/op) | 0.01 ns | 0.01 ns | 🔴 +4.01% |
| random_access_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_200000/ (ns/op) | 0.03 ns | 0.03 ns | 🟢 -0.88% |
| random_access_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_300000/ (ns/op) | 0.04 ns | 0.05 ns | 🔴 +4.39% |
| random_access_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| editing_trace_bench/ (ns/op) | 0.00 ns | 0.00 ns | 🔴 +10.65% |
| editing_trace_bench/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| editing_trace_bench/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkSync
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| memory_sync_10_test/ (ns/op) | 7288.00 ns | 7104.00 ns | 🟢 -2.52% |
| memory_sync_10_test/ (B/op) | 1.34 KB | 1.34 KB | ⚪ 0% |
| memory_sync_10_test/ (allocs/op) | 35 allocs | 35 allocs | ⚪ 0% |
| memory_sync_100_test/ (ns/op) | 55353.00 ns | 56751.00 ns | 🔴 +2.53% |
| memory_sync_100_test/ (B/op) | 9.51 KB | 9.50 KB | 🟢 -0.02% |
| memory_sync_100_test/ (allocs/op) | 268 allocs | 268 allocs | ⚪ 0% |
| memory_sync_1000_test/ (ns/op) | 616285.00 ns | 635101.00 ns | 🔴 +3.05% |
| memory_sync_1000_test/ (B/op) | 75.92 KB | 75.60 KB | 🟢 -0.42% |
| memory_sync_1000_test/ (allocs/op) | 2,111 allocs | 2,101 allocs | 🟢 -0.47% |
| memory_sync_10000_test/ (ns/op) | 7.47 ms | 8.11 ms | 🔴 +8.56% |
| memory_sync_10000_test/ (B/op) | 761.49 KB | 755.20 KB | 🟢 -0.83% |
| memory_sync_10000_test/ (allocs/op) | 20,475 allocs | 20,463 allocs | 🟢 -0.06% |
BenchmarkTextEditing
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 5.18 s | 5.44 s | 🔴 +5.11% |
| (B/op) | 3.92 GB | 3.92 GB | ⚪ 0% |
| (allocs/op) | 20,619,777 allocs | 20,619,840 allocs | ⚪ 0% |
BenchmarkTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| 10000_vertices_to_protobuf/ (ns/op) | 4.17 ms | 4.33 ms | 🔴 +3.85% |
| 10000_vertices_to_protobuf/ (B/op) | 6.36 MB | 6.36 MB | ⚪ 0% |
| 10000_vertices_to_protobuf/ (allocs/op) | 70,025 allocs | 70,025 allocs | ⚪ 0% |
| 10000_vertices_from_protobuf/ (ns/op) | 217.30 ms | 234.82 ms | 🔴 +8.06% |
| 10000_vertices_from_protobuf/ (B/op) | 442.30 MB | 442.31 MB | ⚪ 0% |
| 10000_vertices_from_protobuf/ (allocs/op) | 290,038 allocs | 290,057 allocs | ⚪ 0% |
| 20000_vertices_to_protobuf/ (ns/op) | 8.84 ms | 9.27 ms | 🔴 +4.92% |
| 20000_vertices_to_protobuf/ (B/op) | 12.89 MB | 12.89 MB | ⚪ 0% |
| 20000_vertices_to_protobuf/ (allocs/op) | 140,028 allocs | 140,028 allocs | ⚪ 0% |
| 20000_vertices_from_protobuf/ (ns/op) | 884.61 ms | 902.85 ms | 🔴 +2.06% |
| 20000_vertices_from_protobuf/ (B/op) | 1.70 GB | 1.70 GB | ⚪ 0% |
| 20000_vertices_from_protobuf/ (allocs/op) | 580,043 allocs | 580,046 allocs | ⚪ 0% |
| 30000_vertices_to_protobuf/ (ns/op) | 14.26 ms | 14.73 ms | 🔴 +3.29% |
| 30000_vertices_to_protobuf/ (B/op) | 18.98 MB | 18.98 MB | ⚪ 0% |
| 30000_vertices_to_protobuf/ (allocs/op) | 210,029 allocs | 210,030 allocs | ⚪ 0% |
| 30000_vertices_from_protobuf/ (ns/op) | 2.00 s | 2.03 s | 🔴 +1.20% |
| 30000_vertices_from_protobuf/ (B/op) | 3.75 GB | 3.75 GB | ⚪ 0% |
| 30000_vertices_from_protobuf/ (allocs/op) | 870,147 allocs | 870,056 allocs | 🟢 -0.01% |
BenchmarkVersionVector
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| clients_10/ (ns/op) | 160.21 ms | 163.10 ms | 🔴 +1.80% |
| clients_10/ (1_changepack(bytes)) | 745.00 B | 745.00 B | ⚪ 0% |
| clients_10/ (2_snapshot(bytes)) | 379.00 B | 379.00 B | ⚪ 0% |
| clients_10/ (3_pushpull(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (4_attach(ms)) | 6.00 ms | 6.00 ms | ⚪ 0% |
| clients_10/ (5_changepack_after_detach(bytes)) | 805.00 B | 805.00 B | ⚪ 0% |
| clients_10/ (6_snapshot_after_detach(bytes)) | 136.00 B | 136.00 B | ⚪ 0% |
| clients_10/ (7_pushpull_after_detach(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (B/op) | 19.93 MB | 20.28 MB | 🔴 +1.73% |
| clients_10/ (allocs/op) | 83,762 allocs | 83,354 allocs | 🟢 -0.49% |
| clients_100/ (ns/op) | 1.41 s | 1.46 s | 🔴 +3.55% |
| clients_100/ (1_changepack(bytes)) | 6.14 KB | 6.14 KB | ⚪ 0% |
| clients_100/ (2_snapshot(bytes)) | 3.08 KB | 3.08 KB | ⚪ 0% |
| clients_100/ (3_pushpull(ms)) | 11.00 ms | 15.00 ms | 🔴 +36.36% |
| clients_100/ (4_attach(ms)) | 11.00 ms | 10.00 ms | 🟢 -9.09% |
| clients_100/ (5_changepack_after_detach(bytes)) | 6.21 KB | 6.21 KB | ⚪ 0% |
| clients_100/ (6_snapshot_after_detach(bytes)) | 137.00 B | 137.00 B | ⚪ 0% |
| clients_100/ (7_pushpull_after_detach(ms)) | 9.00 ms | 9.00 ms | ⚪ 0% |
| clients_100/ (B/op) | 230.31 MB | 215.40 MB | 🟢 -6.47% |
| clients_100/ (allocs/op) | 1,539,768 allocs | 1,484,696 allocs | 🟢 -3.58% |
| clients_1000/ (ns/op) | 60.97 s | 47.44 s | 🟢 -22.20% |
| clients_1000/ (1_changepack(bytes)) | 60.16 KB | 60.16 KB | ⚪ 0% |
| clients_1000/ (2_snapshot(bytes)) | 30.08 KB | 30.08 KB | ⚪ 0% |
| clients_1000/ (3_pushpull(ms)) | 95.00 ms | 95.00 ms | ⚪ 0% |
| clients_1000/ (4_attach(ms)) | 249.00 ms | 102.00 ms | 🟢 -59.04% |
| clients_1000/ (5_changepack_after_detach(bytes)) | 60.22 KB | 60.22 KB | ⚪ 0% |
| clients_1000/ (6_snapshot_after_detach(bytes)) | 139.00 B | 139.00 B | ⚪ 0% |
| clients_1000/ (7_pushpull_after_detach(ms)) | 26.00 ms | 23.00 ms | 🟢 -11.54% |
| clients_1000/ (B/op) | 22.07 GB | 6.59 GB | 🟢 -70.14% |
| clients_1000/ (allocs/op) | 111,762,106 allocs | 93,478,838 allocs | 🟢 -16.36% |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
pkg/document/internal_document.go (1)
124-130: Simplify changeID initialization.The current two-step initialization can be simplified by directly passing the actual values to
change.NewID.- changeID := change.NewID( - change.InitialClientSeq, - change.InitialServerSeq, - change.InitialLamport, - time.InitialActorID, - time.NewVersionVector()) - changeID.SetClocks(lamport, vector) + changeID := change.NewID( + change.InitialClientSeq, + change.InitialServerSeq, + lamport, + time.InitialActorID, + vector)
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
api/converter/from_pb.go(1 hunks)pkg/document/internal_document.go(2 hunks)test/helper/helper.go(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (2)
- api/converter/from_pb.go
- test/helper/helper.go
⏰ Context from checks skipped due to timeout of 90000ms (3)
- GitHub Check: bench
- GitHub Check: complex-test
- GitHub Check: build
🔇 Additional comments (2)
pkg/document/internal_document.go (2)
100-105: LGTM! Improved initialization of changeID.The explicit initialization of
changeIDusingchange.NewIDwith initial values improves code clarity and maintainability.
297-346:❓ Verification inconclusive
Verify alignment with PR objectives.
The PR objectives mention optimizing max VersionVector in ApplyChanges for memory efficiency, but the changes in this file focus on
changeIDinitialization instead. TheApplyChangesmethod remains unchanged. Please clarify if additional changes are needed to achieve the memory optimization goal.
🏁 Script executed:
#!/bin/bash # Description: Search for other files that might contain the optimization changes # mentioned in the PR objectives. echo "Searching for files containing VersionVector and ApplyChanges..." rg -l "VersionVector.*ApplyChanges|ApplyChanges.*VersionVector" echo "Searching for Max method implementation in version vector..." ast-grep --pattern 'func $_($$) Max($_, $_) { $$$ }'Length of output: 392
Clarify Memory Optimization Alignment
- The PR objectives target optimizing the max VersionVector for memory efficiency in
ApplyChanges, yet the changes in this file focus solely onchangeIDinitialization.- Our search did not reveal any modifications regarding VersionVector or its
Maxmethod in this or adjacent files.- Please confirm if additional updates addressing the VersionVector optimization are intended, or if these changes appear in another segment of the PR.
There was a problem hiding this comment.
Go Benchmark Analysis 📊
This is a comparison result between the previous(e687d61) and the current commit(d1c0be0).
Significant Changes (≥20% difference)
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| BenchmarkVersionVector/clients_1000/ (B/op) | 22.07 GB | 6.59 GB | 🟢 -70.15% |
| BenchmarkVersionVector/clients_1000/ (4_attach(ms)) | 249.00 ms | 101.00 ms | 🟢 -59.44% |
| BenchmarkVersionVector/clients_1000/ (ns/op) | 60.97 s | 47.55 s | 🟢 -22.02% |
Key Observations 🔍
-
The
BenchmarkVersionVector/clients_1000/suite exhibited significant improvements across multiple metrics:- A remarkable 70.15% decrease in memory usage (
B/op) from 22.07 GB to 6.59 GB. - The time taken for attachment (
4_attach(ms)) was reduced by 59.44% from 249.00 ms to 101.00 ms. - The execution time (
ns/op) saw a notable 22.02% decrease from 60.97 s to 47.55 s.
- A remarkable 70.15% decrease in memory usage (
-
The
BenchmarkRPCsuite showed noteworthy reduction across several benchmarks:client_to_client_via_server/ (B/op)witnessed an 8.06% decrease in memory usage.attach_large_document/ (ns/op)experienced a significant 5.91% decrease in execution time.adminCli_to_server/ (B/op)demonstrated a 6.35% decrease in memory usage.
-
Overall, in the various benchmark suites, a trend of optimization and efficiency improvement is observed, with a predominant focus on reducing memory consumption and execution times.
Clock Analysis
Lamport (v0.5.2)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 84.96 ms | 793.94 ms | 34.79 s |
| Memory Allocations | 35.11 MB | 219.92 MB | 4.91 GB |
| Number of Allocations (allocs/op) | 69,271 | 1,246,728 | 81,485,288 |
| ChangePack Size | 138.0 B | 137.0 B | 141.0 B |
| Snapshot Size | 379.0 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 2.0 ms | 1.5 ms | 4.0 ms |
| Attach Time | 4.5 ms | 11.0 ms | 31.0 ms |
| ChangePack After Detach | 138.0 B | 140.0 B | 141.0 B |
| Snapshot After Detach | 136.0 B | 137.0 B | 139.0 B |
| Push-Pull After Detach | 2.5 ms | 5.0 ms | 9.5 ms |
VV (current)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 162.84 ms | 1.46 s | 47.55 s |
| Memory Allocations | 18.61 MB | 220.46 MB | 6.59 GB |
| Number of Allocations (allocs/op) | 83,300 | 1,485,110 | 93,477,657 |
| ChangePack Size | 745.00 B | 6.14 KB | 60.16 KB |
| Snapshot Size | 379.00 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 8.00 ms | 11.00 ms | 95.00 ms |
| Attach Time | 6.00 ms | 12.00 ms | 101.00 ms |
| ChangePack After Detach | 805.00 B | 6.21 KB | 60.22 KB |
| Snapshot After Detach | 136.00 B | 137.00 B | 139.00 B |
| Push-Pull After Detach | 8.00 ms | 10.00 ms | 23.00 ms |
Summary
- Lamport clock generally outperforms Version Vector in terms of total operation time across all client counts.
- However, Version Vector consumes less memory for higher client counts compared to Lamport.
- Lamport clock has significantly lower number of allocations compared to Version Vector for higher client counts.
- Version Vector has larger ChangePack Size for all client counts, indicating it may be more data-intensive.
- Attach Time and Push-Pull After Detach time increase with higher client counts for both clocks but are generally lower for Lamport.
