perf: reduce heap residency for large base64 relay requests

Three layered optimizations targeting Gemini-style 5MB base64 payloads where
RSS could balloon to tens of GB under concurrent load:

1. Byte-based param override (relay/common/override.go)
   - Switch legacy/operations hot paths from common.Marshal round-trips and
     map[string]any conversions to gjson/sjson on []byte directly.
   - Avoids cloning 5MB strings during each Set/Delete operation.

2. strings.Builder for Gemini response markdown (relay/channel/gemini/relay-gemini.go)
   - Replace string concatenation + strings.Join when assembling
     "![image](data:...;base64,DATA)" content for inline image responses.
   - Pre-allocates capacity from inline_data byte sizes.

3. Outbound BodyStorage + streaming Decoder (this commit's core)
   - New relay/common/outbound_body.go helper wraps marshaled upstream bodies
     in common.BodyStorage, allowing disk-cache mode to offload jsonData to
     a temp file while waiting for upstream TTFB. The original []byte can
     then be GC'd, removing ~5MB/req of heap residency during the longest
     window of a request.
   - All 7 relay handlers (gemini/claude/responses/embedding/image/compatible/
     rerank) plus chat_completions_via_responses adopt the helper with
     defer closer.Close() and explicit jsonData = nil.
   - relay/common/relay_info.go: new UpstreamRequestBodySize so
     relay/channel/api_request.go can populate req.ContentLength (lost when
     body becomes a type-erased io.Reader).
   - common/gin.go UnmarshalBodyReusable: when storage is disk-backed and
     content-type is JSON, decode via DecodeJson(storage) instead of
     storage.Bytes()+Unmarshal, removing one transient 5MB copy per request.
     memory mode and form/multipart paths unchanged.
This commit is contained in:
CaIon
2026-05-22 19:08:38 +08:00
parent b9bc6f0e21
commit fddf54ccc5
15 changed files with 407 additions and 169 deletions
+2 -2
View File
@@ -37,7 +37,7 @@ func checkWriter(writer io.Writer) stringWriter {
// W3C Working Draft 29 October 2009
// http://www.w3.org/TR/2009/WD-eventsource-20091029/
var contentType = []string{"text/event-stream"}
var writeContentType = []string{"text/event-stream"}
var noCache = []string{"no-cache"}
var fieldReplacer = strings.NewReplacer(
@@ -79,7 +79,7 @@ func (r CustomEvent) WriteContentType(w http.ResponseWriter) {
r.Mutex.Lock()
defer r.Mutex.Unlock()
header := w.Header()
header["Content-Type"] = contentType
header["Content-Type"] = writeContentType
if _, exist := header["Cache-Control"]; !exist {
header["Cache-Control"] = noCache