There was a write up a few months ago featuring my machine...
http://windowshelp.microsoft.com/windows/en-us/Help/60d9b045-e2fe-4f7a-9111-e2f2222851991033.mspx
Saturday, September 8, 2007
Wednesday, September 5, 2007
Vacation
For anyone that is actually still subscribed to this blog... lol you know I've taken a bit of a vacation.
Here are a few updates!
When I built this machine last year I had expected that I would be upgrading to two 8 core processors. This unfortunately has not happened due to AMD seriously slipping on their delivery schedule for the Phenom line. At the moment it looks as if there is going to be a serious wait for those of us who wish to take advantage of 8 cores. I'm really disappointed by these turn of events. So much for the 4x4 becoming a "platform". More information about the release schedule is available here. I think I'm tempted to wait for the FX-91 to launch. I can't really see the benefits of taking a step back in MHz. Of course, clock is not everything but...
When I make the move to 8 cores it will be time for a disk upgrade as well. One of the issues that the current machine faces is that a large number of processes causes excessive I/O and effectively limits the capacity of the machine. Vista indicates a ling queue length. A good example of this is running 3 or four virtual machines in addition to "normal" development tasks. I've been exploring options. At the moment, out and deep come to mind. I'm thinking about adding another array and possibly trying a 3 disk RAID 0 to see if there is better performance. I'm not convinced that will alleviate queing issues though so it might be worth test (how?).
The drivers for the 8800 are now WHQL, there have not been too many issues with it. Upgrading using NVidia's package has been easy. I would not recommend using Windows update to upgrade the NVidia drivers, especially the storage drivers as I have had issues in the past. There is a new board package for the 680a although I'm really not too interested in "upgrading" anything that has to do with the RAID array. As they say "If it ain't broke don't fix it".
Performance monitoring still does not work correctly and I have no idea why.
The recently reported bug involving decreased network performance while playing audio under Vista affects this machine. It's really bad too. When transfering Multi-GB virtual machine images over the network I can get 107 MB/s peak and appx. 90 MB/s average between another Dell server with a RAID 0 array. The same transfer with audio playing will reduce the transfer speed to appx. 16 MB/s average. Terrible.
Overall the system continues to run well and continue to meet and exceed the demands that I place on it.
I'm still on the fence if I will move to the AMD chipset. We'll see if they are able to provide a compelling reason to make a move. Although, it looks like the 680a is largely dead. NVidia has already released a new version of the 680i chipset with more features. To be fair I'm not sure what they could add to the 680a besides SLI drivers that work!
LG
Here are a few updates!
When I built this machine last year I had expected that I would be upgrading to two 8 core processors. This unfortunately has not happened due to AMD seriously slipping on their delivery schedule for the Phenom line. At the moment it looks as if there is going to be a serious wait for those of us who wish to take advantage of 8 cores. I'm really disappointed by these turn of events. So much for the 4x4 becoming a "platform". More information about the release schedule is available here. I think I'm tempted to wait for the FX-91 to launch. I can't really see the benefits of taking a step back in MHz. Of course, clock is not everything but...
When I make the move to 8 cores it will be time for a disk upgrade as well. One of the issues that the current machine faces is that a large number of processes causes excessive I/O and effectively limits the capacity of the machine. Vista indicates a ling queue length. A good example of this is running 3 or four virtual machines in addition to "normal" development tasks. I've been exploring options. At the moment, out and deep come to mind. I'm thinking about adding another array and possibly trying a 3 disk RAID 0 to see if there is better performance. I'm not convinced that will alleviate queing issues though so it might be worth test (how?).
The drivers for the 8800 are now WHQL, there have not been too many issues with it. Upgrading using NVidia's package has been easy. I would not recommend using Windows update to upgrade the NVidia drivers, especially the storage drivers as I have had issues in the past. There is a new board package for the 680a although I'm really not too interested in "upgrading" anything that has to do with the RAID array. As they say "If it ain't broke don't fix it".
Performance monitoring still does not work correctly and I have no idea why.
The recently reported bug involving decreased network performance while playing audio under Vista affects this machine. It's really bad too. When transfering Multi-GB virtual machine images over the network I can get 107 MB/s peak and appx. 90 MB/s average between another Dell server with a RAID 0 array. The same transfer with audio playing will reduce the transfer speed to appx. 16 MB/s average. Terrible.
Overall the system continues to run well and continue to meet and exceed the demands that I place on it.
I'm still on the fence if I will move to the AMD chipset. We'll see if they are able to provide a compelling reason to make a move. Although, it looks like the 680a is largely dead. NVidia has already released a new version of the 680i chipset with more features. To be fair I'm not sure what they could add to the 680a besides SLI drivers that work!
