An exclusive gaming industry community targeted
to, and designed for Professionals, Businesses
and Students in the sectors and industries
of Gaming, New Media and the Web, all closely
related with it's Business and Industry.
A Rich content driven service including articles,
contributed discussion, news, reviews, networking, downloads,
and debate.
We strive to cater for cultural influencers,
technology decision makers, early adopters and business leaders in the gaming industry.
A medium to share your or contribute your ideas,
experiences, questions and point of view or network
with other colleagues here at iVirtua Community.
\"No offence to the actual forums you visit, but I have visited HWA, which I see you post a lot at and I have tried to find intelligient posts and every topic I check out has a whole bunch of people who have no idea what they were talking about. I especially liked the topic predator posted about RAID-0 where everybody there clearly showed they had no idea what they were talking about.\"
I remember that discussion. Someone was saying that RAID 0 didn't offer any performance gains and that person was from another forum. I take it that was someone from here? Anyway, that is a joke and it is obvious that there is at least 1 person here that has no clue what they are talking about.
Anyway, my ears were burning and I wanted to confront the person that said that no one at HWA has any idea what they are talking about. My web site is located on MY computer that's sitting right beside me. I configured it as a server. I built the web pages. I built the CGI scripts. It also contains pictures of the new computer that I've recently built and the earlier PC that I modded. You can find my site here:
From what I see here currently, I have found a rented forum on a rented server and a bunch of ATI fans that are not accepting the fact that NVidia blew ATI out of the water.
As far as this particular debate goes, I want to see real results and not talk. It seems that's all ATI is good at. If they knew what they were doing, these promised products would have been here back in April...
Last edited by Blue on Tue Oct 11, 2005 8:43 pm; edited 1 time in total
That 'person' would be KoolDrew. He was from IFSZ at the time I posted that. This is not a rented forum, it is owned and created by me. The servers, I can choose whether or not to move the forum to another server of my choice, but that would be a waste of my time and money, so I choose to stick with InvisionFree's.
And secondly, we are not ATI fan boys. We admit that ATI was blown out this round, but you come in with no prior knowledge of the argument that was here before with PCGEEK.
He could not admit that a 6800GT at stock would lose to an X850XT PE in DirectX-powered games.
So, since you are so knowledgable, please tell me how accurate PCGEEK is, hmm?
If we were ATI fan boys, then why would I be buying a 6800GT and the other co-admin buying a 7800GT?
Contributed by Predator, Guest 510 iVirtua Loyalty Points • • • Back to Top
People have a right to there opinion right. Browse this Forum & you will soon realize that there are many intelligent people posting here. HWA is also the same way. And of course there are the few which like posting crap.
\"but you come in with no prior knowledge of the argument that was here before with PCGEEK.\"
I can't find that anywhere in this thread.
I was told that there was someone saying disrespectful things about people at HWA, so I came to see what was being said. When I read this thread, I noticed that it was true and there could possibly be even more things said that were \"cleaned\". I just thought that I would make an appearance and ask you to put your skills where your mouth is. If you can talk the talk, then walk the walk. PCGeek's scores with his 6800GT beat my x850 xt, so that should tell you something... Considering that I still have the card, you can't say that I'm lying. Check my web site pics if you don't believe me. You'll see the arctic freezer cooler on it in the blue PC.
Anyway, don't talk about people you don't know. They just might show up.
Last edited by Blue on Tue Oct 11, 2005 9:10 pm; edited 1 time in total
Hi Super! It's good to see you again. It looks like you're still doing good. How's the house?
I came here with the intentions of fighting, but things don't look too bad. Perhaps it was cleaned up? I don't know, but it fires me up when people say that I don't know what I'm talking about. I've spent too much time learning to put up with that.
Well, according to many review sites, the X850 XT wins over the 6800GT. Now you are talking about PCGEEK's 6800GT. PCGEEK knows his stuff. And I do admit that the 6800GT OC'ed better than the X850 XT.
But when we are talking about \"BONE STOCK\" the X850 XT wins. If the X800 XL keeps right up there side by side with the 6800GT, then what do you thing the X800 XT, XT PE & X850 XT will do?
ANyway, in regards the ATI's new X1800 XT, I am not very impressed. And I already explained it a few posts above.
Take Care,
Last edited by Super XP on Tue Oct 11, 2005 9:40 pm; edited 1 time in total
First of all, why are you typing in big, blue letters?
Quote:
Someone was saying that RAID 0 didn't offer any performance gains and that person was from another forum.
