Some people withing Sun seem to be scared though that an Open-Source Java standard could be "polluted" by Microsoft.
I think Sun's major concern about Open Source Java should be IBM, not Microsoft. IBM has, for a while, been one of the major players embracing both GPL and Java, and IBM embracing GPL'd Java (on Linux) would be McNealys worst nightmare. Already IBM is _the_ company driving enterprise features into J2EE and I just could imagine that they'd have the motivation to push Java adoption on Linux, despite the recent issues. It's all about hardware sales after all.
"Why would an industry alliance need to define a standard to share an MP3 file between a smart phone and a PC?"
If you really have ever used any kind of smartphones, you should already know that any kind of standards are desperately needed. Just try to sync your calendar via BlueTooth between different vendor's phones, let alone do anything more sophisticated like automatically discover media files from foreign devices.
As a sidenote, I see no reason to limit this functionality to smartphones. It would be rather nice to have all the digital appliances discover playable media from the home network like play DivX on your set-top box using Ethernet of Wi-Fi link to your file server, or stream music from your MP3 player to your home stereo. I'd really like to see this digital media hub thing get started instead of all the nice marketing speech. But in order to do this, DRM is required in order to gain industry support.
I wonder why these two projects haven't shown up yet:
Single System Image Clusters for Linux and Cluster Infrastrucure for Linux. The following sentence just caught my eye on CI for Linux overview: "This project is developing a common infrastructure for Linux clustering by extending the Cluster Membership and Internode Communication Subsystems from HP's NonStop Clusters for Unixware code base." A similar sentence can be found of SSI Cluster page. It's about time for HP and IBM to team up and do what's necessary in order to shut up SCO.
"Clustered TPC-C benchmarks are of dubious value. I've yet to encounter any business that implements an OLTP system like this and it's for a good reason. Clusters of this sort are very difficult to implement and operate. You basically end up having to physcally partition your database across dozens of servers!"
This is not true if you use Oracle 9i and Real Application Cluster.
Any kind of software is different from physical items as physical items are usually manufactured. Software is usually engineered and that is a huge difference when it comes to things like quality and defects. But you're right, Open Source Software should also be held as liable for defects as any commercial software if there is going to be some sort of law for that. Of course, that would eventually mean the death of Open Source.:-)
Well, Microsoft only had a license for JDK 1.1.4 level stuff and even that license was already expiring. Why should they bundle Java with their OS? I do not see a single valid argument why they should do so as you can always get the Java support by downloading the VM from either Microsoft (1.1.x) or Sun (1.2.x). As technically oriented person, I see removing support for obsolete software better than bundling that stone-age VM (with Java standard in mind) with Windows.
Just because code is buried in the OS instead of the application (like it should be) doesn't mean that it isn't part of the application.
This is just a bunch of crap. The rendering capability is used all over the OS as well as the networking components and so on. You simply cannot remove the rendering controls without crippling the OS (well, you might be able to boot into console on W2K or XP).
You just might as well think TCP/IP stack should not be a part of the Unix kernel - instead each application should implement it over and over again. The way Microsoft has done it is actually efficient encapsulation leveraging COM(+) functionality.
Why would anyone want to buy such expensive boxes to run linux? The only reason I see is that they think they can save money by having fewer linux admins. Me, I think you can buy a lot of linux admin payroll for the 5-10$ million premium you pay for a big iron. I also think that an operation with some big iron tends to require a higher head count than the same computing power on commodity servers.
Do you have any kind of understanding how much does the physical space in a hosting facility cost? Not to mention about the setup cost. With one *huge* box running several Linux-instances you can easily save some serious money if you are a corporate user with a need for some hardcore hosting (a datacenter or such). Linux on IBM mainframe is not aimed at casual users, it's aimed at the big corporations... Just call HP or IBM Global Services and ask how much does the hosting cost. Of course, you can get cheapo hosting somewhere, but we're talking about corporate users and big investments here. With low-end hardware you'll end up adding more boxen based on current need and pay a huge setup costs per box, with IBM's mainframe you'll just add another Linux partition. Simple as that.
Maybe you should really check out the performance you get with relatively cheap Intel-compatible HW. Basically all a Sun box can offer is fast I/O and you can achieve that with Intel-based server if you have capable RAID controllers and multiple NICs in place. You will have the downtime though, as majority of Intel-based HW is not as hot-pluggable as real enterprise level HW. If you want to have that, check out IBM's OS/390 portfolio (or whatever zSeries that is) or HP's SuperDome. With Sun, you're left with overpriced HW with slow CPUs, no enterprise level uptime and not that good hardware abstraction.