- Lamport clock outperforms Version Vector in some key metrics, but Version Vector offers benefits in memory efficiency and scalability for larger client counts.
Detailed Test Results
BenchmarkDocument
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| constructor_test/ (ns/op) | 1439.00 ns | 1467.00 ns | 🔴 +1.95% |
| constructor_test/ (B/op) | 1.39 KB | 1.43 KB | 🔴 +3.47% |
| constructor_test/ (allocs/op) | 24 allocs | 25 allocs | 🔴 +4.17% |
| status_test/ (ns/op) | 1028.00 ns | 1078.00 ns | 🔴 +4.86% |
| status_test/ (B/op) | 1.35 KB | 1.40 KB | 🔴 +3.55% |
| status_test/ (allocs/op) | 22 allocs | 23 allocs | 🔴 +4.55% |
| equals_test/ (ns/op) | 7864.00 ns | 7962.00 ns | 🔴 +1.25% |
| equals_test/ (B/op) | 7.56 KB | 7.71 KB | 🔴 +1.90% |
| equals_test/ (allocs/op) | 129 allocs | 132 allocs | 🔴 +2.33% |
| nested_update_test/ (ns/op) | 17079.00 ns | 19798.00 ns | 🔴 +15.92% |
| nested_update_test/ (B/op) | 12.31 KB | 12.36 KB | 🔴 +0.39% |
| nested_update_test/ (allocs/op) | 258 allocs | 259 allocs | 🔴 +0.39% |
| delete_test/ (ns/op) | 27313.00 ns | 22936.00 ns | 🟢 -16.03% |
| delete_test/ (B/op) | 15.79 KB | 15.84 KB | 🔴 +0.30% |
| delete_test/ (allocs/op) | 339 allocs | 340 allocs | 🔴 +0.29% |
| object_test/ (ns/op) | 8546.00 ns | 8671.00 ns | 🔴 +1.46% |
| object_test/ (B/op) | 7.03 KB | 7.08 KB | 🔴 +0.68% |
| object_test/ (allocs/op) | 118 allocs | 119 allocs | 🔴 +0.85% |
| array_test/ (ns/op) | 28984.00 ns | 29111.00 ns | 🔴 +0.44% |
| array_test/ (B/op) | 12.14 KB | 12.19 KB | 🔴 +0.40% |
| array_test/ (allocs/op) | 273 allocs | 274 allocs | 🔴 +0.37% |
| text_test/ (ns/op) | 32155.00 ns | 31776.00 ns | 🟢 -1.18% |
| text_test/ (B/op) | 15.19 KB | 15.24 KB | 🔴 +0.32% |
| text_test/ (allocs/op) | 484 allocs | 485 allocs | 🔴 +0.21% |
| text_composition_test/ (ns/op) | 31674.00 ns | 31558.00 ns | 🟢 -0.37% |
| text_composition_test/ (B/op) | 18.70 KB | 18.75 KB | 🔴 +0.26% |
| text_composition_test/ (allocs/op) | 501 allocs | 502 allocs | 🔴 +0.20% |
| rich_text_test/ (ns/op) | 87424.00 ns | 87535.00 ns | 🔴 +0.13% |
| rich_text_test/ (B/op) | 39.36 KB | 39.40 KB | 🔴 +0.12% |
| rich_text_test/ (allocs/op) | 1,146 allocs | 1,147 allocs | 🔴 +0.09% |
| counter_test/ (ns/op) | 18201.00 ns | 18613.00 ns | 🔴 +2.26% |
| counter_test/ (B/op) | 11.81 KB | 11.86 KB | 🔴 +0.41% |
| counter_test/ (allocs/op) | 253 allocs | 254 allocs | 🔴 +0.40% |
| text_edit_gc_100/ (ns/op) | 1.39 ms | 1.39 ms | 🔴 +0.09% |
| text_edit_gc_100/ (B/op) | 864.90 KB | 864.89 KB | ⚪ 0% |
| text_edit_gc_100/ (allocs/op) | 17,281 allocs | 17,283 allocs | 🔴 +0.01% |
| text_edit_gc_1000/ (ns/op) | 53.39 ms | 52.13 ms | 🟢 -2.37% |
| text_edit_gc_1000/ (B/op) | 46.84 MB | 46.84 MB | ⚪ 0% |
| text_edit_gc_1000/ (allocs/op) | 185,598 allocs | 185,597 allocs | ⚪ 0% |
| text_split_gc_100/ (ns/op) | 2.12 ms | 2.14 ms | 🔴 +0.72% |
| text_split_gc_100/ (B/op) | 1.58 MB | 1.58 MB | ⚪ 0% |
| text_split_gc_100/ (allocs/op) | 15,950 allocs | 15,952 allocs | 🔴 +0.01% |
| text_split_gc_1000/ (ns/op) | 128.25 ms | 127.34 ms | 🟢 -0.70% |
| text_split_gc_1000/ (B/op) | 137.79 MB | 137.79 MB | ⚪ 0% |
| text_split_gc_1000/ (allocs/op) | 185,000 allocs | 184,996 allocs | ⚪ 0% |
| text_delete_all_10000/ (ns/op) | 18.43 ms | 16.96 ms | 🟢 -8.00% |
| text_delete_all_10000/ (B/op) | 10.58 MB | 10.58 MB | 🔴 +0.02% |
| text_delete_all_10000/ (allocs/op) | 56,134 allocs | 56,141 allocs | 🔴 +0.01% |
| text_delete_all_100000/ (ns/op) | 312.31 ms | 298.64 ms | 🟢 -4.38% |
| text_delete_all_100000/ (B/op) | 105.54 MB | 105.53 MB | 🟢 -0.02% |
| text_delete_all_100000/ (allocs/op) | 566,133 allocs | 566,095 allocs | ⚪ 0% |
| text_100/ (ns/op) | 234634.00 ns | 232592.00 ns | 🟢 -0.87% |
| text_100/ (B/op) | 120.94 KB | 120.99 KB | 🔴 +0.04% |
| text_100/ (allocs/op) | 5,181 allocs | 5,182 allocs | 🔴 +0.02% |
| text_1000/ (ns/op) | 2.46 ms | 2.46 ms | 🟢 -0.26% |
| text_1000/ (B/op) | 1.16 MB | 1.16 MB | ⚪ 0% |
| text_1000/ (allocs/op) | 51,084 allocs | 51,085 allocs | ⚪ 0% |
| array_1000/ (ns/op) | 1.24 ms | 1.23 ms | 🟢 -0.52% |
| array_1000/ (B/op) | 1.09 MB | 1.09 MB | ⚪ 0% |
| array_1000/ (allocs/op) | 11,879 allocs | 11,880 allocs | ⚪ 0% |
| array_10000/ (ns/op) | 13.33 ms | 13.43 ms | 🔴 +0.68% |
| array_10000/ (B/op) | 9.89 MB | 9.89 MB | ⚪ 0% |
| array_10000/ (allocs/op) | 120,735 allocs | 120,734 allocs | ⚪ 0% |
| array_gc_100/ (ns/op) | 131750.00 ns | 131431.00 ns | 🟢 -0.24% |
| array_gc_100/ (B/op) | 99.89 KB | 99.94 KB | 🔴 +0.05% |
| array_gc_100/ (allocs/op) | 1,266 allocs | 1,267 allocs | 🔴 +0.08% |
| array_gc_1000/ (ns/op) | 1.42 ms | 1.42 ms | 🟢 -0.03% |
| array_gc_1000/ (B/op) | 1.14 MB | 1.14 MB | ⚪ 0% |
| array_gc_1000/ (allocs/op) | 12,926 allocs | 12,927 allocs | ⚪ 0% |
| counter_1000/ (ns/op) | 202098.00 ns | 205998.00 ns | 🔴 +1.93% |
| counter_1000/ (B/op) | 178.13 KB | 178.18 KB | 🔴 +0.03% |
| counter_1000/ (allocs/op) | 5,771 allocs | 5,772 allocs | 🔴 +0.02% |
| counter_10000/ (ns/op) | 2.17 ms | 2.17 ms | 🔴 +0.26% |
| counter_10000/ (B/op) | 2.07 MB | 2.07 MB | ⚪ 0% |
| counter_10000/ (allocs/op) | 59,778 allocs | 59,779 allocs | ⚪ 0% |
| object_1000/ (ns/op) | 1.39 ms | 1.40 ms | 🔴 +1.10% |
| object_1000/ (B/op) | 1.44 MB | 1.44 MB | ⚪ 0% |
| object_1000/ (allocs/op) | 9,925 allocs | 9,925 allocs | ⚪ 0% |
| object_10000/ (ns/op) | 14.82 ms | 14.77 ms | 🟢 -0.35% |
| object_10000/ (B/op) | 12.35 MB | 12.35 MB | 🟢 -0.02% |
| object_10000/ (allocs/op) | 101,232 allocs | 101,225 allocs | ⚪ 0% |
| tree_100/ (ns/op) | 1.02 ms | 1.02 ms | 🟢 -0.02% |
| tree_100/ (B/op) | 951.02 KB | 951.08 KB | ⚪ 0% |
| tree_100/ (allocs/op) | 6,102 allocs | 6,103 allocs | 🔴 +0.02% |
| tree_1000/ (ns/op) | 74.23 ms | 75.92 ms | 🔴 +2.28% |
| tree_1000/ (B/op) | 86.58 MB | 86.58 MB | ⚪ 0% |
| tree_1000/ (allocs/op) | 60,111 allocs | 60,112 allocs | ⚪ 0% |
| tree_10000/ (ns/op) | 9.68 s | 9.68 s | 🟢 -0.01% |
| tree_10000/ (B/op) | 8.58 GB | 8.58 GB | ⚪ 0% |
| tree_10000/ (allocs/op) | 600,173 allocs | 600,186 allocs | ⚪ 0% |
| tree_delete_all_1000/ (ns/op) | 78.41 ms | 82.02 ms | 🔴 +4.61% |
| tree_delete_all_1000/ (B/op) | 87.57 MB | 87.57 MB | ⚪ 0% |
| tree_delete_all_1000/ (allocs/op) | 75,289 allocs | 75,291 allocs | ⚪ 0% |
| tree_edit_gc_100/ (ns/op) | 3.96 ms | 4.02 ms | 🔴 +1.56% |
| tree_edit_gc_100/ (B/op) | 4.15 MB | 4.15 MB | ⚪ 0% |
| tree_edit_gc_100/ (allocs/op) | 15,147 allocs | 15,148 allocs | ⚪ 0% |
| tree_edit_gc_1000/ (ns/op) | 332.75 ms | 326.58 ms | 🟢 -1.85% |
| tree_edit_gc_1000/ (B/op) | 384.04 MB | 384.04 MB | ⚪ 0% |
| tree_edit_gc_1000/ (allocs/op) | 154,952 allocs | 154,939 allocs | ⚪ 0% |
| tree_split_gc_100/ (ns/op) | 2.67 ms | 2.66 ms | 🟢 -0.23% |
| tree_split_gc_100/ (B/op) | 2.41 MB | 2.41 MB | ⚪ 0% |
| tree_split_gc_100/ (allocs/op) | 11,131 allocs | 11,132 allocs | ⚪ 0% |
| tree_split_gc_1000/ (ns/op) | 197.74 ms | 198.53 ms | 🔴 +0.40% |
| tree_split_gc_1000/ (B/op) | 222.50 MB | 222.50 MB | ⚪ 0% |
| tree_split_gc_1000/ (allocs/op) | 122,053 allocs | 122,075 allocs | 🔴 +0.02% |
BenchmarkRPC
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| client_to_server/ (ns/op) | 431.85 ms | 424.47 ms | 🟢 -1.71% |
| client_to_server/ (B/op) | 16.13 MB | 16.12 MB | 🟢 -0.08% |
| client_to_server/ (allocs/op) | 223,674 allocs | 223,418 allocs | 🟢 -0.11% |
| client_to_client_via_server/ (ns/op) | 788.62 ms | 788.64 ms | ⚪ 0% |
| client_to_client_via_server/ (B/op) | 37.20 MB | 34.20 MB | 🟢 -8.06% |
| client_to_client_via_server/ (allocs/op) | 478,656 allocs | 475,472 allocs | 🟢 -0.67% |
| attach_large_document/ (ns/op) | 1.32 s | 1.25 s | 🟢 -5.91% |
| attach_large_document/ (B/op) | 1.89 GB | 1.90 GB | 🔴 +0.53% |
| attach_large_document/ (allocs/op) | 12,321 allocs | 12,279 allocs | 🟢 -0.34% |
| adminCli_to_server/ (ns/op) | 542.08 ms | 546.45 ms | 🔴 +0.81% |
| adminCli_to_server/ (B/op) | 21.76 MB | 20.37 MB | 🟢 -6.35% |
| adminCli_to_server/ (allocs/op) | 291,952 allocs | 291,933 allocs | ⚪ 0% |
BenchmarkLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 82.86 ns | 81.38 ns | 🟢 -1.79% |
| (B/op) | 32.00 B | 32.00 B | ⚪ 0% |
| (allocs/op) | 1 allocs | 1 allocs | ⚪ 0% |
BenchmarkLockerParallel
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 45.80 ns | 46.08 ns | 🔴 +0.61% |
| (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkLockerMoreKeys
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 180.50 ns | 176.60 ns | 🟢 -2.16% |
| (B/op) | 31.00 B | 31.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkRWLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| RWLock_rate_2/ (ns/op) | 50.25 ns | 49.81 ns | 🟢 -0.88% |
| RWLock_rate_2/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_2/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_10/ (ns/op) | 44.88 ns | 43.70 ns | 🟢 -2.63% |
| RWLock_rate_10/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_10/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_100/ (ns/op) | 63.08 ns | 59.90 ns | 🟢 -5.04% |
| RWLock_rate_100/ (B/op) | 2.00 B | 2.00 B | ⚪ 0% |
| RWLock_rate_100/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_1000/ (ns/op) | 91.91 ns | 88.50 ns | 🟢 -3.71% |
