Deliver on HIT, otherwise redirect using "503; Location: ..."

Tue Dec 20 17:02:33 CET 2016

Thanks for the context. So, if I get what you're writing, the goal is too
redirect to a node that has the object in cache?

Question is, what's the time needed to:
- send a request to the server on the LAN and receive the object
- send the redirect across the web, and wait for the client to send a new
request, again across the web.

If the former is not at least an order of magnitude larger than the latter,
I wouldn't bother.

The issues I have with your redirection scheme are that:
- IIUC, you are basically explaining to people where the backend is,
instead of shielding it with Varnish
- it doesn't lower the backend traffic
- as said, I'm not even sure the user-experience is better/faster

-- 
Guillaume Quintard

On Sun, Dec 18, 2016 at 9:21 PM, Anton Berezhkov <
bubonic.pestilence at gmail.com> wrote:

> We have 6 servers with 6TB on each one (same video files). Currently
> they're hitting iowait limit of SATA disk (240ops total). At same time,
> each server can provide 500Mbit of guaranteed bandwidth.
>
> With HDD restriction, each server provides about 320Mbit. There is also
> problem with fragmentation, which is caused by nature of HTML5 video
> players & HTTP (allowing to request partial data with Range header).
>
> Before this moment, we were scaling horizontally, by duplicating this
> servers.
>
> There is also option to get same server with 2x480GB SSDs. As i
> reasearched from nginx logs, 98% of daily traffic lays in ≈800GB of files.
>
> What i want to achieve: To build a varnish server with 2x480GB SSDs(no
> raid), with storage for varnish about 800GBs. Which will guarantedly fill
> all available bandwidth for a server.
>
> Also, I built simple load-balancer, which monitors each server for current
> eth0 load (in Mbps) and decide to which one redirect (using HTTP Location
> header).
>
> Request for Video -> LBServer: Find lowest loaded(1 of 6) & Redirect to
> LBNode -> LBN: serve request
>
> To add new HDD-LBN, i need to setup server, sync videos, setup some
> additional software.
>
> My wish: add new SSD-LBN, setup & sync varnish config, and it will build
> cached pool itself.
>
> Why i need redirect?
> 1. It will offload bandwidth of SSD-LBN, pass-through will take bandwidth
> of both servers + still cause iowait problems on HDD-LBN.
> 2. It will "prove" that uncached video will be take from HDD-LBN which
> always have all videos.
>
> Currently all LBN servers are hosted on OVH and we're good with them,
> especially because of low price :)
>
> If you have any suggestions, i'll be glad to hear them :)
>
> > On Dec 18, 2016, at 10:59 PM, Guillaume Quintard <
> guillaume at varnish-software.com> wrote:
> >
> > I think Jason is right in asking "why?". What do you want to achieve
> specifically with this behavior?
> >
> > Varnish has streaming and request coalescing, meaning a request can be
> served as soon as data starts being available AND the backend doesn't
> suffer from simultaneous misses on the same object. I feel that should
> cover almost all your needs, so I'm curious about the use-case.
> >
> > On Dec 18, 2016 20:27, "Jason Price" <japrice at gmail.com> wrote:
> > It would be possible to do this with varnish... but I have to ask... why
> bother?
> >
> > If the purpose is to offload the IO load, then varnish is good, but you
> need to prime the cache... TBH, what I'd do first is put one or a pair of
> varnish boxes really close to the overloaded box, and force all traffic to
> that server through the close varnish boxes... using the do_stream feature,
> you'll get stuff out there fairly quickly.
> >
> > After that is working nicely, I'd layer in the further out varnish boxes
> which interact with the near-varnish boxes to get their data.
> >
> > This works well at scale since the local caches offer whatever's useful
> local to them, and the 'near-varnish' boxes handle the 'global caching'
> world.
> >
> > This was how I arranged it at $PreviousGig and the outer CDN was getting
> a 85-90% cache hit ratio, and the inner tier was seeing 60% cache hit
> ratio's.  (The inner tier's ratio will depend heavily on how many outer
> tier's there are...)
> >
> > On Sat, Dec 17, 2016 at 8:09 PM, Anton Berezhkov <
> bubonic.pestilence at gmail.com> wrote:
> > This is how I semi-implemented: http://pastebin.com/drDP8JxP
> > Now i need to use script which will run "curi -I -X PUT
> <url-to-put-into-cache>".
> >
> >
> > > On Dec 18, 2016, at 3:58 AM, Mark Staudinger <mark.staudinger at nyi.net>
> wrote:
> > >
> > > Hi Anton,
> > >
> > > Have you looked into the "do_stream" feature of Varnish?  This will
> begin serving the content to the visitor without waiting for the entire
> object to be downloaded and stored in cache.  Set in vcl_backend_response.
> > >
> > > https://github.com/mattiasgeniar/varnish-4.0-
> configuration-templates/blob/master/default.vcl
> > >
> > > Cheers,
> > > Mark
> > >
> > > On Sat, 17 Dec 2016 19:05:48 -0500, Anton Berezhkov <
> bubonic.pestilence at gmail.com> wrote:
> > >
> > >> Hello.
> > >>
> > >> Switched to Varnish from Nginx for additional functionality and
> better control of handling requests.
> > >> But still can't implement what i want. And I want simple behaviour
> "Redirect on MISS/PASS".
> > >> I want to use VC for deploying quick "cdn" servers for our
> mp4-video-servers (used for HTML5 players), without need to store all files
> on this quick (ssd, upto 2x480GB space, full database about 6TB).
> > >>
> > >> Currently we have 6 servers with SATA HDDs and hitting iowait like a
> trucks :)
> > >>
> > >> Examples:
> > >> - Request -> Varnish -> HIT: serve it using Varnish.
> > >> - Request -> Varnish -> MISS: start caching data from backend, and
> instantly reply to client: `Location: http://backend/$req.url"
> > >> - Request -> Varnish -> UPDATE: see `-> MISS` behaviour.
> > >>
> > >> From my perspective, i should do this "detach & reply redirect"
> somewhere in `vcl_miss` OR `vcl_backend_fetch`, because if i understood
> correctly https://www.varnish-cache.org/docs/4.1/reference/states.html, i
> need vcl_backend_response to keep run in background (as additional thread)
> while doing return(synth(...)) to redirect user.
> > >>
> > >> Similiar thing is "hitting stale content while object is updating".
> > >> But in my case "replying redirect while object is updating".
> > >>
> > >> Also, i pray to implement this without writing additional scripts,
> why? I could do external php/ruby checker/cache-pusher with nginx & etc.
> But scared by performance downgrade :(
> > >> _______________________________________________
> > >> varnish-misc mailing list
> > >> varnish-misc at varnish-cache.org
> > >> https://www.varnish-cache.org/lists/mailman/listinfo/varnish-misc
> >
> >
> > _______________________________________________
> > varnish-misc mailing list
> > varnish-misc at varnish-cache.org
> > https://www.varnish-cache.org/lists/mailman/listinfo/varnish-misc
> >
> >
> > _______________________________________________
> > varnish-misc mailing list
> > varnish-misc at varnish-cache.org
> > https://www.varnish-cache.org/lists/mailman/listinfo/varnish-misc
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://www.varnish-cache.org/lists/pipermail/varnish-misc/attachments/20161220/64b55019/attachment.html>