Four X25-E Extreme SSDs Combined In Hardware RAID

theraindog writes "Intel's X25-E Extreme SSD is easily the fastest flash drive on the market, and contrary to what one might expect, it actually delivers compelling value if you're looking at performance per dollar rather than gigabytes. That, combined with a rackmount-friendly 2.5" form factor and low power consumption make the drive particularly appealing for enterprise RAID. So just how fast are four of them in a striped array hanging off a hardware RAID controller? The Tech Report finds out, with mixed but at times staggeringly impressive results."

Comments

Oh good

[LordKaT]

I'll be sure to do that, and replace them every 5 years when they run out of write operations.

Re:Oh good

[spazdor]

'cause regular hard drives usually survive 5 years in an enterprise environment, yep yep.

Re:Oh good

[LordKaT]

'cause SSD's don't cost $300-$500 more than their spindle counterparts, yep yep.

Re:Oh good

[CyprusBlue113]

Umm.... yes they do. You need to stop shopping for drives on Ebay.

Re:Oh good

[Anonymous Coward]

woosh!

Re:Oh good

[poot_rootbeer]

I'll be sure to do that, and replace them every 5 years when they run out of write operations.

Winchester drives, on the other hand, use a time-honored complex system of delicate moving parts, and last virtually forever. They certainly do not start experiencing sudden failures if kept in continuous service for more than 5 years.

Re:Oh good

[ChienAndalu]

Make that 228 years.

Life expectancy 2 Million Hours Mean Time Before Failure (MTBF)

Hint: learn about "wear leveling"

Re:Oh good

[spazdor]

Your enterprise environment must not be hitting its drives very hard.

Where SSDs is in disk operations that are usually lagged out by seek times; a big unwieldy database that gets a lot of writes and no downtime, for instance, is happiest when it lives on a striped SSD array.

Coincidentally, this is exactly the type of workload which is most likely to shorten a magnetic drive's life.

Re:Oh good

[FauxPasIII]

> 'cause SSD's don't cost $300-$500 more than their spindle counterparts, yep yep.

Hint: Enterprise storage purchasing often looks at dollars/IOPS rather than dollars/GB.

Re:Oh good

[Anonymous Coward]

in 5 years they wont

Re:Oh good

[spazdor]

er, "where SSDs shine is..."

Re:Oh good

[Anonymous Coward]

So are SSDs ready for prime-time?
Last year I attended IBM's Sydney Technical Conference and listened in to a presentation by ?????, one of the lead designer's of IBM's 3950 chipset.

Part of the presentation was on SSD technology. Whilst viewing the graphs showing SSD closing the gap in cents / gigabyte, someone asked the pointed question: "Is there any future in spinning platter technology?". The presenter actually stopped for well over half a minue (an age in public speaking) before replying carefully "I do not speak officially for IBM now, but I can see no future at all for spinning-platter technology. Not even for bulk storage"

As others have noted that once SSD drives are available in a price-competative form at volumes of around 150GB, tradditional drives will immediately and permamently exit the notebook market.

And I can wait for that to happen

Re:Oh good

[Anonymous Coward]

"Enterprise storage purchasing often looks at dollars/IOPS rather than dollars/GB."

Which is good news, as this Intel Slashdot advert says its "compelling value if you're looking at performance per dollar rather than gigabytes.".

Re:Oh good

[neoform]

I must be doing something wrong then. Should I put my computer in the freezer when I'm not using it or something, like, to keep it fresh longer?

Re:Oh good

[Piranhaa]

http://www.anandtech.com/cpuchipsets/intel/showdoc.aspx?i=3403&p=4

[quote]Given the 100GB per day x 5 year lifespan of Intel's MLC SSDs, there's no cause for concern from a data reliability perspective for the desktop/notebook usage case. High load transactional database servers could easily outlast the lifespan of MLC flash and that's where SLC is really aimed at. These days the MLC vs. SLC debate is more about performance, but as you'll soon see - Intel has redefined what to expect from an MLC drive.[/quote]

So.. 100GB/day/drive = 100GBx4 = 400GB/day for (5*365)= 400GB*1825(days) = 730TB of data transferred. If you seriously go through THAT much data, you are either a pirate or you actually own your own movie studio.

Obviously these numbers can change, based on case temperature, wear leveling, etc. HOWEVER, they are what Intel states the drives can handle...

Re:Oh good

[bluefoxlucid]

All modern hard drives are Winchester drives; Winchester drives are just the first iteration, made by IBM, who figured they'd ship two 30MB platters and name the hard drive after the Winchester 30-30 rifle. Who the hell modded you insightful, especially for claiming a system of delicate moving parts lasts virtually forever...

Re:Oh good

[JCSoRocks]

Who the hell modded you insightful, especially for claiming a system of delicate moving parts lasts virtually forever...

What about watches? /sarcasm

Re:Oh good

[Tubal-Cain]

Or replace them in 5 years because better drives are on the wholesale rack.

Re:Oh good

[msu320]

Make that 228 years.

Life expectancy 2 Million Hours Mean Time Before Failure (MTBF)

Hint: learn about "wear leveling"

Hint: you should learn what is meant by "Mean Time".

Re:Oh good

[CMonk]

I think you're comparing against SATA drives. People that worry about IOPS are normally using FC drives which are much more closely aligned in price with SSDs. (btw, been a while since I was in the market for FC drives)

Re:Oh good

[Piranhaa]

MTBF is a highly inaccurate way to show how long you should expect a drive to live. The whole Seagate Fiasco is a prime example of why NOT to believe them.

It can be a good ballpark figure, to differentiate between enterprise class drives and consumer drives, but should NOT be an expected number.

