Skip to Content.
Sympa Menu

per-entity - Re: [Per-Entity] distribution of aggregate metadata

Subject: Per-Entity Metadata Working Group

List archive

Re: [Per-Entity] distribution of aggregate metadata


Chronological Thread 
  • From: Nicholas Roy <>
  • To: <>
  • Subject: Re: [Per-Entity] distribution of aggregate metadata
  • Date: Fri, 12 Aug 2016 16:02:00 -0600
  • Authentication-results: spf=none (sender IP is ) ;
  • Ironport-phdr: 9a23:iKctHxb6VdGWWeKtYgtzTAT/LSx+4OfEezUN459isYplN5qZpsS9bnLW6fgltlLVR4KTs6sC0LWG9f27EjVdqb+681k8M7V0HycfjssXmwFySOWkMmbcaMDQUiohAc5ZX0Vk9XzoeWJcGcL5ekGA6ibqtW1aNwvyLzV1J/j4X8v7x4Tyjrjqus6bXwId0CKwe/Z/Kgm3sRT5t88dho5nLaB3zQHG9ChmYeNTkEVpLlKUmx/nrv237dY39T5Xqtog8dJNS6P3Y/5+QLBFWmd1e1sp7dHm4EGQBTCE4WERByBPykJF
  • Spamdiagnosticmetadata: NSPM
  • Spamdiagnosticoutput: 1:99



On 8/12/16 4:00 PM, Nicholas Roy wrote:
>
> On 8/12/16 3:59 PM, Tom Scavo wrote:
>> On Fri, Aug 12, 2016 at 12:02 PM, IJ Kim
>> <>
>> wrote:
>>> It occurs to me that running multiple mdq metadata providers wouldn't be
>>> too hard while I'm not sure if clients can chain them or can consume a
>>> second mdq provider with something like "backingMDQUrl". Achieving five
>>> 9s among these providers would be much feasible.
>> This is a great idea. Ops might run a single, primary HA MDQ server on
>> the CDN of choice and then look to the community to add one or more
>> backup servers to the pool. Deployers could rely on the primary alone
>> or configure a chain of primary and secondary servers, where the
>> secondary is chosen from one of the servers in the pool.
>>
>> Tom
> +1 to this being a great idea. This might also be the way that we gain
> the diversity of CDNs we may end up thinking we need - one addition to
> the chain per CDN that ops might run.

/s/run/publish to/g
>

--
Nick


Attachment: signature.asc
Description: OpenPGP digital signature




Archive powered by MHonArc 2.6.19.

Top of Page