chunkloris: phoenix

part of the chunkloris per-chunk amplification survey. this page is the per-server record for phoenix under http/1.1 chunked transfer encoding.

at a glance

server: phoenix 1.7 on plug_cowboy 2.7 / cowboy 2.15.0
runtime: erlang-otp-27.1.2 / elixir-1.17.3
ecosystem: beam
concurrency model: actor
parser: cowlib cow_http_te (via Phoenix.Endpoint.Cowboy2Adapter)
delivery granularity: per-chunk
chunk-limit helper: none exposed by the framework
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): 0.83 (wall time vs N, log-log slope across common cells)
scaling exponent (mode b): 0.96

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	0.164	85.0	2.800	wall	✓
`A-bridge-coalesced`	100,000	0.285	85.0	2.400	wall	✓
`A-bridge-coalesced`	250,000	0.619	85.0	2.100	wall	✓
`B-paced-100us`	50,000	5.576	26.0	29.000	server-cpu-overhead	✓
`B-paced-100us`	100,000	11.121	24.0	27.000	server-cpu-overhead	✓
`B-paced-100us`	250,000	26.060	34.0	35.000	server-cpu-overhead	✓

parser path — source citations

decoder — cowlib src/cow_http_te.erl stream_chunked/3 → source
adapter — plug_cowboy lib/plug/cowboy/conn.ex read_req_body/2 → source

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 phoenix 1.7 on plug_cowboy 2.7 / cowboy 2.15.0 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.