Guest Eugene

Western Digital Raptor WD1500

Recommended Posts

I am wondering, if TCQ/NCQ is such a detriment to single user performance, why is it left on for single user tests on all of the SCSI devices tested, while it is disabled on all SATA devices? TCQ/NCQ has a dramatic performance increase on all drives in multi-user scenarios, perhaps disabling it will help the SCSI devices compete in the single user tests. I know even my old LSIU160 has the option to disable tagged queues in its BIOS, surely these new fancy PCI-X cards have similar features, not to mention the option in windows device manager.

I am wondering what the results would be like.

Edited by SlipperyPete

Share this post


Link to post
Share on other sites

While TCQ/NCQ only has a small negative impact on IDE/ATA drives in single user scenarios, the impact is even less on SCSI drives, because the SCSI implementation of command queueing is more mature and carries less overhead. Disabling it really doesn't help much on SCSI, and will severely affect multi-user performance, as you mentioned.

The main reason SCSI drives fare relatively poorly for their cache size and mechanics is because they're optimised for the random seeks of multi-user loads rather than the localised seeks of single user loads. Put simplistically, it's a question of how much read-ahead caching you do, where more read-ahead caching helps single user loads but hinders multi-user loads, and vice versa. SCSI drives are expected to see multi user loads, while IDE/ATA drives are expected to see single user loads, and they are optimised accordingly.

Share this post


Link to post
Share on other sites
While TCQ/NCQ only has a small negative impact on IDE/ATA drives in single user scenarios, the impact is even less on SCSI drives, because the SCSI implementation of command queueing is more mature and carries less overhead. Disabling it really doesn't help much on SCSI, and will severely affect multi-user performance, as you mentioned.

The main reason SCSI drives fare relatively poorly for their cache size and mechanics is because they're optimised for the random seeks of multi-user loads rather than the localised seeks of single user loads. Put simplistically, it's a question of how much read-ahead caching you do, where more read-ahead caching helps single user loads but hinders multi-user loads, and vice versa. SCSI drives are expected to see multi user loads, while IDE/ATA drives are expected to see single user loads, and they are optimised accordingly.

Hi all,

I have read the entire test and all the pages but haven't find yet an answer to my questions.

I actually own two Cheetah 15K.4 36Gb HDD, I intented to change my controller (a poor hostraid 29320 A-R, ressource eater) because windows (XP64) starts up much faster (SCSI driver loading) with a common SATA seagate 250Gb drive than with my RAID 0 SCSI 15K.4 configuration and there also always seems to be a sort of small lag before the SCSI starts to read (hostraid computing ?).

After reading all the news/reviews from SR, I was surprised to see how the raptors seem to be good in single user environnement. My question is :

Should I maintain my Raid0 15K.4 configuration but now with a LSI Megaraid 320-2X 128MB Cache PCI-X 133MHz controller, or this is useless and I better should use the standard SATA controller (ASUS P5WDGS2 WS PRO motherboard) in Raid 1 with two Raptor 74GB.

The question is, finally, could the cheetah 15K.4, come back at top with a 128MB equipped controller ?

You have already partially answered.... but is this kind of idea intende to be tested ? The controller memory influence....

Both the ways would cost approximatly the same price, so what do you think ?

Share this post


Link to post
Share on other sites

I'm considering getting a WD1500 but I was wondering--how does it compare in performance to the Seagate 320GB 7200.10?

Eugene: As far as I've seen all the comparisons in the review and the Performance Database are to the 7200.9 series. Could the 7200.10 be added so we can get a comparative analysis?

Share this post


Link to post
Share on other sites
Guest 888
I'm considering getting a WD1500 but I was wondering--how does it compare in performance to the Seagate 320GB 7200.10?

Use the Seagate ES performance information which is included in database here. It is generally the same as 7200.10 (Yes there's 750GB model only in database but it will still give some glue what 320GB version also could do).