LG
Friday, May 11, 2007
Driver Upgrade
NVidia has released a new driver package!
Drivers for x64 vista have been spotty to date but this update to nTune seemed to go a long way in providing me with decent system stats. It is also the only way we'll be able to OC the 8800.
http://www.nvidia.com/object/ntune_5.05.38.00.html
Also, new 8800 drivers were released on May 2nd!
http://www.nvidia.com/object/winvista_x64_158.18.html
The install process is easier. I can now play texas hold 'em with out that nasty flicker. Stay away from the DreamScene content though, it apparenly causes major issues.
**Note** I would highly recommend running all of the control panels as administrator, they seem to crash when they are not.
Drivers for x64 vista have been spotty to date but this update to nTune seemed to go a long way in providing me with decent system stats. It is also the only way we'll be able to OC the 8800.
http://www.nvidia.com/object/ntune_5.05.38.00.html
Also, new 8800 drivers were released on May 2nd!
http://www.nvidia.com/object/winvista_x64_158.18.html
The install process is easier. I can now play texas hold 'em with out that nasty flicker. Stay away from the DreamScene content though, it apparenly causes major issues.
**Note** I would highly recommend running all of the control panels as administrator, they seem to crash when they are not.
4x4 in the news
Some great news from Toms Hardware and TG Daily. Apparently AMD is showing off new boards and chipsets (something on my wish list):
http://www.tgdaily.com/content/view/31991/118/
Apparently our new motherboard platform will be called Wahoo.
And the 4 core processor? It's apparently 45nm and was demoed this week as well! It will be called "Agena".
http://www.tgdaily.com/content/view/31977/135/
Pretty exciting stuff!
News about R600 has been a little disappointing. Apparently AMD is releasing a model that is between the 8800 GTS and GTX but about the same price as the GTS. I believe the model is the 2900 XT. The monster card is the 2900 XTX which is supposed to be shipping around the same time as the board and processor parts.
It seems the ATI community is pretty happy about their drivers - encouraging. Hopefully ATI is doing the right thing and not developing their driver codebase on the fly.
Here is some info on the 2900's performance:
2900 XT Benchmarks
http://www.tgdaily.com/content/view/31991/118/
Apparently our new motherboard platform will be called Wahoo.
And the 4 core processor? It's apparently 45nm and was demoed this week as well! It will be called "Agena".
http://www.tgdaily.com/content/view/31977/135/
Pretty exciting stuff!
News about R600 has been a little disappointing. Apparently AMD is releasing a model that is between the 8800 GTS and GTX but about the same price as the GTS. I believe the model is the 2900 XT. The monster card is the 2900 XTX which is supposed to be shipping around the same time as the board and processor parts.
It seems the ATI community is pretty happy about their drivers - encouraging. Hopefully ATI is doing the right thing and not developing their driver codebase on the fly.
Here is some info on the 2900's performance:
2900 XT Benchmarks
Monday, April 30, 2007
Disk Disk Disk
I think the one of the upcoming challenges for the 4 and 8 core workstation market is going to be resolving a major problem for multi core systems. I/O contention.
In the 4x4 we have two processors with a total of four cores, soon to be 8. So much CPU - and yet I find that I still wait. So I must of course ask the question "What am I waiting for?". Invariably the answer is the hard drive. As I continuted to cogitate I realized now that the machine can run four concurrent processes - system or otherwise, and there can be 4 active threads ( minimum ) that would be able to and need access to the hard disk. Each thread on it's own is quite capable of saturating the hard disk with requests.
With 8 threads running concurrently we're going to have even more trouble feeding them the data that they need. It's an unfortunate scenario because there does not seem to be a decent answer.
For now I see the most viable option is to add between 4 and 8 disks to your system. I will elaborate.
To truly take advantage of the 8 cores I think that we'll need the following:
Drives Purpose
1/2 (R0) System Disk
1/2 (R0) Program Files
1/2 (R0) User Data
1/2 (R0) User application data (My Documents, Music, Etc.)
These are all areas that are accessed very frequently and demand a high level of I/O. The nvidia chipset has a large number of SATA slots, and it's possible that the designers were thinking that it would be wise to use them all. I can see now, why this is the case.
This is likely overkill - you could probably get away with using 2 of the 4 sets. But if you need and use Virtual Machines a 3rd or 4th set is not out of the question.
I suspect there would be performance boost, but I'm not entirely sure how we'd go about measuring this.
Just food for thought.
In the 4x4 we have two processors with a total of four cores, soon to be 8. So much CPU - and yet I find that I still wait. So I must of course ask the question "What am I waiting for?". Invariably the answer is the hard drive. As I continuted to cogitate I realized now that the machine can run four concurrent processes - system or otherwise, and there can be 4 active threads ( minimum ) that would be able to and need access to the hard disk. Each thread on it's own is quite capable of saturating the hard disk with requests.