There are too many things to take into account: temperature surrounding the drive, how many days it's on for, how long per day it's on for, how many writes to the drive, how much voltage is supplied, etc etc..

More about it here: http://en.wikipedia.org/wiki/Mean_time_between_failures

Problems with MTBF As of 1995, the use of MTBF in the aeronautical industry (and others) has been called into question due to the inaccuracy of its application to real systems and the nature of the culture which it engenders. Many component MTBFs are given in databases, and often these values are very inaccurate. This has led to the negative exponential distribution being used much more than it should have been. Some estimates say that only 40% of components have failure rates described by this. It has also been corrupted into the notion of an "acceptable" level of failures, which removes the desire to get to the root cause of a problem and take measures to delete it. The British Royal Air Force is looking at other methods to describe reliability, such as maintenance-free operating period (MFOP). Similarly, the National Aeronautics and Space Administration (NASA) is pursuing time to failure research using scenario and condition based methods derived from the field of prognostics.

Re:Oh good

[Anonymous Coward]

Double woosh!

Re:Oh good

[bluefoxlucid]

They break down eventually... watch smiths fix them. A coworker just had her watch (about 10 years old) gutted and re-geared. Very nice hand-crafted piece.

Re:Oh good

[Anonymous Coward]

Does this take into account things like, half the drive is filled with stuff that doesn't change or does it imply nothing is on the drive and you just keep writing to it for no reason? ie that would drop those MTBF factors by half? Tried to wrap my brain around wear leveling and can't seem to grasp it.

Re:Oh good

[DMalic]

It's obvious sarcasm.

Re:Oh good

[Anonymous Coward]

Which require repair / reconditioning from time to time - no pun intended... okay - pun intended...

Re:Oh good

[djtachyon]

Let me know when MRAM gets to gigabyte sizes. With unlimited writes and running at SRAM speeds, it could be the future.

Re:Oh good

[wastedlife]

They must not have humor where you are from. The "Winchester drive" comment was obviously sarcasm, and the "watch" comment had "/sarcasm" at the end.

Re:Oh good

[Anonymous Coward]

The article that you point out is for the MLC NAND which is what you have shown. The NAND used in the X25-E series is SLC which has anywhere from 10x to 100x the write endurance.

Re:Oh good

[bluefoxlucid]

Obviously, sarcasm is +5 insightful rather than +3 funny.

Re:Oh good

[d'fim]

Yes.

Re:Oh good

[blueskies]

what about penises? (peni?)

Re:Oh good

[horza]

MTBF is a highly inaccurate way to show how long you should expect a drive to live. The whole Seagate Fiasco is a prime example of why NOT to believe them.

Misuse of a statistical figure is a problem with those misinterpreting it. Obviously things have changed since schools taught the difference between the mean, the mode, the median, and the minimum. If I run an ISP then MTBF is useful for me to calculate costs, both in replacements and labour costs. It's not supposed to be a measurement for consumers though that will be buying single unit quantities.

Buying a hard drive is like buying a washing machine. If I'm lucky it will go on practically for ever. On the other hand if I'm unlucky it could die tomorrow. As Piranhaa says, there are too many variables. All I can go on is that if it comes with a garauntee of 3 years then I assume the manufacturers have designed it to mostly exceed that figure otherwise they would end up losing money on the product. I still have to ensure I have a contingency plan in case it breaks down.

Phillip.

Re:Oh good

[RightSaidFred99]

Hint: You should learn that people tend to compare things using some "measure". In the disk world, that's MTBF. 2 million hours MTBF is comparable or better than other enterprise drives. Hence original poster is, indeed, clueless.

Re:Oh good

[RightSaidFred99]

Your point? It's a highly inaccurate way used on _all_ drives. The point is that these drives are as reliable or more than other enterprise drives.

Re:Oh good

[duckInferno]

ULTRA WHOOSH

Re:Oh good

[Retric]

Think of it like this let's say you have a 1MB log file that changes every hour, and 1 MB system file that never changed. You keep writing that log file to the same place until 1,000 times. The drive then says ok if that file is really volatile let's swap the log and system file so the log file is in a place that's been overwritten 2twice, and the system file is in a place that's over written ~1,000 times. You can then write to that log file 1,000 more times and now the average usage of the disk is ~1,000 times in both areas.

Re:Oh good

[sexconker]

Hint: Remember to include "Hint: you should learn what is meant by "failure"." when replying to morans who quote MTBF.

Hint: "Failure" means dying or doing stupid shit unexpectedly. If you're told to replace the drive ever year, or expect capacity to dwindle to 10% over the period, or other such nonsense, "failure" has a different meaning than what most people would think.

Re:Oh good

[htnprm]

EPIC WOOOOOOOOOOOSH.

Re:Oh good

[Spy Hunter]

Imagine a drive 99% full of unchanging data, and 1% full of constantly changing data. The wear leveler could, every X number of writes, move 1% of the unchanging data to expose a fresh section of drive for the changing data. There would be a small performance penalty that could easily be adjusted by changing various parameters, and the increase in drive lifetime would be more than worth it.

Now, I don't know specifically if the wear leveling algorithms used by Intel's SSDs or Samsung's SSDs or random Chinese OEM's SSDs actually do this, but it's certainly possible.

Re:Oh good

[urbanriot]

The MTBF is the same or better than other *enterprise* mechanical drives, at 1.2 - 2 million hours MTBF, let alone home user drives which are considerably less. Obvious troll fails.

Re:Oh good

[hasdikarlsam]

Oh, you can take it for granted that they use anything you can come up with in half an hour.

They probably do lots more complex stuff, too. ;)

Re:Oh good

[CarpetShark]

regular hard drives usually survive 5 years in an enterprise environment, yep yep.

