mirror of
https://github.com/hanzoai/ci.git
synced 2026-10-20 15:28:05 +00:00
perf(site): ask the origin's sample all at once, hash on every core, and say where the time went
The twenty sampled assets were asked one after another, each a round trip through the edge to the origin: 10.4 s from dgx, seconds of every publish from a runner. They go out together now, and one that does not answer still sends everything. Hashing runs one batch per core into a file of its own, sorted after, so the record is the same bytes in any order. A last line, `timing:`, names each phase's seconds.
This commit is contained in:
@@ -98,6 +98,21 @@ human() { LC_ALL=C awk -v b="$1" 'BEGIN{ split("B KiB MiB GiB", u, " "); i = 1
|
||||
# second grant would send the first site's files into the other's prefix.
|
||||
work=$(mktemp -d); trap 'rm -rf "$work"' EXIT
|
||||
|
||||
# ---- where the time goes ------------------------------------------------------
|
||||
# One line at the end names each phase's seconds, so a slow publish says which
|
||||
# leg was slow on the run that was slow, rather than after a second run with a
|
||||
# stopwatch. EPOCHREALTIME is bash 5's; an older bash counts whole seconds.
|
||||
lap() {
|
||||
local t=${EPOCHREALTIME:-$SECONDS}
|
||||
printf '%s %s\n' "$1" "${t/,/.}" >> "$work/laps"
|
||||
}
|
||||
laps() {
|
||||
[ -s "$work/laps" ] || return 0
|
||||
LC_ALL=C awk 'NR > 1 { printf "%s%s %.1fs", sep, $1, $2 - prev; sep = ", " }
|
||||
{ prev = $2 } END { if (NR > 1) print "" }' "$work/laps" | sed 's/^/timing: /'
|
||||
}
|
||||
lap start
|
||||
|
||||
[ -d "$dir" ] || { echo "::error::$dir is not a directory — the build produced no export"; exit 1; }
|
||||
|
||||
# ---- content type -----------------------------------------------------------
|
||||
@@ -192,6 +207,7 @@ body=$(wc -c < "$work/sd-done.json" | tr -d ' ') # BSD wc pads its count, GNU
|
||||
echo "::error::publish aborted: the completion manifest is $(human "$body") ($body bytes) for $count files, over the $(human "$max_body") ($max_body bytes) edge limit (GATEWAY_BODY_LIMIT, cloud internal/edge/edge.go:38). The bytes stream per file and are not the problem — the manifest cloud reconciles the prefix against is one body, and fasthttp refuses an oversized POST before any handler runs, answering only 'Error when parsing request', which names neither size nor cause. Reduce the object count: a full prerender is what makes an export this wide."
|
||||
exit 1; }
|
||||
|
||||
lap scan
|
||||
if [ -n "${SITE_PLAN:-}" ]; then
|
||||
printf 'slug=%s dir=%s files=%s\n' "$slug" "$dir" "$count"
|
||||
while IFS= read -r k; do [ -n "$k" ] && printf '%s\t%s\n' "$k" "$(ctype "$k")"; done <<< "$manifest"
|
||||
@@ -367,6 +383,7 @@ if [ -z "$upload_url" ]; then
|
||||
fi
|
||||
jq -c '{id,version,status,bucket,prefix}' "$work"/sd-enq.json
|
||||
|
||||
lap enqueue
|
||||
# A build that dies after this point would leave the deployment "queued" and the
|
||||
# project stuck "building" forever. Report the failure so cloud records an honest
|
||||
# terminal state instead of a lie by omission.
|
||||
@@ -396,7 +413,16 @@ trap 'fail' ERR
|
||||
# 200 all mean "send everything". SITE_FULL=1 forces that.
|
||||
mkdir -p "$dir/_site"
|
||||
grep -vxF "$mkey" "$work/manifest" > "$work/real"
|
||||
(cd "$dir" && tr '\n' '\0' < "$work/real" | xargs -0 -n 512 bash -c 'if command -v sha256sum >/dev/null 2>&1; then sha256sum "$@"; else shasum -a 256 "$@"; fi' _) > "$work/hashes"