First I never said \"RAID-0 offered no benefit.\" RAID-0 does offer benefits, but the majority of the people that use it use it for the wrong reason and will not benefit at all from it.
Yes, when using a RAID-0 array your sustained transfer rate is increased by a lot, but the fact of the matter is that, in most situations, the drive spends the vast majority of the time reading and writing to its own buffer. The majority of the rest of the time is spent positioning the actuator to the read/write location. The actual time spent reading and writing data to a drives platter is pretty minute.
So, really the increase in sequential transfer rate does not translate to an increase in performance in most situations. RAID-0 may help substantially when doing something like video editing.. e.g. taking uncompressed video such as DV and adding/splicing/editing one or more addiitonal tracks will generally benefit from RAID0, but not necessarily by a huge amount. In this case, the ideal setup is to have the source files on one RAID0 array, and the target drive as another RAID0 array on another adaptor (a completely seperate bus).
If you are transcoding video, e.g. from avi/mpg - (and I wont ask what, or where from, but shall we say files around the 700mb mark from various usenet groups!) - to (s)vcd/mpeg2/dvd-mpeg, then RAID0 will be of no benefit. The disk drive will be waiting on the CPU to transcode the data. The only possible exception is when both source and target are on same drive, which is a daft idea and one is better off copying the source file to C: drive is that is the case.
When it comes to things like gaming, RAID-0 will offer little or no benefit and even in some cases may decrease performance because of the worsened seek times. The reason for this is because each drive has to seek to their portion of the data. Seek time is the dominating factor in most situations, because of this RAID-0 is bad for the OS (it is filled with small files) and the pagefile which is only read or written to in now larger then 64KB chunks.
RAID-0 may offer a performance advantage in some games, though. Such games benefit from RAID-0 because the maps are essentiall just large bitmaps and the higehr sequential transfer rate while using RAID-0 helps in this situations. This is because the hard drive is reading one large data file in a linear fashion as opposed to the heads having to move rapidly back and forth to access many different files. FPS games really would not benefit, and as I said, it may decrease performance because of the worsened seek times.
You also have to put into consideration that RAID-0 significantly reduces reliability. The failure of ANY disk will result in the complete loss of all data on the array. This doubles the probability of failure. A short-term glitch in the controller, cable or drive can cause the drive to be struck from the array, resulting is the loss of data. With a single drive, the system would retry a few times, abort the request, and probably get valid data on the next read. This SIGNIFICANTLY increases the probability of failure. In larger RAID-0 arrays, this is the largest cause of array failure.
There is also other things which may not be as important, but could be considered drawbacks by many. Such things include increased noise levels and power consumption.
RAID-0 does have its advantages in some areas, where the data files are huge and/or data requests are highly sequential in nature. However, data requests are not in most situations. So, don't assume RAID-0 offers a huge performance advantage just because of the increased sequential transfer rate. Using a RAID-0 array also significantly reduces reliability. So, RAID-0 appropriate for CERTAIN USES (where fast data transfer on large blocks of data I/O is important), but is a waste for most.
Do you want some more info to back up what I am saying if you do not belive me? Here you go:
Quote:
If you haven't gotten the hint by now, we'll spell it out for you: there is no place, and no need for a RAID-0 array on a desktop computer. The real world performance increases are negligible at best and the reduction in reliability, thanks to a halving of the mean time between failure, makes RAID-0 far from worth it on the desktop. http://www.anandtech.com/storage/showdoc.aspx?i=2101
Quote:
The enthusiasm of the power user community combined with the marketing apparatus of firms catering to such crowds has led to an extraordinarily erroneous belief that striping data across two or more drives yields significant performance benefits for the majority of non-server uses. This could not be farther from the truth! Non-server use, even in heavy multitasking situations, generates lower-depth, highly-localized access patterns where read-ahead and write-back strategies dominate. Theory has told those willing to listen that striping does not yield significant performance benefits. Some time ago, a controlled, empirical test backed what theory suggested. Doubts still lingered- irrationally, many believed that results would somehow be different if the array was based off of an SATA or SCSI interface. As shown above, the results are the same. Save your time, money and data- leave RAID for the servers! http://storagereview.com/articles/200406/20040625TCQ_6.html
Quote:
I noticed no change in load up times across the board in the games ( except for Far Cry). Stipe size made no real difference in how long it took to load the levels. As to how Raid-0 stacks up against a single raptor... the only difference is in the benchmark scores... other then that.... in real world use... there is NO REAL IMPROVEMENT in load up times. http://www.ocforums.com/showthread.php?t=310250
There are plenty of other ones that prove what I am saying is true.