Hardly a fair comparison. If an enterprise drive doesn't get stolen on the way out of dry dock, it surely won't be long before the thing is being attacked by Romulans.

Re:Oh good

[Anonymous Coward]

That's only because we don't have -1 Retard.

Re:Oh good

[Anonymous Coward]

I'll be sure to do that, and replace them every 5 years when they run out of write operations.

There are things that are read-mostly but still want large IOPS that are well suited for a Flash SSD - e.g. database indices, static web content, etc.

Also many database schema are split such that recent transactions are put in a log (e.g. the full inventory + deltas based on the day's transactions) and then there is a separate batch processing step to integrate the log into the main set of indices. This is often done only once a day as there are frequently complex business logic performed in this step that would kill transactional performance. So the log (and its associated indices) could be on magnetic media or RAM SSD, and the real indices could be on Flash SSD and you still wouldn't toast the SSD prematurely.

Re:Oh good

[H3g3m0n]

SSD drives are not as unreliable as people seem to think, It would take a *minimum* of 5 years of *continuous* writing and thats for the cheaper SSD's like you would find in a netbook rather than the $300 Intel top of the line ones, not to mention ones being used in a RAID would have a longer life.

Besides even if some blocks go bad you can map around them, the SSD itself might even do it.

Besides, you are unlikely to be using the same drive in 5 years time and magnetic drives have a much higher chance of failure, also when magnetic drives die often the entire drive dies at once, a few blocks failing is a much better solution.

In addition to that, the following is from the info on the SandDisc 3G drives: "The G3 SSDs provide a Long-term Data Endurance (LDE) of 160 terabytes written (TBW) for the 240GB version, sufficient for over 100 years of typical user usage.(2,3)", 4GB of writing a day is typical.

Re:Oh good

[WuphonsReach]

SSD drives are not as unreliable as people seem to think, It would take a *minimum* of 5 years of *continuous* writing and thats for the cheaper SSD's like you would find in a netbook rather than the $300 Intel top of the line ones, not to mention ones being used in a RAID would have a longer life.

Pretty sure that's only true for a drive that is empty. If the drive is half full, or even 75% full, the SSD has a lot less unused space to spread wear over. That can cut lifespan down to 1/4 of the original.

(Unless it's a really really good bit of firmware that moves rarely written blocks over to blocks that are frequently written during idle time.)

Re:Oh good

[drsmithy]

'cause SSD's don't cost $300-$500 more than their spindle counterparts, yep yep.

15k RPM drives and SSDs cost about the same on a $/GB basis, and on a $/IOP basis, SSDs absolutely wipe the floor.

Sadly, drop-in SSD replacements seem to be slow making into enterprise SANs. :(

Re:Oh good

[WuphonsReach]

On the more expensive drives maybe... but on the cheaper SSDs? Why should the low-cost drive maker pay for that complexity?

Re:Oh good

[Adriax]

M-M-M-MONSTER WOOOOSH...

Re:Oh good

[Anonymous Coward]

C-C-C-COMBO-BREAKER!!!

Re:Oh good

[spazdor]

The firmware is exactly how you suggest.

The 'wear leveling' actually shifts logical disk addresses around the physical media to account for the fact that different parts of the disk get different amounts of activity. Each physical storage element will get an equal turn holding the never-written data, given enough time.

Re:Oh good

[cerberusss]

That is a good idea, but the other half of the battle is ensuring that your PC gets fresh power. You can easily make sure of this by smelling close to the power outlet. Old power has a slightly, but distinctly musty smell, like French cheese.

Re:Oh good

[xouumalperxe]

I'd say that this post made a rather insightful point. The tone was quite sarcastic, but that doesn't in any way detract from the underlying point.

Re:Oh good

[profplump]

What you describe here doesn't necessarily do what the parent describes. It might exist, but I have yet to see an implementation of either that takes in-use sectors and moves them to not-in-use sectors.

Re-mapping not-in-use blocks and selecting the least-used blocks for writing is pretty easy, and can be 0-overhead in terms of main storage bandwidth. But remapping in-use blocks requires stealing at least one read and one write cycle for every block you move. Those extra cycles detract directly from the available disk bandwidth, and would drive impede performance; it hardly seems like the sort of thing a company touting the speed of the disks would do.

Re:Oh good

[profplump]

You're assuming the system file is re-written at some point, so that it's previous position becomes available. What happens if I have 50% of my disk full of data that won't ever be re-written over the life of the drive? Does the drive interrupt my writes, do some internally copying, and then let me access it again? It does, is there any way I can make it stop, so I don't have unpredictable delays related to garbage collection?

Re:Oh good

[profplump]

The "small performance penalty" is potentially tripling the amount of time it takes to write a block -- you have to read the old block, re-write the old block someplace else, and then write the new block. It doesn't happen every time, but it's quite a penalty when it does, and there's no parameter you can tune to make that penalty smaller. If you're rating drives in IOPS/$ there's no "idle" time to do housekeeping like this, and it results in a direct performance loss.

Re:Oh good

[Cormacus]

No, no, no good. You actually did some reading before you did some posting. Get out of here. Just go. Leave. You're not wanted here. // jk . . .

Re:Oh good

[xouumalperxe]

The point is that these drives are as reliable or more than other enterprise drives as measured with an inaccurate metric

In case I wasn't clear enough: "Yeah, I measured those two wall with my hand, and I'm 100% sure this one is bigger than than one by a hand's breadth."

Re:Oh good

[RightSaidFred99]

Uhhh, I don't like this car, it gets less than 1000 miles per gallon!

That's effectively what the original poster said. He pointed out having to "replace them every 5 years". Considering these drives have as good or better reliability compared to traditional enterprise drives - what's his point?

Re:Oh good

[Retric]

No, the controller will move the system file even it's just been sitting there for months.

