Awesome strategy
on
Podcasting
·
· Score: 2, Informative
Step 1: Start Drama with book author on Yahoo Groups list.
Step 2: Submit a bitter, mean spirited, personal attack disguised as a book review to Slashdot.
Step 3: ?????
Step 4: Profit.
(Disclaimer: Don't know either of them. Actually thought, based on the review, that the reviewer was writing his own podcast book and was back-channel promoting it while tearing down another book. Found the thread in the google search trying to validate this. Actually proud of reviewer for creative flaming strategy and wish I had though of that first.)
In the software industry, the common example of thinking at the wrong level is a team of rock star programmers who can make anything, but don't really know what to make: so they tend to build whatever things come to mind, never stopping to find someone who might not be adept at writing code, but can see where the value of their programming skills would be best applied
Well, you can think what you want, but I'm not a paid Apple shill surfing Slashdot for posting opportunities. I saw the story go up, and since I do cluster pre-sales at work, I thought I had some topical comments. I even mentioned running Linux on the Xserves.:)
Well, the Workgroup Cluster is really turn-key. It comes with everything, ethernet cables, ethernet switch, a small rolling rack, etc... and includes the Bioteam iNquiry software on disk images, so you just load the images and go.
So, fair enough with the marketing comment. I do technical pre-sales for Apple, so I've really touched and used this stuff. If you do have any techie questions, fire away.:)
Well, he's complaining about something quite minor, which is just having to uncheck the updates you don't what when you run an update. By comparison, in the Linux world Novell forces you to purchase Red Carpet update service for the same feature, and I believe Red Hat does the same with RHEL.
So, I'm not sure why all the hate. The software update server is bundled with Tiger Server, which you can get for as little as $500.
Tiger Server lets you run your own Software Update Server, which would solve this problem for you. You run a central update server, point all your servers and clients at that, and then you can approve or disapprove each update before it goes out.
That's simply not true. We stock parts for all Apple equipment for at least seven years. The drive caddys for the old Xserve G4 are exactly the same as what we ship in the current Xserve RAID, so not only is the drive caddy still available, it's also still in use.
Actually, the cheapest way to go would be to buy the 250GB ADM, apple part number M9356G/A, and pull out the 250GB drive and use it somewhere else (or just use that drive). Service parts tend to be pricey (like everyone else).
At Apple we sell the Xserve Cluster node which has been used for clusters as large as the 1,566 node COLSA cluster. We also sell it in small turn-key configurations.
Probably the most interesting news lately for OS X for HPC is the inclusion of Xgrid with Tiger. Xgrid is a low-end job manager that comes built-in to Tiger Client. Tiger Server can then control up to 128 nodes in a folding@home job management style. I've seen a lot of interest from customers in using this instead of tools like Sun Grid Engine for small clusters.
You can find some good technical info on running clustered code on OS X here.
The advantage of the Xserve is that it is cooler and uses less power than either Itanium or Xeon, and it's usually better than Opteron depending on the system. In my experience almost all C or Fortran code runs fine on OS X straight over from Linux with minimal tweaking. The disadvantage is that you only have one choice: a dual-CPU 1U box - no blades, no 8-CPU boxes, just the one server model. So if your clustered app needs lots of CPU power it might not be a good fit. For most sci-tech apps, though, it works fine.
If you're against OSX but still like the Xserve, Yellow Dog makes an HPC-specific Linux distro for the Xserve.
Well, actually sales and marketing are quite different. And pre-sales technical SE and marketing are quite a bit different.
We get involved in a lot of practical deployments, like most SE's in reseller organizations, and most corporate enterprise SE's in large companies.
So it's fair to say that I have less real-world experience than, say, an Oracle DBA doing large enterprise deployments, it's completely unfair to say that I never get my hands dirty. I talk to customers every day and help them with real world deployment issues.
In our space, you never win. You don't have large-memory capabilities or redundant PSUs. That, combined with the lack of a supported Linux distro, makes XServe a non-starter.
Well, that's certainly not true. We certainly sell a lot of units as DB servers, web servers, scientific clusters, etc. If you're making an Oracle RAC, then the individual pieces aren't important. You can see the success stories on our websites. Oh wait, biased!:)
Does DB2, Oracle, or MSSQL run on your systems?
Yes.
Don't post marketing on Slashdot.
Oh please, you're making a tempest in a teapot over a performance white paper. Ok, forget that. Your HP server in a dual CPU configuration uses 2x the power and 3x the cooling, based on vendor numbers. And get's 40% to 60% more performance. Maybe that makes sense for some customers. Maybe not.