Quote:
I take it that was someone from here?
It was me, but the discussion was actually at another forum.
Quote:
Anyway, that is a joke and it is obvious that there is at least 1 person here that has no clue what they are talking about.
If I actually said \"RAID-0 offers no benefits,\" then I would agree that I was wrong, but I didn't.
Quote:
Anyway, my ears were burning and I wanted to confront the person that said that no one at HWA has no idea what they are talking about. You can find my site here. It is located on MY computer that's sitting right beside me. I configured it as a server. I built the web pages. I built the CGI scripts. It also contains pictures of the new computer that I've recently built and the earlier PC that I modded.
Ok, what does this prove?
Quote:
From what I see here currently, I have found a rented forum on a rented server and a bunch of ATI fans that are not accepting the fact that NVidia blew ATI out of the water.
How are any of us ATI fans? In this thread Predator and I have been saying ATI wins in D3D and nVidia wins in OpenGL. This is a proven fact. Anybody who says nVidia is better then ATI (or vice versa) is just plain ignorant.
Quote:
As far as this particular debate goes, I want to see real results and not talk. It seems that's all ATI is good at. If they knew what they were doing, these promised products would have been here back in April...
Look at any benchmark of an OpenGL game (Doom 3 maybe?) and nVidia will win. Look at a D3D benchmark (HL2 maybe) ATI will win. Of course, when comparing cards that are comparable in performance (not 6800GT vs X700 Pro).
Quote:
PCGeek's scores with his 6800GT beat my x850 xt, so that should tell you something
It proves nothing. PCGEEK was trying to argue that ATi does not perform better in D3D games. Other benchmarks mean nothing when it comes to this discussion.
Also, I was talking about HWA as a whole. Seriously, when I go there I really don't see many intelligient posts at all. There may be a few very intelligient people there, but I am talking about the forum as a whole. I never said any particular person there (besides PCGEEK in the past) didn't know what they were talking about.
Quote:
KoolDrew read one or two of the threads in HWA and jumped to that conclusion.
It was MUCH more then one or two threads. The majority of the posts there back up my conclusion.
Last edited by KoolDrew on Wed Oct 12, 2005 6:46 pm; edited 1 time in total
\"First of all, why are you typing in big, blue letters?\"
1. Have you ever listened to that song called, \"Blue\"? 2. I bet you can easily see which part of the post is mine and which is quoted. ;)
\"First I never said \"RAID-0 offered no benefit.\" RAID-0 does offer benefits, but the majority of the people that use it use it for the wrong reason and will not benefit at all from it.
Yes, when using a RAID-0 array your sustained transfer rate is increased by a lot, but the fact of the matter is that, in most situations, the drive spends the vast majority of the time reading and writing to its own buffer. The majority of the rest of the time is spent positioning the actuator to the read/write location. The actual time spent reading and writing data to a drives platter is pretty minute.
So, really the increase in sequential transfer rate does not translate to an increase in performance in most situations. RAID-0 may help substantially when doing something like video editing.. e.g. taking uncompressed video such as DV and adding/splicing/editing one or more addiitonal tracks will generally benefit from RAID0, but not necessarily by a huge amount. In this case, the ideal setup is to have the source files on one RAID0 array, and the target drive as another RAID0 array on another adaptor (a completely seperate bus).
If you are transcoding video, e.g. from avi/mpg - (and I wont ask what, or where from, but shall we say files around the 700mb mark from various usenet groups!) - to (s)vcd/mpeg2/dvd-mpeg, then RAID0 will be of no benefit. The disk drive will be waiting on the CPU to transcode the data. The only possible exception is when both source and target are on same drive, which is a daft idea and one is better off copying the source file to C: drive is that is the case.
When it comes to things like gaming, RAID-0 will offer little or no benefit and even in some cases may decrease performance because of the worsened seek times. The reason for this is because each drive has to seek to their portion of the data. Seek time is the dominating factor in most situations, because of this RAID-0 is bad for the OS (it is filled with small files) and the pagefile which is only read or written to in now larger then 64KB chunks.
