#!/usr/bin/env julia # # bench.jl: measure end-to-end throughput and server memory for a running DarkStruct. # # Two things make this pipeline awkward to benchmark with off-the-shelf tools # (ab/hey/wrk), and both shape what this script does: # # 1. HTTP latency is not throughput. /upload returns 202 as soon as the bytes # are spooled and a reference is enqueued, and all four stages run afterwards. # So real throughput is the *arrival rate at the terminal sinks* # (done/, text_done/, binary/, failed/), not the response rate. We upload a # corpus, then poll the sinks until the file count stops moving. # # 2. End-to-end throughput doesn't name the slow stage. The four stages run # concurrently behind their own queues, so the pipeline's rate is the # slowest stage's rate and the others are invisible. Directory polling can't # recover them either: every in-flight file sits in spool/ whatever stage it # is at, since stages route by enqueueing rather than by moving bytes. So the # server keeps per-stage counters # (src/stats.jl) and we scrape GET /stats before and after: the deltas give # each stage's throughput, mean service time, and worker utilization, and # utilization is what actually names the bottleneck (see `stage_report`). # # 3. Memory should be flat in file size, and that claim needs checking on two # axes. The workers read bounded prefixes (16+16 bytes to classify, 8 KB to # sniff, 64 KB to language-detect), and intake streams each upload from the # socket to the spool file a chunk at a time (FS_UPLOAD_CHUNK_BYTES, see # src/multipart.jl). So peak RSS should track *concurrency*, not file size: # sweeping --size at fixed --concurrency should be a flat line, and that is # the regression this measures. We sample the server's RSS throughout and # report the high-water mark. # # (Before intake was streamed it buffered each upload whole, several times # over, and a 256 MiB upload grew RSS by ~700 MiB. If a --size sweep ever # slopes upward again, something has started buffering.) # # The harness talks to the server only over HTTP (/upload, /health, /stats) and # reads the on-disk sink layout; it must run on the same machine (sink dirs and # /proc). If /stats is missing (an older build) everything else still works and # the per-stage section is skipped. # # Usage: # julia --project=. -t auto bin/bench.jl [options] # # --url URL server base URL (default: $FS_URL or http://127.0.0.1:8080) # --files N number of files to upload (default: 200) # --size S size of each generated file, e.g. 4k, 512k, 8m, 1g (default: 64k) # --concurrency J uploads in flight at once (default: 8) # --kind K binary | text | mixed: what to generate (default: binary) # --corpus DIR upload an existing directory instead of generating # (the only way to exercise stage 2: point it at real known files) # --keep-corpus don't delete the generated corpus on exit # --pid PID server pid for memory sampling (default: autodetect) # --no-mem skip memory sampling entirely # --no-stats skip the per-stage /stats scrape and its table # --sample-ms MS sink/RSS sampling interval (default: 200) # --timeout SEC give up after this long with no drain progress (default: 120) # --json PATH also write the results as JSON # --force skip the corpus-size safety check # # Examples: # # throughput: many small files, high concurrency # julia --project=. -t auto bin/bench.jl --files 2000 --size 8k --concurrency 32 # # # memory: flat in file size? sweep --size with concurrency pinned # julia --project=. -t auto bin/bench.jl --files 4 --size 256m --concurrency 1 # julia --project=. -t auto bin/bench.jl --files 2 --size 1g --concurrency 1 # julia --project=. -t auto bin/bench.jl --files 8 --size 1g --concurrency 8 # # # stage 2 (exiftool) with real known files # julia --project=. -t auto bin/bench.jl --corpus ../training_set --concurrency 16 using HTTP using JSON3 using Random # ---------------------------------------------------------------- option parsing const DEFAULTS = Dict{String,Any}( "url" => get(ENV, "FS_URL", "http://127.0.0.1:8080"), "files" => 200, "size" => 64 * 1024, "concurrency" => 