Results 70 issues of Craig Tiller

lang/core
bloat/none
per-call-memory/neutral
per-channel-memory/neutral

Detected by a fuzzer in b/295671965: There's a race between signalling goaway to the transport and handling incoming requests (which would increment the call count and not send goaway). Since...

lang/core
release notes: no
bloat/low
per-call-memory/neutral
per-channel-memory/neutral

Allows use of the party party wakeup batching stuff, which reduces threadhops drastically for this transport.

lang/core
bloat/none
per-call-memory/neutral
per-channel-memory/neutral

Two new benchmarks here-in. Benchmark 1: `bm_picker` ------ Measures various load balancing policies pick performance. For now we cover `pick_first` and `weighted_round_robin` at 1, 10, 100, 1000, 10000, and 100000...

lang/core
release notes: no
bloat/none
per-call-memory/decrease
per-channel-memory/neutral

It looks like this ends up being useful for ASAN builds too!

lang/core
bloat/none
per-call-memory/increase
per-channel-memory/neutral

release notes: no
disposition/stale
area/infra
bloat/none
per-call-memory/neutral
per-channel-memory/neutral

I believe the time sweeping behavior of fuzzing event engine is unnecessary at this point and can be removed. (Gives at least a 100x speedup to many fuzzers).

lang/core
bloat/none
per-call-memory/increase
per-channel-memory/neutral