Re:Oh good

[spazdor]

It doesn't need to happen nearly as often as the "real" disk activity. The disk could remap as few as 100 sectors a day and it would be enough to keep all the storage elements aging at about the same rate.

Re:Oh good

[Retric]

Also, the disk has a write cache so you can keep sending data even while it's moving data around. I don't think there is a universal implementation out there, but even normal HDD do the same type of stuff when it notices a sector is going bad. (I don't know the specific's on how that works, but look up Self-Monitoring Analysis and Reporting Technology or SMART HDD.)

Anyway, lazy writes are not a problem as long as you can read from the cache so I don't know how you would notice without doing some strange things with your data.

Re:Oh good

[spazdor]

Also, bear in mind that the swapping-around is done internally by the disk, and none of that information need ever be sent down the bus. There's no reason the disk couldn't do this asynchronously, without eating up any bandwidth at all.

Solid State Slashdot Drive.

[Ostracus]

"So just how fast are four of them in a striped array hanging off a hardware RAID controller? The Tech Report finds out, with mixed but at times staggeringly impressive results.""

So in other words I'll get First Post much faster since slashdot switched over.

Actually, that RAID card seems more interesting

[the_humeister]

A 1.2 GHz processor with 256 DDR2 memory? Holy crap! That's faster than my new Celeron 220! And the perennial quesion: can this thing run Linux?

Re:Actually, that RAID card seems more interesting

[Wonko the Sane]

That RAID card was the bottleneck. It can't support 4x the raw transfer rate of a single drive.

Re:Actually, that RAID card seems more interesting

[default luser]

Actually, I felt that the limiting factor was probably the craptastic single-core Pentium 4 EE they used to run all these benchmarks.

What, you shove thousands of dollars worth of I/O into a system, and run it through the paces with a CPU that sucked in 2005? I'm not surprised at all that most tests showed very little improvement with the RAID.

Re:Actually, that RAID card seems more interesting

[rcw-home]

What I want to know is if the RAID controller had a battery backup unit installed so write caching could be enabled. There is no BBU shown in the article's picture of the controller.

I recently built a new Exchange server with 6 X-25Ms (we couldn't get the 64GB X25-Es when we ordered it) hooked to a 3ware 9650 in three separate RAID1 arrays. Turning on write caching switches the whole feel of the system from disappointingly sluggish to there-is-no-way-these-tire-marks-were-made-by-a-'64-Buick-Skylark-convertible fast.

Re:Actually, that RAID card seems more interesting

[Anonymous Coward]

Well, there is NO enterprise that would run 4 SSDs in RAID0 or RAID5. None. It is stupid, you'd run them on RAID1 or, since we're talking 4 SSDs, RAID 10.

These guys are just a bunch of yahoos with lots of money to waste on SSDs.

Performance matters, but if reliability doesn't, it is done using RAM, dammit. It doesn't take a big ammount of brains to get that one. And nothing you will find in a datacenter takes less than 32GB of RAM nowadays.

Now, let's look at a *real* enterprise PoV.

We have already established that reliability matters, since we will not be using server RAM. This takes RAID0 and single-disk out of the picture.

Performance also matters a great deal, or we wouldn't be considering SSD instead of much cheaper SAS 15k RPM. That takes out anything that needs an engine, i.e. RAID5, RAID6, RAIDX, RAIDZ, etc.

The resulting set of acceptable configurations are: RAID1, RAID10 and friends.

And, of course, you should do such benchmarks with something resembling the type of server that would use SSDs. That means at least a 5400-series Xeon octa-core box, and AMD's to make it a bit easier (IBM p-series are really expensive, and so are the Sun boxes).

Re:Actually, that RAID card seems more interesting

[Anonymous Coward]

I thought the same thing when I saw the ICH7R chipset!

What I want to see

[XanC]

Is 4 of these in a RAID-1, running a seek-heavy database. Nobody does this benchmark, unfortunately.

Re:What I want to see

[Aqualung812]

Why not run RAID-5 (or 50 or 15) if it is seek-heavy? I thought RAID-1 was only used if you had to deal with a lot of writes. Those are slower on 5 than 1, but 5 is much faster for reads.

Re:What I want to see

[jgtg32a]

A seek-heavy DB would be a great bench mark but why RAID1, it doesn't give any performance boost. It would just be reading off of the primary the entire time.

Do you mean RAID 0?

Re:What I want to see

[afidel]

Good controllers do read interleaving where every other batch of reads is dispatched to a separate drive.

Re:What I want to see

[Anonymous Coward]

This person is asking for information about a real world usage scenario, for a heavily hit database.

Only a fool would use RAID0 in a production environment--even with clustering or log shipping.

Re:What I want to see

[Anonymous Coward]

RAID5 has terrible random write performance, because every write causes a write to every disk in the array. it's VERY easy to saturate traditional disks random write capabilities with raid5/6. So, it's rightly avoided like the plague for heavily hit databases.

I'm not certain how much of the performance hit is due to latencies of disks. So i feel it would be an interesting test to also see raid5 database performance.

Also, Raid1 (or 10 to be more fair when comparing with RAID5) in a highly saturated environment. reading data should do marginally better than Raid5 since you don't lose a disk to parity--and any raid controller worth it's salt will send independent reads or round robin your read's to both disks).

Then, there is also that whole disk failure thing. It's a huge performance hit to lose a disk in RAID5. For that reason alone in a heavily hit environment it would probably be best to avoid it.

Disk failure is not an IF, but a WHEN. i Dont care what manufacturers say about MTBF's.

Re:What I want to see

[XanC]

RAID5's write performance is so awful because it requires so much reading to do a write.