|
||||
# Every core at once. Each batch writes a file of its own: hashers sharing one
|
||||
# pipe flush in blocks that can end mid-line, and two of them interleaving there
|
||||
# would corrupt a line. Sorted after, so the record reads the same whatever order
|
||||
# they finished in; -k3 is the key, since two spaces follow the hash.
|
||||
cores=$(getconf _NPROCESSORS_ONLN 2>/dev/null || echo 4)
|
||||
mkdir -p "$work/h"
|
||||
(cd "$dir" && tr '\n' '\0' < "$work/real" | H="$work/h" xargs -0 -n 256 -P "$cores" bash -c \
|
||||
'if command -v sha256sum >/dev/null 2>&1; then sha256sum "$@"; else shasum -a 256 "$@"; fi > "$(mktemp "$H/b.XXXXXX")"' _)
|
||||
cat "$work"/h/b.* | LC_ALL=C sort -t ' ' -k3 > "$work/hashes"
|
||||
lap hash
|
||||
[ "$(grep -c . "$work/hashes")" = "$((count - 1))" ] || { echo "::error::hashed $(grep -c . "$work/hashes") of $((count - 1)) files"; exit 1; }
|
||||
cp "$work/real" "$work/upload"
|
||||
: > "$work/prev"
|
||||
@@ -421,9 +447,18 @@ if [ -s "$work/prev" ]; then
|
||||
{f=substr($0,67); if (p[f] != substr($0,1,64)) print f}' "$work/prev" "$work/hashes" > "$work/changed"
|
||||
# Ask the origin for a sample of what it is about to be trusted to still hold.
|
||||
sample=$(grep -vxFf "$work/changed" "$work/real" | grep '^_next/static/' | LC_ALL=C sort -R | head -20 || true)
|
||||
bad=
|
||||
# All at once: each is a round trip through the edge to the origin, and twenty
|
||||
# of them one after another were seconds of every publish.
|
||||
bad= i=0
|
||||
for rel in $sample; do
|
||||
c=$(curl -g -sS -m 20 -r 0-0 -o /dev/null -w '%{http_code}' "$base/$rel?t=$(date +%s)" 2>/dev/null || true)
|
||||
i=$((i + 1))
|
||||
( c=$(curl -g -sS -m 20 -r 0-0 -o /dev/null -w '%{http_code}' "$base/$rel?t=$(date +%s)" 2>/dev/null || true)
|
||||
printf '%s %s\n' "${c:-000}" "$rel" > "$work/probe.$i" ) &
|
||||
done
|
||||
wait
|
||||
for f in "$work"/probe.*; do
|
||||
[ -e "$f" ] || continue
|
||||
read -r c rel < "$f"
|
||||
case "$c" in 200|206) ;; *) bad="$rel ($c)"; break ;; esac
|
||||
done
|
||||
if [ -n "$bad" ]; then
|
||||
@@ -435,6 +470,7 @@ if [ -s "$work/prev" ]; then
|
||||
else
|
||||
echo "no previous manifest at the live host; sending everything"
|
||||
fi
|
||||
lap diff
|
||||
# ---- 1c. what the plane can copy ----------------------------------------------
|
||||
# A host that shares its build with a site published a moment ago (SITE_COPY_FROM
|
||||
# = "<slug>:<dir>") differs from it by a page or two. The objects of this upload
|
||||
@@ -545,6 +581,7 @@ fi
|
||||
# are all in the bucket, so it goes last.
|
||||
printf '%s\n' "$mkey" > "$work/manifest.last"
|
||||
put_all "$work/manifest.last"
|
||||
lap upload
|
||||
|
||||
# ---- 3. flip it live --------------------------------------------------------
|
||||
# The body was built and measured at the top, before a single object moved, so
|
||||
@@ -564,6 +601,7 @@ if [ "$code" != "200" ]; then
|
||||
echo "::error::complete returned HTTP $code"; head -c 600 "$work"/sd-resp.json; echo; fail; exit 1