| RWLock_rate_1000/ (B/op) | 8.00 B | 8.00 B | ⚪ 0% |
| RWLock_rate_1000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkChange
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_10_Changes/ (ns/op) | 4.54 ms | 4.54 ms | 🔴 +0.02% |
| Push_10_Changes/ (B/op) | 150.42 KB | 149.46 KB | 🟢 -0.63% |
| Push_10_Changes/ (allocs/op) | 1,623 allocs | 1,623 allocs | ⚪ 0% |
| Push_100_Changes/ (ns/op) | 16.52 ms | 16.27 ms | 🟢 -1.49% |
| Push_100_Changes/ (B/op) | 770.59 KB | 781.03 KB | 🔴 +1.36% |
| Push_100_Changes/ (allocs/op) | 8,509 allocs | 8,510 allocs | 🔴 +0.01% |
| Push_1000_Changes/ (ns/op) | 129.20 ms | 130.65 ms | 🔴 +1.12% |
| Push_1000_Changes/ (B/op) | 7.22 MB | 7.21 MB | 🟢 -0.06% |
| Push_1000_Changes/ (allocs/op) | 79,325 allocs | 79,324 allocs | ⚪ 0% |
| Pull_10_Changes/ (ns/op) | 3.70 ms | 3.70 ms | 🟢 -0.16% |
| Pull_10_Changes/ (B/op) | 124.59 KB | 124.43 KB | 🟢 -0.12% |
| Pull_10_Changes/ (allocs/op) | 1,456 allocs | 1,456 allocs | ⚪ 0% |
| Pull_100_Changes/ (ns/op) | 5.32 ms | 5.29 ms | 🟢 -0.68% |
| Pull_100_Changes/ (B/op) | 354.61 KB | 354.35 KB | 🟢 -0.07% |
| Pull_100_Changes/ (allocs/op) | 5,182 allocs | 5,183 allocs | 🔴 +0.02% |
| Pull_1000_Changes/ (ns/op) | 10.88 ms | 10.88 ms | 🔴 +0.04% |
| Pull_1000_Changes/ (B/op) | 2.20 MB | 2.20 MB | 🟢 -0.05% |
| Pull_1000_Changes/ (allocs/op) | 44,681 allocs | 44,682 allocs | ⚪ 0% |
BenchmarkSnapshot
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_3KB_snapshot/ (ns/op) | 19.55 ms | 18.99 ms | 🟢 -2.88% |
| Push_3KB_snapshot/ (B/op) | 905.58 KB | 893.59 KB | 🟢 -1.32% |
| Push_3KB_snapshot/ (allocs/op) | 8,516 allocs | 8,512 allocs | 🟢 -0.05% |
| Push_30KB_snapshot/ (ns/op) | 132.18 ms | 133.72 ms | 🔴 +1.16% |
| Push_30KB_snapshot/ (B/op) | 8.24 MB | 8.18 MB | 🟢 -0.78% |
| Push_30KB_snapshot/ (allocs/op) | 89,008 allocs | 89,188 allocs | 🔴 +0.20% |
| Pull_3KB_snapshot/ (ns/op) | 7.80 ms | 7.68 ms | 🟢 -1.54% |
| Pull_3KB_snapshot/ (B/op) | 1.12 MB | 1.06 MB | 🟢 -5.05% |
| Pull_3KB_snapshot/ (allocs/op) | 20,064 allocs | 19,251 allocs | 🟢 -4.05% |
| Pull_30KB_snapshot/ (ns/op) | 19.91 ms | 19.78 ms | 🟢 -0.64% |
| Pull_30KB_snapshot/ (B/op) | 9.31 MB | 8.77 MB | 🟢 -5.84% |
| Pull_30KB_snapshot/ (allocs/op) | 193,610 allocs | 185,672 allocs | 🟢 -4.10% |
BenchmarkSplayTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| stress_test_100000/ (ns/op) | 0.19 ns | 0.19 ns | 🟢 -1.50% |
| stress_test_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_200000/ (ns/op) | 0.40 ns | 0.39 ns | 🟢 -1.34% |
| stress_test_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_300000/ (ns/op) | 0.57 ns | 0.60 ns | 🔴 +5.44% |
| stress_test_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_100000/ (ns/op) | 0.01 ns | 0.01 ns | 🔴 +0.16% |
| random_access_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_200000/ (ns/op) | 0.03 ns | 0.03 ns | 🔴 +5.34% |
| random_access_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_300000/ (ns/op) | 0.04 ns | 0.04 ns | 🟢 -4.25% |
| random_access_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| editing_trace_bench/ (ns/op) | 0.00 ns | 0.00 ns | 🔴 +4.93% |
| editing_trace_bench/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| editing_trace_bench/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkSync
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| memory_sync_10_test/ (ns/op) | 7288.00 ns | 7150.00 ns | 🟢 -1.89% |
| memory_sync_10_test/ (B/op) | 1.34 KB | 1.34 KB | ⚪ 0% |
| memory_sync_10_test/ (allocs/op) | 35 allocs | 35 allocs | ⚪ 0% |
| memory_sync_100_test/ (ns/op) | 55353.00 ns | 56326.00 ns | 🔴 +1.76% |
| memory_sync_100_test/ (B/op) | 9.51 KB | 9.50 KB | 🟢 -0.08% |
| memory_sync_100_test/ (allocs/op) | 268 allocs | 268 allocs | ⚪ 0% |
| memory_sync_1000_test/ (ns/op) | 616285.00 ns | 618704.00 ns | 🔴 +0.39% |
| memory_sync_1000_test/ (B/op) | 75.92 KB | 76.08 KB | 🔴 +0.21% |
| memory_sync_1000_test/ (allocs/op) | 2,111 allocs | 2,115 allocs | 🔴 +0.19% |
| memory_sync_10000_test/ (ns/op) | 7.47 ms | 8.57 ms | 🔴 +14.71% |
| memory_sync_10000_test/ (B/op) | 761.49 KB | 753.09 KB | 🟢 -1.10% |
| memory_sync_10000_test/ (allocs/op) | 20,475 allocs | 20,408 allocs | 🟢 -0.33% |
BenchmarkTextEditing
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 5.18 s | 5.28 s | 🔴 +1.99% |
| (B/op) | 3.92 GB | 3.92 GB | ⚪ 0% |
| (allocs/op) | 20,619,777 allocs | 20,619,789 allocs | ⚪ 0% |
BenchmarkTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| 10000_vertices_to_protobuf/ (ns/op) | 4.17 ms | 4.27 ms | 🔴 +2.30% |
| 10000_vertices_to_protobuf/ (B/op) | 6.36 MB | 6.36 MB | ⚪ 0% |
| 10000_vertices_to_protobuf/ (allocs/op) | 70,025 allocs | 70,025 allocs | ⚪ 0% |
| 10000_vertices_from_protobuf/ (ns/op) | 217.30 ms | 230.81 ms | 🔴 +6.22% |
| 10000_vertices_from_protobuf/ (B/op) | 442.30 MB | 442.30 MB | ⚪ 0% |
| 10000_vertices_from_protobuf/ (allocs/op) | 290,038 allocs | 290,038 allocs | ⚪ 0% |
| 20000_vertices_to_protobuf/ (ns/op) | 8.84 ms | 9.22 ms | 🔴 +4.30% |
| 20000_vertices_to_protobuf/ (B/op) | 12.89 MB | 12.89 MB | ⚪ 0% |
| 20000_vertices_to_protobuf/ (allocs/op) | 140,028 allocs | 140,028 allocs | ⚪ 0% |
| 20000_vertices_from_protobuf/ (ns/op) | 884.61 ms | 887.66 ms | 🔴 +0.35% |
| 20000_vertices_from_protobuf/ (B/op) | 1.70 GB | 1.70 GB | ⚪ 0% |
| 20000_vertices_from_protobuf/ (allocs/op) | 580,043 allocs | 580,045 allocs | ⚪ 0% |
| 30000_vertices_to_protobuf/ (ns/op) | 14.26 ms | 13.53 ms | 🟢 -5.15% |
| 30000_vertices_to_protobuf/ (B/op) | 18.98 MB | 18.98 MB | ⚪ 0% |
| 30000_vertices_to_protobuf/ (allocs/op) | 210,029 allocs | 210,029 allocs | ⚪ 0% |
| 30000_vertices_from_protobuf/ (ns/op) | 2.00 s | 1.99 s | 🟢 -0.56% |
| 30000_vertices_from_protobuf/ (B/op) | 3.75 GB | 3.75 GB | ⚪ 0% |
| 30000_vertices_from_protobuf/ (allocs/op) | 870,147 allocs | 870,143 allocs | ⚪ 0% |
BenchmarkVersionVector
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| clients_10/ (ns/op) | 160.21 ms | 162.84 ms | 🔴 +1.64% |
| clients_10/ (1_changepack(bytes)) | 745.00 B | 745.00 B | ⚪ 0% |
| clients_10/ (2_snapshot(bytes)) | 379.00 B | 379.00 B | ⚪ 0% |
| clients_10/ (3_pushpull(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (4_attach(ms)) | 6.00 ms | 6.00 ms | ⚪ 0% |
| clients_10/ (5_changepack_after_detach(bytes)) | 805.00 B | 805.00 B | ⚪ 0% |
| clients_10/ (6_snapshot_after_detach(bytes)) | 136.00 B | 136.00 B | ⚪ 0% |
| clients_10/ (7_pushpull_after_detach(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (B/op) | 19.93 MB | 18.61 MB | 🟢 -6.62% |
| clients_10/ (allocs/op) | 83,762 allocs | 83,300 allocs | 🟢 -0.55% |
| clients_100/ (ns/op) | 1.41 s | 1.46 s | 🔴 +3.71% |
| clients_100/ (1_changepack(bytes)) | 6.14 KB | 6.14 KB | ⚪ 0% |
| clients_100/ (2_snapshot(bytes)) | 3.08 KB | 3.08 KB | ⚪ 0% |
| clients_100/ (3_pushpull(ms)) | 11.00 ms | 11.00 ms | ⚪ 0% |
| clients_100/ (4_attach(ms)) | 11.00 ms | 12.00 ms | 🔴 +9.09% |
| clients_100/ (5_changepack_after_detach(bytes)) | 6.21 KB | 6.21 KB | ⚪ 0% |
| clients_100/ (6_snapshot_after_detach(bytes)) | 137.00 B | 137.00 B | ⚪ 0% |
| clients_100/ (7_pushpull_after_detach(ms)) | 9.00 ms | 10.00 ms | 🔴 +11.11% |
| clients_100/ (B/op) | 230.31 MB | 220.46 MB | 🟢 -4.28% |
| clients_100/ (allocs/op) | 1,539,768 allocs | 1,485,110 allocs | 🟢 -3.55% |
| clients_1000/ (ns/op) | 60.97 s | 47.55 s | 🟢 -22.02% |
| clients_1000/ (1_changepack(bytes)) | 60.16 KB | 60.16 KB | ⚪ 0% |
| clients_1000/ (2_snapshot(bytes)) | 30.08 KB | 30.08 KB | ⚪ 0% |
| clients_1000/ (3_pushpull(ms)) | 95.00 ms | 95.00 ms | ⚪ 0% |
| clients_1000/ (4_attach(ms)) | 249.00 ms | 101.00 ms | 🟢 -59.44% |
| clients_1000/ (5_changepack_after_detach(bytes)) | 60.22 KB | 60.22 KB | ⚪ 0% |
| clients_1000/ (6_snapshot_after_detach(bytes)) | 139.00 B | 139.00 B | ⚪ 0% |
| clients_1000/ (7_pushpull_after_detach(ms)) | 26.00 ms | 23.00 ms | 🟢 -11.54% |
| clients_1000/ (B/op) | 22.07 GB | 6.59 GB | 🟢 -70.15% |
| clients_1000/ (allocs/op) | 111,762,106 allocs | 93,477,657 allocs | 🟢 -16.36% |
hackerwins
reviewed
Feb 20, 2025
pkg/document/time/version_vector.go
Outdated
Comment on lines
158
to
183
| // Max returns new vv consists of every max value in each column. | ||
| func (v VersionVector) Max(other VersionVector) VersionVector { | ||
| maxVV := NewVersionVector() | ||
| func (v VersionVector) Max(other *VersionVector) VersionVector { | ||
| if other == nil { | ||
| return v | ||
| } | ||
|
|
||
| for key, value := range v { | ||
| if otherValue, exists := other[key]; exists { | ||
| if otherValue, exists := (*other)[key]; exists { | ||
| if value > otherValue { | ||
| maxVV[key] = value | ||
| v[key] = value | ||
| } else { | ||
| maxVV[key] = otherValue | ||
| v[key] = otherValue | ||
| } | ||
| } else { | ||
| maxVV[key] = value | ||
| v[key] = value | ||
| } | ||
| } | ||
|
|
||
| for key, value := range other { | ||
| for key, value := range *other { | ||
| if _, exists := v[key]; !exists { | ||
| maxVV[key] = value | ||
| v[key] = value | ||
| } | ||
| } | ||
|
|
||
| return maxVV | ||
| return v | ||
| } |
There was a problem hiding this comment.