Just that it runs non-Intel architecture as default does not make it that good. At work we have pretty good uptimes for the Intel boxes running Windows 2000 and especially those running Linux:-) So in my opinion the Unix-hardware-is-better-than-standard-Wintel is just a myth. _Good_ Intel based server HW is just as good as standard Sun stuff, you just don't have to pay the extra for the brand...
And you really should do those benchmarks, a Sun R440 that costs $$$$$$ just gets beaten when compared with a Compaq's dual CPU server that costs around USD 5000. And this is just something I have personally worked with, maybe you have other kind of experiences.
Maybe Sun is jealous because they *still* have no real enterprise level HW/SW combination that can do real clustering and partitioning. Just compare the stuff Sun can offer with their competitors (HP and IBM). Sun-cluster has downtime (at least with certain applications) up to several minutes and that is not what I call enterprise level operating environment. With IBM HW you get partitioning and abstraction that will you replace every single component in the system with zero downtime. And what comes to performance, I'd recommend cheap Intel boxen to all customers instead of Sun, they're basically identical when it comes to capabilities and Intel just runs Java much better (just try WebSphere, ATG Dynamo or even Tomcat).
I know Solaris is something like the standard Unix in the corporate world and I hate AIX and HP/UX, but the HW just is so much better. Now, with the rise of Linux, you get the superior HW with decent Unix-like OS.
"Also, on the RAID-5 system we get about 10MB/sec writing, and 60MB/sec reading. Remember, most networks can't handle more than 10MB/sec anyway."
Yeah right. Usually you will have a gigabit fiber from the file server to the switch and from there on gigabit fiber to other servers and 100 megabit lines for the workstations. 100 megabit file serving network is hardly enough for any serious use and you would have such if you need that amount of storage.
And you have really not used a Mac since mid-90's? Where do you think the Open Source people stole the idea? Why does Evolution look like a carbon copy of Outlook? Why is KDE like Windows 95?:-) Open Source community is in my opinion the greatest thief of all times when it comes to user interfaces and software in general. Eventually it is not a bad thing as it keeps the competition up (by making OS software competetive and compatible with proprietary one) but then again, little true innovation is happening.
This is offtopic, but do you happen to know a good way to expand A3000 RAM without using ZIP-packeged DRAM? I only have 8 megs of fast RAM on board and that's hardly enough for running Linux...
Have you ever checked out the IDE64 project or the CMD product portfolio? I'd love to have those for my C64, but I'll save the money for a G4 turboboard for my Amiga 3000.:-) Retro is cool!
Installing new games or other software is integrated to the browser. The Smart Card slots will most probably be used for subscription based services as well as electronical user identification. In Finland we have electronic ID cards available that you can use when you need to proof your identity electronically. It works for web services using SmartTrust iD2 and traditional smart card based user authentication when dealing with government officials and so on. I wouldn't be suprised if there would be support for electronic ID in the Finnish version of the box as you could then do really secure online commerce. No more dozens of user IDs and passwords.:) It is a known fact that Nokia + Visa + others are investigating the possibility to add electronic identity support to the digiTV stuff used in Finland, there was a press release about it some time ago. Please see http://www.digitv.fi/english/uutinen.asp?path=9;12 35;1244;1582 for more info on the subject.
You should really make a CVS checkout from ostdev. Software is installable via the Mozilla browser, installing a game is just as easy as clicking a link. The installation scripts are of course XML-based. Nokia of all companies is the one that know how to make easy user interfaces for (generally) stupid users.
Just a thougt; has anyone any knowledge if Nokia is going to link their box with Club Nokia? The 3330 GSM phone is able to download new levels for the built in games from Club Nokia. Each download costs some Club Nokia "credits" one can buy online. It would really be a logical step to integrate some Club Nokia stuff to the box as the profit for the boxes may be poor but the real revenue stream in the future may be the branded content. Just see what the others (Microsoft and Sony) are doing...
What the Media Terminal is primarily about is the digital TV standard commonly used in the Europe, MHP. All the fancy functionality is there just to kill the competition. Nokia has proven to be _very_ successful in the past doing the same thing in the GSM market and is now trying to do the same on digiTV field. If Nokia is able to launch their set-top box with a good software support (read: games), I think the competitors are going to have a tough time catching up with it. Most of the digiTV appliances only have the minimum set of functionality, the MHP implementation to be exact, so this is basically the history repeating itself once again: offer a bit more, publish the API to get the developer and market support, watch the competitors die.:)
Slashdot Mirror
Some people withing Sun seem to be scared though that an Open-Source Java standard could be "polluted" by Microsoft.