You can be a zealot all you want, I know what my customers are doing with their servers. And you obviously know what yours are doing too.
Agreed. The only real benchmark is in-house testing with the actual app. But, see the previous reply where the poster is getting 20% to 30% more performance with a system with 2x more power draw and 3x more heat.
Like I said, in my experience the Xserve usually wins in price/performance if the cost of cooling and power matter. In many cases departments in corporations and universities don't pay for their own power or cooling, so they don't care. Which is too bad, but the article was about power draw, which is why I piped up in the first place.
This isn't marketing trickery, the PPC970 just runs cooler and the Xserve is well-engineered. I wish more people would check them out.
Oh hey, one more followup. Since you mentioned the HP DL585 I configured that in a dual CPU config versus the dual CPU Xserve using the specs here and the "marketing document" I linked earlier for the Xserve.
Here's what I got: DL585 800 Watts Max 2730 BTU Max XServeG5 290 Watts Max 990 BTU Max
So, for 20% to 30% more performance, according to your numbers, you use 2x the power and 3x the cooling by using the HP DL585. In some cases that may make sense for the customer, in some cases in won't. But, I do think it illustrates my point that the Xserve often has better price/performance when you factor in power and cooling expense.
No, it's not. It's an Apple marketing piece. As is the other iterm that you linked.
Actually, the other item I linked was the support article showing the actual power draw and BTU's generated. I guess you didn't actually click through and read it. That's OK, it's Slashdot.:)
Let me guess, you work for Apple?
Yes. And you?
It can also win on applications that use lots of memory bandwidth. Databases, for example, are almost always bandwidth-hungry. So are distributed filesystems. Many technical and scientific computing applications are also memory-bound.
True. What I said is also true, especially since it was about my experience with my customers. Empirically true. How about you? In your experience what's the mix between memory bound and cpu bound applications?
Our mileage does vary. My company has compared PPC970, Xeon, and Opteron using the SAN solution that we integrate, and Opteron is the clear winner. For database systems as well, Opteron is 20-30% faster than Xeon and PPC970.
Yes, indeedy, just like I said. How about price/performance versus cost of heating and cost of power? This was an article about power draw, after all.
Also, you have a CPU-bound SAN solution? Tell me more.
It's great that you're picking the real-world winner based on testing. That's exactly what you should do. In my experience we win sometimes and Opteron wins sometimes, but we usually win on price/performance when factoring in the cost of power and cooling for large systems.
Moreover, XServe doesn't support more than 8GB of memory. That's simply not enough for our customers. Heck, the 64GB provided by HP's DL585 *still* isn't enough.
You are incorrect. I would link you to the correct specs but you'd dismiss them as a marketing piece.:)
Look, Apple has some nice products, but without a true commercially-supported Linux distro, it's hard to sell your product. People buying servers want Linux or Windows, and they want something that is supported by the vendor.
Funny, I thought we were selling a commercially-supported UNIX distro, and that our server sales were going up. I guess our customers are buying things they don't want!:)
The G5 (PowerPC 970) has similar specs. I haven't seen new wattage numbers on the new 2.7GHz models, but I imagine they are similar. The PPC970 draws about 40 watts as far as I know.
More important are power draws and BTU's for the entire system. I've done some comparisons between the Apple Xserve and competing Opteron/Xeon/Itanium2 systems for customers, and the Xserve is usually better at total power consumption and generates less heat. Our numbers are published here. Performance numbers between cross-platform code running on an Xserve and on a comparable dual-CPU system are usually competitive, depending on what the test is. The Opteron can certainly win on synthetic benchmarks that test memory bandwidth due to the memory architecture, but most people don't actually need that bandwidth.
When testing actual customer code we're usually the same or better in performance, with lower power draw and less heat generation. As always, your mileage may vary.
There's a lot of stuff broken, although a lot of stuff still works (like Ethereal, as I mentioned). irssi is the biggest annoyance for me, and I think irssi is broken because glib is broken, but I could be wrong. I also couldn't get MySQL to install through fink on my Tiger client.
I've heard many reports of different things being broken here and there. If the stuff you use works, then I guess you don't have any problems.:)
Everything I had loaded ran fine, including some APE stuff with a few haxies. Even GeekTool continued to run, which really surprised me. Office for Mac (2004) ran fine for me after the upgrade, although Word crashed the first time I opened it. (Maybe a coincidence.)