@coderabbitai This function changes the given vector to the max value in-place. Is this a dangerous method?
There was a problem hiding this comment.
@hackerwins The method is safe but could be more explicit about its behavior. While it modifies the receiver in-place, this is actually consistent with Go's map behavior (maps are reference types). The input parameter other is safely handled and only read, not modified.
However, to make the behavior more obvious to callers, we could:
- Rename the method to
UpdateMaxto indicate mutation - Add documentation explicitly stating that the receiver is modified
Would you like me to propose these changes?
✏️ Learnings added
Learnt from: hackerwins
PR: yorkie-team/yorkie#1164
File: pkg/document/time/version_vector.go:158-183
Timestamp: 2025-02-20T11:31:21.590Z
Learning: In the Yorkie project, the `VersionVector.Max` method modifies the receiver in-place and returns it, which is an intentional design decision for memory efficiency. The method takes a pointer parameter but only reads from it, maintaining input integrity.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
There was a problem hiding this comment.
@coderabbitai I agree about documenting the receiver modification explicitly. This would help make the side effects more obvious to anyone using the function. And since we also have a Min() function, we should apply the same pattern there to maintain consistency and avoid confusion.
There was a problem hiding this comment.
@chacha912 I'll propose documentation and implementation changes for both functions to maintain consistency:
// Min modifies the receiver in-place to contain the minimum values between itself
// and the given version vector, and returns the modified receiver.
// Note: This method modifies the receiver for memory efficiency.
func (v VersionVector) Min(other *VersionVector) VersionVector {
if other == nil {
return v
}
for key, value := range v {
if otherValue, exists := (*other)[key]; exists {
if value < otherValue {
v[key] = value
} else {
v[key] = otherValue
}
} else {
v[key] = 0
}
}
for key := range *other {
if _, exists := v[key]; !exists {
v[key] = 0
}
}
return v
}
// Max modifies the receiver in-place to contain the maximum values between itself
// and the given version vector, and returns the modified receiver.
// Note: This method modifies the receiver for memory efficiency.
func (v VersionVector) Max(other *VersionVector) VersionVector {
if other == nil {
return v
}
for key, value := range v {
if otherValue, exists := (*other)[key]; exists {
if value > otherValue {
v[key] = value
} else {
v[key] = otherValue
}
} else {
v[key] = value
}
}
for key, value := range *other {
if _, exists := v[key]; !exists {
v[key] = value
}
}
return v
}✏️ Learnings added
Learnt from: chacha912
PR: yorkie-team/yorkie#1164
File: pkg/document/time/version_vector.go:158-183
Timestamp: 2025-02-21T04:54:17.804Z
Learning: In the Yorkie project, the `VersionVector.Min` and `VersionVector.Max` methods should maintain consistent behavior and documentation. Both methods should modify the receiver in-place for memory efficiency, take pointer parameters, and document their side effects clearly.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
🧠 Learnings used
Learnt from: hackerwins
PR: yorkie-team/yorkie#1164
File: pkg/document/time/version_vector.go:158-183
Timestamp: 2025-02-20T11:31:21.714Z
Learning: In the Yorkie project, the `VersionVector.Max` method modifies the receiver in-place and returns it, which is an intentional design decision for memory efficiency. The method takes a pointer parameter but only reads from it, maintaining input integrity.
chacha912
reviewed
Feb 21, 2025
pkg/document/time/version_vector.go
Outdated
Comment on lines
158
to
183
| // Max returns new vv consists of every max value in each column. | ||
| func (v VersionVector) Max(other VersionVector) VersionVector { | ||
| maxVV := NewVersionVector() | ||
| func (v VersionVector) Max(other *VersionVector) VersionVector { | ||
| if other == nil { | ||
| return v | ||
| } | ||
|
|
||
| for key, value := range v { | ||
| if otherValue, exists := other[key]; exists { | ||
| if otherValue, exists := (*other)[key]; exists { | ||
| if value > otherValue { | ||
| maxVV[key] = value | ||
| v[key] = value | ||
| } else { | ||
| maxVV[key] = otherValue | ||
| v[key] = otherValue | ||
| } | ||
| } else { | ||
| maxVV[key] = value | ||
| v[key] = value | ||
| } | ||
| } | ||
|
|
||
| for key, value := range other { | ||
| for key, value := range *other { | ||
| if _, exists := v[key]; !exists { | ||
| maxVV[key] = value | ||
| v[key] = value | ||
| } | ||
| } | ||
|
|
||
| return maxVV | ||
| return v | ||
| } |
There was a problem hiding this comment.
@coderabbitai I agree about documenting the receiver modification explicitly. This would help make the side effects more obvious to anyone using the function. And since we also have a Min() function, we should apply the same pattern there to maintain consistency and avoid confusion.
test/helper/helper.go
Outdated
Comment on lines
120
to
125
| change.NewID( | ||
| change.InitialClientSeq, | ||
| change.InitialServerSeq, | ||
| change.InitialLamport, | ||
| time.InitialActorID, | ||
| time.NewVersionVector()), |
There was a problem hiding this comment.
@coderabbitai What if we remove the var InitialID and replace it with a function like GetInitialID? Since we shouldn't use InitialID as a value directly, I think creating a function would be a better approach.
There was a problem hiding this comment.
🧩 Analysis chain
@chacha912 That's a great suggestion! Converting InitialID to a function would indeed be a better approach as it:
- Enforces proper initialization through an explicit function call
- Prevents potential issues with shared mutable state
- Makes the code's intent clearer
Would you like me to create an issue to track this improvement?
(｀^ω^´)
🏁 Script executed:
#!/bin/bash
# Find all occurrences of InitialID
rg "InitialID" -A 2 -B 2
Length of output: 459
@chacha912 Looking at the code, I see that InitialID is only used in pkg/document/change/id.go. Converting it to a function would be even more straightforward than initially thought. We could:
- Remove the
var InitialIDdeclaration - Add a
GetInitialID()function that returns the same initialization:
func GetInitialID() ID {
return NewID(InitialClientSeq, InitialServerSeq, InitialLamport, time.InitialActorID, time.InitialVersionVector)
}Would you like me to create an issue to track this refactoring?
(｀^ω^´)
✏️ Learnings added
Learnt from: chacha912
PR: yorkie-team/yorkie#1164
File: test/helper/helper.go:120-125
Timestamp: 2025-02-21T04:54:29.166Z
Learning: In the Yorkie codebase, avoid using `InitialID` directly as a value. Instead, prefer explicit initialization using `NewID` with appropriate initial values or use a dedicated function like `GetInitialID` to enforce proper initialization.
Learnt from: chacha912
PR: yorkie-team/yorkie#1164
File: test/helper/helper.go:120-125
Timestamp: 2025-02-21T04:54:29.166Z
Learning: In `pkg/document/change/id.go`, the `InitialID` variable represents the initial state where nothing has been edited. Consider using a function like `GetInitialID()` instead of the package-level variable to enforce proper initialization and prevent shared mutable state.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
There was a problem hiding this comment.
Go Benchmark Analysis 📊
This is a comparison result between the previous(e687d61) and the current commit(f0449e1).
Significant Changes (≥20% difference)
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| BenchmarkVersionVector/clients_1000/ (B/op) | 22.07 GB | 6.43 GB | 🟢 -70.85% |
| BenchmarkVersionVector/clients_1000/ (4_attach(ms)) | 249.00 ms | 100.00 ms | 🟢 -59.84% |
| BenchmarkVersionVector/clients_1000/ (ns/op) | 60.97 s | 45.71 s | 🟢 -25.03% |
Key Observations 🔍
-
In the BenchmarkVersionVector suite, there were significant improvements in performance for the
clients_1000/benchmarks:- (ns/op) decreased by 25.03%, indicating a notable reduction in the time taken per operation.
- (4_attach(ms)) saw a substantial improvement of 59.84%, suggesting significant optimization in attachment operations.
- (B/op) showed a remarkable decrease of 70.85%, indicating a substantial reduction in memory usage.
-
The BenchmarkRPC suite displayed overall improvements in performance:
- client_to_server/ (ns/op) and client_to_client_via_server/ (ns/op) saw reductions of 3.24% and 2.06%, respectively, in the time taken per operation.
- attach_large_document/ (ns/op) improved by 8.50%, indicating faster processing of large document attachments.
-
The BenchmarkTextEditing suite exhibited a slight increase in performance, with a 0.14% decrease in time taken for operations.
Clock Analysis
Lamport (v0.5.2)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 84.96 ms | 793.94 ms | 34.79 s |
| Memory Allocations | 35.11 MB | 219.92 MB | 4.91 GB |
| Number of Allocations (allocs/op) | 69,271 | 1,246,728 | 81,485,288 |
| ChangePack Size | 138.0 B | 137.0 B | 141.0 B |
| Snapshot Size | 379.0 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 2.0 ms | 1.5 ms | 4.0 ms |
| Attach Time | 4.5 ms | 11.0 ms | 31.0 ms |
| ChangePack After Detach | 138.0 B | 140.0 B | 141.0 B |
| Snapshot After Detach | 136.0 B | 137.0 B | 139.0 B |
| Push-Pull After Detach | 2.5 ms | 5.0 ms | 9.5 ms |
VV (current)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 159.49 ms | 1.39 s | 45.71 s |
| Memory Allocations | 21.06 MB | 215.11 MB | 6.43 GB |
| Number of Allocations (allocs/op) | 83,263 | 1,481,226 | 93,353,871 |
| ChangePack Size | 745.00 B | 6.14 KB | 60.16 KB |
| Snapshot Size | 379.00 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 7.00 ms | 1.5 ms | 22.00 ms |
| Attach Time | 6.00 ms | 10.0 ms | 100.00 ms |
| ChangePack After Detach | 805.00 B | 6.21 KB | 60.22 KB |
| Snapshot After Detach | 136.00 B | 137.00 B | 139.00 B |
| Push-Pull After Detach | 8.00 ms | 9.00 ms | 22.00 ms |
Summary
- Lamport clock generally outperforms Version Vector in terms of total operation time across all levels of client concurrency.
- Version Vector shows better performance in memory allocations for 10 and 100 clients but incurs higher memory usage for 1000 clients.
- Lamport clock requires significantly fewer allocations per operation compared to Version Vector for all client levels.
- Version Vector exhibits better ChangePack size handling and lower Push-Pull times in some scenarios, especially with 1000 clients.
- Lamport clock has faster Attach times and better handling of ChangePack and Snapshot sizes after detach operation.
- Version Vector shows improvements in Push-Pull times after detach, especially with 1000 clients.
