High TTFB

[igorescobar]

Hi,

It's me again :)

I'm pretty new to HAProxy + Nuster and I was wondering if there is anything I could do to reduce the TTFB:

Worth mentioning that Nuster is Behind an AWS ELB and the TTFB seems pretty high for a file that is cached on disk.

I get a pretty similar TTFB even for non-cached JSON requests:

This is my configuration at the moment:

defaults
  log global
  mode http

  log-format     '{"time":{"tr":%Tr,"tq":%Tq,"tw":%Tw,"tc":%Tc,"tt":%Tt},"haproxy":{"retries":%rc,"request":{"method":"%HM","uri":"%[capture.req.uri]","protocol":"%HV","header":{"host":"%[capture.req.hdr(0),json(utf8s)]","xforwardfor":"%[capture.req.hdr(1),json(utf8s)]","referer":"%[capture.req.hdr(2),json(utf8s)]"}},"name":{"server":"%s"},"response":{"status_code":%ST,"header":{"xrequestid":"%[capture.res.hdr(0),json(utf8s)]"}},"bytes":{"uploaded":%U,"read":%B}}}'
  option          http-keep-alive
  option          dontlognull
  option          tcp-smart-accept
  option          tcp-smart-connect

  retries 1
  option redispatch
  timeout http-keep-alive  72s
  timeout client           72s
  timeout connect          72s
  timeout server           72s

frontend fe
  bind *:3001
  option forwardfor
  default_backend be

backend be
  nuster cache on
  nuster rule r0 memory off disk on key method.scheme.host.path ttl 12d if { res.hdr(Content-Type) -m beg image/ }
  http-response set-header x-cache HIT if { nuster.cache.hit }
  server s1 localhost:3000

[jiangwenyuan]

@igorescobar There are some general advices regarding performance tuning on haproxy.org. For this specific TTFB on your specific environment, it's very hard to tell. Does all requests suffer such long ttfb? How does ELB perform? What if remove nuster? what happens if use memory on? etc.
I look forward to your investigation and tuning report:)