8, "kind" => "binary", "corpus" => nothing, "keep-corpus" => false, "pid" => nothing, "no-mem" => false, "no-stats" => false, "sample-ms" => 200, "timeout" => 120, "json" => nothing, "force" => false, ) const FLAGS = ("keep-corpus", "no-mem", "no-stats", "force") # Approximate RSS of a freshly started server (Lux + the loaded classifier + the # language detector, measured on Julia 1.12 / -t auto). Only used to notice that # a baseline is inflated by a previous run's un-returned GC memory, so a rough # figure is enough. const FRESH_RSS_HINT = 950 * 1024^2 "Parse `4k`/`8M`/`1g`/`4096` into a byte count." function parse_size(s::AbstractString)::Int m = match(r"^(\d+(?:\.\d+)?)\s*([kKmMgG]?)[bB]?$", strip(s)) m === nothing && error("bad --size: $s (expected e.g. 512, 64k, 8m, 1g)") mult = Dict('k' => 1024, 'm' => 1024^2, 'g' => 1024^3) scale = isempty(m[2]) ? 1 : mult[lowercase(m[2])[1]] return round(Int, parse(Float64, m[1]) * scale) end function parse_args(argv)::Dict{String,Any} opts = copy(DEFAULTS) i = 1 while i <= length(argv) a = argv[i] startswith(a, "--") || error("unexpected argument: $a (see the header of $(PROGRAM_FILE))") key = a[3:end] haskey(opts, key) || error("unknown option: $a") if key in FLAGS opts[key] = true i += 1 continue end i + 1 <= length(argv) || error("option --$key needs a value") val = argv[i+1] opts[key] = key == "size" ? parse_size(val) : key in ("files", "concurrency", "sample-ms") ? parse(Int, val) : key == "timeout" ? parse(Float64, val) : key == "pid" ? parse(Int, val) : val i += 2 end opts["kind"] in ("binary", "text", "mixed") || error("--kind must be binary, text or mixed (got $(opts["kind"]))") opts["files"] >= 1 || error("--files must be >= 1") opts["concurrency"] >= 1 || error("--concurrency must be >= 1") return opts end # ------------------------------------------------------------------------- dirs # # Resolved from the same environment variables src/config.jl reads, so a server # started with custom dirs is benchmarked correctly. Kept as a standalone table # rather than `using DarkStruct` so the harness doesn't pay to load Lux. sinkdirs() = ( done = get(ENV, "FS_DONE_DIR", "data/done"), text_done = get(ENV, "FS_TEXT_DONE_DIR", "data/text_done"), binary = get(ENV, "FS_BINARY_DIR", "data/binary"), failed = get(ENV, "FS_FAILED_DIR", "data/failed"), ) # One directory, not four. Files no longer move between stages: spool/ holds # every in-flight file at every stage, and which stage it has reached lives in # the queue holding its reference (src/worker.jl header). So this depth is # "files in flight", full stop; per-stage depth comes from /stats, which is the # only place that can see it at all. stagedirs() = (spool = get(ENV, "FS_SPOOL_DIR", "data/spool"),) "Count work items in `dir`, ignoring the .meta.json sidecars stages 2/4 write." function count_files(dir::AbstractString)::Int isdir(dir) || return 0 n = 0 for name in readdir(dir) endswith(name, ".meta.json") && continue isfile(joinpath(dir, name)) && (n += 1) end return n end counts(dirs) = NamedTuple{keys(dirs)}(map(count_files, values(dirs))) total(c) = sum(values(c)) deltas(now_, base) = NamedTuple{keys(now_)}(map(-, values(now_), values(base))) # ----------------------------------------------------------------------- memory "Read (VmRSS, VmHWM) in bytes for `pid`, or `nothing` if unreadable." function read_rss(pid::Int) rss = hwm = nothing try for line in eachline("/proc/$pid/status") if startswith(line, "VmRSS:") rss = parse(Int, split(line)[2]) * 1024 elseif startswith(line, "VmHWM:") hwm = parse(Int, split(line)[2]) * 1024 end end catch return nothing end return (rss === nothing || hwm === nothing) ? nothing : (rss, hwm) end """ Find the running server process, or `nothing`. `pgrep -f` matches against the whole command line, which catches more than the server: any shell launched with the command in its own argv (`sh -c 'julia … bin/server.jl > log'`, a `setsid`/`nohup` wrapper, even the terminal running the benchmark) matches the same pattern. Sampling one of those reports a few MiB of shell as the server's memory: a wrong answer that looks plausible, which is the worst kind. So candidates are filtered by what each process *is* (`/proc//comm`, the executable name) rather than by what its arguments say. No pattern over argv can make that distinction. """ function detect_pid() out = try readchomp(`pgrep -f "bin/server.jl"`) catch return nothing end candidates = parse.