The biggest annoyance for me right now is that fink and darwinports are partially broken. Ethereal continued to run (which was not expected), but glib appears to be broken so irssi won't run for me right now. That's OK, I needed an IRC break anyway.:)
Zomax mostly serves customers in the computer hardware manufacturing and software publishing industries. It provides replication, telemarketing, and fulfillment services to software giant Microsoft, which accounts for about 22% of the company's sales. Another 19% come from Dell. Zomax operates through facilities in North America and Europe.
Seems legit, although aren't they breaking the law by not supplying a legitimate phone number? My registrar send me ominous messages about once a year about how I am LEGALLY REQUIRED TO KEEP MY CONTACT INFO UP TO DATE, blah blah blah....
I agree. I just booted my 1.5GHz Powerbook, 1.2GB RAM.
Power-on to login screen: 59 seconds.
Enter on login to finished login: 29 seconds.
Now, the nice thing about OSX is that you generally don't have to reboot ever unless there is an OS update, so I boot about once a month (for the point updates and security updates). OSX resumes *instantly* from sleep, which is really nice.
Re:Anyone really using XServes?
on
Return of the Mac
·
· Score: 4, Informative
I'm a pre-sales SE for Apple Enterprise Sales (USA). If you fill out this form:
and mark that you are a business, I guarantee that someone from Apple direct sales will call you.
We've got a large, growing enterprise direct sales organization that's ready to work with big customers. I'm ex-Novell, and my co-workers are ex-Oracle, ex-NetApp, and generally ex-big enterprise companies. In fact, I can only think of one guy in our group who is "old" Apple. We send him all the OS9 questions.:)
The mac mini comes with a tiny DVI to VGA adapter, so I'm not sure what DVI buys you, especially for an eyepiece that is probably 800x600 max.
But I could be missing something, is there a reason you need DVI and not VGA? It seems like in a car-mounted or wearable environment you wouldn't care about perfect video quality so much.
Slashdot Mirror
Don't confuse my humor with facts. :)
Step 1: Start Drama with book author on Yahoo Groups list.
Step 2: Submit a bitter, mean spirited, personal attack disguised as a book review to Slashdot.
Step 3: ?????
Step 4: Profit.
(Disclaimer: Don't know either of them. Actually thought, based on the review, that the reviewer was writing his own podcast book and was back-channel promoting it while tearing down another book. Found the thread in the google search trying to validate this. Actually proud of reviewer for creative flaming strategy and wish I had though of that first.)
In the software industry, the common example of thinking at the wrong level is a team of rock star programmers who can make anything, but don't really know what to make: so they tend to build whatever things come to mind, never stopping to find someone who might not be adept at writing code, but can see where the value of their programming skills would be best applied
Well, that explains Daikatana
You couldn't be more wrong.
To be fair, I can think of many ways in which he could be more wrong. For example:
100% of the gaming world will be using chips grown from genetically-engineered bananas in the next year - year and a half
I think we all can agree that this is more wrong than the original statement.
Well, you can think what you want, but I'm not a paid Apple shill surfing Slashdot for posting opportunities. I saw the story go up, and since I do cluster pre-sales at work, I thought I had some topical comments. I even mentioned running Linux on the Xserves. :)
What the heck are you talking about?
Well, the Workgroup Cluster is really turn-key. It comes with everything, ethernet cables, ethernet switch, a small rolling rack, etc... and includes the Bioteam iNquiry software on disk images, so you just load the images and go.
:)
So, fair enough with the marketing comment. I do technical pre-sales for Apple, so I've really touched and used this stuff. If you do have any techie questions, fire away.
Well, he's complaining about something quite minor, which is just having to uncheck the updates you don't what when you run an update. By comparison, in the Linux world Novell forces you to purchase Red Carpet update service for the same feature, and I believe Red Hat does the same with RHEL.
So, I'm not sure why all the hate. The software update server is bundled with Tiger Server, which you can get for as little as $500.
Tiger Server lets you run your own Software Update Server, which would solve this problem for you. You run a central update server, point all your servers and clients at that, and then you can approve or disapprove each update before it goes out.
That's simply not true. We stock parts for all Apple equipment for at least seven years. The drive caddys for the old Xserve G4 are exactly the same as what we ship in the current Xserve RAID, so not only is the drive caddy still available, it's also still in use.
Actually, the cheapest way to go would be to buy the 250GB ADM, apple part number M9356G/A, and pull out the 250GB drive and use it somewhere else (or just use that drive). Service parts tend to be pricey (like everyone else).