I have to read from _every drive in the array_ in order to do a write, because the parity has to be calculated. Note that it's not the calculation that's slow, it's getting the data for it. So that's multiple operations to do a simple write.

A write on RAID1 requires writing to all the drives, but only writing. It's a single operation.

RAID1 is definitely faster (or as fast) for seek-heavy, high-concurrency loads, because each drive can be pulling up a different piece of data simultaneously.

Re:What I want to see

[XanC]

It's not simply a matter of interleaving; independent requests can be executed simultaneously. Read performance, especially seeking, can scale linearly with the number of drives in a RAID1.

Re:What I want to see

[dfn_deux]

Good controllers let you set the behaviors as do good implementations of software raid. For instance on Solaris with SVM you can set a raid 1 to read only from a the primary, roundrobin alternation, or (my favorite) read from whichever drive that has a head in position closest to the requested block. For random read biased application the final option wins hands down on latency, for sequential streaming reads the roundrobin seems to be the best option, and for absolute hardware reliability the "read from primary" ensures that your secondary drive gets far less activity than your primary and reduces the chances of "walking dead" failures which are no uncommon in 2 disk mirrors. I.E. the primary fails and the secondary fails within minutes or hours of the primary since their usage patterns are basically identical.

Re:What I want to see

[Anonymous Coward]

Any RAID5 controller worth its money will cache writes and attempt to overwrite whole stripes at once as much as possible, so that it doesn't have to read in old data in order to calculate parity.

Even though this isn't possible 100% of the time, you'll still find that RAID5 has better write performance than RAID1 for many common workloads, due to the fact that with RAID1 you need to write everything to every disk in the array, while with RAID5 the writes are distributed evenly on the disks so they have less work to do.

A RAID5 controller still needs to calculate parity though, but that's not really an expensive operation, and is usually hardware accelerated.

Where RAID1 really shines is with read-heavy workloads, the more drives in the array the better it is. RAID5 performs slightly worse than RAID0 here due to the parity overhead (the more drives in the array, the smaller the difference).

Re:What I want to see

[rthille]

If you setup your Raid block size and your Filesystem block size appropriately, you won't have to read-before-write, at least not very often. Setting up RAIDFrame on NetBSD, with a 4-drive raid-5 setup, performance was dismal because every write was a partial write (3 data disks meant that it was impossible for the FS block size to match or be an even multiple of the Raid block size). Going to 3 drives or 5 drives performance increased about 8-10 times.

Re:What I want to see

[WuphonsReach]

I suspect the OP meant RAID-10, which is generally RAID-0 spread across a bunch of RAID-1 pairs. The advantage there is that you get the speed of RAID-0, where performance mostly increases linearly as you add spindles, with the safety of RAID-1. (You also get small rebuild windows, because a rebuild only has to reconstruct a single drive in the array to rebuild a mirror pair.) RAID-10 over a dozen spindles is very speedy.

A good RAID-1 implementation should have the same write performance as a single disk. Reads *could* be sped up based on the # of drives in the mirror set, but doesn't always happen. On the other hand, it's easy to use RAID-1, mirrored across 3 drives instead of only 2 drives, to protect against double-drive failures.

Re:What I want to see

[Anonymous Coward]

Going to be testing something like this soon. We got a whole bunch of ssds in to test mysql perf with. Though we will be doing raid0 as these will all be slaves for now. We're not sure what the lifecycle of the drives is going to be yet so we aren't ready to move the masters.

Re:What I want to see

[Elladan]

Anonymous Coward:

RAID5 has terrible random write performance, because every write causes a write to every disk in the array.

XanC:

I have to read from _every drive in the array_ in order to do a write, because the parity has to be calculated. Note that it's not the calculation that's slow, it's getting the data for it. So that's multiple operations to do a simple write.

No it does not. An x+1 parity computation only requires the parity block and the block being overwritten to write the new block. You take the parity, "subtract" the old data, and "add" the new data (in fact, the "subtract" and "add" are both just XOR).

Alternatively, if you're writing a full stripe, you can just compute the parity directly. This is of course preferable to doing reads, since reads are slow. Your random write performance is suffering because you have to read and write exactly two disks in the stripe.

I don't know why this old myth comes up so often. Any decent reference will explain how parity works. Maybe if Kari Byron explained RAID parity striping, it would sink in?

Doing random reads is not slow for an SSD, so of course the random write performance with RAID 5 will be much better with SSDs.

Re:What I want to see

[TheThiefMaster]

I can easily imagine crap controllers recalculating the parity by reading the whole stripe instead of doing a delta change (subtract old add new as you put it).

Re:What I want to see

[stonecypher]

If you're willing to accept random block access instead of database access, TweakTown has what you're looking for.

Incidentally, the article is about the FusionIO, which spanks the pants off of the Intel x25 one against eight. The slashdot article is fundamentally wrong.

paging benefits?

[Neotrantor]

i wonder what sort of benefits we could see if an SSD had a paging file on it?

Re:paging benefits?

[tom17]

I really don't get this obsession with page files these days. Say you have 4GB ram and an 4GB page file. Memory is cheap these days, so rather than using 4GB of (relatively slow) SSD, why not just get another 4GB ram?

Re:paging benefits?

[Vectronic]

I'm no expert, but wouldn't that be a redundant statistic? if it handles normal read/writes faster than a disk drive, then could you presume paging would be faster as well?

Although it would be interesting to see a RAM-less PC try and run on SSD's only... somehow using normal data read/write, and memory read/write on the same SSD (if thats possible). Guess that's what we'll end up with eventually anyways, where your amount of MEM is the amount of free-space you have on your SSD, no longer seperated components.

Re:paging benefits?

[xenolion]

I think this all has to due to the program or database you are running, a pagefile maybe more usefull than just ram. I all depends on the app you are using and how it works. Some items run better with a swap others just want ram.

