Closed tobz closed 3 weeks ago
Run ID: 964a9d0c-4ee3-443b-922b-5fd2d827b9ca
Baseline: 7.52.0 Comparison: 7.52.1
Performance changes are noted in the perf column of each table:
Confidence level: 90.00% Effect size tolerance: |Δ mean %| ≥ 5.00%
There were no significant changes in experiment optimization goals at this confidence level and effect size tolerance.
Run ID: 23b33689-eb6b-4704-aa94-f754b854b471
Baseline: f0a8b4c7b06e49a9f97f4067cf2a94cabd1cfbed Comparison: c4b22621952998036a651717d1b8b2dbefd1a71e
Performance changes are noted in the perf column of each table:
Confidence level: 90.00% Effect size tolerance: |Δ mean %| ≥ 5.00%
There were no significant changes in experiment optimization goals at this confidence level and effect size tolerance.
experiment | link(s) |
---|---|
dsd_uds_100mb_250k_contexts | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_100mb_3k_contexts | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_100mb_3k_contexts_distributions_only | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_10mb_3k_contexts | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_1mb_3k_contexts | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_1mb_50k_contexts | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_1mb_50k_contexts_memlimit | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_500mb_3k_contexts | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_512kb_3k_contexts | [Profiling (ADP)] [Profiling (DSD)] [SMP Dashboard] |
dsd_uds_50mb_10k_contexts_no_inlining (ADP only) | [Profiling (ADP)] [SMP Dashboard] |
dsd_uds_50mb_10k_contexts_no_inlining_no_allocs (ADP only) | [Profiling (ADP)] [SMP Dashboard] |
Context
This PR integrates the new internal API machinery into
memory-accounting
in order to expose an API handler that can show the current allocation groups, both in terms of their originally declared bounds and their actual live usage.Most of the changes are new code, with a smattering of things we had to update around how allocation statistics are queried, since previously only one caller could query them as querying had consume semantics. Now every caller has to manage tracking the previous state for determining usage deltas, so multiple callers can visit the statistics without clashing.