At Apple we sell the Xserve Cluster node which has been used for clusters as large as the 1,566 node COLSA cluster. We also sell it in small turn-key configurations.
Probably the most interesting news lately for OS X for HPC is the inclusion of Xgrid with Tiger. Xgrid is a low-end job manager that comes built-in to Tiger Client. Tiger Server can then control up to 128 nodes in a folding@home job management style. I've seen a lot of interest from customers in using this instead of tools like Sun Grid Engine for small clusters.
You can find some good technical info on running clustered code on OS X here.
The advantage of the Xserve is that it is cooler and uses less power than either Itanium or Xeon, and it's usually better than Opteron depending on the system. In my experience almost all C or Fortran code runs fine on OS X straight over from Linux with minimal tweaking. The disadvantage is that you only have one choice: a dual-CPU 1U box - no blades, no 8-CPU boxes, just the one server model. So if your clustered app needs lots of CPU power it might not be a good fit. For most sci-tech apps, though, it works fine.
If you're against OSX but still like the Xserve, Yellow Dog makes an HPC-specific Linux distro for the Xserve.
Because it's a smaller die? I'm not sure, actually, I'll see what I can find out.
Well, actually sales and marketing are quite different. And pre-sales technical SE and marketing are quite a bit different.
We get involved in a lot of practical deployments, like most SE's in reseller organizations, and most corporate enterprise SE's in large companies.
So it's fair to say that I have less real-world experience than, say, an Oracle DBA doing large enterprise deployments, it's completely unfair to say that I never get my hands dirty. I talk to customers every day and help them with real world deployment issues.
Hi Dan!
In our space, you never win. You don't have large-memory capabilities or redundant PSUs. That, combined with the lack of a supported Linux distro, makes XServe a non-starter.
:)
Well, that's certainly not true. We certainly sell a lot of units as DB servers, web servers, scientific clusters, etc. If you're making an Oracle RAC, then the individual pieces aren't important. You can see the success stories on our websites. Oh wait, biased!
Does DB2, Oracle, or MSSQL run on your systems?
Yes.
Don't post marketing on Slashdot.
Oh please, you're making a tempest in a teapot over a performance white paper. Ok, forget that. Your HP server in a dual CPU configuration uses 2x the power and 3x the cooling, based on vendor numbers. And get's 40% to 60% more performance. Maybe that makes sense for some customers. Maybe not.
You can be a zealot all you want, I know what my customers are doing with their servers. And you obviously know what yours are doing too.
Try getting Oracle to run on OS X server.
:)
Been there. Done that.
Agreed. The only real benchmark is in-house testing with the actual app. But, see the previous reply where the poster is getting 20% to 30% more performance with a system with 2x more power draw and 3x more heat.
Like I said, in my experience the Xserve usually wins in price/performance if the cost of cooling and power matter. In many cases departments in corporations and universities don't pay for their own power or cooling, so they don't care. Which is too bad, but the article was about power draw, which is why I piped up in the first place.
This isn't marketing trickery, the PPC970 just runs cooler and the Xserve is well-engineered. I wish more people would check them out.
Oh hey, one more followup. Since you mentioned the HP DL585 I configured that in a dual CPU config versus the dual CPU Xserve using the specs here and the "marketing document" I linked earlier for the Xserve.
Here's what I got:
DL585 800 Watts Max 2730 BTU Max
XServeG5 290 Watts Max 990 BTU Max
So, for 20% to 30% more performance, according to your numbers, you use 2x the power and 3x the cooling by using the HP DL585. In some cases that may make sense for the customer, in some cases in won't. But, I do think it illustrates my point that the Xserve often has better price/performance when you factor in power and cooling expense.
No, it's not. It's an Apple marketing piece. As is the other iterm that you linked.
:)
:)
:)
:)
Actually, the other item I linked was the support article showing the actual power draw and BTU's generated. I guess you didn't actually click through and read it. That's OK, it's Slashdot.
Let me guess, you work for Apple?
Yes. And you?
It can also win on applications that use lots of memory bandwidth. Databases, for example, are almost always bandwidth-hungry. So are distributed filesystems. Many technical and scientific computing applications are also memory-bound.
True. What I said is also true, especially since it was about my experience with my customers. Empirically true. How about you? In your experience what's the mix between memory bound and cpu bound applications?
Our mileage does vary. My company has compared PPC970, Xeon, and Opteron using the SAN solution that we integrate, and Opteron is the clear winner. For database systems as well, Opteron is 20-30% faster than Xeon and PPC970.