Detailed Test Results
BenchmarkDocument
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| constructor_test/ (ns/op) | 1439.00 ns | 1463.00 ns | 🔴 +1.67% |
| constructor_test/ (B/op) | 1.39 KB | 1.43 KB | 🔴 +3.47% |
| constructor_test/ (allocs/op) | 24 allocs | 25 allocs | 🔴 +4.17% |
| status_test/ (ns/op) | 1028.00 ns | 1087.00 ns | 🔴 +5.74% |
| status_test/ (B/op) | 1.35 KB | 1.40 KB | 🔴 +3.55% |
| status_test/ (allocs/op) | 22 allocs | 23 allocs | 🔴 +4.55% |
| equals_test/ (ns/op) | 7864.00 ns | 7884.00 ns | 🔴 +0.25% |
| equals_test/ (B/op) | 7.56 KB | 7.71 KB | 🔴 +1.90% |
| equals_test/ (allocs/op) | 129 allocs | 132 allocs | 🔴 +2.33% |
| nested_update_test/ (ns/op) | 17079.00 ns | 17394.00 ns | 🔴 +1.84% |
| nested_update_test/ (B/op) | 12.31 KB | 12.36 KB | 🔴 +0.39% |
| nested_update_test/ (allocs/op) | 258 allocs | 259 allocs | 🔴 +0.39% |
| delete_test/ (ns/op) | 27313.00 ns | 23039.00 ns | 🟢 -15.65% |
| delete_test/ (B/op) | 15.79 KB | 15.84 KB | 🔴 +0.30% |
| delete_test/ (allocs/op) | 339 allocs | 340 allocs | 🔴 +0.29% |
| object_test/ (ns/op) | 8546.00 ns | 10234.00 ns | 🔴 +19.75% |
| object_test/ (B/op) | 7.03 KB | 7.08 KB | 🔴 +0.68% |
| object_test/ (allocs/op) | 118 allocs | 119 allocs | 🔴 +0.85% |
| array_test/ (ns/op) | 28984.00 ns | 28228.00 ns | 🟢 -2.61% |
| array_test/ (B/op) | 12.14 KB | 12.19 KB | 🔴 +0.40% |
| array_test/ (allocs/op) | 273 allocs | 274 allocs | 🔴 +0.37% |
| text_test/ (ns/op) | 32155.00 ns | 31765.00 ns | 🟢 -1.21% |
| text_test/ (B/op) | 15.19 KB | 15.24 KB | 🔴 +0.32% |
| text_test/ (allocs/op) | 484 allocs | 485 allocs | 🔴 +0.21% |
| text_composition_test/ (ns/op) | 31674.00 ns | 31554.00 ns | 🟢 -0.38% |
| text_composition_test/ (B/op) | 18.70 KB | 18.75 KB | 🔴 +0.26% |
| text_composition_test/ (allocs/op) | 501 allocs | 502 allocs | 🔴 +0.20% |
| rich_text_test/ (ns/op) | 87424.00 ns | 85746.00 ns | 🟢 -1.92% |
| rich_text_test/ (B/op) | 39.36 KB | 39.41 KB | 🔴 +0.12% |
| rich_text_test/ (allocs/op) | 1,146 allocs | 1,147 allocs | 🔴 +0.09% |
| counter_test/ (ns/op) | 18201.00 ns | 18166.00 ns | 🟢 -0.19% |
| counter_test/ (B/op) | 11.81 KB | 11.86 KB | 🔴 +0.40% |
| counter_test/ (allocs/op) | 253 allocs | 254 allocs | 🔴 +0.40% |
| text_edit_gc_100/ (ns/op) | 1.39 ms | 1.39 ms | 🟢 -0.11% |
| text_edit_gc_100/ (B/op) | 864.90 KB | 864.91 KB | ⚪ 0% |
| text_edit_gc_100/ (allocs/op) | 17,281 allocs | 17,283 allocs | 🔴 +0.01% |
| text_edit_gc_1000/ (ns/op) | 53.39 ms | 53.59 ms | 🔴 +0.37% |
| text_edit_gc_1000/ (B/op) | 46.84 MB | 46.84 MB | ⚪ 0% |
| text_edit_gc_1000/ (allocs/op) | 185,598 allocs | 185,590 allocs | ⚪ 0% |
| text_split_gc_100/ (ns/op) | 2.12 ms | 2.11 ms | 🟢 -0.61% |
| text_split_gc_100/ (B/op) | 1.58 MB | 1.58 MB | ⚪ 0% |
| text_split_gc_100/ (allocs/op) | 15,950 allocs | 15,952 allocs | 🔴 +0.01% |
| text_split_gc_1000/ (ns/op) | 128.25 ms | 126.99 ms | 🟢 -0.98% |
| text_split_gc_1000/ (B/op) | 137.79 MB | 137.79 MB | ⚪ 0% |
| text_split_gc_1000/ (allocs/op) | 185,000 allocs | 184,981 allocs | 🟢 -0.01% |
| text_delete_all_10000/ (ns/op) | 18.43 ms | 16.99 ms | 🟢 -7.85% |
| text_delete_all_10000/ (B/op) | 10.58 MB | 10.58 MB | ⚪ 0% |
| text_delete_all_10000/ (allocs/op) | 56,134 allocs | 56,136 allocs | ⚪ 0% |
| text_delete_all_100000/ (ns/op) | 312.31 ms | 264.68 ms | 🟢 -15.25% |
| text_delete_all_100000/ (B/op) | 105.54 MB | 105.52 MB | 🟢 -0.02% |
| text_delete_all_100000/ (allocs/op) | 566,133 allocs | 566,103 allocs | ⚪ 0% |
| text_100/ (ns/op) | 234634.00 ns | 235592.00 ns | 🔴 +0.41% |
| text_100/ (B/op) | 120.94 KB | 120.96 KB | 🔴 +0.01% |
| text_100/ (allocs/op) | 5,181 allocs | 5,182 allocs | 🔴 +0.02% |
| text_1000/ (ns/op) | 2.46 ms | 2.50 ms | 🔴 +1.37% |
| text_1000/ (B/op) | 1.16 MB | 1.16 MB | 🔴 +0.03% |
| text_1000/ (allocs/op) | 51,084 allocs | 51,085 allocs | ⚪ 0% |
| array_1000/ (ns/op) | 1.24 ms | 1.27 ms | 🔴 +2.05% |
| array_1000/ (B/op) | 1.09 MB | 1.09 MB | ⚪ 0% |
| array_1000/ (allocs/op) | 11,879 allocs | 11,880 allocs | ⚪ 0% |
| array_10000/ (ns/op) | 13.33 ms | 13.50 ms | 🔴 +1.21% |
| array_10000/ (B/op) | 9.89 MB | 9.89 MB | ⚪ 0% |
| array_10000/ (allocs/op) | 120,735 allocs | 120,735 allocs | ⚪ 0% |
| array_gc_100/ (ns/op) | 131750.00 ns | 134514.00 ns | 🔴 +2.10% |
| array_gc_100/ (B/op) | 99.89 KB | 99.95 KB | 🔴 +0.06% |
| array_gc_100/ (allocs/op) | 1,266 allocs | 1,267 allocs | 🔴 +0.08% |
| array_gc_1000/ (ns/op) | 1.42 ms | 1.44 ms | 🔴 +1.63% |
| array_gc_1000/ (B/op) | 1.14 MB | 1.14 MB | ⚪ 0% |
| array_gc_1000/ (allocs/op) | 12,926 allocs | 12,927 allocs | ⚪ 0% |
| counter_1000/ (ns/op) | 202098.00 ns | 204092.00 ns | 🔴 +0.99% |
| counter_1000/ (B/op) | 178.13 KB | 178.19 KB | 🔴 +0.03% |
| counter_1000/ (allocs/op) | 5,771 allocs | 5,772 allocs | 🔴 +0.02% |
| counter_10000/ (ns/op) | 2.17 ms | 2.18 ms | 🔴 +0.36% |
| counter_10000/ (B/op) | 2.07 MB | 2.07 MB | ⚪ 0% |
| counter_10000/ (allocs/op) | 59,778 allocs | 59,779 allocs | ⚪ 0% |
| object_1000/ (ns/op) | 1.39 ms | 1.42 ms | 🔴 +2.06% |
| object_1000/ (B/op) | 1.44 MB | 1.44 MB | 🔴 +0.03% |
| object_1000/ (allocs/op) | 9,925 allocs | 9,927 allocs | 🔴 +0.02% |
| object_10000/ (ns/op) | 14.82 ms | 14.48 ms | 🟢 -2.28% |
| object_10000/ (B/op) | 12.35 MB | 12.35 MB | ⚪ 0% |
| object_10000/ (allocs/op) | 101,232 allocs | 101,235 allocs | ⚪ 0% |
| tree_100/ (ns/op) | 1.02 ms | 1.03 ms | 🔴 +0.89% |
| tree_100/ (B/op) | 951.02 KB | 951.07 KB | ⚪ 0% |
| tree_100/ (allocs/op) | 6,102 allocs | 6,103 allocs | 🔴 +0.02% |
| tree_1000/ (ns/op) | 74.23 ms | 78.80 ms | 🔴 +6.15% |
| tree_1000/ (B/op) | 86.58 MB | 86.58 MB | ⚪ 0% |
| tree_1000/ (allocs/op) | 60,111 allocs | 60,113 allocs | ⚪ 0% |
| tree_10000/ (ns/op) | 9.68 s | 9.50 s | 🟢 -1.84% |
| tree_10000/ (B/op) | 8.58 GB | 8.58 GB | ⚪ 0% |
| tree_10000/ (allocs/op) | 600,173 allocs | 600,187 allocs | ⚪ 0% |
| tree_delete_all_1000/ (ns/op) | 78.41 ms | 78.67 ms | 🔴 +0.34% |
| tree_delete_all_1000/ (B/op) | 87.57 MB | 87.57 MB | ⚪ 0% |
| tree_delete_all_1000/ (allocs/op) | 75,289 allocs | 75,287 allocs | ⚪ 0% |
| tree_edit_gc_100/ (ns/op) | 3.96 ms | 3.85 ms | 🟢 -2.83% |
| tree_edit_gc_100/ (B/op) | 4.15 MB | 4.15 MB | ⚪ 0% |
| tree_edit_gc_100/ (allocs/op) | 15,147 allocs | 15,147 allocs | ⚪ 0% |
| tree_edit_gc_1000/ (ns/op) | 332.75 ms | 321.78 ms | 🟢 -3.30% |
| tree_edit_gc_1000/ (B/op) | 384.04 MB | 384.04 MB | ⚪ 0% |
| tree_edit_gc_1000/ (allocs/op) | 154,952 allocs | 154,939 allocs | ⚪ 0% |
| tree_split_gc_100/ (ns/op) | 2.67 ms | 2.65 ms | 🟢 -0.66% |
| tree_split_gc_100/ (B/op) | 2.41 MB | 2.41 MB | ⚪ 0% |
| tree_split_gc_100/ (allocs/op) | 11,131 allocs | 11,132 allocs | ⚪ 0% |
| tree_split_gc_1000/ (ns/op) | 197.74 ms | 200.90 ms | 🔴 +1.60% |
| tree_split_gc_1000/ (B/op) | 222.50 MB | 222.50 MB | ⚪ 0% |
| tree_split_gc_1000/ (allocs/op) | 122,053 allocs | 122,080 allocs | 🔴 +0.02% |
BenchmarkRPC
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| client_to_server/ (ns/op) | 431.85 ms | 417.85 ms | 🟢 -3.24% |
| client_to_server/ (B/op) | 16.13 MB | 16.11 MB | 🟢 -0.11% |
| client_to_server/ (allocs/op) | 223,674 allocs | 223,273 allocs | 🟢 -0.18% |
| client_to_client_via_server/ (ns/op) | 788.62 ms | 772.36 ms | 🟢 -2.06% |
| client_to_client_via_server/ (B/op) | 37.20 MB | 38.52 MB | 🔴 +3.54% |
| client_to_client_via_server/ (allocs/op) | 478,656 allocs | 471,659 allocs | 🟢 -1.46% |
| attach_large_document/ (ns/op) | 1.32 s | 1.21 s | 🟢 -8.50% |
| attach_large_document/ (B/op) | 1.89 GB | 1.92 GB | 🔴 +1.81% |
| attach_large_document/ (allocs/op) | 12,321 allocs | 12,410 allocs | 🔴 +0.72% |
| adminCli_to_server/ (ns/op) | 542.08 ms | 546.23 ms | 🔴 +0.76% |
| adminCli_to_server/ (B/op) | 21.76 MB | 21.31 MB | 🟢 -2.06% |
| adminCli_to_server/ (allocs/op) | 291,952 allocs | 316,674 allocs | 🔴 +8.47% |
BenchmarkLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 82.86 ns | 81.23 ns | 🟢 -1.97% |
| (B/op) | 32.00 B | 32.00 B | ⚪ 0% |
| (allocs/op) | 1 allocs | 1 allocs | ⚪ 0% |
BenchmarkLockerParallel
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 45.80 ns | 44.27 ns | 🟢 -3.34% |
| (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkLockerMoreKeys
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 180.50 ns | 175.30 ns | 🟢 -2.88% |
| (B/op) | 31.00 B | 31.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkRWLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| RWLock_rate_2/ (ns/op) | 50.25 ns | 49.12 ns | 🟢 -2.25% |
| RWLock_rate_2/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_2/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_10/ (ns/op) | 44.88 ns | 43.31 ns | 🟢 -3.50% |
| RWLock_rate_10/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_10/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_100/ (ns/op) | 63.08 ns | 60.35 ns | 🟢 -4.33% |
| RWLock_rate_100/ (B/op) | 2.00 B | 2.00 B | ⚪ 0% |
| RWLock_rate_100/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_1000/ (ns/op) | 91.91 ns | 86.78 ns | 🟢 -5.58% |
| RWLock_rate_1000/ (B/op) | 8.00 B | 8.00 B | ⚪ 0% |
| RWLock_rate_1000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkChange
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_10_Changes/ (ns/op) | 4.54 ms | 4.47 ms | 🟢 -1.44% |
| Push_10_Changes/ (B/op) | 150.42 KB | 149.87 KB | 🟢 -0.36% |
| Push_10_Changes/ (allocs/op) | 1,623 allocs | 1,623 allocs | ⚪ 0% |
| Push_100_Changes/ (ns/op) | 16.52 ms | 16.39 ms | 🟢 -0.75% |
| Push_100_Changes/ (B/op) | 770.59 KB | 781.79 KB | 🔴 +1.45% |
| Push_100_Changes/ (allocs/op) | 8,509 allocs | 8,511 allocs | 🔴 +0.02% |
| Push_1000_Changes/ (ns/op) | 129.20 ms | 131.25 ms | 🔴 +1.58% |
| Push_1000_Changes/ (B/op) | 7.22 MB | 7.19 MB | 🟢 -0.45% |
| Push_1000_Changes/ (allocs/op) | 79,325 allocs | 79,325 allocs | ⚪ 0% |
| Pull_10_Changes/ (ns/op) | 3.70 ms | 3.65 ms | 🟢 -1.31% |
| Pull_10_Changes/ (B/op) | 124.59 KB | 124.56 KB | 🟢 -0.02% |
| Pull_10_Changes/ (allocs/op) | 1,456 allocs | 1,454 allocs | 🟢 -0.14% |
| Pull_100_Changes/ (ns/op) | 5.32 ms | 5.26 ms | 🟢 -1.24% |
| Pull_100_Changes/ (B/op) | 354.61 KB | 354.87 KB | 🔴 +0.07% |
| Pull_100_Changes/ (allocs/op) | 5,182 allocs | 5,180 allocs | 🟢 -0.04% |
| Pull_1000_Changes/ (ns/op) | 10.88 ms | 10.86 ms | 🟢 -0.10% |
| Pull_1000_Changes/ (B/op) | 2.20 MB | 2.20 MB | 🟢 -0.14% |