I think Sun's major concern about Open Source Java should be IBM, not Microsoft. IBM has, for a while, been one of the major players embracing both GPL and Java, and IBM embracing GPL'd Java (on Linux) would be McNealys worst nightmare. Already IBM is _the_ company driving enterprise features into J2EE and I just could imagine that they'd have the motivation to push Java adoption on Linux, despite the recent issues. It's all about hardware sales after all.
"Why would an industry alliance need to define a standard to share an MP3 file between a smart phone and a PC?"
If you really have ever used any kind of smartphones, you should already know that any kind of standards are desperately needed. Just try to sync your calendar via BlueTooth between different vendor's phones, let alone do anything more sophisticated like automatically discover media files from foreign devices.
As a sidenote, I see no reason to limit this functionality to smartphones. It would be rather nice to have all the digital appliances discover playable media from the home network like play DivX on your set-top box using Ethernet of Wi-Fi link to your file server, or stream music from your MP3 player to your home stereo. I'd really like to see this digital media hub thing get started instead of all the nice marketing speech. But in order to do this, DRM is required in order to gain industry support.
I wonder why these two projects haven't shown up yet:
Single System Image Clusters for Linux and Cluster Infrastrucure for Linux. The following sentence just caught my eye on CI for Linux overview: "This project is developing a common infrastructure for Linux clustering by extending the Cluster Membership and Internode Communication Subsystems from HP's NonStop Clusters for Unixware code base." A similar sentence can be found of SSI Cluster page. It's about time for HP and IBM to team up and do what's necessary in order to shut up SCO.
Well I hope it isn't 1.4.1 as it always reboots my machine when I quit an graphical Java application. Have to stick with 1.4.0_3. :)
Mikko.
"Clustered TPC-C benchmarks are of dubious value. I've yet to encounter any business that implements an OLTP system like this and it's for a good reason. Clusters of this sort are very difficult to implement and operate. You basically end up having to physcally partition your database across dozens of servers!"
This is not true if you use Oracle 9i and Real Application Cluster.
The Windows cluster was also running older version of Tuxedo.
As I recall, the XML parts also originate from IBM, they donated those to Apache XML project.
The JSP compiler is Jasper by the way. But all the enterprise level functionality is closed source.
Any kind of software is different from physical items as physical items are usually manufactured. Software is usually engineered and that is a huge difference when it comes to things like quality and defects. But you're right, Open Source Software should also be held as liable for defects as any commercial software if there is going to be some sort of law for that. Of course, that would eventually mean the death of Open Source. :-)
As I recall, if the EULA is in conflict with the legistlation, the legistlation wins. At least this is the case in most European countries.
...licensing scheme that everybody in the Open Source Community should bitch and moan?
Just a thought.
Well, Microsoft only had a license for JDK 1.1.4 level stuff and even that license was already expiring. Why should they bundle Java with their OS? I do not see a single valid argument why they should do so as you can always get the Java support by downloading the VM from either Microsoft (1.1.x) or Sun (1.2.x). As technically oriented person, I see removing support for obsolete software better than bundling that stone-age VM (with Java standard in mind) with Windows.
Just because code is buried in the OS instead of the application (like it should be) doesn't mean that it isn't part of the application.
This is just a bunch of crap. The rendering capability is used all over the OS as well as the networking components and so on. You simply cannot remove the rendering controls without crippling the OS (well, you might be able to boot into console on W2K or XP).
You just might as well think TCP/IP stack should not be a part of the Unix kernel - instead each application should implement it over and over again. The way Microsoft has done it is actually efficient encapsulation leveraging COM(+) functionality.
Why would anyone want to buy such expensive boxes to run linux? The only reason I see is that they think they can save money by having fewer linux admins. Me, I think you can buy a lot of linux admin payroll for the 5-10$ million premium you pay for a big iron. I also think that an operation with some big iron tends to require a higher head count than the same computing power on commodity servers.
Do you have any kind of understanding how much does the physical space in a hosting facility cost? Not to mention about the setup cost. With one *huge* box running several Linux-instances you can easily save some serious money if you are a corporate user with a need for some hardcore hosting (a datacenter or such). Linux on IBM mainframe is not aimed at casual users, it's aimed at the big corporations... Just call HP or IBM Global Services and ask how much does the hosting cost. Of course, you can get cheapo hosting somewhere, but we're talking about corporate users and big investments here. With low-end hardware you'll end up adding more boxen based on current need and pay a huge setup costs per box, with IBM's mainframe you'll just add another Linux partition. Simple as that.
Maybe you should really check out the performance you get with relatively cheap Intel-compatible HW. Basically all a Sun box can offer is fast I/O and you can achieve that with Intel-based server if you have capable RAID controllers and multiple NICs in place. You will have the downtime though, as majority of Intel-based HW is not as hot-pluggable as real enterprise level HW. If you want to have that, check out IBM's OS/390 portfolio (or whatever zSeries that is) or HP's SuperDome. With Sun, you're left with overpriced HW with slow CPUs, no enterprise level uptime and not that good hardware abstraction.
