Menu
▾
▴
hydrac-users — User Mail List
You can subscribe to this list here.
| 2008 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(3) |
Nov
|
Dec
(2) |
|---|
|
From: David D. <da...@do...> - 2008-12-23 05:39:16
|
Hey Alex, No, I was not aware of this project. It looks extremely similar to HydraCache and is well advanced too. Such a duplicated effort sounds like a waste but it may just be the nature of the bazaar... Tan/Nick: should we ping Ray (the Crank master)? Thanks anyway for letting us know! David On Thu, Dec 18, 2008 at 4:24 PM, Alex Cruise <ac...@gm...> wrote: > Hey guys, > > Have you seen this? > > http://github.com/GreyLensman/crank/tree/master/README > > Unfortunately he's recently re-licensed to GPLv3 so there's not much > hope of collaboration. :/ > > -0xe1a > > > ------------------------------------------------------------------------------ > _______________________________________________ > hydrac-users mailing list > hyd...@li... > https://lists.sourceforge.net/lists/listinfo/hydrac-users > |
|
From: Alex C. <ac...@gm...> - 2008-12-19 01:24:33
|
Hey guys, Have you seen this? http://github.com/GreyLensman/crank/tree/master/README Unfortunately he's recently re-licensed to GPLv3 so there's not much hope of collaboration. :/ -0xe1a |
|
From: Nick Z. <auc...@gm...> - 2008-10-24 17:43:27
|
Hi Alex, Congratulations! You are the first post on the mail list. My name is Nick one of the project admin and moderator of this list. First of all I am glad that you are interested in the project. Hydra is still a very very young project, although we are making some solid progress. At this stage we welcome any kind of help from trial user to documentation to load testing lab and as always developers so let me know what kind of things interest you. Cheers, Nick On Wed, Oct 22, 2008 at 4:38 PM, Alex Cruise <al...@cl...> wrote: > Hey folks, > > SF is having trouble with the list archive so if this is the first post > ever, welcome everyone to a project I've just found out about today! > > If not, let me just say that I was very excited by the Vogels paper and > would love to help. > > Perhaps interestingly, I independently reinvented a dumber version of > the load-balancing-by-consistent-hashing technique years ago but > the company died before I found out just how dumb my idea was. > > Basically we wanted to have a cluster of application servers, and I > would assign newly provisioned user accounts a primary and secondary > server by seeding a Random with the user's unique ID, then extracting > two ints, modulo the number of nodes in the cluster. The load balancer > would need to rerun the hash function and compare the results against the > app server scoreboard to figure out where to send the request. > > Tuning the hash algorithm when the cluster changed in size was going to be > a problem, but thankfully I never got a chance to solve it and the world > was spared. ;) > > -0xe1a > > > ------------------------------------------------------------------------- > This SF.Net email is sponsored by the Moblin Your Move Developer's > challenge > Build the coolest Linux based applications with Moblin SDK & win great > prizes > Grand prize is a trip for two to an Open Source event anywhere in the world > http://moblin-contest.org/redirect.php?banner_id=100&url=/ > _______________________________________________ > hydrac-users mailing list > hyd...@li... > https://lists.sourceforge.net/lists/listinfo/hydrac-users > |
|
From: <auc...@gm...> - 2008-10-23 15:17:08
|
Hi Alex, Congratulations! You are the first post on the maillist. My name is Nick one of the project admin and moderator of this list. First of all I am glad that you are interested in the project. Hydra is still a very very young project, although we are making some solid progress. At this stage we welcome any kind of help from trial user to documentation to load testing lab and as always developers so let me know what kind of things interest you. Cheers, Nick Sent on the TELUS Mobility network with BlackBerry -----Original Message----- From: Alex Cruise <al...@cl...> Date: Wed, 22 Oct 2008 13:38:17 To: <hyd...@li...> Subject: [Hydrac-users] Hi! Hey folks, SF is having trouble with the list archive so if this is the first post ever, welcome everyone to a project I've just found out about today! If not, let me just say that I was very excited by the Vogels paper and would love to help. Perhaps interestingly, I independently reinvented a dumber version of the load-balancing-by-consistent-hashing technique years ago but the company died before I found out just how dumb my idea was. Basically we wanted to have a cluster of application servers, and I would assign newly provisioned user accounts a primary and secondary server by seeding a Random with the user's unique ID, then extracting two ints, modulo the number of nodes in the cluster. The load balancer would need to rerun the hash function and compare the results against the app server scoreboard to figure out where to send the request. Tuning the hash algorithm when the cluster changed in size was going to be a problem, but thankfully I never got a chance to solve it and the world was spared. ;) -0xe1a ------------------------------------------------------------------------- This SF.Net email is sponsored by the Moblin Your Move Developer's challenge Build the coolest Linux based applications with Moblin SDK & win great prizes Grand prize is a trip for two to an Open Source event anywhere in the world http://moblin-contest.org/redirect.php?banner_id=100&url=/ _______________________________________________ hydrac-users mailing list hyd...@li... https://lists.sourceforge.net/lists/listinfo/hydrac-users |
|
From: Alex C. <al...@cl...> - 2008-10-22 20:38:20
|
Hey folks, SF is having trouble with the list archive so if this is the first post ever, welcome everyone to a project I've just found out about today! If not, let me just say that I was very excited by the Vogels paper and would love to help. Perhaps interestingly, I independently reinvented a dumber version of the load-balancing-by-consistent-hashing technique years ago but the company died before I found out just how dumb my idea was. Basically we wanted to have a cluster of application servers, and I would assign newly provisioned user accounts a primary and secondary server by seeding a Random with the user's unique ID, then extracting two ints, modulo the number of nodes in the cluster. The load balancer would need to rerun the hash function and compare the results against the app server scoreboard to figure out where to send the request. Tuning the hash algorithm when the cluster changed in size was going to be a problem, but thankfully I never got a chance to solve it and the world was spared. ;) -0xe1a |
