I hate to say it but I think the words that came out of Brian or
Eric's mouth were something like "... so you don't need something like
a proxy ..." when describing either gearman or memcached (and both are
conceptually the same from a scaling methodology)

There may be a usage model for this but it is fundamentally against
the point of the application's shared-nothing design. I will say
though that protocol conversion and some other things might be
interesting and useful but treating it like a traditional proxy is
basically against the point.

However, if each memcached client has its own moxi client, moxi must
have its own hashing algorithm then etc. I am wondering though how
much of the L1 cache functionality could be pushed to the application
layer instead of a middle-man to the memcached servers?

Calling this a proxy initially threw me off, reading the post a little
further it -is- a proxy but "proxy" makes people think what I
initially thought - something like MySQL proxy, etc...


>> On Jun 27, 4:25 am, "steve.yen" <[email protected]> wrote:
>> > Hi!
>> >
>> > I saw some talk about memcached proxies on the list today, so figured
>> > it'd be good to let you all know about "moxi", a new open-source
>> > memcached proxy.  Dustin Sallings, Matt Ingenthron and I have been
>> > working on it, where moxi fits together the latest memcached (1.4) and
>> > libmemcached projects.  License is BSD, and more info's at...
>> >
>> >  http://labs.northscale.com/moxi
>> >
>> > We needed something that spoke memcached binary protocol, initially on
>> > the proxy-to-memcached side of things, and wanted something that could
>> > be kept up to date with the latest memcached + libmemcached features.
>> >
>> > The idea with moxi is that webapp processes and scripts connect to it
>> > running at localhost:11211.  Then, moxi multiplexes traffic to a pool
>> > of memcached servers.
>> >
>> > On compatibility, moxi passes the same test suite as memcached, except
>> > for the ones that don't make sense for a proxy, eg testing "dash-M"
>> > command-line flags.  There are also new test cases to exercise
>> > proxy-only features and topologies.
>> >
>> > moxi also supports protocol conversions, so webapp processes and
>> > scripts can still speak ascii protocol, while moxi can optionally use
>> > binary protocol to speak to memcached servers.
>> >
>> > One possibly useful optimization: moxi has a configurable front cache,
>> > so it can keep a small number of hot items in moxi's memory, saving on
>> > wire network hops.  In other words, an L1 cache.
>> >
>> > Another optimization, moxi can de-deplicate concurrent GET requests
>> > for popular keys, based on ideas from Dustin Sallings' spymemcached
>> > client.  See:http://code.google.com/p/spymemcached/wiki/Optimizations
>> >
>> > There are more features and ideas in plan, but they're more
>> > work-in-progress.  Appreciate any feedback, share what you want to
>> > see, not see, etc.
>> >
>> > Cheers,
>> > Steve
>
>

Reply via email to