While researching for an upcoming article I’m writing, I stumbled on this cloud architectures white paper from Jinesh Varia, technological evangelist @ Amazon web services (AWS).
This is an interesting document and peoples interested in presenting a valid use-case to management for the deployment of applications over a cloud should really like it.
This bring me to the big question of why Quebec isn’t a leader in this virtualization/on-demand computing industry. Always though that having a very low electricity cost was an incentive to invest in big data center and then try to automatize everything. This would have led to the really interesting technology that is virtualization (cutting provision time by a very big margin) -
Maybe this low cost electricity is exactly what made international concurrents more interested in saving cpu cycle…
Applying green computing to clusters,
by Steven Alan DuChene from SGI @ Ottawa Linux Symposium
The presentation is a high level review of metrics that are wanted and/or required to have controlled clusters computing and the road-map to the creation of an “environmental aware” job scheduler / resources manager.
It feel funny to hear the same talk that has been around for home automation about a data center installation. Especially since it does seem like a cheat to apply it to high performance since semi-random load are still a big part of the charge of a data center… and in HPC setup, the race to idle is normally the easiest and lower power consumption path.
Also weird that there is no mention of the advantage of cloud computing & fast provisioning that virtualization can bring to a green data center.
Cloud Computing: Coming out of the Fog
By Gerrit Huizenga, from IBM @ Ottawa Linux Symposium
Its very strange to hear a talk about cloud computing from an IBM employee since they have not yet shown any serious stats about their Blue Cloud system. Still, it’s a good review of the cloud computing field.
Despite the fact that the presentation is built upon the statement that cloud computing isn’t about servers provisioning, it clearly revolve around the two following points of views:
From outside of the cloud :
You want your applications (complex systems) to be deployed fast, with next to no configurations to be done. 3Tera system is shown as a “good” way of doing that - personally, having built something similar for a client, Amazon EC2 is also a good contender for the title. From my POV, this is really about provisioning and the capacity of building virtual appliance.
From inside of the cloud :
You want to have a fully (automatic, dynamically) managed data center. Technology is already there. This is ALL about server provisioning.
The presentation moved from this “reviewing definition” to “why it is presently not everywhere” and “how to build a general interface for cloud system”. Guess this speaker is reading the cloud computing mailing list at Google Group since those are hot subjects right now.
As a closure (this wasn’t mentioned in the presentation) : here is a quick stock index of related corporation.
On Peter Laird’s blog (which is very - very - good), and re-hosted here, there is an interesting cloud computing/SaaS/*aaS industry mind-map.
There might be a couple field missing (data as a service : hadoop, SimpleDB, BigTable, microsoft also offer some data management), but as a overview, it is pretty accurate.
This map is also interesting as a base for investment decision - not that much to modify (and source are available) to get a precise market snapshot.
Oups !
J’ai oublié de mentioner que le Linux Symposium d’Ottawa arrive à grand pas. Je vais y être présent, du 22 au 26 Juillet 2008, pour blogger sur les différents acteurs du milieu de l’OpenSource. Compte tenu mon “background” en storage / virtualisation / cloud computing ; j’ai un intéret particulier pour les discussions suivantes:
“Tux meets Radar O’reilly - Linux in military telecom” : Il est toujours intéressant de voir un déploiement dans une optique militaire. Dans le militaire, tout comme pour le bancaire et medical, l’erreur est beaucoup moins tolérée et peut être source de répercussions incroyables… Pour prévenir les bourdes, les systèmes sont testés très précisement - le commun des mortels a surement beaucoup à apprendre de cet état d’esprit. Investir pour la stabilité - ce n’est pas fou comme idée!
“A Survey of Virtualization Workloads” : Simple, mais si la présentation - et les recherches! - est bien effectuée, il peut y avoir correlation avec des use-case que je rencontre lors de mes consultations. Elle est suivie d’une deuxième présentation qui lui semble quasi identique - worst case : j’irai voir les deux.
Applying Green Computing to clusters and the data center” : Je ne connais que très superficiellement ce domaine, si nous excluons le “tu configures du wake-on-lan associé avec un control de charge”. Étant particulièrement biasé vers la solution “tu ajoutes des systèmes” - autant au niveau création d’actif financier et réduction de coûts - J’imagine que je vais pouvoir briser le voile de mon ignorance et changer ma position.
“SynergyFS: A Stackable File System Creating Synergies Between Heterogeneous Storage Devices” : Les discussions sur le stockage sur des environnements hybrides m’acrochent toujours. Le storage est un problème avec plus de 50 solutions dans le monde GNU/Linux (50+ fs supportés par le noyau) - chacune d’entre elle avec des forces et faiblesses. Voyons voir comment profiter des forces en “patchant les faiblesses avec d’autre système de fichiers”.
“If I turn this knob… what happens?” :
Dernière présentation qui à le mérite de mon intéret - et pas la moindre. Il est question de la prise de métrique (io, scheduler, lock_wait, sys/proc fs,…) et d’agir sur les résultats. En résumé, elle calque exactement ce que je fais en capacity planning pour les clouds/clusters que je déploie. J’aime toujours voir et dialoguer sur les processus utilisés par d’autres consultants.
See you there!
