Chang's blog @ssh67-blog - Tumblr Blog

I am anxiously waiting for 64bit ARM chip as well.

Overview

This project aims to demonstrate a novel bloom filter implementation that can scale, and provide not only the addition of new members, but reliable removal of existing members.

Motivation

bitly has billions and billions of links and an infrastructure that serves thousands of decode...

nosql

Dapper, a Large-Scale Distributed Systems Tracing Infrastructure

Google’s paper about their large-scale distributed systems tracing solution Dapper which inspired Twitter’s Zipkin:

Here we introduce the design of Dapper, Google’s production distributed systems tracing infrastructure, and describe how our design goals of low overhead, application-level transparency, and ubiquitous deployment on a very large scale system were met. Dapper shares conceptual similarities with other tracing systems, particularly Magpie [3] and X-Trace [12], but certain design choices were made that have been key to its success in our environment, such as the use of sampling and restricting the instrumentation to a rather small number of common libraries.

Download or read the paper after the break.

Is software (applications, library, OS, drivers) ready for this change?

whos-v-blog

API Design Best Practices

API’s can be fundamentally important for an organization. However, its use, contrary to popular belief, is not just for external clients & developers, but they can play an important role in building system wide applications & towards an API driven architectural...

All problems in computer science can be solved by another level of indirection... Except for the problem of too many layers of indirection

David Wheeler

QUINLAN: We ended up putting a fair amount of effort into tuning master performance, and it’s atypical of Google to put a lot of work into tuning any one particular binary. Generally, our approach is just to get things working reasonably well and then turn our focus to scalability—which usually works well in that you can generally get your performance back by scaling things.

An excerpt from ACM queue magazine article on GFS: A discussion between Kirk McKusick and Sean Quinlan. We can see that Google engineers do not prematurely work on single binary optimization, rather they work on scalability.

#Google #GFS #scalability

Steve Jobs talks about workstation business market and his grand scheme of things. The plan was great, but NeXT failed. But did NeXT really failed? Just have a look at MacOS & iOS SDK.

#Steve Jobs #NeXT

OpenFlow

OpenFlow is a new protocol that is gaining tremendous momentum among switch makers: the protocol enables IDC admins complete control over routing based on policy, QoS, etc. Network virtualization is possible with this L2-based protocol.

Some important links

http://www.networkworld.com/news/2011/051311-interop-openflow.html

http://www.networkworld.com/news/2011/041411-open-flow.html

Fifteen vendor participants in the Interop lab were showing beta products. They included Big Switch, Broadcom, Brocade, Citrix, Dell, Extreme Networks, Fulcrum, HP, IBM, Juniper, Marvell, NEC, NetGear and NetOptics. Pronto Systems, a maker of switches that can run OpenFlow software, contributed products that are already shipping.

You can also use this to build a huge web service without dedicated L4 hardware load balancers.

#network #openflow #load balancer #network virtualization

Dart is a new web language, and Google tries to bring a new dish to web browsing table. It still is slower than JavaScript, but more choice and more competition means better quality.

#webkit #google #dart #javascript

Cube: A new system for time series chart. It uses node.js, MongoDB, D3, and it can be integrated into collectd. Now try to build a new "Hubble" with this, Arcus team!

#collectd #monitoring

nosql

Greg Luck[1] following up on his article Ehcache: Distributed Cache or NoSQL Store? talks about architectural differences between distributed caches, NoSQL database, and RDBMS and where distributed caches fit:

NoSQL and RDBMS are generally on disk. Disks are mechanical devices and exhibit large latencies due to seek time as the head moves to the right track and read or write times dependent on the RPM of the disk platter. NoSQL tends to optimise disk use, for example, by only appending to logs with the disk head in place and occasionally flushing to disk. By contrast, caches are principally in memory. […] With RDBMS a cache is added to avoid these scale out difficulties. For NoSQL, scale out is built-in, so the cache will get used when lower latencies are required.

Greg Luck: Founder and CTO, Ehcache ↩

#cache #noSQL #ehcache

This is a simple tutorial for those who know nothing about Scala.

#scala #language #tutorial

Scala & Akka

Can Scala and Akka save the day? Or is it still too early for web developers to adopt functional language and actor model?

#scala #akka #language

Rust는 Ruby, Java, 그리고 Erlang/Go 의 hybrid language인것 같네요. Go는 아직 thread가 CPU bound operation 시 runtime이 무한정 thread를 spawn 시키는 문제가 있는데, Rust는 이 문제를 어떻게 풀었는데 궁금하네요.

#rust #go #concurerncy #language

Trending Blogs

Recently Viewed Blogs

Chang's blog