With 8 threads running concurrently we're going to have even more trouble feeding them the data that they need. It's an unfortunate scenario because there does not seem to be a decent answer.
For now I see the most viable option is to add between 4 and 8 disks to your system. I will elaborate.
To truly take advantage of the 8 cores I think that we'll need the following:
Drives Purpose
1/2 (R0) System Disk
1/2 (R0) Program Files
1/2 (R0) User Data
1/2 (R0) User application data (My Documents, Music, Etc.)
These are all areas that are accessed very frequently and demand a high level of I/O. The nvidia chipset has a large number of SATA slots, and it's possible that the designers were thinking that it would be wise to use them all. I can see now, why this is the case.
This is likely overkill - you could probably get away with using 2 of the 4 sets. But if you need and use Virtual Machines a 3rd or 4th set is not out of the question.
I suspect there would be performance boost, but I'm not entirely sure how we'd go about measuring this.
Just food for thought.
L1N64-SLI WS Ethernet DOA Part 2
Well, it seems that the Ethernet DOA - was not.
Apparently the firmware for my motherboard was not properly initalized leaving the MAC address for the Ethernet in it's default (and invalid) state.
I found through the helpful advice of another reader that setting the MAC address manually in Vista allowed me to use the on-board ethernet. Whoo!
I was quite happy about this and immediately did some benchmarking with a server on my network that has a RAID 0 disk and a GbE controller. The result under Vista was an astonishing 92 MB/sec - very close to the benchmarked maximum read speed of my disks.
Apparently there is another ASUS BIOS update out there or possibly still in beta that will allow you to write the MAC address value directly to the firmware. However because setting the address manually worked I have not invested much time in exploring BIOS updates.
Of course there is a caveat - I found that running the same transfer 12 hours later yielded performance in the 18 - 24 MB/s range. I guess the dynamic TCP windowing capability of Vista is not that smart :(
My guess is that if 99% of your traffic is internet based then the window function will tend towards a much smaller MTU, and the advantatges of the large MTU will be lost over the local LAN. This is of course speculation - but the likelyhood that the dynamic windowing function is unaware of the context of the transmission (local LAN vs. WAN) is quite likely given where it would sit on the network stack to do it's job.
Bottom line: reboot for multi GB transfers over GbE.
An interesting note however is that there is a very noticeable difference between my onboard card vs. netgear card. The onboard completely outpaced the netgear card even after rebooting and retrying the transfers.
Apparently the firmware for my motherboard was not properly initalized leaving the MAC address for the Ethernet in it's default (and invalid) state.
I found through the helpful advice of another reader that setting the MAC address manually in Vista allowed me to use the on-board ethernet. Whoo!
I was quite happy about this and immediately did some benchmarking with a server on my network that has a RAID 0 disk and a GbE controller. The result under Vista was an astonishing 92 MB/sec - very close to the benchmarked maximum read speed of my disks.
Apparently there is another ASUS BIOS update out there or possibly still in beta that will allow you to write the MAC address value directly to the firmware. However because setting the address manually worked I have not invested much time in exploring BIOS updates.
Of course there is a caveat - I found that running the same transfer 12 hours later yielded performance in the 18 - 24 MB/s range. I guess the dynamic TCP windowing capability of Vista is not that smart :(
My guess is that if 99% of your traffic is internet based then the window function will tend towards a much smaller MTU, and the advantatges of the large MTU will be lost over the local LAN. This is of course speculation - but the likelyhood that the dynamic windowing function is unaware of the context of the transmission (local LAN vs. WAN) is quite likely given where it would sit on the network stack to do it's job.
Bottom line: reboot for multi GB transfers over GbE.
An interesting note however is that there is a very noticeable difference between my onboard card vs. netgear card. The onboard completely outpaced the netgear card even after rebooting and retrying the transfers.
Still here
To answer a readers question: we're still up and running. I've been running around quite a bit lately and it hasn't involved spending a lot of QT with my 4x4.
As we get closer to the AMD launch I'll be providing some details on AMD's support for the upcoming Barcelona platform as well as the new R600.
When the time comes we'll be documenting the upgrade from the FX-70 to the new Barcelona chips.
Believe it or not, I'll be needing the CPU!
As we get closer to the AMD launch I'll be providing some details on AMD's support for the upcoming Barcelona platform as well as the new R600.
When the time comes we'll be documenting the upgrade from the FX-70 to the new Barcelona chips.
Believe it or not, I'll be needing the CPU!
Subscribe to:
Posts (Atom)