:-) So in my opinion the Unix-hardware-is-better-than-standard-Wintel is just a myth. _Good_ Intel based server HW is just as good as standard Sun stuff, you just don't have to pay the extra for the brand...
Just that it runs non-Intel architecture as default does not make it that good. At work we have pretty good uptimes for the Intel boxes running Windows 2000 and especially those running Linux
And you really should do those benchmarks, a Sun R440 that costs $$$$$$ just gets beaten when compared with a Compaq's dual CPU server that costs around USD 5000. And this is just something I have personally worked with, maybe you have other kind of experiences.
Maybe Sun is jealous because they *still* have no real enterprise level HW/SW combination that can do real clustering and partitioning. Just compare the stuff Sun can offer with their competitors (HP and IBM). Sun-cluster has downtime (at least with certain applications) up to several minutes and that is not what I call enterprise level operating environment. With IBM HW you get partitioning and abstraction that will you replace every single component in the system with zero downtime. And what comes to performance, I'd recommend cheap Intel boxen to all customers instead of Sun, they're basically identical when it comes to capabilities and Intel just runs Java much better (just try WebSphere, ATG Dynamo or even Tomcat).
I know Solaris is something like the standard Unix in the corporate world and I hate AIX and HP/UX, but the HW just is so much better. Now, with the rise of Linux, you get the superior HW with decent Unix-like OS.
"Also, on the RAID-5 system we get about 10MB/sec writing, and 60MB/sec reading. Remember, most networks can't handle more than 10MB/sec anyway."
Yeah right. Usually you will have a gigabit fiber from the file server to the switch and from there on gigabit fiber to other servers and 100 megabit lines for the workstations. 100 megabit file serving network is hardly enough for any serious use and you would have such if you need that amount of storage.
And you have really not used a Mac since mid-90's? Where do you think the Open Source people stole the idea? Why does Evolution look like a carbon copy of Outlook? Why is KDE like Windows 95? :-) Open Source community is in my opinion the greatest thief of all times when it comes to user interfaces and software in general. Eventually it is not a bad thing as it keeps the competition up (by making OS software competetive and compatible with proprietary one) but then again, little true innovation is happening.
This is offtopic, but do you happen to know a good way to expand A3000 RAM without using ZIP-packeged DRAM? I only have 8 megs of fast RAM on board and that's hardly enough for running Linux...
Have you ever checked out the IDE64 project or the CMD product portfolio? I'd love to have those for my C64, but I'll save the money for a G4 turboboard for my Amiga 3000. :-) Retro is cool!
Installing new games or other software is integrated to the browser. The Smart Card slots will most probably be used for subscription based services as well as electronical user identification. In Finland we have electronic ID cards available that you can use when you need to proof your identity electronically. It works for web services using SmartTrust iD2 and traditional smart card based user authentication when dealing with government officials and so on. I wouldn't be suprised if there would be support for electronic ID in the Finnish version of the box as you could then do really secure online commerce. No more dozens of user IDs and passwords. :) It is a known fact that Nokia + Visa + others are investigating the possibility to add electronic identity support to the digiTV stuff used in Finland, there was a press release about it some time ago. Please see http://www.digitv.fi/english/uutinen.asp?path=9;12 35;1244;1582 for more info on the subject.
You should really make a CVS checkout from ostdev. Software is installable via the Mozilla browser, installing a game is just as easy as clicking a link. The installation scripts are of course XML-based. Nokia of all companies is the one that know how to make easy user interfaces for (generally) stupid users. Just a thougt; has anyone any knowledge if Nokia is going to link their box with Club Nokia? The 3330 GSM phone is able to download new levels for the built in games from Club Nokia. Each download costs some Club Nokia "credits" one can buy online. It would really be a logical step to integrate some Club Nokia stuff to the box as the profit for the boxes may be poor but the real revenue stream in the future may be the branded content. Just see what the others (Microsoft and Sony) are doing...
What the Media Terminal is primarily about is the digital TV standard commonly used in the Europe, MHP. All the fancy functionality is there just to kill the competition. Nokia has proven to be _very_ successful in the past doing the same thing in the GSM market and is now trying to do the same on digiTV field. If Nokia is able to launch their set-top box with a good software support (read: games), I think the competitors are going to have a tough time catching up with it. Most of the digiTV appliances only have the minimum set of functionality, the MHP implementation to be exact, so this is basically the history repeating itself once again: offer a bit more, publish the API to get the developer and market support, watch the competitors die. :)