Re:paging benefits?

[guruevi]

SSD shouldn't be for paging. That would become very expensive (even with wear leveling) if you have a minimal amount of RAM (say 256M) to run large (say 16G) operations. It would also be slow since you have the overhead of whatever bus system your hard drive/ssd is connected to.

Technically hard drives aren't supposed to be paging either, it's just a cheap and simple trick to avoid having people pay a lot for (expensive) RAM or have their programs crash when occasionally they run out of RAM. However if your system is paging heavily it's better and faster with more RAM.

Anecdote: I worked at a place once where cheap ($500) hardware was sold as dedicated SQL/IIS servers (you could fit 10 of them in 5U) and a lot of customers thought they could run whatever they wanted (Microsoft ran MSN for a whole country of one for a while) in them but they only supported a maximum of 2G RAM (4G according to BIOS but the modules back then were too expensive). Of course PHB just said: let them swap and besides the heavy slow downs they ran fairly fine. Well, those heavy users all crashed their software-RAID's in less than a year (the heavy load made Windows get the RAID system out of sync and then you had the first hard drive fail). The temperature was fine but simply swapping out was too much for the cheap hard drives (Maxtor and Seagate) and they all failed.

Re:paging benefits?

[petermgreen]

Desktop memory is indeed cheap.

However I don't think i've seen a desktop board that could go over 8 gigabytes and most top out at four. Server boards can go higher BUT

* intel xeon boards requires FBDIMMs which are expensive.
* AMD opteron boards can use ordinary DDR2 but the CPU performance sucks compared to the aforementioned xeons.

Re:paging benefits?

[Wonko the Sane]

* AMD opteron boards can use ordinary DDR2 but the CPU performance sucks compared to the aforementioned xeons.

If you go multiprocessor (not multicore) then you get much higher memory bandwidth (NUMA). Sometimes that matters more than CPU power.

Re:paging benefits?

[bluefoxlucid]

SSD shouldn't be for paging. That would become very expensive (even with wear leveling) if you have a minimal amount of RAM (say 256M) to run large (say 16G) operations. It would also be slow since you have the overhead of whatever bus system your hard drive/ssd is connected to.

You talk like you know what you're talking about; but then the reader realizes you don't understand what happens when the CPU spends 99% of its life in wait state waiting for paging operations. Swap is not a high-intensity workload; swap workload increases six orders of magnitude faster than CPU workload, meaning when you start swapping, you spend lots of time swapping.

As the hard disk is external, this number increases with CPU speed; a swap operation taking 1,000,000 cycles on a 1GHz CPU (1mS) will take 10,000,000 cycles on a 10GHz (1mS) CPU. Triggering a seek operation between 4 and 9 mS on a 2.0GHz CPU (modern AMD) is a disaster; triggering these continuously, every 10mS, halves your CPU performance and performs 50 operations a second. Write operations take more than read operations, substantially, so we're talking 20-30mS, at which point ... if you're swapping even 2-3 times a second you notice it. AND ALL THAT SEEK WILL KILL HARD DRIVES.

Re:paging benefits?

[bluefoxlucid]

Most people have this mistaken belief that SWAP is interacted with as often as RAM (hundreds or thousands of times a second, at least; RAM is interacted with sometimes hundreds of thousands of times per second). They think swap is an actual extension of RAM, not a long-term slow storage shelf.

Re:paging benefits?

[Cthefuture]

I don't think anyone should be using a page file at all if you have 4 GB or more of RAM. Maybe even 2 GB. It just doesn't make sense. With that much memory what good is a 512 MB page file going to do really? And if you're swapping more than 512 MB of RAM to disk your machine is going to be thrashing like mad and unusable anyway.

It's stupid that many OS's allocate 2 times your RAM as a page file. Are you really going to swap 8 GB of RAM to disk? I mean seriously, that would be unusable.

Even when I had 2 GB of RAM I never used a swap file and now with low-end machines running 8+ GB (only about $100 of RAM), page files just don't make sense any more.

Re:paging benefits?

[AliasMarlowe]

However I don't think i've seen a desktop board that could go over 8 gigabytes and most top out at four.

Maybe this was true a year ago, but not now. I recently got a PC with an Asus P5Qpro motherboard - it supports up to 16GB. http://www.asus.com/products.aspx?l1=3&l2=11&l3=709&l4=0&model=2269&modelmenu=2

Re:paging benefits?

[ErikZ]

I'm Betaing Windows 7. Before going to bed I set up a swap partition for it. After getting up the next morning and checking, it was full.

I have *no idea* what W7 put in there while I was sleeping.

Re:paging benefits?

[ErikZ]

The new I7 boards from Intel are either 12GB or 24 maximum.

Re:paging benefits?

[conureman]

I'd run my page file on DRAM chips, if I could afford it. Serious applications might want a card that interfaces through the PCIe bus. I can't even afford to ask how much one of those costs.

Re:paging benefits?

[Anonymous Coward]

Must be all that pr0n I downloaded on that win7 beta box I rooted last night.

Re:paging benefits?

[sexconker]

Flash (and buses) have a looooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooong way to go before they could ever compete with current memory speeds.

Re:paging benefits?

[Anonymous Coward]

...it's just a cheap and simple trick to avoid having people pay a lot for (expensive) RAM or have their programs crash when occasionally they run out of RAM...

Don't forget it was a tactic to breed lazy-ass dime a dozen programmers that don't give a crap about RAM usage...or any other HW issue for that matter...

Why does a freaking browser need 100MB of ram on a plain jain site like /.?

Re:paging benefits?

