chunkloris: axum (on hyper)

part of the chunkloris per-chunk amplification survey. this page is the per-server record for axum (on hyper) under http/1.1 chunked transfer encoding.

at a glance

server: axum (on hyper) 0.7 / hyper 1.x
runtime: rust-1.83 (release build)
ecosystem: rust
concurrency model: event-loop
parser: hyper internal chunked decoder (ChunkedState::Body)
delivery granularity: per-chunk
chunk-limit helper: exposed-stdlib
verdict: per-chunk — the parser/dispatcher boundary delivers one event per wire chunk. cpu cost under paced mode b is measurable per chunk.
scaling exponent (mode a): 0.98 (wall time vs N, log-log slope across common cells)
scaling exponent (mode b): 1.00

measurements

all cells run on a 1-vcpu docker container. cpu cost is derived from the target container’s cgroup v2 cpu.stat usage_usec delta around each cell.

mode	N	wall (s)	server cpu %	µs / chunk	basis	ok
`A-bridge-coalesced`	50,000	0.019	254.6	0.959	server-cpu-cgroup	✓
`A-bridge-coalesced`	100,000	0.037	153.8	0.567	server-cpu-cgroup	✓
`A-bridge-coalesced`	250,000	0.092	131.8	0.483	server-cpu-cgroup	✓
`B-paced-100us`	50,000	5.160	5.4	5.534	server-cpu-cgroup	✓
`B-paced-100us`	100,000	10.251	4.8	4.873	server-cpu-cgroup	✓
`B-paced-100us`	250,000	25.615	4.7	4.830	server-cpu-cgroup	✓
`control-single-write`	1,500,000	0.008	—	—	wall	✓

what this means

the parser/dispatcher path on this server delivers one event per chunked-transfer-encoding chunk, so an attacker who sends a body as N one-byte chunks consumes roughly N × (mode-b µs/chunk) of server cpu on a single core. amplification scales linearly with N until the framework’s max_request_body_size (or equivalent) is hit.

what to do today

if this server runs as an origin behind nginx with the default proxy_request_buffering on, the per-chunk attack shape does not reach this server — nginx delivers one content-length-framed body to the upstream in a single recv().
if deployed direct-exposed, behind haproxy with default streaming, or behind any reverse proxy with proxy_request_buffering off, the per-chunk cost reaches this server.
there is no framework-level chunk-count limit in the default config; use a frontend buffer, transport-layer rate limiting, or a wrapping middleware that imposes a chunk-count cap before draining the body.

reproducer

the full reproducer for this server is in the paper repo. the docker container pins axum (on hyper) 0.7 / hyper 1.x and constrains the test container to a single cpu (--cpus=1). the prober script implements mode a (bridge-coalesced) and mode b (paced 100 µs) per the methodology section.

see the draft pdf for the full per-framework discussion.