| Pull_1000_Changes/ (allocs/op) | 44,681 allocs | 44,682 allocs | ⚪ 0% |
BenchmarkSnapshot
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_3KB_snapshot/ (ns/op) | 19.55 ms | 18.84 ms | 🟢 -3.64% |
| Push_3KB_snapshot/ (B/op) | 905.58 KB | 896.48 KB | 🟢 -1.00% |
| Push_3KB_snapshot/ (allocs/op) | 8,516 allocs | 8,512 allocs | 🟢 -0.05% |
| Push_30KB_snapshot/ (ns/op) | 132.18 ms | 132.80 ms | 🔴 +0.47% |
| Push_30KB_snapshot/ (B/op) | 8.24 MB | 8.15 MB | 🟢 -1.06% |
| Push_30KB_snapshot/ (allocs/op) | 89,008 allocs | 87,802 allocs | 🟢 -1.35% |
| Pull_3KB_snapshot/ (ns/op) | 7.80 ms | 7.36 ms | 🟢 -5.72% |
| Pull_3KB_snapshot/ (B/op) | 1.12 MB | 1.06 MB | 🟢 -4.90% |
| Pull_3KB_snapshot/ (allocs/op) | 20,064 allocs | 19,254 allocs | 🟢 -4.04% |
| Pull_30KB_snapshot/ (ns/op) | 19.91 ms | 19.01 ms | 🟢 -4.51% |
| Pull_30KB_snapshot/ (B/op) | 9.31 MB | 8.77 MB | 🟢 -5.86% |
| Pull_30KB_snapshot/ (allocs/op) | 193,610 allocs | 185,672 allocs | 🟢 -4.10% |
BenchmarkSplayTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| stress_test_100000/ (ns/op) | 0.19 ns | 0.19 ns | 🔴 +0.31% |
| stress_test_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_200000/ (ns/op) | 0.40 ns | 0.40 ns | 🔴 +2.46% |
| stress_test_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_300000/ (ns/op) | 0.57 ns | 0.58 ns | 🔴 +1.65% |
| stress_test_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_100000/ (ns/op) | 0.01 ns | 0.01 ns | 🟢 -1.57% |
| random_access_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_200000/ (ns/op) | 0.03 ns | 0.04 ns | 🔴 +12.35% |
| random_access_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_300000/ (ns/op) | 0.04 ns | 0.04 ns | 🔴 +0.77% |
| random_access_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| editing_trace_bench/ (ns/op) | 0.00 ns | 0.00 ns | 🔴 +8.68% |
| editing_trace_bench/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| editing_trace_bench/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkSync
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| memory_sync_10_test/ (ns/op) | 7288.00 ns | 7187.00 ns | 🟢 -1.39% |
| memory_sync_10_test/ (B/op) | 1.34 KB | 1.34 KB | 🔴 +0.07% |
| memory_sync_10_test/ (allocs/op) | 35 allocs | 35 allocs | ⚪ 0% |
| memory_sync_100_test/ (ns/op) | 55353.00 ns | 55486.00 ns | 🔴 +0.24% |
| memory_sync_100_test/ (B/op) | 9.51 KB | 9.50 KB | 🟢 -0.02% |
| memory_sync_100_test/ (allocs/op) | 268 allocs | 268 allocs | ⚪ 0% |
| memory_sync_1000_test/ (ns/op) | 616285.00 ns | 623115.00 ns | 🔴 +1.11% |
| memory_sync_1000_test/ (B/op) | 75.92 KB | 75.72 KB | 🟢 -0.26% |
| memory_sync_1000_test/ (allocs/op) | 2,111 allocs | 2,104 allocs | 🟢 -0.33% |
| memory_sync_10000_test/ (ns/op) | 7.47 ms | 7.69 ms | 🔴 +2.93% |
| memory_sync_10000_test/ (B/op) | 761.49 KB | 761.44 KB | ⚪ 0% |
| memory_sync_10000_test/ (allocs/op) | 20,475 allocs | 20,489 allocs | 🔴 +0.07% |
BenchmarkTextEditing
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 5.18 s | 5.19 s | 🔴 +0.14% |
| (B/op) | 3.92 GB | 3.92 GB | ⚪ 0% |
| (allocs/op) | 20,619,777 allocs | 20,619,754 allocs | ⚪ 0% |
BenchmarkTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| 10000_vertices_to_protobuf/ (ns/op) | 4.17 ms | 4.37 ms | 🔴 +4.66% |
| 10000_vertices_to_protobuf/ (B/op) | 6.36 MB | 6.36 MB | ⚪ 0% |
| 10000_vertices_to_protobuf/ (allocs/op) | 70,025 allocs | 70,025 allocs | ⚪ 0% |
| 10000_vertices_from_protobuf/ (ns/op) | 217.30 ms | 223.44 ms | 🔴 +2.83% |
| 10000_vertices_from_protobuf/ (B/op) | 442.30 MB | 442.31 MB | ⚪ 0% |
| 10000_vertices_from_protobuf/ (allocs/op) | 290,038 allocs | 290,039 allocs | ⚪ 0% |
| 20000_vertices_to_protobuf/ (ns/op) | 8.84 ms | 9.12 ms | 🔴 +3.21% |
| 20000_vertices_to_protobuf/ (B/op) | 12.89 MB | 12.89 MB | ⚪ 0% |
| 20000_vertices_to_protobuf/ (allocs/op) | 140,028 allocs | 140,028 allocs | ⚪ 0% |
| 20000_vertices_from_protobuf/ (ns/op) | 884.61 ms | 884.11 ms | 🟢 -0.06% |
| 20000_vertices_from_protobuf/ (B/op) | 1.70 GB | 1.70 GB | ⚪ 0% |
| 20000_vertices_from_protobuf/ (allocs/op) | 580,043 allocs | 580,044 allocs | ⚪ 0% |
| 30000_vertices_to_protobuf/ (ns/op) | 14.26 ms | 13.97 ms | 🟢 -2.05% |
| 30000_vertices_to_protobuf/ (B/op) | 18.98 MB | 18.98 MB | ⚪ 0% |
| 30000_vertices_to_protobuf/ (allocs/op) | 210,029 allocs | 210,029 allocs | ⚪ 0% |
| 30000_vertices_from_protobuf/ (ns/op) | 2.00 s | 2.00 s | 🔴 +0.16% |
| 30000_vertices_from_protobuf/ (B/op) | 3.75 GB | 3.75 GB | ⚪ 0% |
| 30000_vertices_from_protobuf/ (allocs/op) | 870,147 allocs | 870,143 allocs | ⚪ 0% |
BenchmarkVersionVector
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| clients_10/ (ns/op) | 160.21 ms | 159.49 ms | 🟢 -0.45% |
| clients_10/ (1_changepack(bytes)) | 745.00 B | 745.00 B | ⚪ 0% |
| clients_10/ (2_snapshot(bytes)) | 379.00 B | 379.00 B | ⚪ 0% |
| clients_10/ (3_pushpull(ms)) | 8.00 ms | 7.00 ms | 🟢 -12.50% |
| clients_10/ (4_attach(ms)) | 6.00 ms | 6.00 ms | ⚪ 0% |
| clients_10/ (5_changepack_after_detach(bytes)) | 805.00 B | 805.00 B | ⚪ 0% |
| clients_10/ (6_snapshot_after_detach(bytes)) | 136.00 B | 136.00 B | ⚪ 0% |
| clients_10/ (7_pushpull_after_detach(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (B/op) | 19.93 MB | 21.06 MB | 🔴 +5.64% |
| clients_10/ (allocs/op) | 83,762 allocs | 83,263 allocs | 🟢 -0.60% |
| clients_100/ (ns/op) | 1.41 s | 1.39 s | 🟢 -1.31% |
| clients_100/ (1_changepack(bytes)) | 6.14 KB | 6.14 KB | ⚪ 0% |
| clients_100/ (2_snapshot(bytes)) | 3.08 KB | 3.08 KB | ⚪ 0% |
| clients_100/ (3_pushpull(ms)) | 11.00 ms | 11.00 ms | ⚪ 0% |
| clients_100/ (4_attach(ms)) | 11.00 ms | 10.00 ms | 🟢 -9.09% |
| clients_100/ (5_changepack_after_detach(bytes)) | 6.21 KB | 6.21 KB | ⚪ 0% |
| clients_100/ (6_snapshot_after_detach(bytes)) | 137.00 B | 137.00 B | ⚪ 0% |
| clients_100/ (7_pushpull_after_detach(ms)) | 9.00 ms | 9.00 ms | ⚪ 0% |
| clients_100/ (B/op) | 230.31 MB | 215.11 MB | 🟢 -6.60% |
| clients_100/ (allocs/op) | 1,539,768 allocs | 1,481,226 allocs | 🟢 -3.80% |
| clients_1000/ (ns/op) | 60.97 s | 45.71 s | 🟢 -25.03% |
| clients_1000/ (1_changepack(bytes)) | 60.16 KB | 60.16 KB | ⚪ 0% |
| clients_1000/ (2_snapshot(bytes)) | 30.08 KB | 30.08 KB | ⚪ 0% |
| clients_1000/ (3_pushpull(ms)) | 95.00 ms | 93.00 ms | 🟢 -2.11% |
| clients_1000/ (4_attach(ms)) | 249.00 ms | 100.00 ms | 🟢 -59.84% |
| clients_1000/ (5_changepack_after_detach(bytes)) | 60.22 KB | 60.22 KB | ⚪ 0% |
| clients_1000/ (6_snapshot_after_detach(bytes)) | 139.00 B | 139.00 B | ⚪ 0% |
| clients_1000/ (7_pushpull_after_detach(ms)) | 26.00 ms | 22.00 ms | 🟢 -15.38% |
| clients_1000/ (B/op) | 22.07 GB | 6.43 GB | 🟢 -70.85% |
| clients_1000/ (allocs/op) | 111,762,106 allocs | 93,353,871 allocs | 🟢 -16.47% |
There was a problem hiding this comment.
Go Benchmark Analysis 📊
This is a comparison result between the previous(e687d61) and the current commit(b5429d7).
Significant Changes (≥20% difference)
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| BenchmarkVersionVector/clients_1000/ (B/op) | 22.07 GB | 6.43 GB | 🟢 -70.85% |
| BenchmarkVersionVector/clients_1000/ (4_attach(ms)) | 249.00 ms | 99.00 ms | 🟢 -60.24% |
| BenchmarkVersionVector/clients_1000/ (ns/op) | 60.97 s | 46.94 s | 🟢 -23.01% |
Key Observations 🔍
- The
BenchmarkVersionVectorsuite exhibited significant improvements in performance with a decrease of 70.85% in memory consumption (B/op) for theclients_1000test. This substantial optimization could lead to enhanced efficiency and resource utilization in scenarios involving a high number of clients. - In the
BenchmarkTreesuite, the10000_vertices_from_protobuftest showed an increase of 4.31% in processing time (ns/op). Similarly, the20000_vertices_to_protobuftest experienced a 3.41% increase in processing time. These increments suggest potential areas for further optimization to streamline vertex data handling in the tree structure. - Across various benchmark suites, the trend of minor performance improvements is noticeable, with several tests displaying marginal decreases in processing times (ns/op) and memory usage (B/op). These incremental enhancements indicate ongoing efforts to refine the efficiency and effectiveness of the tested functionalities.
Clock Analysis
Lamport (v0.5.2)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time | 84.96 ms | 793.94 ms | 34.79 s |
| Memory Allocations | 35.11 MB | 219.92 MB | 4.91 GB |
| Number of Allocations (allocs/op) | 69,271 | 1,246,728 | 81,485,288 |
| ChangePack Size | 138.0 B | 137.0 B | 141.0 B |
| Snapshot Size | 379.0 B | 3.08 KB | 30.08 KB |
| Push-Pull Time | 2.0 ms | 1.5 ms | 4.0 ms |
| Attach Time | 4.5 ms | 11.0 ms | 31.0 ms |
| ChangePack After Detach | 138.0 B | 140.0 B | 141.0 B |
| Snapshot After Detach | 136.0 B | 137.0 B | 139.0 B |
| Push-Pull After Detach | 2.5 ms | 5.0 ms | 9.5 ms |
VV (current)
| Metric | 10 clients | 100 clients | 1000 clients |
|---|---|---|---|
| Total Operation Time (ns/op) | 161.52 ms | 1.43 s | 46.94 s |
| Memory Allocated (B/op) | 20.73 MB | 215.94 MB | 6.43 GB |
| Number of Allocations (allocs/op) | 83,261 | 1,481,218 | 93,356,999 |
| ChangePack Size (bytes) | 745.00 B | 6.14 KB | 60.16 KB |
| Snapshot Size (bytes) | 379.00 B | 3.08 KB | 30.08 KB |
| Push-Pull Time (ms) | 8.00 ms | 11.00 ms | 94.00 ms |
| Attach Time (ms) | 6.00 ms | 9.00 ms | 99.00 ms |
| ChangePack After Detach (bytes) | 805.00 B | 6.21 KB | 60.22 KB |
| Snapshot After Detach (bytes) | 136.00 B | 137.00 B | 139.00 B |
| Push-Pull After Detach (ms) | 8.00 ms | 10.00 ms | 23.00 ms |
Summary
- Lamport clock shows better performance in total operation time for 10 clients, but Version Vector performs better for 100 and 1000 clients.
- Memory allocations are higher for Version Vector across all client scenarios.
- The number of allocations is significantly higher for Version Vector compared to Lamport clock.
- Version Vector has larger ChangePack and Snapshot sizes but lower Push-Pull times compared to Lamport clock.
- The Attach time for Version Vector is more consistent and lower than Lamport clock across all client scenarios.
- ChangePack and Snapshot sizes after detach are larger for Version Vector.
- Push-Pull time after detach is better for Version Vector in 10 and 100 client scenarios, but worse for 1000 clients.
