feat: add Throughput to all criterion benchmarks so critcmp shows ops/sec

[deepjoy]

• All criterion benchmarks now declare Throughput::Elements(N) so critcmp
  reports real throughput (tasks/sec, queries/sec) instead of ? ?/sec.
• Standalone bench_function calls are converted to BenchmarkGroups since
  criterion only exposes throughput on groups. This changes benchmark names
  from flat (e.g. submit_1000_tasks) to structured (e.g. submit_tasks/1000).
• Parameterized benchmarks (dependency chains, fan-in) set throughput per
  parameter to reflect the actual element count at each size.

[github-actions]

Benchmark Comparison

Click to expand

group                                       main                                    pr
-----                                       ----                                    --
backoff_delay/constant                      1.05     50.1±0.09ns        ? ?/sec     1.00     47.9±0.11ns 397.9 MElem/sec
backoff_delay/exponential                   1.00    187.0±0.49ns        ? ?/sec     1.00    187.2±1.09ns 101.9 MElem/sec
backoff_delay/exponential_jitter            1.00    269.9±2.52ns        ? ?/sec     1.00    269.2±0.90ns 70.8 MElem/sec
backoff_delay/linear                        1.00     76.3±0.17ns        ? ?/sec     1.06     81.1±1.00ns 235.1 MElem/sec
batch_submit/1000                                                                   1.00     32.7±2.65ms 29.8 KElem/sec
batch_submit_1000                           1.00     34.0±2.40ms        ? ?/sec   
byte_progress/byte_reporting_500            1.03    242.2±6.15ms        ? ?/sec     1.00    234.3±5.53ms  2.1 KElem/sec
byte_progress/noop_500                      1.03    241.2±4.08ms        ? ?/sec     1.00    233.5±4.07ms  2.1 KElem/sec
byte_progress_snapshot/100_tasks                                                    1.00     78.3±2.25ms  1277 Elem/sec
byte_progress_snapshot_100_tasks            1.00     80.3±1.89ms        ? ?/sec   
concurrency_scaling/1                       1.03    374.3±4.28ms        ? ?/sec     1.00    363.2±3.79ms  1376 Elem/sec
concurrency_scaling/2                       1.03    310.4±3.40ms        ? ?/sec     1.00    301.5±3.86ms  1658 Elem/sec
concurrency_scaling/4                       1.03    267.8±4.60ms        ? ?/sec     1.00    259.8±5.00ms  1924 Elem/sec
concurrency_scaling/8                       1.03    241.8±4.12ms        ? ?/sec     1.00    235.0±4.09ms  2.1 KElem/sec
count_by_tags/100                           1.03    127.7±2.85µs        ? ?/sec     1.00    124.2±2.61µs  7.9 KElem/sec
count_by_tags/1000                          1.02    215.5±2.86µs        ? ?/sec     1.00    211.0±4.03µs  4.6 KElem/sec
count_by_tags/5000                          1.03    616.1±7.04µs        ? ?/sec     1.00    597.9±3.24µs  1672 Elem/sec
dep_chain_dispatch/10                       1.04     10.9±0.10ms        ? ?/sec     1.00     10.5±0.13ms   956 Elem/sec
dep_chain_dispatch/25                       1.05     26.6±0.62ms        ? ?/sec     1.00     25.2±0.44ms   990 Elem/sec
dep_chain_dispatch/50                       1.04     52.8±0.88ms        ? ?/sec     1.00     50.6±0.74ms   988 Elem/sec
dep_chain_submit/10                         1.05      3.1±0.13ms        ? ?/sec     1.00      2.9±0.10ms  3.3 KElem/sec
dep_chain_submit/200                        1.04     78.0±3.76ms        ? ?/sec     1.00     75.3±3.44ms  2.6 KElem/sec
dep_chain_submit/50                         1.06     17.0±0.76ms        ? ?/sec     1.00     16.1±0.78ms  3.0 KElem/sec
dep_fan_in_dispatch/10                      1.04      7.0±0.09ms        ? ?/sec     1.00      6.8±0.09ms  1625 Elem/sec
dep_fan_in_dispatch/100                     1.03     52.0±1.04ms        ? ?/sec     1.00     50.6±0.76ms  1997 Elem/sec
dep_fan_in_dispatch/50                      1.03     26.7±0.64ms        ? ?/sec     1.00     25.9±0.48ms  1969 Elem/sec
dispatch_and_complete/1000                                                          1.00    471.3±5.46ms  2.1 KElem/sec
dispatch_and_complete_1000                  1.00    485.0±5.97ms        ? ?/sec   
dispatch_group_scaling/1                    1.04    417.5±5.31ms        ? ?/sec     1.00    401.0±4.33ms  1246 Elem/sec
dispatch_group_scaling/10                   1.04    416.9±5.01ms        ? ?/sec     1.00    401.6±5.68ms  1244 Elem/sec
dispatch_group_scaling/100                  1.03    416.1±4.47ms        ? ?/sec     1.00    402.1±4.87ms  1243 Elem/sec
