github-actions[bot]
commented
11 months ago Note The flamegraph link only works after you merge. Unchanged benchmarks are omitted.
Collection libraries
Measure different collection libraries written in both Motoko and Rust.
The library names with _rs suffix are written in Rust; the rest are written in Motoko.
We use the same random number generator with fixed seed to ensure that all collections contain the same elements, and the queries are exactly the same. Below we explain the measurements of each column in the table:
- generate 1m. Insert 1m Nat64 integers into the collection. For Motoko collections, it usually triggers the GC; the rest of the column are not likely to trigger GC.
- max mem. For Motoko, it reports
rts_max_heap_sizeaftergeneratecall; For Rust, it reports the Wasm's memory page * 32Kb. - batch_get 50. Find 50 elements from the collection.
- batch_put 50. Insert 50 elements to the collection.
- batch_remove 50. Remove 50 elements from the collection.
💎 Takeaways
- The platform only charges for instruction count. Data structures which make use of caching and locality have no impact on the cost.
- We have a limit on the maximal cycles per round. This means asymptotic behavior doesn't matter much. We care more about the performance up to a fixed N. In the extreme cases, you may see an $O(10000 n\log n)$ algorithm hitting the limit, while an $O(n^2)$ algorithm runs just fine.
- Amortized algorithms/GC may need to be more eager to avoid hitting the cycle limit on a particular round.
- Rust costs more cycles to process complicated Candid data, but it is more efficient in performing core computations.
Note
- The Candid interface of the benchmark is minimal, therefore the serialization cost is negligible in this measurement.
- Due to the instrumentation overhead and cycle limit, we cannot profile computations with large collections. Hopefully, when deterministic time slicing is ready, we can measure the performance on larger memory footprint.
hashmapuses amortized data structure. When the initial capacity is reached, it has to copy the whole array, thus the cost ofbatch_put 50is much higher than other data structures.btreecomes from mops.one/stableheapbtreemap.zhenya_hashmapcomes from mops.one/map.vectorcomes from mops.one/vector. Compare withbuffer,puthas better worst case time and space complexity ($O(\sqrt{n})$ vs $O(n)$);gethas a slightly larger constant overhead.hashmap_rsuses thefxhashcrate, which is the same asstd::collections::HashMap, but with a deterministic hasher. This ensures reproducible result.imrc_hashmap_rsuses theim-rccrate, which is the immutable version hashmap in Rust.
Map
| binary_size | generate 1m | max mem | batch_get 50 | batch_put 50 | batch_remove 50 | |
|---|---|---|---|---|---|---|
| hashmap | 136_674 | 8_608_696_480 | 61_987_732 | 352_319 | 6_688_149_059 | 380_480 |
| triemap | 137_423 | 14_635_117_716 | 74_216_052 | 287_719 | 702_751 | 687_522 |
| rbtree | 137_984 | 7_173_338_280 | 57_995_940 | 100_835 | 319_607 | 350_056 |
| splay | 134_108 | 14_444_672_641 | 53_995_876 | 688_885 | 725_442 | 998_352 |
| btree | 177_329 | 10_991_847_496 | 31_103_892 | 367_465 | 515_286 | 573_932 |
| zhenya_hashmap | 145_419 | 3_378_997_121 | 65_987_480 | 86_454 | 107_552 | 128_794 |
| btreemap_rs | 446_267 | 1_797_752_179 | 13_762_560 | 74_544 | 126_136 | 92_839 |
| imrc_hashmap_rs | 446_166 | 2_571_892_333 | 122_454_016 | 38_956 | 179_095 | 115_561 |
| hashmap_rs | 439_346 | 447_664_894 | 36_536_320 | 22_228 | 27_664 | 25_290 |
Priority queue
| binary_size | heapify 1m | max mem | pop_min 50 | put 50 | ||
|---|---|---|---|---|---|---|
| heap | 130_848 | 6_220_330_310 | 29_995_836 | 675_652 | 251_392 | 643_610 |
| heap_rs | 437_278 | 142_914_793 | 9_109_504 | 59_850 | 23_726 | 60_072 |
Growable array
| binary_size | generate 5k | max mem | batch_get 500 | batch_put 500 | batch_remove 500 | |
|---|---|---|---|---|---|---|
| buffer | 138_384 | 2_906_293 | 65_508 | 116_018 | 920_351 | 182_018 |
| vector | 137_157 | 2_493_696 | 24_764 | 179_705 | 238_501 | 230_000 |
| vec_rs | 435_834 | 290_143 | 655_360 | 17_605 | 31_014 | 25_400 |
Cryptographic libraries
Measure different cryptographic libraries written in both Motoko and Rust.
- SHA-2 benchmarks
SHA-256/SHA-512. Compute the hash of a 1M Wasm binary.account_id. Compute the ledger account id from principal, based on SHA-224.neuron_id. Compute the NNS neuron id from principal, based on SHA-256.
- Certified map. Merkle Tree for storing key-value pairs and generate witness according to the IC Interface Specification.
generate 10k. Insert 10k 7-character word as both key and value into the certified map.max mem. For Motoko, it reportsrts_max_heap_sizeaftergeneratecall; For Rust, it reports the Wasm's memory page * 32Kb.inc. Increment a counter and insert the counter value into the map.witness. Generate the root hash and a witness for the counter.
