Ari Zilka on RAM is the New Disk & BigMemory
August 16, 2011; Topics: BigMemory, Enterprise Ehcache
Ari Zilka, Founder and CTO of Terracotta, discusses the evolving trends for large-scale Java applications.
He describes RAM as "the new disk" and emphasizes that users can take advantage of scaling up with BigMemory.
Read more ›
Watch the full interview on InfoQ ›
A Little Bit About BigMemory
November 2, 2010; Topics: BigMemory
In talking to our users it is clear that applications are getting more and more data hungry. According to IDC, data
requirements are growing at an annual rate of 60 percent. There is good news though. Server class machines purchased
this year have a minimum of 8 Gig of RAM and likely have 32 Gig. Cisco is now selling mainstream UCS boxes with over
380 Gig of RAM. Memory has gotten big and extremely cheap compared to things like developer time and user
satisfaction.
The Terracotta software stack, including Ehcache and Terracotta's out-of-process distributed cache server, the
Terracotta Server Array, is now available to Ubuntu users in a set of easy to install packages.
In this webcast, you will learn how Ubuntu users can take advantage of Ehcache and the Terracotta Server Array for
terabyte-scale distributed caching and web session management in an Ubuntu server cloud.
Attend this webcast if you are an Ubuntu user interested in learning about application performance and scalability
or if you are an Ehcache user interested in learning more about how to get cloud scale on Ubuntu servers.
Read more ›
Watch webcast ›
300GB+ in Memory on a Single JVM with No GC Pauses: Snap in Performance for Java with BigMemory for Enterprise Ehcache
November 10, 2010; Topics: Enterprise Ehcache, BigMemory
Today's servers come with lots of memory-16, 32 GBs or more-but the long-standing problem of garbage collection (GC)
limits the ability of Java apps to use it effectively. With no easy solution to GC, your application is taking a costly
performance hit that will only get worse as data volumes grow.
Unfortunately a problem exists as well. For Java/JVM applications it is becoming an ever increasing challenge to
use all that data and memory due to GC Pauses.
In this talk I'm going to cover the problems we identified and the technology we built to solve those problems.
I'll cover:
- A bit about it's history and the history of the problem
- The where, when why of BigMemory
- Throughput, latency, Garbage Collection, SLA and scaling characteristics
- Configuration of Ehcache with BigMemory in an existing application with just a few lines of config code
- Ehcache's tiered storage architecture: MemoryStore, the OffHeapMemoryStore and the DiskStore
- Ehcache BigMemory with scale-out
- Best practices
- Implications for your caching architecture
Read more ›
Watch webcast ›
Leveraging the Terracotta Toolkit for Scale
October 26, 2010; Topics: Topics: Enterprise Ehcache, BigMemory, Quartz Scheduler, Web Sessions, Terracotta Enterprise Suite
Scheduling, caching, ORM, and web sessions are the most common obstacles to scaling Java applications today. Terracotta
makes scaling as easy as a few lines of config, a jar, and the Terracotta server by integrating into the Quartz scheduler,
Ehcache caching system, Hibernate cache provider, and app server sessions.
While developing these easy to use, highly available, scaled out frameworks, we discovered a core set of pieces
and parts that were broadly applicable. We've now packaged these up as the toolkit for developers to solve other
scale problems not addressed by an existing Terracotta integration. You can leverage the Terracotta Toolkit to
build your own customized scalable Java application.
The following core APIs will be demoed and discussed: Cluster Aware API, Clustered Collections, Clustered
Locking, and Clustered Utilities.
Read more ›
Watch webcast ›