Or you can just use http://www.anandtech.com/storage/showdoc.aspx?i=2803 where's WD1500, 7200.10/320, 7200.10/750 and others compared in many many tests.

Share this post


Link to post
Share on other sites

I'm considering getting a WD1500 but I was wondering--how does it compare in performance to the Seagate 320GB 7200.10?

Use the Seagate ES performance information which is included in database here. It is generally the same as 7200.10 (Yes there's 750GB model only in database but it will still give some glue what 320GB version also could do).

Or you can just use http://www.anandtech.com/storage/showdoc.aspx?i=2803 where's WD1500, 7200.10/320, 7200.10/750 and others compared in many many tests.

Thanks. I forgot about the Anandtech article (I've read it before).

Share this post


Link to post
Share on other sites
Hi all,

I have read the entire test and all the pages but haven't find yet an answer to my questions.

I actually own two Cheetah 15K.4 36Gb HDD, I intented to change my controller (a poor hostraid 29320 A-R, ressource eater) because windows (XP64) starts up much faster (SCSI driver loading) with a common SATA seagate 250Gb drive than with my RAID 0 SCSI 15K.4 configuration and there also always seems to be a sort of small lag before the SCSI starts to read (hostraid computing ?).

After reading all the news/reviews from SR, I was surprised to see how the raptors seem to be good in single user environnement. My question is :

Should I maintain my Raid0 15K.4 configuration but now with a LSI Megaraid 320-2X 128MB Cache PCI-X 133MHz controller, or this is useless and I better should use the standard SATA controller (ASUS P5WDGS2 WS PRO motherboard) in Raid 1 with two Raptor 74GB.

The question is, finally, could the cheetah 15K.4, come back at top with a 128MB equipped controller ?

You have already partially answered.... but is this kind of idea intende to be tested ? The controller memory influence....

Both the ways would cost approximatly the same price, so what do you think ?

I have the same hard drives as Robur above, and I'm also debating to upgrading to the same controller card.

In short, I also need an answer to his question.

Can anyone please help us with this decision?

Thanks.

Edited by Dawgneck

Share this post


Link to post
Share on other sites

Hi all,

I have read the entire test and all the pages but haven't find yet an answer to my questions.

I actually own two Cheetah 15K.4 36Gb HDD, I intented to change my controller (a poor hostraid 29320 A-R, ressource eater) because windows (XP64) starts up much faster (SCSI driver loading) with a common SATA seagate 250Gb drive than with my RAID 0 SCSI 15K.4 configuration and there also always seems to be a sort of small lag before the SCSI starts to read (hostraid computing ?).

After reading all the news/reviews from SR, I was surprised to see how the raptors seem to be good in single user environnement. My question is :

Should I maintain my Raid0 15K.4 configuration but now with a LSI Megaraid 320-2X 128MB Cache PCI-X 133MHz controller, or this is useless and I better should use the standard SATA controller (ASUS P5WDGS2 WS PRO motherboard) in Raid 1 with two Raptor 74GB.

The question is, finally, could the cheetah 15K.4, come back at top with a 128MB equipped controller ?

You have already partially answered.... but is this kind of idea intende to be tested ? The controller memory influence....

Both the ways would cost approximatly the same price, so what do you think ?

I have the same hard drives as Robur above, and I'm also debating to upgrading to the same controller card.

In short, I also need an answer to his question.

Can anyone please help us with this decision?

Thanks.

I have a similar dilemma. What I can tell is that the onboard cache on your LSI controller will do a better job in random writes that are extremely common in a desktop environment in windows.

I have a LSI 320-1x with 2 fujitsu MAU 73gb drives on my current machine, which is outdated and run just fine for everyday use. Next month I'm building a gaming rig. For desktop performance raptors surpasses 10k scsi drives. With 15k setups, the performance of the sata raid controller matters. If u plan to not use a dedicated controller card, you are wasting your money on more than 2 drives.

