How large do you have the cache configured to be? The default is 64MB unless overridden. What do the memcached statistics show when you telnet into each instance? Are you seeing a lot of evictions I wonder?
Also, how many core does each memcached server have? Generally speaking the memcached thread count should be the same as the number of available cores available. Any more than that increases the likelihood of thread contention on the cache itself. The default number of threads is 4 threads (assuming you're using 1.4.3). After all adding more threads is not a free lunch otherwise we'd all just set it to be 10,000 and be done with it. I doubt you have a 20 core server with only 512MB of ram. ;) To tune your memcached setup for maximum efficiency spend some time checking out the various load testing and benchmarking tools such as Brutis or memslap. However, if it were me I would immediately correct the thread count setting as mentioned above. Thanks, Paul On Sun, Feb 20, 2011 at 12:15 PM, Patrick Santora <[email protected]>wrote: > I am having issues with Memcached at the moment. I have multiple > servers on the front end that each have 100 connections round robining > to memcached. I have 2 memcached servers, each with 512MB of ram and > 20 threads (might be a little high) available to each. > > What I am seeing is that when my memcached container hits around 10MB > of written traffic is starts to bottleneck causing my front end > systems to slow WAY down. I've turned on verbose debugging and see no > issues and there are no complaints on the front end stating that the > connection clients are not able to hit memcached. > > Has anyone seen anything like this before? > > I would appreciate any feedback that could help out with this. > > Thanks > -Pat