[Siffy]

You can get a socket 771 board with an Intel 5100 chipset, and it'll be compatible with DDR2 ECC memory. It does not require FB-DIMMs. Most of those boards are 32/48GB max RAM. Most newer desktop boards for AM2 and 775 "support" 16GB RAM, but the availability of 4GB non-ECC sticks is low. So you're stuck with "only" 8GB for playing 64-bit solitaire, visiting the interwebz, and listening to itunes.

Re:paging benefits?

[Siffy]

Even saturating 4 lanes of SATA would be much slower than DRAM. 4 x 300MB/s = 1.2GB/s vs 12.8GB/s (for DDR3 1600). Yes SSDs handle random requests better than magnetic media but still offer no where near the speed required from true "random access memory". It could work if you were still using a 486 maybe. In the future it may work, but I doubt it will be with flash memory.

Re:paging benefits?

[tepples]

Are you really going to swap 8 GB of RAM to disk?

Yes. When you hibernate your workstation, it writes the entire allocated contents of RAM to the page file.

Re:paging benefits?

[Anonymous Coward]

Wrong. Hibernation has it's own storage for the current state.

Re:paging benefits?

[symbolset]

The others have pointed this out, so I'll just stick with a nice informative link. Up to 24GB in 6 sockets, DDR3 1600, triple channel. $234 plus shipping today. They have 23 different ones today just that support the I7.

/happens to me all the time.

Re:paging benefits?

[Anonymous Coward]

Maybe it was caching and streaming out your pr0n?

Re:paging benefits?

[zerocool^]

I'm going to go out on a limb here and say that you should eliminate page files / swap space entirely.

I know there are edge cases, and one would be where you're moving something from disk into a ramdisk or some such thing, but in my experience... there's no circumstance under common usage where running out of ram and swapping to disk is preferable to running out of ram and having the program crash. To be honest, I would rather things hard crash than run in a slow degraded state.

And these days, with 8 and 16 GB of ram being sort of standard in servers, if something fills up 8GB of ram and you weren't anticipating it to do so, it's going to fill up another 1/4/8/16GB or whatever of swap.

Swap, I think, is a legacy and we should shed it sooner rather than later. Now, having said that, I'm not exactly brave enough to do that in a production environment.

~x

Re:paging benefits?

[Firehed]

FBDIMMs aren't that bad these days either. Sure, it's more than standard desktop memory, but I paid $300 for 4x2GB sticks for my Mac Pro about six months back, and that same amount has already dropped to a hundred bucks for a 2x2GB kit (about $300 for the higher-density 2x4GB kit). No, it's not the $8/GB I'm seeing at some standard DDR2 sticks at Newegg, but it's hardly crazy-expensive either.

Hell, at that price, I'm almost tempted to get that 8GB kit just because I still have two RAM slots free in the thing, not that my current 10GB isn't cutting it (almost... I'd rather get more storage, or even a nice fast SSD for a boot drive)

Re:paging benefits?

[Anonymous Coward]

The Intel 5100 series chipset uses plain DDR2, and they run a lot cooler than the old the FBDIMM boards.

Re:paging benefits?

[Mad Merlin]

Have you actually loaded it up with 16G of RAM? Often times boards advertise maximum capacities which aren't really ever tested at that capacity, or have other caveats (like the memory doesn't run at full speed anymore).

Re:paging benefits?

[Anonymous Coward]

I paid $300 for 4x2GB sticks for my Mac Pro about six months back(about $300 for the higher-density 2x4GB kit). No, it's not the $8/GB I'm seeing at some standard DDR2 sticks at Newegg, but it's hardly crazy-expensive either.

So if ~5x as much isn't crazy expensive, just how many times as much is? This is classic behavior that earns Mac people scorn, as opposed to people who just use macs.

Re:paging benefits?

[Anonymous Coward]

That's the porn you downloaded. Because Win7 calculates wear-leveling by categorizing data types, Microsoft simply saves your solid state disk by putting whatever you're most likely to use more in paging files. Which goes for all your porn, given your surfing habits.
You didn't read the EULA?

Re:paging benefits?

[tom17]

I hope you are going for +1 Funny...

What would be the point in getting DRAM chips on an extra card so that you can simulate a swap file that is effectively only there cos of a lack of... DRAM cips.

It doesn't make sense (unless you have maxed out the motherboard capabilities, but then you probably have bigger issues anyways)

Tom...

Re:paging benefits?

[tom17]

Although I questioned the use of page files in this day and age, I do recognize that there are edge case usages.

Although I use no swap on my 6GB Linux at home, one of our dev Solaris boxes at work, with 16GB physical RAM does indeed use a lot of swap. We had to enable 16GB of swap on this box. It sounds awful, but we have a case where the main workload of this box is a gazillion Weblogic JVMs running and for the most part sitting idle (but devs want them always on, typical).

This works for us as buying an extra 16GB ram would just be a waste as 99.9% of the time the JVMs sit idly in the swap file. Performance is not crucial so it's fine.

Naturally we would not do this in a production environment.

Re:paging benefits?

[TheThiefMaster]

Any decent OS would dispatch the read request and switch threads to one that didn't need to swap. Of course, that only works if your "active set" of ram pages actually all fit in ram, and you don't need to swap code pages just to run.

Much like what happens on a cpu with multiple threads supported by one physical core (like "hyperthreading") and a cache miss is encountered.

Re:paging benefits?

[TheThiefMaster]

Presumably it copied everything in ram to the swap allow the pages still in ram to be discarded without waiting to write them to disk if your ram usage suddenly spiked and you needed to swap.

I think it's called "pre-emptive swapping".

Re:paging benefits?