I can tell you that the LSI controller is a wonderful little piece of hardware, expecially considering the time it came out (4.5 years ago!). I dont experience any delay in booting, except the controller initialization. OS used: xp32, 2003 server x32, vista32. Sorry the cpu is not 64 bit :D

This is what I'm planning to build:

Areca ARC-1210 pci-e controller. PCI-express has overall higher bandwith. Latest version comes with 256mb of ram onboard, which i find extremely good. Nothing beats it, period. 300€ well spent IMO.

4x WD raptor 150gb raid0 (i'm considering also using the 74gb models)

WD 5000KS or Seagate 1200.10 750GB as backup unit

This will run vista x64 home premium.

Share this post


Link to post
Share on other sites

Hi all,

I have read the entire test and all the pages but haven't find yet an answer to my questions.

I actually own two Cheetah 15K.4 36Gb HDD, I intented to change my controller (a poor hostraid 29320 A-R, ressource eater) because windows (XP64) starts up much faster (SCSI driver loading) with a common SATA seagate 250Gb drive than with my RAID 0 SCSI 15K.4 configuration and there also always seems to be a sort of small lag before the SCSI starts to read (hostraid computing ?).

After reading all the news/reviews from SR, I was surprised to see how the raptors seem to be good in single user environnement. My question is :

Should I maintain my Raid0 15K.4 configuration but now with a LSI Megaraid 320-2X 128MB Cache PCI-X 133MHz controller, or this is useless and I better should use the standard SATA controller (ASUS P5WDGS2 WS PRO motherboard) in Raid 1 with two Raptor 74GB.

The question is, finally, could the cheetah 15K.4, come back at top with a 128MB equipped controller ?

You have already partially answered.... but is this kind of idea intende to be tested ? The controller memory influence....

Both the ways would cost approximatly the same price, so what do you think ?

I have the same hard drives as Robur above, and I'm also debating to upgrading to the same controller card.

In short, I also need an answer to his question.

Can anyone please help us with this decision?

Thanks.

I have a similar dilemma. What I can tell is that the onboard cache on your LSI controller will do a better job in random writes that are extremely common in a desktop environment in windows.

I have a LSI 320-1x with 2 fujitsu MAU 73gb drives on my current machine, which is outdated and run just fine for everyday use. Next month I'm building a gaming rig. For desktop performance raptors surpasses 10k scsi drives. With 15k setups, the performance of the sata raid controller matters. If u plan to not use a dedicated controller card, you are wasting your money on more than 2 drives.

I can tell you that the LSI controller is a wonderful little piece of hardware, expecially considering the time it came out (4.5 years ago!). I dont experience any delay in booting, except the controller initialization. OS used: xp32, 2003 server x32, vista32. Sorry the cpu is not 64 bit :D

This is what I'm planning to build:

Areca ARC-1210 pci-e controller. PCI-express has overall higher bandwith. Latest version comes with 256mb of ram onboard, which i find extremely good. Nothing beats it, period. 300€ well spent IMO.

4x WD raptor 150gb raid0 (i'm considering also using the 74gb models)

WD 5000KS or Seagate 1200.10 750GB as backup unit

This will run vista x64 home premium.

Telstar, thanks for your input.

Based on SR's reviews and forum member comments, as of this moment I think I will purchase one WD1500 for my main boot drive, and I am debating several 15k Cheetahs or Atlas 15II drives for everything else.

I am looking for faster boot and program start times. I believe the Raptor is best for this, but if the LSI/Cheetah or Atlas 15II would be better, please advise.

I plan to use my system for everything from Photo and HD film editing (Photoshop and Avid Media Composer) to minor gaming and music editing. I also consider myself a power user. I will use the SCSI drives for archiving programs and working with the HD digital media.

Outside of the reliability issue, I am still on the fence about the need to continue using SCSI drives when the Raptor seems to be today's rave.

I am really thinking about totally ditching SCSI, especially since the WD1500 is the same size as the SCSI units.

I sure wish I could make up my mind, but that's shy we visit this site.

What is your thoughts?