(Int, split(out)) pids = filter(candidates) do pid comm = try readchomp("/proc/$pid/comm") catch return false # exited between pgrep and here end startswith(comm, "julia") end isempty(pids) && return nothing length(pids) > 1 && @warn "multiple server processes matched; sampling the first" pids return first(pids) end """ Reset the kernel's peak-RSS counter so VmHWM reflects only this run. Without it, VmHWM carries the high-water mark from startup (model load) or from an earlier benchmark, which would silently dominate a small run's result. Requires the server to run as the same user; on failure we say so and fall back to sampled VmRSS, which can miss a spike between samples. """ function reset_peak_rss(pid::Int)::Bool try write("/proc/$pid/clear_refs", "5") return true catch return false end end # ------------------------------------------------------------- per-stage counters # # The server exposes monotonic counters at GET /stats (src/stats.jl). Rates are # ours to compute: scrape once before the run and once after, subtract, divide by # the elapsed *server* clock so a slow scrape doesn't distort the window. "Fetch and parse GET /stats, or `nothing` if the server doesn't serve it." function scrape_stats(url::String) try resp = HTTP.get(string(rstrip(url, '/'), "/stats"); status_exception = false, retry = false, readtimeout = 5) resp.status == 200 || return nothing return JSON3.read(String(resp.body)) catch return nothing end end "One stage's activity between two scrapes." struct StageDelta stage::Int name::String workers::Int completed::Int failed::Int bytes::Int busy::Float64 # summed handler seconds across all workers in the pool blocked::Float64 # of `busy`, seconds parked on a full downstream queue peak_depth::Int # deepest its queue got, from the sampler capacity::Int end files_per_sec(d::StageDelta, window) = d.completed / max(window, 1e-9) mib_per_sec(d::StageDelta, window) = d.bytes / max(window, 1e-9) / 1024^2 "Mean wall time one file spends in one worker of this stage." service_ms(d::StageDelta) = d.completed == 0 ? NaN : (d.busy - d.blocked) / d.completed * 1000 """ Fraction of the pool's capacity spent doing this stage's own work. Blocked time is subtracted first: a stage parked on a full downstream queue is waiting, not working, and leaving it in would light up every stage upstream of a jam as though each were the jam. """ utilization(d::StageDelta, window) = (d.busy - d.blocked) / max(window * d.workers, 1e-9) blocked_share(d::StageDelta) = d.busy <= 0 ? 0.0 : d.blocked / d.busy "Subtract two scrapes into per-stage deltas, folding in sampled peak depths." function stage_deltas(before, after, peak_depth::Dict{Int,Int}) out = StageDelta[] for (b, a) in zip(before.stages, after.stages) push!(out, StageDelta(a.stage, String(a.name), a.workers, a.completed - b.completed, a.failed - b.failed, a.bytes - b.bytes, a.busy_seconds - b.busy_seconds, a.blocked_seconds - b.blocked_seconds, get(peak_depth, Int(a.stage), 0), a.queue_capacity)) end return out end "JSON has no NaN. A stage that completed nothing has no service time, and `null` is the honest way to say that; writing NaN just makes JSON3 throw." json_num(x::Real) = isfinite(x) ? x : nothing pad(s, n) = rpad(string(s), n) lpad_(s, n) = lpad(string(s), n) """ Print the per-stage table and say which stage is the bottleneck. The verdict reads utilization, not throughput: in a pipeline every stage completes the same files, so at steady state they all report nearly the same files/s regardless of which one is the constraint. What separates them is how hard each pool had to work to keep up: the bottleneck is pinned near 1.0 while its neighbours idle. """ function stage_report(deltas::Vector{StageDelta}, window::Float64) println("PER-STAGE (server counters, delta over the end-to-end window)") println(" stage files/s MiB/s svc ms util blocked peak queue failed") for d in deltas svc = service_ms(d) println(" $(d.stage) $(pad(d.name, 10)) " * lpad_(fmt(files_per_sec(d, window)), 8) * " " * lpad_(fmt(mib_per_sec(d, window)), 8) * " " * lpad_(isnan(svc) ? "—" : fmt(svc, 1), 8) * " " * lpad_(fmt(utilization(d, window)), 6) * " " * lpad_(fmt(blocked_share(d) * 100, 0) * "%", 7) * " " * lpad_("$(d.peak_depth)/$(d.capacity)", 11) * " " * lpad_(d.failed, 7)) end # Per-stage files/s are not comparable across rows and saying so costs one # line: the stages process different subsets (stage 2 only known files, # stage 4 only text), so a low rate can mean "little work arrived here" # rather than "slow". Utilization is the column that compares. println(" (files/s counts only files routed to that stage; svc is per-file wall time in") println(" one worker; util = (busy − blocked) / (window × workers))") worked = filter(d -> d.completed > 0, deltas) if isempty(worked) println(" (no stage completed a file in this window)") return nothing end top = argmax(d -> utilization(d, window), worked) println(" bottleneck stage $(top.stage) ($(top.name)) at " * "$(fmt(utilization(top, window) * 100, 0))% utilization of " * "$(top.workers) worker(s)") if utilization(top, window) < 0.5 println(" ...but no stage is near saturated: the pipeline is " * "waiting on intake,\n not on itself. Raise --concurrency " * "or --files to load it properly.") end for d in worked blocked_share(d) > 0.25 && println(" ! stage $(d.stage) ($(d.name)) spent " * "$(fmt(blocked_share(d) * 100, 0))% of its time parked on a full downstream " * "queue.\n It is being held up by the stage after it, not doing that work itself.") end return nothing end # ------------------------------------------------------------------------ corpus const WORDS = split("the quick brown fox jumps over a lazy dog while parsing " * "headers and spooling bytes onto disk for later enrichment " * "because throughput matters more than latency here") "Write one file of exactly `size` bytes, in bounded chunks so the generator itself never holds a whole 1 GB file in memory." function write_file(path::AbstractString, size::Int, kind::Symbol, rng) chunk = 1024 * 1024 open(path, "w") do io remaining = size while remaining > 0 n = min(chunk, remaining) if kind === :binary write(io, rand(rng, UInt8, n)) else buf = IOBuffer() while buf.size < n print(buf, rand(rng, WORDS), rand(rng) < 0.06 ? ".\n" : " ") end write(io, take!(buf)[1:n]) end remaining -= n end end return nothing end "Generate the corpus and return (dir, paths, total_bytes)." function make_corpus(opts) n, size, kind = opts["files"], opts["size"], opts["kind"] totalbytes = n * size if totalbytes > 16 * 1024^3 && !opts["force"] error("corpus would be $(human(totalbytes)) on disk; pass --force if that's intended") end dir = mktempdir(; prefix = "fsbench-") rng = MersenneTwister(1234) paths = String[] for i in 1:n k = kind == "mixed" ? (isodd(i) ? :binary : :text) : kind == "text" ? :text : :binary ext = k === :text ? "txt" : "bin" path = joinpath(dir, "bench-$(lpad(i, 6, '0')).$ext") write_file(path, size, k, rng) push!(paths, path) end return dir, paths, totalbytes end function existing_corpus(dir::AbstractString) isdir(dir) || error("--corpus is not a directory: $dir") paths = sort(filter(isfile, readdir(dir; join = true))) isempty(paths) && error("--corpus directory is empty: $dir") return paths, sum(filesize, paths) end # ----------------------------------------------------------------------- upload struct Upload status::Int # HTTP status, or 0 if the request threw accepted::Int # jobs the server actually queued (from the 202/503 body) seconds::Float64 end "POST one file as multipart/form-data and report what the server accepted." function upload_one(url::String, path::String)::Upload t0 = time() try form = HTTP.Form(["file" => HTTP.Multipart(basename(path), open(path, "r"), "application/octet-stream")]) resp = HTTP.post(url, [], form; status_exception = false, retry = false) # 202 and 503 both carry an `accepted` array: a partially-accepted batch # still queued those jobs, and they will show up in the sinks. acc = try length(JSON3.read(String(resp.body)).accepted) catch resp.status == 202 ? 