Detailed Test Results
BenchmarkDocument
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| constructor_test/ (ns/op) | 1439.00 ns | 1459.00 ns | 🔴 +1.39% |
| constructor_test/ (B/op) | 1.39 KB | 1.43 KB | 🔴 +3.47% |
| constructor_test/ (allocs/op) | 24 allocs | 25 allocs | 🔴 +4.17% |
| status_test/ (ns/op) | 1028.00 ns | 1067.00 ns | 🔴 +3.79% |
| status_test/ (B/op) | 1.35 KB | 1.40 KB | 🔴 +3.55% |
| status_test/ (allocs/op) | 22 allocs | 23 allocs | 🔴 +4.55% |
| equals_test/ (ns/op) | 7864.00 ns | 8148.00 ns | 🔴 +3.61% |
| equals_test/ (B/op) | 7.56 KB | 7.71 KB | 🔴 +1.90% |
| equals_test/ (allocs/op) | 129 allocs | 132 allocs | 🔴 +2.33% |
| nested_update_test/ (ns/op) | 17079.00 ns | 17062.00 ns | 🟢 -0.10% |
| nested_update_test/ (B/op) | 12.31 KB | 12.36 KB | 🔴 +0.39% |
| nested_update_test/ (allocs/op) | 258 allocs | 259 allocs | 🔴 +0.39% |
| delete_test/ (ns/op) | 27313.00 ns | 22845.00 ns | 🟢 -16.36% |
| delete_test/ (B/op) | 15.79 KB | 15.84 KB | 🔴 +0.30% |
| delete_test/ (allocs/op) | 339 allocs | 340 allocs | 🔴 +0.29% |
| object_test/ (ns/op) | 8546.00 ns | 8573.00 ns | 🔴 +0.32% |
| object_test/ (B/op) | 7.03 KB | 7.08 KB | 🔴 +0.68% |
| object_test/ (allocs/op) | 118 allocs | 119 allocs | 🔴 +0.85% |
| array_test/ (ns/op) | 28984.00 ns | 28384.00 ns | 🟢 -2.07% |
| array_test/ (B/op) | 12.14 KB | 12.19 KB | 🔴 +0.40% |
| array_test/ (allocs/op) | 273 allocs | 274 allocs | 🔴 +0.37% |
| text_test/ (ns/op) | 32155.00 ns | 38483.00 ns | 🔴 +19.68% |
| text_test/ (B/op) | 15.19 KB | 15.24 KB | 🔴 +0.32% |
| text_test/ (allocs/op) | 484 allocs | 485 allocs | 🔴 +0.21% |
| text_composition_test/ (ns/op) | 31674.00 ns | 31714.00 ns | 🔴 +0.13% |
| text_composition_test/ (B/op) | 18.70 KB | 18.75 KB | 🔴 +0.26% |
| text_composition_test/ (allocs/op) | 501 allocs | 502 allocs | 🔴 +0.20% |
| rich_text_test/ (ns/op) | 87424.00 ns | 85966.00 ns | 🟢 -1.67% |
| rich_text_test/ (B/op) | 39.36 KB | 39.40 KB | 🔴 +0.12% |
| rich_text_test/ (allocs/op) | 1,146 allocs | 1,147 allocs | 🔴 +0.09% |
| counter_test/ (ns/op) | 18201.00 ns | 18280.00 ns | 🔴 +0.43% |
| counter_test/ (B/op) | 11.81 KB | 11.86 KB | 🔴 +0.41% |
| counter_test/ (allocs/op) | 253 allocs | 254 allocs | 🔴 +0.40% |
| text_edit_gc_100/ (ns/op) | 1.39 ms | 1.42 ms | 🔴 +2.35% |
| text_edit_gc_100/ (B/op) | 864.90 KB | 864.92 KB | ⚪ 0% |
| text_edit_gc_100/ (allocs/op) | 17,281 allocs | 17,283 allocs | 🔴 +0.01% |
| text_edit_gc_1000/ (ns/op) | 53.39 ms | 53.66 ms | 🔴 +0.51% |
| text_edit_gc_1000/ (B/op) | 46.84 MB | 46.84 MB | ⚪ 0% |
| text_edit_gc_1000/ (allocs/op) | 185,598 allocs | 185,595 allocs | ⚪ 0% |
| text_split_gc_100/ (ns/op) | 2.12 ms | 2.12 ms | 🟢 -0.07% |
| text_split_gc_100/ (B/op) | 1.58 MB | 1.58 MB | ⚪ 0% |
| text_split_gc_100/ (allocs/op) | 15,950 allocs | 15,951 allocs | ⚪ 0% |
| text_split_gc_1000/ (ns/op) | 128.25 ms | 129.43 ms | 🔴 +0.92% |
| text_split_gc_1000/ (B/op) | 137.79 MB | 137.79 MB | ⚪ 0% |
| text_split_gc_1000/ (allocs/op) | 185,000 allocs | 185,000 allocs | ⚪ 0% |
| text_delete_all_10000/ (ns/op) | 18.43 ms | 17.78 ms | 🟢 -3.55% |
| text_delete_all_10000/ (B/op) | 10.58 MB | 10.58 MB | ⚪ 0% |
| text_delete_all_10000/ (allocs/op) | 56,134 allocs | 56,136 allocs | ⚪ 0% |
| text_delete_all_100000/ (ns/op) | 312.31 ms | 288.54 ms | 🟢 -7.61% |
| text_delete_all_100000/ (B/op) | 105.54 MB | 105.51 MB | 🟢 -0.03% |
| text_delete_all_100000/ (allocs/op) | 566,133 allocs | 566,034 allocs | 🟢 -0.02% |
| text_100/ (ns/op) | 234634.00 ns | 232723.00 ns | 🟢 -0.81% |
| text_100/ (B/op) | 120.94 KB | 120.99 KB | 🔴 +0.04% |
| text_100/ (allocs/op) | 5,181 allocs | 5,182 allocs | 🔴 +0.02% |
| text_1000/ (ns/op) | 2.46 ms | 2.47 ms | 🔴 +0.34% |
| text_1000/ (B/op) | 1.16 MB | 1.16 MB | ⚪ 0% |
| text_1000/ (allocs/op) | 51,084 allocs | 51,085 allocs | ⚪ 0% |
| array_1000/ (ns/op) | 1.24 ms | 1.25 ms | 🔴 +0.45% |
| array_1000/ (B/op) | 1.09 MB | 1.09 MB | 🔴 +0.01% |
| array_1000/ (allocs/op) | 11,879 allocs | 11,880 allocs | ⚪ 0% |
| array_10000/ (ns/op) | 13.33 ms | 13.30 ms | 🟢 -0.24% |
| array_10000/ (B/op) | 9.89 MB | 9.89 MB | ⚪ 0% |
| array_10000/ (allocs/op) | 120,735 allocs | 120,732 allocs | ⚪ 0% |
| array_gc_100/ (ns/op) | 131750.00 ns | 132529.00 ns | 🔴 +0.59% |
| array_gc_100/ (B/op) | 99.89 KB | 99.95 KB | 🔴 +0.05% |
| array_gc_100/ (allocs/op) | 1,266 allocs | 1,267 allocs | 🔴 +0.08% |
| array_gc_1000/ (ns/op) | 1.42 ms | 1.42 ms | 🟢 -0.29% |
| array_gc_1000/ (B/op) | 1.14 MB | 1.14 MB | 🔴 +0.01% |
| array_gc_1000/ (allocs/op) | 12,926 allocs | 12,928 allocs | 🔴 +0.02% |
| counter_1000/ (ns/op) | 202098.00 ns | 199985.00 ns | 🟢 -1.05% |
| counter_1000/ (B/op) | 178.13 KB | 178.18 KB | 🔴 +0.03% |
| counter_1000/ (allocs/op) | 5,771 allocs | 5,772 allocs | 🔴 +0.02% |
| counter_10000/ (ns/op) | 2.17 ms | 2.15 ms | 🟢 -0.82% |
| counter_10000/ (B/op) | 2.07 MB | 2.07 MB | ⚪ 0% |
| counter_10000/ (allocs/op) | 59,778 allocs | 59,779 allocs | ⚪ 0% |
| object_1000/ (ns/op) | 1.39 ms | 1.40 ms | 🔴 +0.70% |
| object_1000/ (B/op) | 1.44 MB | 1.44 MB | 🔴 +0.03% |
| object_1000/ (allocs/op) | 9,925 allocs | 9,926 allocs | 🔴 +0.01% |
| object_10000/ (ns/op) | 14.82 ms | 14.97 ms | 🔴 +1.06% |
| object_10000/ (B/op) | 12.35 MB | 12.35 MB | 🔴 +0.02% |
| object_10000/ (allocs/op) | 101,232 allocs | 101,246 allocs | 🔴 +0.01% |
| tree_100/ (ns/op) | 1.02 ms | 1.02 ms | 🟢 -0.22% |
| tree_100/ (B/op) | 951.02 KB | 951.07 KB | ⚪ 0% |
| tree_100/ (allocs/op) | 6,102 allocs | 6,103 allocs | 🔴 +0.02% |
| tree_1000/ (ns/op) | 74.23 ms | 75.49 ms | 🔴 +1.69% |
| tree_1000/ (B/op) | 86.58 MB | 86.58 MB | ⚪ 0% |
| tree_1000/ (allocs/op) | 60,111 allocs | 60,113 allocs | ⚪ 0% |
| tree_10000/ (ns/op) | 9.68 s | 9.68 s | 🟢 -0.03% |
| tree_10000/ (B/op) | 8.58 GB | 8.58 GB | ⚪ 0% |
| tree_10000/ (allocs/op) | 600,173 allocs | 600,190 allocs | ⚪ 0% |
| tree_delete_all_1000/ (ns/op) | 78.41 ms | 76.98 ms | 🟢 -1.82% |
| tree_delete_all_1000/ (B/op) | 87.57 MB | 87.57 MB | ⚪ 0% |
| tree_delete_all_1000/ (allocs/op) | 75,289 allocs | 75,291 allocs | ⚪ 0% |
| tree_edit_gc_100/ (ns/op) | 3.96 ms | 3.83 ms | 🟢 -3.25% |
| tree_edit_gc_100/ (B/op) | 4.15 MB | 4.15 MB | ⚪ 0% |
| tree_edit_gc_100/ (allocs/op) | 15,147 allocs | 15,147 allocs | ⚪ 0% |
| tree_edit_gc_1000/ (ns/op) | 332.75 ms | 315.76 ms | 🟢 -5.10% |
| tree_edit_gc_1000/ (B/op) | 384.04 MB | 384.05 MB | ⚪ 0% |
| tree_edit_gc_1000/ (allocs/op) | 154,952 allocs | 154,950 allocs | ⚪ 0% |
| tree_split_gc_100/ (ns/op) | 2.67 ms | 2.62 ms | 🟢 -1.99% |
| tree_split_gc_100/ (B/op) | 2.41 MB | 2.41 MB | ⚪ 0% |
| tree_split_gc_100/ (allocs/op) | 11,131 allocs | 11,132 allocs | ⚪ 0% |
| tree_split_gc_1000/ (ns/op) | 197.74 ms | 193.35 ms | 🟢 -2.22% |
| tree_split_gc_1000/ (B/op) | 222.50 MB | 222.50 MB | ⚪ 0% |
| tree_split_gc_1000/ (allocs/op) | 122,053 allocs | 122,064 allocs | ⚪ 0% |
BenchmarkRPC
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| client_to_server/ (ns/op) | 431.85 ms | 421.09 ms | 🟢 -2.49% |
| client_to_server/ (B/op) | 16.13 MB | 16.10 MB | 🟢 -0.17% |
| client_to_server/ (allocs/op) | 223,674 allocs | 223,158 allocs | 🟢 -0.23% |
| client_to_client_via_server/ (ns/op) | 788.62 ms | 785.19 ms | 🟢 -0.43% |
| client_to_client_via_server/ (B/op) | 37.20 MB | 35.30 MB | 🟢 -5.11% |
| client_to_client_via_server/ (allocs/op) | 478,656 allocs | 474,350 allocs | 🟢 -0.90% |
| attach_large_document/ (ns/op) | 1.32 s | 1.33 s | 🔴 +0.75% |
| attach_large_document/ (B/op) | 1.89 GB | 1.92 GB | 🔴 +1.72% |
| attach_large_document/ (allocs/op) | 12,321 allocs | 12,332 allocs | 🔴 +0.09% |
| adminCli_to_server/ (ns/op) | 542.08 ms | 545.63 ms | 🔴 +0.65% |
| adminCli_to_server/ (B/op) | 21.76 MB | 21.53 MB | 🟢 -1.03% |
| adminCli_to_server/ (allocs/op) | 291,952 allocs | 316,683 allocs | 🔴 +8.47% |
BenchmarkLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 82.86 ns | 80.82 ns | 🟢 -2.46% |
| (B/op) | 32.00 B | 32.00 B | ⚪ 0% |
| (allocs/op) | 1 allocs | 1 allocs | ⚪ 0% |
BenchmarkLockerParallel
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 45.80 ns | 44.95 ns | 🟢 -1.86% |
| (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkLockerMoreKeys
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 180.50 ns | 176.00 ns | 🟢 -2.49% |
| (B/op) | 31.00 B | 31.00 B | ⚪ 0% |
| (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkRWLocker
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| RWLock_rate_2/ (ns/op) | 50.25 ns | 49.22 ns | 🟢 -2.05% |
| RWLock_rate_2/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_2/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_10/ (ns/op) | 44.88 ns | 43.21 ns | 🟢 -3.72% |
| RWLock_rate_10/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| RWLock_rate_10/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_100/ (ns/op) | 63.08 ns | 58.47 ns | 🟢 -7.31% |
| RWLock_rate_100/ (B/op) | 2.00 B | 2.00 B | ⚪ 0% |
| RWLock_rate_100/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| RWLock_rate_1000/ (ns/op) | 91.91 ns | 87.34 ns | 🟢 -4.97% |
| RWLock_rate_1000/ (B/op) | 8.00 B | 8.00 B | ⚪ 0% |
| RWLock_rate_1000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkChange
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_10_Changes/ (ns/op) | 4.54 ms | 4.52 ms | 🟢 -0.50% |
| Push_10_Changes/ (B/op) | 150.42 KB | 150.37 KB | 🟢 -0.03% |