|
||||
fi
|
||||
jq -c '{status,liveUrl,version,files,bytes}' "$work"/sd-resp.json
|
||||
lap complete
|
||||
|
||||
# ---- 4. read back what we just published ------------------------------------
|
||||
# A publish that uploads and flips live has still proved nothing about whether
|
||||
@@ -653,3 +691,5 @@ else
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
lap readback
|
||||
laps
|
||||
|
||||
+17
-1
@@ -178,7 +178,9 @@ case "$url" in
|
||||
# its body; unset answers 404, which is a first publish.
|
||||
https://a-slug.hanzo.app/_site/manifest.txt*)
|
||||
if [ -n "${T_PREV:-}" ]; then printf '%s\n' "$T_PREV" > "$out"; printf '200'; else : > "$out"; printf '404'; fi ;;
|
||||
https://a-slug.hanzo.app/_next/*) printf '200' ;;
|
||||
# A sampled unchanged asset. T_PROBE=gone answers 404, which is an origin that
|
||||
# no longer holds what the previous manifest says it does.
|
||||
https://a-slug.hanzo.app/_next/*) if [ "${T_PROBE:-}" = gone ]; then printf '404'; else printf '200'; fi ;;
|
||||
# The deployment the run completed, as cloud records it: what the completion
|
||||
# sent, which is what cloud stores (apps/projects/deploy.go land). T_REC
|
||||
# replaces it to make the record disagree.
|
||||
@@ -512,6 +514,20 @@ t "an incremental publish succeeds" "$rc" "0"
|
||||
t " ...uploads the changed page and the manifest" "$(wc -l < "$tmp/uploads" | tr -d ' ')" "2"
|
||||
t " ...not the unchanged ones" "$(grep -c 'key=acme/a-slug/index.html\|a.js' "$tmp/uploads")" "0"
|
||||
t " ...but the completion names every key" "$(jq -r '.keys|length' "$tmp/complete.body")" "4"
|
||||
t " ...asked the origin for the unchanged asset" "$(grep -c '^GET https://a-slug.hanzo.app/_next/static/a.js' "$tmp/calls")" "1"
|
||||
# Hashed on every core, then sorted, so the record is the same bytes whichever
|
||||
# hasher finished first.
|
||||
t " ...its record is sorted by key" "$(awk '{print substr($0, 67)}' "$inc/_site/manifest.txt" | LC_ALL=C sort -c 2>&1 && echo sorted)" "sorted"
|
||||
t " ...and says where its time went" "$(printf '%s\n' "$out" | grep -c '^timing: scan [0-9.]*s, enqueue [0-9.]*s, hash [0-9.]*s, diff [0-9.]*s, upload [0-9.]*s, complete [0-9.]*s, readback [0-9.]*s$')" "1"
|
||||
# The sample is asked all at once, and one asset the origin no longer answers is
|
||||
# enough to distrust the record: everything goes.
|
||||
rm -f "$tmp/calls" "$tmp/uploads"
|
||||
out=$(PATH="$shim:$PATH" HANZO_API=https://api.test HANZO_DEPLOY_TOKEN=sk-test \
|
||||
SITE_JOBS=1 T_DIR="$tmp" T_ENQ="$ENQ" T_DONE="$DONE" T_PREV="$prev" T_PROBE=gone \
|
||||
bash "$SD" a-slug "$inc" 2>&1); rc=$?
|
||||
t "an unchanged asset gone: the publish succeeds" "$rc" "0"
|
||||
t " ...distrusts the record" "$(printf '%s\n' "$out" | grep -c 'previous manifest is not trusted: _next/static/a.js (404)')" "1"
|
||||
t " ...and sends everything" "$(wc -l < "$tmp/uploads" | tr -d ' ')" "4"
|
||||
rm -f "$tmp/calls" "$tmp/uploads"
|
||||
out=$(PATH="$shim:$PATH" HANZO_API=https://api.test HANZO_DEPLOY_TOKEN=sk-test \
|
||||
SITE_JOBS=1 T_DIR="$tmp" T_ENQ="$ENQ" T_DONE="$DONE" T_PREV="not a manifest" \
|
||||
|
||||
Reference in New Issue
Block a user