1 : 0 end return Upload(resp.status, acc, time() - t0) catch e e isa InterruptException && rethrow() @warn "upload failed" file = basename(path) exception = e return Upload(0, 0, time() - t0) end end """ Upload every path, at most `concurrency` in flight. A bounded set of worker tasks pulling from a shared index keeps exactly `concurrency` requests in flight for the whole run, unlike batching, where each batch stalls on its slowest (largest) file and the real concurrency sags. """ function upload_all(url::String, paths::Vector{String}, concurrency::Int) endpoint = string(rstrip(url, '/'), "/upload") results = Vector{Upload}(undef, length(paths)) next = Threads.Atomic{Int}(1) @sync for _ in 1:min(concurrency, length(paths)) Threads.@spawn while true i = Threads.atomic_add!(next, 1) i > length(paths) && break results[i] = upload_one(endpoint, paths[i]) end end return results end # ------------------------------------------------------------------- formatting function human(bytes::Real) b = Float64(bytes) for unit in ("B", "KiB", "MiB", "GiB", "TiB") (abs(b) < 1024 || unit == "TiB") && return "$(round(b; digits = 2)) $unit" b /= 1024 end end fmt(x::Real, digits::Int = 2) = string(round(Float64(x); digits = digits)) function percentile(sorted::Vector{Float64}, p::Float64) isempty(sorted) && return NaN idx = clamp(ceil(Int, p * length(sorted)), 1, length(sorted)) return sorted[idx] end # ------------------------------------------------------------------------- main function main(argv) opts = parse_args(argv) url = string(opts["url"]) # Fail fast and clearly if there's no server, rather than reporting a run of zeros. try HTTP.get(string(rstrip(url, '/'), "/health"); retry = false, readtimeout = 5) catch e println(stderr, "cannot reach $url/health. Is the server running?") println(stderr, " start it with: julia --project=. -t auto bin/server.jl") return 1 end sinks, stages = sinkdirs(), stagedirs() # Leftovers mid-pipeline would land in the sinks during our window and be # counted as our throughput, so say so up front rather than quietly skewing. pending = total(counts(stages)) pending > 0 && @warn "pipeline is not idle: $pending file(s) still in spool/; " * "throughput will include their completions" # --- corpus generated = opts["corpus"] === nothing corpusdir, paths, corpusbytes = if generated print("generating corpus: $(opts["files"]) × $(human(opts["size"])) ($(opts["kind"]))… ") t = time() d, p, b = make_corpus(opts) println("done in $(fmt(time() - t))s → $d") d, p, b else p, b = existing_corpus(String(opts["corpus"])) println("using corpus: $(length(p)) file(s), $(human(b)) from $(opts["corpus"])") String(opts["corpus"]), p, b end try pid = opts["no-mem"] ? nothing : something(opts["pid"], detect_pid(), Some(nothing)) if pid === nothing && !opts["no-mem"] @warn "could not find the server process; skipping memory (pass --pid PID)" end baseline_rss = nothing peak_reset = false if pid !== nothing r = read_rss(pid) r === nothing && (@warn "cannot read /proc/$pid/status; skipping memory"; pid = nothing) if pid !== nothing peak_reset = reset_peak_rss(pid) peak_reset || @warn "could not reset the peak-RSS counter (/proc/$pid/clear_refs); " * "reporting sampled RSS only" # Baseline is read *after* the reset, not before. VmHWM restarts # from whatever RSS is at the moment of the reset, so a baseline # sampled earlier is measured against a different origin, and if # the GC hands memory back in between, the run reports negative # growth, which is nonsense on its face. r2 = read_rss(pid) baseline_rss = r2 === nothing ? r[1] : r2[1] end end if Threads.nthreads() == 1 && opts["size"] > 64 * 1024^2 @warn "running with 1 thread and large files: the sampler shares a thread with " * "blocking file reads, so the RSS curve will be coarse. Prefer -t auto." end base_sinks = counts(sinks) interval = opts["sample-ms"] / 1000 # --- per-stage counters: the "before" half of the delta. stats_before = opts["no-stats"] ? nothing : scrape_stats(url) if stats_before === nothing && !opts["no-stats"] @warn "no /stats endpoint on this server; skipping the per-stage table " * "(the server predates src/stats.jl)" end # --- sampler: RSS curve, spool depth, and queue depths. stop = Threads.Atomic{Bool}(false) rss_samples = Float64[] depth_max = Dict(k => 0 for k in keys(stages)) queue_peak = Dict{Int,Int}() sampler = Threads.