RAID-0 may offer a performance advantage in some games, though. Such games benefit from RAID-0 because the maps are essentiall just large bitmaps and the higehr sequential transfer rate while using RAID-0 helps in this situations. This is because the hard drive is reading one large data file in a linear fashion as opposed to the heads having to move rapidly back and forth to access many different files. FPS games really would not benefit, and as I said, it may decrease performance because of the worsened seek times.
You also have to put into consideration that RAID-0 significantly reduces performance. The failure of ANY disk will result in the complete loss of all data on the array. This doubles the probability of failure. A short-term glitch in the controller, cable or drive can cause the drive to be struck from the array, resulting is the loss of data. With a single drive, the system would retry a few times, abort the request, and probably get valid data on the next read. This SIGNIFICANTLY increases the probability of failure. In larger RAID-0 arrays, this is the largest cause of array failure.
There is also other things which may not be as important, but could be considered drawbacks by many. Such things include increased noise levels and power consumption.
RAID-0 does have its advantages in some areas, where the data files are huge and/or data requests are highly sequential in nature. However, data requests are not in most situations. So, don't assume RAID-0 offers a huge performance advantage just because of the increased sequential transfer rate. Using a RAID-0 array also significantly reduces reliability. So, RAID-0 appropriate for CERTAIN USES (where fast data transfer on large blocks of data I/O is important), but is a waste for most.
Do you want some more info to back up what I am saying if you do not belive me? Here you go: QUOTE If you haven't gotten the hint by now, we'll spell it out for you: there is no place, and no need for a RAID-0 array on a desktop computer. The real world performance increases are negligible at best and the reduction in reliability, thanks to a halving of the mean time between failure, makes RAID-0 far from worth it on the desktop. http://www.anandtech.com/storage/showdoc.aspx?i=2101
QUOTE The enthusiasm of the power user community combined with the marketing apparatus of firms catering to such crowds has led to an extraordinarily erroneous belief that striping data across two or more drives yields significant performance benefits for the majority of non-server uses. This could not be farther from the truth! Non-server use, even in heavy multitasking situations, generates lower-depth, highly-localized access patterns where read-ahead and write-back strategies dominate. Theory has told those willing to listen that striping does not yield significant performance benefits. Some time ago, a controlled, empirical test backed what theory suggested. Doubts still lingered- irrationally, many believed that results would somehow be different if the array was based off of an SATA or SCSI interface. As shown above, the results are the same. Save your time, money and data- leave RAID for the servers! http://storagereview.com/articles/200406/20040625TCQ_6.html
QUOTE I noticed no change in load up times across the board in the games ( except for Far Cry). Stipe size made no real difference in how long it took to load the levels. As to how Raid-0 stacks up against a single raptor... the only difference is in the benchmark scores... other then that.... in real world use... there is NO REAL IMPROVEMENT in load up times. http://www.ocforums.com/showthread.php?t=310250\"
http://www.barefeats.com/hard38.html
\"Ok, what does this prove?\"
It proves that I'm very knowledgeable about computers and that my knowledge surpasses yours. :)
\"How are any of us ATI fans? In this thread Predator and I have been saying ATI wins in D3D and nVidia wins in OpenGL. This is a proven fact. Anybody who says nVidia is better then ATI (or vice versa) is just plain ignorant.\"
It looks like it from the way many here are saying how the x1800xt is beating 7800GTX in SLI.
\"Look at any benchmark of an OpenGL game (Doom 3 maybe?) and nVidia will win. Look at a D3D benchmark (HL2 maybe) ATI will win. Of course, when comparing cards that are comparable in performance (not 6800GT vs X700 Pro).\"
I guess you don't even want to consider resolutions, power used, and heat?
\"It proves nothing. PCGEEK was trying to argue that ATi does not perform better in D3D games. Other benchmarks mean nothing when it comes to this discussion.\"
Well, if it isn't written in the thread, then I can't see it...
\"Also, I was talking about HWA as a whole. Seriously, when I go there I really don't see many intelligient posts at all. There may be a few very intelligient people there, but I am talking about the forum as a whole. I never said any particular person there (besides PCGEEK in the past) didn't know what they were talking about.\"
It doesn't look like you go there very much. You certainly didn't show up to debate the RAID 0 issue and it looks as if you don't even know me, so it doesn't look like you have much to go on.
\"It was MUCH more then one or two threads. The majority of the posts there back up my conclusion.\"
lol There are some misinformed posts, but saying that an entire forum is filled with uneducated posts is uncalled for. If you can't back that up, then don't say it.
Digg Topic
Tag topic on On del.icio.us
Technorati Search
Post to Slashdot