dispatch_group_scaling/50                   1.04    417.0±5.43ms        ? ?/sec     1.00    401.3±5.05ms  1245 Elem/sec
dispatch_no_groups/500                                                              1.00    235.0±4.17ms  2.1 KElem/sec
dispatch_no_groups_500                      1.00    243.2±3.65ms        ? ?/sec   
dispatch_one_group/500                                                              1.00    393.5±5.05ms  1270 Elem/sec
dispatch_one_group_500                      1.00    415.1±6.92ms        ? ?/sec   
dispatch_permanent_failure/500                                                      1.00    349.3±3.71ms  1431 Elem/sec
dispatch_permanent_failure_500              1.00    362.2±3.71ms        ? ?/sec   
history_by_type/100                         1.01   889.4±19.51µs        ? ?/sec     1.00   882.8±28.45µs  1132 Elem/sec
history_by_type/1000                        1.03   922.8±38.92µs        ? ?/sec     1.00   894.0±28.25µs  1118 Elem/sec
history_by_type/5000                        1.01   921.5±26.39µs        ? ?/sec     1.00   913.9±19.73µs  1094 Elem/sec
history_query/100                           1.02    543.1±8.12µs        ? ?/sec     1.00   534.7±16.11µs  1870 Elem/sec
history_query/1000                          1.02    545.1±7.17µs        ? ?/sec     1.00    537.0±8.08µs  1862 Elem/sec
history_query/5000                          1.02    559.8±6.39µs        ? ?/sec     1.00    548.0±7.18µs  1824 Elem/sec
history_stats/100                           1.03    148.2±0.73µs        ? ?/sec     1.00    143.9±0.54µs  6.8 KElem/sec
history_stats/1000                          1.02    367.3±1.28µs        ? ?/sec     1.00    359.7±0.69µs  2.7 KElem/sec
history_stats/5000                          1.00   1331.5±7.62µs        ? ?/sec     1.01   1340.6±2.49µs   745 Elem/sec
mixed_priority_dispatch/500                                                         1.00    259.2±4.99ms  1928 Elem/sec
mixed_priority_dispatch_500                 1.00    268.5±4.56ms        ? ?/sec   
peek_next/100                               1.03    119.8±2.98µs        ? ?/sec     1.00    116.6±2.57µs  8.4 KElem/sec
peek_next/1000                              1.03    120.1±2.98µs        ? ?/sec     1.00    116.2±1.99µs  8.4 KElem/sec
peek_next/5000                              1.02    119.6±2.77µs        ? ?/sec     1.00    117.1±2.49µs  8.3 KElem/sec
query_by_tags/100                           1.00  1238.0±140.88µs        ? ?/sec    1.03  1275.9±163.07µs   783 Elem/sec
query_by_tags/1000                          1.08     10.3±1.30ms        ? ?/sec     1.00      9.6±0.37ms   104 Elem/sec
query_by_tags/5000                          1.00     54.6±1.96ms        ? ?/sec     1.01     55.4±8.62ms    18 Elem/sec
retryable_dead_letter/constant              1.04    147.4±2.17ms        ? ?/sec     1.00    141.8±1.79ms   705 Elem/sec
retryable_dead_letter/exponential           1.03    147.1±1.90ms        ? ?/sec     1.00    142.3±2.35ms   702 Elem/sec
retryable_dead_letter/exponential_jitter    1.03    146.5±1.73ms        ? ?/sec     1.00    141.8±1.53ms   705 Elem/sec
retryable_dead_letter/linear                1.04    147.0±1.97ms        ? ?/sec     1.00    141.7±1.78ms   705 Elem/sec
submit_1000_tasks                           1.00    180.4±4.51ms        ? ?/sec   
submit_dedup_hit/1000                                                               1.00    232.6±7.03ms  4.2 KElem/sec
submit_dedup_hit_1000                       1.00    239.1±7.44ms        ? ?/sec   
submit_tasks/1000                                                                   1.00    176.5±4.73ms  5.5 KElem/sec
submit_with_tags/0                          1.04     90.3±3.36ms        ? ?/sec     1.00     86.9±2.62ms  5.6 KElem/sec
submit_with_tags/10                         1.03    240.1±8.14ms        ? ?/sec     1.00    233.0±9.63ms  2.1 KElem/sec
submit_with_tags/20                         1.03   395.4±17.26ms        ? ?/sec     1.00   383.8±16.63ms  1302 Elem/sec
submit_with_tags/5                          1.04    167.6±7.40ms        ? ?/sec     1.00    160.7±5.67ms  3.0 KElem/sec
tag_values/100                              1.02    133.1±3.84µs        ? ?/sec     1.00    131.0±3.84µs  7.5 KElem/sec
tag_values/1000                             1.01    195.4±2.89µs        ? ?/sec     1.00    194.2±3.73µs  5.0 KElem/sec
tag_values/5000                             1.02    470.6±4.60µs        ? ?/sec     1.00    461.2±5.31µs  2.1 KElem/sec