Yes, indeedy, just like I said. How about price/performance versus cost of heating and cost of power? This was an article about power draw, after all.
Also, you have a CPU-bound SAN solution? Tell me more.
It's great that you're picking the real-world winner based on testing. That's exactly what you should do. In my experience we win sometimes and Opteron wins sometimes, but we usually win on price/performance when factoring in the cost of power and cooling for large systems.
Moreover, XServe doesn't support more than 8GB of memory. That's simply not enough for our customers. Heck, the 64GB provided by HP's DL585 *still* isn't enough.
You are incorrect. I would link you to the correct specs but you'd dismiss them as a marketing piece.
Look, Apple has some nice products, but without a true commercially-supported Linux distro, it's hard to sell your product. People buying servers want Linux or Windows, and they want something that is supported by the vendor.
Funny, I thought we were selling a commercially-supported UNIX distro, and that our server sales were going up. I guess our customers are buying things they don't want!
Have a great day, and try to relax a little.
The G5 (PowerPC 970) has similar specs. I haven't seen new wattage numbers on the new 2.7GHz models, but I imagine they are similar. The PPC970 draws about 40 watts as far as I know.
Here's a recently updated performance benchmark on the G5.
More important are power draws and BTU's for the entire system. I've done some comparisons between the Apple Xserve and competing Opteron/Xeon/Itanium2 systems for customers, and the Xserve is usually better at total power consumption and generates less heat. Our numbers are published here. Performance numbers between cross-platform code running on an Xserve and on a comparable dual-CPU system are usually competitive, depending on what the test is. The Opteron can certainly win on synthetic benchmarks that test memory bandwidth due to the memory architecture, but most people don't actually need that bandwidth.
When testing actual customer code we're usually the same or better in performance, with lower power draw and less heat generation. As always, your mileage may vary.
There's a lot of stuff broken, although a lot of stuff still works (like Ethereal, as I mentioned). irssi is the biggest annoyance for me, and I think irssi is broken because glib is broken, but I could be wrong. I also couldn't get MySQL to install through fink on my Tiger client.
:)
I've heard many reports of different things being broken here and there. If the stuff you use works, then I guess you don't have any problems.
Everything I had loaded ran fine, including some APE stuff with a few haxies. Even GeekTool continued to run, which really surprised me. Office for Mac (2004) ran fine for me after the upgrade, although Word crashed the first time I opened it. (Maybe a coincidence.)
:)
The biggest annoyance for me right now is that fink and darwinports are partially broken. Ethereal continued to run (which was not expected), but glib appears to be broken so irssi won't run for me right now. That's OK, I needed an IRC break anyway.
http://www.hoovers.com/zomax-incorporated/--ID__51 171--/free-co-factsheet.xhtml
Zomax mostly serves customers in the computer hardware manufacturing and software publishing industries. It provides replication, telemarketing, and fulfillment services to software giant Microsoft, which accounts for about 22% of the company's sales. Another 19% come from Dell. Zomax operates through facilities in North America and Europe.
Seems legit, although aren't they breaking the law by not supplying a legitimate phone number? My registrar send me ominous messages about once a year about how I am LEGALLY REQUIRED TO KEEP MY CONTACT INFO UP TO DATE, blah blah blah....
I agree. I just booted my 1.5GHz Powerbook, 1.2GB RAM.
Power-on to login screen: 59 seconds.
Enter on login to finished login: 29 seconds.
Now, the nice thing about OSX is that you generally don't have to reboot ever unless there is an OS update, so I boot about once a month (for the point updates and security updates). OSX resumes *instantly* from sleep, which is really nice.
I'm a pre-sales SE for Apple Enterprise Sales (USA). If you fill out this form:
:)
http://programs.apple.com/contactme/xserve/
and mark that you are a business, I guarantee that someone from Apple direct sales will call you.
We've got a large, growing enterprise direct sales organization that's ready to work with big customers. I'm ex-Novell, and my co-workers are ex-Oracle, ex-NetApp, and generally ex-big enterprise companies. In fact, I can only think of one guy in our group who is "old" Apple. We send him all the OS9 questions.
The mac mini comes with a tiny DVI to VGA adapter, so I'm not sure what DVI buys you, especially for an eyepiece that is probably 800x600 max.
But I could be missing something, is there a reason you need DVI and not VGA? It seems like in a car-mounted or wearable environment you wouldn't care about perfect video quality so much.