Principles for Fast Tokio Applications (dial9-rs.github.io)

80 points by carllerche 4 hours ago

dist1ll 28 minutes ago

When you're at a point of tuning Tokio, consider taking a look at ef_vi/DPDK + SPDK

Tsarp 3 hours ago

One great use of agentic coding is being able to add and very granular tracing instrumentation to help with these sort of optimizations.

jeffbee 3 hours ago

Also a great way to make sure that your app spends most of its time in observability overhead. For example even the latency histogram that the OP mentions is wildly expensive.

Veserv 2 hours ago

That just sounds like bad tracing implementations. A good tracing implementation should be able to drive gigabytes per second of trace logs to memory. If you are generating it slow enough to allow actual offload then you should be in the 1—10% range even if you are saturating your offload.

You should, of course, upper bound this overhead by switching to a full time travel debugging solution, thus tracing everything, when you get to the 10-30% range.

The only way you get to “majority” is if your trace implementation is slower than time travel debugging and provides less information, but then why choose something worse in every dimension.

jeffbee 44 minutes ago

nicoburns 2 hours ago

One legitimately great thing about LLMs is that it makes it feasible to add these kind of tracing instrumentations temporarily for profiling and then throw them away so they never reach source control let alone production.

jeffbee 2 hours ago

foota an hour ago

Just curious, why? Is this true even if you did something like a per-CPU histogram that uses atomic ops to increment?

MomsAVoxell 3 hours ago

If you’re not using eBPF to trace your app you’re doing it wrong.

jeffbee 3 hours ago

jeffbee 3 hours ago

All of the significant server applications I have encountered in the industry have suffered from the same problem, which surprised their authors but seemed obvious to me: the application was spending the majority of its CPU time doing meta-work like entering and leaving epoll, stealing work from itself, etc. There are principles for writing Tokio servers and these are good points in the OP but I think they are little-known and too easy to violate.

cube00 3 hours ago

I can't say I'm surprised when I see the 100+ function stack traces that Axum built on Tokio produces.

Before you say Axum is "holding it wrong" the project lives under the tokio-rs GitHub org.

rusbus an hour ago

Note that most of those end up getting inlined in practice