@spawn begin while !stop[] if pid !== nothing r = read_rss(pid) r !== nothing && push!(rss_samples, Float64(r[1])) end d = counts(stages) for k in keys(d) depth_max[k] = max(depth_max[k], getfield(d, k)) end # Queue depth, unlike directory depth, can't be missed by a slow # sample in the same way, since a file's *reference* sits in the # queue for the whole time it waits, so this is the depth the stage # table reports. if stats_before !== nothing s = scrape_stats(url) s === nothing || for st in s.stages k = Int(st.stage) queue_peak[k] = max(get(queue_peak, k, 0), Int(st.queue_depth)) end end sleep(interval) end end # --- intake println("uploading $(length(paths)) file(s) at concurrency $(opts["concurrency"])…") t_start = time() ups = upload_all(url, paths, opts["concurrency"]) t_intake_end = time() accepted = sum(u.accepted for u in ups) n_202 = count(u -> u.status == 202, ups) n_503 = count(u -> u.status == 503, ups) n_err = count(u -> !(u.status in (202, 503)), ups) intake_secs = t_intake_end - t_start lat = sort([u.seconds for u in ups]) println(" intake: $accepted job(s) accepted in $(fmt(intake_secs))s " * "($(fmt(accepted / max(intake_secs, 1e-9))) files/s, " * "$(fmt(corpusbytes / max(intake_secs, 1e-9) / 1024^2)) MiB/s)") n_503 > 0 && println(" backpressure: $n_503 request(s) got 503 (intake queue full)") n_err > 0 && println(" errors: $n_err request(s) failed or returned an unexpected status") # --- drain: poll the terminal sinks until they stop moving. println("draining (polling sinks every $(opts["sample-ms"])ms)…") completed = 0 t_last_progress = time() t_last_completion = t_intake_end timed_out = false while completed < accepted sleep(interval) c = total(deltas(counts(sinks), base_sinks)) if c > completed completed = c t_last_completion = time() t_last_progress = t_last_completion elseif time() - t_last_progress > opts["timeout"] timed_out = true break end end # Scrape before stopping the sampler, so the window closes as near the # last completion as we can manage. stats_after = stats_before === nothing ? nothing : scrape_stats(url) stop[] = true wait(sampler) sink_delta = deltas(counts(sinks), base_sinks) e2e_secs = t_last_completion - t_start # The stage window is the server's own clock across the two scrapes, not # e2e_secs: it starts a scrape earlier and ends a scrape later, and using # our wall time against its counters would misattribute the difference. stage_window, stage_delta = if stats_after === nothing (0.0, StageDelta[]) else (Float64(stats_after.now - stats_before.now), stage_deltas(stats_before, stats_after, queue_peak)) end final_rss = pid === nothing ? nothing : read_rss(pid) peak_rss = if final_rss !== nothing && peak_reset final_rss[2] # kernel VmHWM: catches spikes between samples elseif !isempty(rss_samples) maximum(rss_samples) else nothing end # --- report println() println("=" ^ 68) println("corpus $(length(paths)) file(s), $(human(corpusbytes)) total, " * "$(human(corpusbytes / length(paths))) avg") println("concurrency $(opts["concurrency"])") println() println("INTAKE (HTTP 202: bytes spooled, not processed)") println(" accepted $accepted of $(length(paths)) [202: $n_202, 503: $n_503, error: $n_err]") println(" wall $(fmt(intake_secs))s") println(" rate $(fmt(accepted / max(intake_secs, 1e-9))) files/s, " * "$(fmt(corpusbytes / max(intake_secs, 1e-9) / 1024^2)) MiB/s") println(" latency p50 $(fmt(percentile(lat, 0.5) * 1000, 1))ms " * "p95 $(fmt(percentile(lat, 0.95) * 1000, 1))ms " * "max $(fmt(percentile(lat, 1.0) * 1000, 1))ms") println() println("END-TO-END (files reaching a terminal sink)") println(" completed $completed of $accepted