SHA-2
| binary_size | SHA-256 | SHA-512 | account_id | neuron_id | |
|---|---|---|---|---|---|
| Motoko | 171_816 | 306_043_778 | 290_622_723 | 38_508 | 27_563 |
| Rust | 528_234 | 82_789_387 | 56_794_263 | 50_651 | 53_532 |
Certified map
| binary_size | generate 10k | max mem | inc | witness | |
|---|---|---|---|---|---|
| Motoko | 172_585 | 5_366_164_469 | 3_429_924 | 636_930 | 452_577 |
| Rust | 469_955 | 6_359_442_714 | 1_081_344 | 1_012_174 | 305_119 |
Sample Dapps
Measure the performance of some typical dapps:
- Basic DAO,
with
heartbeatdisabled to make profiling easier. We have a separate benchmark to measure heartbeat performance. - DIP721 NFT
Note
- The cost difference is mainly due to the Candid serialization cost.
- Motoko statically compiles/specializes the serialization code for each method, whereas in Rust, we use
serdeto dynamically deserialize data based on data on the wire.- We could improve the performance on the Rust side by using parser combinators. But it is a challenge to maintain the ergonomics provided by
serde.- For real-world applications, we tend to send small data for each endpoint, which makes the Candid overhead in Rust tolerable.
Basic DAO
| binary_size | init | transfer_token | submit_proposal | vote_proposal | |
|---|---|---|---|---|---|
| Motoko | 227_168 | 47_700 | 22_751 | 18_939 | 20_074 |
| Rust | 763_017 | 552_075 | 105_203 | 128_753 | 139_539 |
DIP721 NFT
| binary_size | init | mint_token | transfer_token | |
|---|---|---|---|---|
| Motoko | 186_953 | 17_772 | 29_817 | 8_883 |
| Rust | 828_238 | 146_257 | 380_260 | 93_763 |
Heartbeat / Timer
Measure the cost of empty heartbeat and timer job.
setTimermeasures both thesetTimer(0)method and the execution of empty job.- It is not easy to reliably capture the above events in one flamegraph, as the implementation detail
of the replica can affect how we measure this. Typically, a correct flamegraph contains both
setTimerandcanister_global_timerfunction. If it's not there, we may need to adjust the script.
Heartbeat
| binary_size | heartbeat | |
|---|---|---|
| Motoko | 122_666 | 23_292 |
| Rust | 25_650 | 549 |
Timer
| binary_size | setTimer | cancelTimer | |
|---|---|---|---|
| Motoko | 128_683 | 52_049 | 4_647 |
| Rust | 470_693 | 69_727 | 11_405 |
Motoko Specific Benchmarks
Measure various features only available in Motoko.
-
Garbage Collection. Measure Motoko garbage collection cost using the Triemap benchmark. The max mem column reports
rts_max_heap_sizeaftergeneratecall. The cycle cost numbers reported here are garbage collection cost only. Some flamegraphs are truncated due to the 2M log size limit. Thedfx/ic-wasmoptimizer is disabled for the garbage collection test cases due to how the optimizer affects function names, making profiling trickier.- default. Compile with the default GC option. With the current GC scheduler,
generatewill trigger the copying GC. The rest of the methods will not trigger GC. - copying. Compile with
--force-gc --copying-gc. - compacting. Compile with
--force-gc --compacting-gc. - generational. Compile with
--force-gc --generational-gc. - incremental. Compile with
--force-gc --incremental-gc.
- default. Compile with the default GC option. With the current GC scheduler,
-
Actor class. Measure the cost of spawning actor class, using the Actor classes example.
Garbage Collection
| generate 800k | max mem | batch_get 50 | batch_put 50 | batch_remove 50 | |
|---|---|---|---|---|---|
| default | 1_338_231_405 | 59_396_776 | 118 | 118 | 118 |
| copying | 1_338_231_287 | 59_396_776 | 1_337_913_569 | 1_338_002_371 | 1_337_919_144 |
| compacting | 1_911_420_608 | 59_396_776 | 1_473_824_186 | 1_756_485_066 | 1_787_369_954 |
| generational | 2_891_818_643 | 59_405_240 | 1_141_865_993 | 1_217_376 | 1_117_840 |
| incremental | 33_436_719 | 1_136_155_048 | 333_734_166 | 336_829_512 | 336_860_690 |
Actor class
| binary size | put new bucket | put existing bucket | get | |
|---|---|---|---|---|
| Map | 259_478 | 711_028 | 16_268 | 16_784 |
Publisher & Subscriber
Measure the cost of inter-canister calls from the Publisher & Subscriber example.
| pub_binary_size | sub_binary_size | subscribe_caller | subscribe_callee | publish_caller | publish_callee | |
|---|---|---|---|---|---|---|
| Motoko | 143_511 | 130_619 | 28_763 | 11_964 | 23_039 | 6_432 |
| Rust | 511_870 | 565_407 | 71_728 | 44_318 | 95_767 | 53_941 |
Map
Priority queue
Growable array
Statistics
SHA-2
Certified map
Statistics
Basic DAO
DIP721 NFT
Statistics
Heartbeat
Timer
Statistics
Garbage Collection
Actor class
Statistics
Publisher & Subscriber
Statistics
binary_size: -13.98% [-14.15%, -13.81%]
max_mem: no change
cycles: -4.83% [-6.12%, -3.55%]
Overall Statistics
binary_size: -14.96% [-15.70%, -14.22%]
max_mem: no change
cycles: -12.78% [-14.00%, -11.57%]