| Push_10_Changes/ (allocs/op) | 1,623 allocs | 1,623 allocs | ⚪ 0% |
| Push_100_Changes/ (ns/op) | 16.52 ms | 16.76 ms | 🔴 +1.48% |
| Push_100_Changes/ (B/op) | 770.59 KB | 779.07 KB | 🔴 +1.10% |
| Push_100_Changes/ (allocs/op) | 8,509 allocs | 8,511 allocs | 🔴 +0.02% |
| Push_1000_Changes/ (ns/op) | 129.20 ms | 132.25 ms | 🔴 +2.36% |
| Push_1000_Changes/ (B/op) | 7.22 MB | 7.03 MB | 🟢 -2.59% |
| Push_1000_Changes/ (allocs/op) | 79,325 allocs | 79,321 allocs | ⚪ 0% |
| Pull_10_Changes/ (ns/op) | 3.70 ms | 3.72 ms | 🔴 +0.48% |
| Pull_10_Changes/ (B/op) | 124.59 KB | 124.43 KB | 🟢 -0.12% |
| Pull_10_Changes/ (allocs/op) | 1,456 allocs | 1,454 allocs | 🟢 -0.14% |
| Pull_100_Changes/ (ns/op) | 5.32 ms | 5.35 ms | 🔴 +0.44% |
| Pull_100_Changes/ (B/op) | 354.61 KB | 354.26 KB | 🟢 -0.10% |
| Pull_100_Changes/ (allocs/op) | 5,182 allocs | 5,180 allocs | 🟢 -0.04% |
| Pull_1000_Changes/ (ns/op) | 10.88 ms | 11.19 ms | 🔴 +2.86% |
| Pull_1000_Changes/ (B/op) | 2.20 MB | 2.20 MB | 🟢 -0.18% |
| Pull_1000_Changes/ (allocs/op) | 44,681 allocs | 44,680 allocs | ⚪ 0% |
BenchmarkSnapshot
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| Push_3KB_snapshot/ (ns/op) | 19.55 ms | 19.03 ms | 🟢 -2.67% |
| Push_3KB_snapshot/ (B/op) | 905.58 KB | 901.77 KB | 🟢 -0.42% |
| Push_3KB_snapshot/ (allocs/op) | 8,516 allocs | 8,513 allocs | 🟢 -0.04% |
| Push_30KB_snapshot/ (ns/op) | 132.18 ms | 135.55 ms | 🔴 +2.55% |
| Push_30KB_snapshot/ (B/op) | 8.24 MB | 8.14 MB | 🟢 -1.22% |
| Push_30KB_snapshot/ (allocs/op) | 89,008 allocs | 88,281 allocs | 🟢 -0.82% |
| Pull_3KB_snapshot/ (ns/op) | 7.80 ms | 7.50 ms | 🟢 -3.96% |
| Pull_3KB_snapshot/ (B/op) | 1.12 MB | 1.06 MB | 🟢 -5.01% |
| Pull_3KB_snapshot/ (allocs/op) | 20,064 allocs | 19,253 allocs | 🟢 -4.04% |
| Pull_30KB_snapshot/ (ns/op) | 19.91 ms | 19.64 ms | 🟢 -1.37% |
| Pull_30KB_snapshot/ (B/op) | 9.31 MB | 8.76 MB | 🟢 -5.94% |
| Pull_30KB_snapshot/ (allocs/op) | 193,610 allocs | 185,674 allocs | 🟢 -4.10% |
BenchmarkSplayTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| stress_test_100000/ (ns/op) | 0.19 ns | 0.19 ns | 🟢 -1.70% |
| stress_test_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_200000/ (ns/op) | 0.40 ns | 0.39 ns | 🟢 -0.94% |
| stress_test_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| stress_test_300000/ (ns/op) | 0.57 ns | 0.56 ns | 🟢 -0.91% |
| stress_test_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| stress_test_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_100000/ (ns/op) | 0.01 ns | 0.01 ns | 🟢 -1.34% |
| random_access_100000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_100000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_200000/ (ns/op) | 0.03 ns | 0.03 ns | 🟢 -2.04% |
| random_access_200000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_200000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| random_access_300000/ (ns/op) | 0.04 ns | 0.05 ns | 🔴 +5.88% |
| random_access_300000/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| random_access_300000/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
| editing_trace_bench/ (ns/op) | 0.00 ns | 0.00 ns | 🔴 +10.01% |
| editing_trace_bench/ (B/op) | 0.00 B | 0.00 B | ⚪ 0% |
| editing_trace_bench/ (allocs/op) | 0 allocs | 0 allocs | ⚪ 0% |
BenchmarkSync
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| memory_sync_10_test/ (ns/op) | 7288.00 ns | 7258.00 ns | 🟢 -0.41% |
| memory_sync_10_test/ (B/op) | 1.34 KB | 1.34 KB | ⚪ 0% |
| memory_sync_10_test/ (allocs/op) | 35 allocs | 35 allocs | ⚪ 0% |
| memory_sync_100_test/ (ns/op) | 55353.00 ns | 55916.00 ns | 🔴 +1.02% |
| memory_sync_100_test/ (B/op) | 9.51 KB | 9.52 KB | 🔴 +0.19% |
| memory_sync_100_test/ (allocs/op) | 268 allocs | 268 allocs | ⚪ 0% |
| memory_sync_1000_test/ (ns/op) | 616285.00 ns | 614126.00 ns | 🟢 -0.35% |
| memory_sync_1000_test/ (B/op) | 75.92 KB | 76.38 KB | 🔴 +0.60% |
| memory_sync_1000_test/ (allocs/op) | 2,111 allocs | 2,125 allocs | 🔴 +0.66% |
| memory_sync_10000_test/ (ns/op) | 7.47 ms | 8.05 ms | 🔴 +7.74% |
| memory_sync_10000_test/ (B/op) | 761.49 KB | 761.00 KB | 🟢 -0.06% |
| memory_sync_10000_test/ (allocs/op) | 20,475 allocs | 20,476 allocs | ⚪ 0% |
BenchmarkTextEditing
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| (ns/op) | 5.18 s | 5.29 s | 🔴 +2.21% |
| (B/op) | 3.92 GB | 3.92 GB | ⚪ 0% |
| (allocs/op) | 20,619,777 allocs | 20,619,841 allocs | ⚪ 0% |
BenchmarkTree
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| 10000_vertices_to_protobuf/ (ns/op) | 4.17 ms | 4.34 ms | 🔴 +4.01% |
| 10000_vertices_to_protobuf/ (B/op) | 6.36 MB | 6.36 MB | ⚪ 0% |
| 10000_vertices_to_protobuf/ (allocs/op) | 70,025 allocs | 70,025 allocs | ⚪ 0% |
| 10000_vertices_from_protobuf/ (ns/op) | 217.30 ms | 226.66 ms | 🔴 +4.31% |
| 10000_vertices_from_protobuf/ (B/op) | 442.30 MB | 442.31 MB | ⚪ 0% |
| 10000_vertices_from_protobuf/ (allocs/op) | 290,038 allocs | 290,039 allocs | ⚪ 0% |
| 20000_vertices_to_protobuf/ (ns/op) | 8.84 ms | 9.14 ms | 🔴 +3.41% |
| 20000_vertices_to_protobuf/ (B/op) | 12.89 MB | 12.89 MB | ⚪ 0% |
| 20000_vertices_to_protobuf/ (allocs/op) | 140,028 allocs | 140,028 allocs | ⚪ 0% |
| 20000_vertices_from_protobuf/ (ns/op) | 884.61 ms | 900.39 ms | 🔴 +1.78% |
| 20000_vertices_from_protobuf/ (B/op) | 1.70 GB | 1.70 GB | ⚪ 0% |
| 20000_vertices_from_protobuf/ (allocs/op) | 580,043 allocs | 580,046 allocs | ⚪ 0% |
| 30000_vertices_to_protobuf/ (ns/op) | 14.26 ms | 14.09 ms | 🟢 -1.19% |
| 30000_vertices_to_protobuf/ (B/op) | 18.98 MB | 18.98 MB | ⚪ 0% |
| 30000_vertices_to_protobuf/ (allocs/op) | 210,029 allocs | 210,029 allocs | ⚪ 0% |
| 30000_vertices_from_protobuf/ (ns/op) | 2.00 s | 1.99 s | 🟢 -0.63% |
| 30000_vertices_from_protobuf/ (B/op) | 3.75 GB | 3.75 GB | ⚪ 0% |
| 30000_vertices_from_protobuf/ (allocs/op) | 870,147 allocs | 870,149 allocs | ⚪ 0% |
BenchmarkVersionVector
| Benchmark suite | Previous | Current | Change |
|---|---|---|---|
| clients_10/ (ns/op) | 160.21 ms | 161.52 ms | 🔴 +0.82% |
| clients_10/ (1_changepack(bytes)) | 745.00 B | 745.00 B | ⚪ 0% |
| clients_10/ (2_snapshot(bytes)) | 379.00 B | 379.00 B | ⚪ 0% |
| clients_10/ (3_pushpull(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (4_attach(ms)) | 6.00 ms | 6.00 ms | ⚪ 0% |
| clients_10/ (5_changepack_after_detach(bytes)) | 805.00 B | 805.00 B | ⚪ 0% |
| clients_10/ (6_snapshot_after_detach(bytes)) | 136.00 B | 136.00 B | ⚪ 0% |
| clients_10/ (7_pushpull_after_detach(ms)) | 8.00 ms | 8.00 ms | ⚪ 0% |
| clients_10/ (B/op) | 19.93 MB | 20.73 MB | 🔴 +3.99% |
| clients_10/ (allocs/op) | 83,762 allocs | 83,261 allocs | 🟢 -0.60% |
| clients_100/ (ns/op) | 1.41 s | 1.43 s | 🔴 +1.57% |
| clients_100/ (1_changepack(bytes)) | 6.14 KB | 6.14 KB | ⚪ 0% |
| clients_100/ (2_snapshot(bytes)) | 3.08 KB | 3.08 KB | ⚪ 0% |
| clients_100/ (3_pushpull(ms)) | 11.00 ms | 11.00 ms | ⚪ 0% |
| clients_100/ (4_attach(ms)) | 11.00 ms | 9.00 ms | 🟢 -18.18% |
| clients_100/ (5_changepack_after_detach(bytes)) | 6.21 KB | 6.21 KB | ⚪ 0% |
| clients_100/ (6_snapshot_after_detach(bytes)) | 137.00 B | 137.00 B | ⚪ 0% |
| clients_100/ (7_pushpull_after_detach(ms)) | 9.00 ms | 10.00 ms | 🔴 +11.11% |
| clients_100/ (B/op) | 230.31 MB | 215.94 MB | 🟢 -6.24% |
| clients_100/ (allocs/op) | 1,539,768 allocs | 1,481,218 allocs | 🟢 -3.80% |
| clients_1000/ (ns/op) | 60.97 s | 46.94 s | 🟢 -23.01% |
| clients_1000/ (1_changepack(bytes)) | 60.16 KB | 60.16 KB | ⚪ 0% |
| clients_1000/ (2_snapshot(bytes)) | 30.08 KB | 30.08 KB | ⚪ 0% |
| clients_1000/ (3_pushpull(ms)) | 95.00 ms | 94.00 ms | 🟢 -1.05% |
| clients_1000/ (4_attach(ms)) | 249.00 ms | 99.00 ms | 🟢 -60.24% |
| clients_1000/ (5_changepack_after_detach(bytes)) | 60.22 KB | 60.22 KB | ⚪ 0% |
| clients_1000/ (6_snapshot_after_detach(bytes)) | 139.00 B | 139.00 B | ⚪ 0% |
| clients_1000/ (7_pushpull_after_detach(ms)) | 26.00 ms | 23.00 ms | 🟢 -11.54% |
| clients_1000/ (B/op) | 22.07 GB | 6.43 GB | 🟢 -70.85% |
| clients_1000/ (allocs/op) | 111,762,106 allocs | 93,356,999 allocs | 🟢 -16.47% |
raararaara
commented
Feb 21, 2025
There was a problem hiding this comment.
I changed the loop to use direct indexing instead of range to avoid potential pointer aliasing issues. Using range in this context could lead to unintended shared references to memory, while direct indexing ensures each element is safely referenced. This change improves the safety and stability of the code.
For more context, refer to this StackOverflow discussion on implicit memory aliasing in for loops: https://stackoverflow.com/questions/62446118/implicit-memory-aliasing-in-for-loop
3 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it:
This PR serves as a follow-up to the previous PR #1153. It optimizes the max version vector in a manner similar to the optimization applied to the min version vector.
During the process of applying remote changes with
ApplyChanges, the version vector was being updated each time. This resulted in unnecessary copy creation of the parameters passed to theMaxmethod. By modifying the function to directly modify the object within instead of creating copies, we enhance memory efficiency.Any background context you want to provide?
Which issue(s) this PR fixes:
Fixes #1152
Special notes for your reviewer:
Does this PR introduce a user-facing change?:
Additional documentation:
Checklist:
Summary by CodeRabbit
Refactor
Tests