Share this post


Link to post
Share on other sites

I noticed Huge difference in the two 150GB models, Raptor WD1500ADFD and Raptor X WD1500AHFD

1st the MTBF: ADFD 1.2 Million Hours MTBF

AHFD according to their site MTBF is unknown, you said 600.000 which is the half!!

2nd Acoustics!!

ADFD:

Idle Mode 29 dBA (average)

Seek Mode 0 36 dBA (average)

AHFD:

Idle Mode 39 dBA (average)

Seek Mode 0 46 dBA (average)

So you pay more for something that is worst!! Great strategy from WD... :angry:

Edited by iron_gr

Share this post


Link to post
Share on other sites

What about the reliability of the disks? I have had such bad luck with other WD-drives and said "never more a WD". But now it's really tempting to buy this ultrafast drive, since the harddrives really are the bottlenecks in my system.

But this (from the article) is not promising:

"According to filtered and analyzed data collected from participating StorageReview.com readers, the Western Digital Raptor WD1500 is more reliable than 12% of the other drives in the survey that meet a certain minimum floor of participation.

According to filtered and analyzed data collected from participating StorageReview.com readers, a predecessor of the Western Digital Raptor WD1500, the Western Digital Raptor WD740GD , is more reliable than 94% of the other drives in the survey that meet a certain minimum floor of participation."

So it's at the bottom 12%, compared to the top 6% by the WD740GD? If that is the case I would stay away from it , just like any WD since my bad luck with them. And it's just not me. A friend of mine has also experienced bad WD;s. We must be really unlucky... :unsure:

Share this post


Link to post
Share on other sites

Hi all. Long time no see. I was going to replace my RAID0 Seagate Barricudas (3 of them) with 4 Raptors (Raptor already used for boot). I will lose some space, but 600 gig would still be sufficient. I thought this was a no-brainer, but I've read claims that Raptors are actually inferior for long, sustained reads/writes.

This would seem ridiculous on its face. The only issue with such r/w's would be the SATA1 limit for the Raptor. But SATA1 limits will not be exceeded by any of today's drives. I have read suggestions that if one RAID0's enough Raptors, the speed limit would be reached, but that seems, again, absurd, as the limit pertains to each drive's individual connection to the bus, not to the speed of the drives RAIDed.

Anyway, if some hard drive brainiac can confirm my take I would be greatful. My system is designed for extended file read/writes, as I use it for statistics on huge data sets. Thanks to the great advice I've gotten here, my system is the envy of everyone who knows anything.

Share this post


Link to post
Share on other sites
Hi all. Long time no see. I was going to replace my RAID0 Seagate Barricudas (3 of them) with 4 Raptors (Raptor already used for boot). I will lose some space, but 600 gig would still be sufficient. I thought this was a no-brainer, but I've read claims that Raptors are actually inferior for long, sustained reads/writes.

This would seem ridiculous on its face. The only issue with such r/w's would be the SATA1 limit for the Raptor. But SATA1 limits will not be exceeded by any of today's drives. I have read suggestions that if one RAID0's enough Raptors, the speed limit would be reached, but that seems, again, absurd, as the limit pertains to each drive's individual connection to the bus, not to the speed of the drives RAIDed.

Anyway, if some hard drive brainiac can confirm my take I would be greatful. My system is designed for extended file read/writes, as I use it for statistics on huge data sets. Thanks to the great advice I've gotten here, my system is the envy of everyone who knows anything.

What exactly do you do with these huge data sets? Unless you keep copying it around, and actually need to access certain bits of it, the Raptor's seek time will help you. Otherwise, yes, the Raptors ARE inferior for long sustained reads and writes and have been for a bit of a while now. There are 7200rpm SATA drives now that AVERAGE faster than the Raptor is in its fastest zone.

As for the little note about the SATA1 interface being a limit, you are right, that is for each drive so whoever was saying that you'll reach the limit by using RAID was indeed flat out wrong.