accepted" * (timed_out ? " ** TIMED OUT **" : "")) println(" wall $(fmt(e2e_secs))s (first upload → last completion)") println(" throughput $(fmt(completed / max(e2e_secs, 1e-9))) files/s, " * "$(fmt(corpusbytes / max(e2e_secs, 1e-9) / 1024^2)) MiB/s") println(" sinks done $(sink_delta.done) text_done $(sink_delta.text_done) " * "binary $(sink_delta.binary) failed $(sink_delta.failed)") println(" peak dir depth spool $(depth_max[:spool]) known $(depth_max[:known]) " * "unknown $(depth_max[:unknown]) text $(depth_max[:text])") println() if !isempty(stage_delta) stage_report(stage_delta, stage_window) println() end if peak_rss !== nothing println("SERVER MEMORY (pid $pid)") println(" baseline RSS $(human(baseline_rss))") println(" peak RSS $(human(peak_rss))" * (peak_reset ? " (kernel VmHWM, reset at start)" : " (sampled; may miss spikes)")) growth = peak_rss - baseline_rss if growth <= 0 # RSS never got back to where it started, so the run's own cost # is below the noise floor of the server settling after startup. # Printing a negative "growth" would invite reading a memory # *saving* into what is really "too small to measure here". println(" growth none measurable (peak never exceeded the baseline)") println(" The baseline was still falling when we sampled it. Give the") println(" server ~30s to settle after startup for a comparable figure.") else println(" growth $(human(growth))") println(" per in-flight $(human(growth / opts["concurrency"])) " * "at $(human(corpusbytes / length(paths))) avg file size") println(" (should not grow with file size: intake streams to disk)") end # Julia's GC returns memory to the OS lazily, so a second run on the # same process starts from an inflated baseline and under-reports # growth. Absolute peak is the number to trust across runs. baseline_rss > 1.3 * FRESH_RSS_HINT && println(" ! baseline is well above a fresh start ($(human(FRESH_RSS_HINT))): the GC " * "has not\n returned memory from earlier work. Compare " * "absolute peak, or restart\n the server for a clean growth figure.") else println("SERVER MEMORY not sampled") end println("=" ^ 68) sink_delta.failed > 0 && println("\nnote: $(sink_delta.failed) file(s) landed in $(sinks.failed); check the server log.") timed_out && println("\nnote: drain stalled with $(accepted - completed) file(s) outstanding. " * "Check the server log and spool/; raise --timeout if the pipeline is just slow.") if opts["json"] !== nothing result = ( url, concurrency = opts["concurrency"], kind = opts["kind"], files = length(paths), corpus_bytes = corpusbytes, avg_file_bytes = corpusbytes / length(paths), intake = (; accepted, n_202, n_503, n_err, seconds = intake_secs, files_per_sec = accepted / max(intake_secs, 1e-9), p50_ms = json_num(percentile(lat, 0.5) * 1000), p95_ms = json_num(percentile(lat, 0.95) * 1000), max_ms = json_num(percentile(lat, 1.0) * 1000)), end_to_end = (; completed, seconds = e2e_secs, timed_out, files_per_sec = completed / max(e2e_secs, 1e-9), mib_per_sec = corpusbytes / max(e2e_secs, 1e-9) / 1024^2, sinks = sink_delta, peak_stage_depth = depth_max), stages = [(; stage = d.stage, name = d.name, workers = d.workers, completed = d.completed, failed = d.failed, bytes = d.bytes, busy_seconds = d.busy, blocked_seconds = d.blocked, window_seconds = stage_window, files_per_sec = files_per_sec(d, stage_window), mib_per_sec = mib_per_sec(d, stage_window), service_ms = json_num(service_ms(d)), utilization = utilization(d, stage_window), blocked_share = blocked_share(d), peak_queue_depth = d.peak_depth, queue_capacity = d.capacity) for d in stage_delta], memory = (; pid, baseline_rss, peak_rss, peak_is_kernel_hwm = peak_reset, growth = peak_rss === nothing ? nothing : peak_rss - baseline_rss, samples = rss_samples), ) open(String(opts["json"]), "w") do io JSON3.write(io, result) end println("\nwrote $(opts["json"])") end return timed_out ? 1 : 0 finally if generated && !opts["keep-corpus"] rm(corpusdir; recursive = true, force = true) elseif generated println("\nkept corpus: $corpusdir") end end end if abspath(PROGRAM_FILE) == @__FILE__ exit(main(ARGS)) end