Share this post


Link to post
Share on other sites
Hi all. Long time no see. I was going to replace my RAID0 Seagate Barricudas (3 of them) with 4 Raptors (Raptor already used for boot). I will lose some space, but 600 gig would still be sufficient. I thought this was a no-brainer, but I've read claims that Raptors are actually inferior for long, sustained reads/writes.

This would seem ridiculous on its face. The only issue with such r/w's would be the SATA1 limit for the Raptor. But SATA1 limits will not be exceeded by any of today's drives. I have read suggestions that if one RAID0's enough Raptors, the speed limit would be reached, but that seems, again, absurd, as the limit pertains to each drive's individual connection to the bus, not to the speed of the drives RAIDed.

Anyway, if some hard drive brainiac can confirm my take I would be greatful. My system is designed for extended file read/writes, as I use it for statistics on huge data sets. Thanks to the great advice I've gotten here, my system is the envy of everyone who knows anything.

What exactly do you do with these huge data sets? Unless you keep copying it around, and actually need to access certain bits of it, the Raptor's seek time will help you. Otherwise, yes, the Raptors ARE inferior for long sustained reads and writes and have been for a bit of a while now. There are 7200rpm SATA drives now that AVERAGE faster than the Raptor is in its fastest zone.

As for the little note about the SATA1 interface being a limit, you are right, that is for each drive so whoever was saying that you'll reach the limit by using RAID was indeed flat out wrong.

Sorry for the delay in my response, Fedor. I do data management and analysis on big data sets (say, 1 gig to 40 gigs). This would entail things like merging data sets, sorting them, writing new ones that are subsets of the old ones. I would create new variables from existing ones. Examples of analyses I would run would be linear regression, logistic regression, and survival analysis. My main program is SAS (http://www.sas.com/). It reads and writes data sequentially, record by record. For my current raid I'm using Barricudas (7200.10).

I suppose I could just buy a Raptor and time the same data task on it vs. a single Barricuda, assuming the results for a 1-to-1 matchup should be the same as for a 3-to-3 matchup.

Share this post


Link to post
Share on other sites

It's been about 15 months or so now, are there any reputable rumors as to the next size increase? I'd say a 300GB 10k Raptor is overdue, given that 1TB 7200 drives are roughly comparable in speed now. I haven't found anything like a roadmap. I know that there were about two years between the 75GB and 150GB model, but I'm seeing very little merit to getting the 150GB model, if any at all.

Share this post


Link to post
Share on other sites
It's been about 15 months or so now, are there any reputable rumors as to the next size increase? I'd say a 300GB 10k Raptor is overdue, given that 1TB 7200 drives are roughly comparable in speed now. I haven't found anything like a roadmap. I know that there were about two years between the 75GB and 150GB model, but I'm seeing very little merit to getting the 150GB model, if any at all.

Frank, I'm not sure who you're directing this to... It seems there is much less traffic on SR than there used to be, and people don't seem to care anymore about this hardware.

It's really, really, really frustrating.

Share this post


Link to post
Share on other sites

I haven't seen any reliable rumors about a 300 GB Raptor drive. I did read something about an upcoming Raptor refresh (I think it was here), but nothing about the capacity.

You're unlikely to ever see a published roadmap from any HDD maker at any rate. They release them to certain key customers, but even those are considered confidential information and subject to change.

Share this post


Link to post
Share on other sites
I haven't seen any reliable rumors about a 300 GB Raptor drive. I did read something about an upcoming Raptor refresh (I think it was here), but nothing about the capacity.

That's kind of a bummer, a refresh of the same capacity is plausible because the 75 and 150GB were apparently refreshed a couple times each.

Maybe they're too worried about losing sales of SAS drives, but I'm not going to buy an adapter card to make SAS work. I wouldn't mind paying more for the speed, but for what I want, I'm just not seeing a performance reason to buy one of the 150GB units, it doesn't look like I'd even notice any difference vs. a leading 1TB 7.2k unit.

Edited by Frank32

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now