[bluefoxlucid]

That's a good theory. Consider that you have one memory controller to access an area of memory (on NUMA, there may be 1 area of memory per core; on Intel chips there is no NUMA, it's one flat memory area). Now consider that the device's DMA I/O is tying up the memory controller. Now consider you just task switched, flushed cache, and the only way to get your task underway is to access memory. These memory access operations will have to wait for the IDE or SATA bus to finish playing with memory, leaving the process stalled in a wait state waiting for code memory.

Re:paging benefits?

[TheThiefMaster]

Hopefully the disk isn't tying up the memory controller when it's not actually transferring data, so you'd get 5ms of execution of another thread before the disk seek is done and it starts reading.

Not saying it would actually work, but it would be nice if it did.

Re:paging benefits?

[illumin8]

I'm Betaing Windows 7. Before going to bed I set up a swap partition for it. After getting up the next morning and checking, it was full.

I have *no idea* what W7 put in there while I was sleeping.

In any modern operating system, including Windows , swap isn't just used for out of physical memory conditions. It's also used to "page out" portions of the operating system and libraries, shared objects, dlls, etc., that aren't being used at the moment. This actually speeds your system up by allowing more memory to be used as disk read/write cache.

I've looked at Linux boxes with 64GB of memory in them and only using 25% of that. I usually get asked by someone, "wasn't 64GB enough? Why is there some usage in swap right now?" It's normal, I explain. The kernel just pages out sections of Linux that aren't needed, to free up more RAM for filesystem caching.

I think perhaps Windows 7 just has a more aggressive way of doing this, probably because if you need to use some obscure Windows Directmedia SuperDRM doubleplusgood Plugin X, it's just as fast to reload it out of swap into memory as it is to load the binary from disk. But 99% of home users will never load that plugin so it can stay safely swapped out, giving you more precious memory for applications and disk cache.

Re:paging benefits?

[bluefoxlucid]

Ah, you're right. What about context switching again? In both directions, of course... and the cost of constant TLB and page faults during that 5mS? Not very much of a performance gain anyway. And again, under swap load (i.e. swapping several times per second), the performance hit adds up really fast. And again, wouldn't the level of swapping that would damage an SSD also damage a hard disk?

Re:paging benefits?

[petermgreen]

though according to intel it can "only" go go 48GB which while high compared to desktop boards is low compared to the FBDIMM based intel boards which can apparently go to 128GB and DDR2 based amd opteron boards which can go to 64GB.

Re:paging benefits?

[TheThiefMaster]

There is no way that a cpu doing nothing for 5ms would be giving you more performance than one that switched to doing something else. 5ms is a hell of a lot of cpu time, especially if you're swapping several times a second, it could really add up.

If it turns out that the thread it switches to needs to swap too a little later, it should just queue it and switch to yet another thread that isn't waiting on a swap.

Of course, running swap on an SSD wouldn't suffer from the same latencies, it's more like 0.1ms. Swapping at the rate that would kill an SSD would probably not damage a hard-disk (unless it's in a portable device and being moved...) but that level of swapping only happens when your current working set of memory pages doesn't fit in ram, so you have to do swap after swap after swap just to switch to the next program, so your performance would be completely gone anyway. So it's a choice between slowly killing a disk and having a pc that makes a 386 look speedy...

Or, you could just put enough ram in the box in the first place.

The biggest concern with using an SSD is making sure that writes are done in a multiple of the SSD's erase block size, so that you don't make it read the data around where you're writing, erase it all and then write it back again.

Re:paging benefits?

[bluefoxlucid]

There is no way that a cpu doing nothing for 5ms would be giving you more performance than one that switched to doing something else. 5ms is a hell of a lot of cpu time, especially if you're swapping several times a second, it could really add up.

Of course, but I mean the gains are insignificant under the loads theorized here. If you have to swap several times per second, continuously, each fault requires a read and write (or else you'd reach a point where everything you need is in memory, and everything you don't is in swap). The only time this stuff really matters is when swap is part of the active working set.

Of course, running swap on an SSD wouldn't suffer from the same latencies, it's more like 0.1ms.

Throughput is much lower, but this can be addressed. The complexity of the operation is still fairly high; remember the MMU actually performs most of the virtual memory work in hardware, doing it in software much less doing it with block copy operations from slow media presents a huge performance loss.

Swapping at the rate that would kill an SSD would probably not damage a hard-disk (unless it's in a portable device and being moved...)

Seeking back and forth constantly wears on the motor. Believe it or not, hard disks aren't made for constant, continuous use, and will wear down quite quickly if you're continuously streaming data on and off them from random areas of disk.

but that level of swapping only happens when your current working set of memory pages doesn't fit in ram, so you have to do swap after swap after swap just to switch to the next program, so your performance would be completely gone anyway. So it's a choice between slowly killing a disk and having a pc that makes a 386 look speedy...

This is my point. By the time you can damage an SSD or hard disk, your computer is non-responsive anyway. It's time to buy more RAM or give up.

Re:paging benefits?

[TheThiefMaster]

Swap is a bit of an outdated concept, it's from an age when CPUs were slow, ram was really slow, and really expensive. Swap was required for a machine to be usable.

Now it's more of a hindrance, at least to those of us who don't have an OEM machine with 256MB of ram and 300MB of OEM startup crap. Especially due to that quirk of the Windows API that allows programs to insist on swap and fail to run if you have it turned off. "ABC requires at least 64MB of swap" -> "I have 4GB of ram, and 3GB of that is unused, use that" -> "No, I want 64MB of swap" grrr.

Re:paging benefits?

[Neotrantor]

if you're working with data larger than you're system's ram, you need a swap file

Re:paging benefits?

[bluefoxlucid]

That's a quirk of programmers, as you can make the same check on Linux. It's stupidity.

Re:paging benefits?

[TheThiefMaster]

Someone once said: "You can't blame the API for the actions of the programmer who uses it" or something like that. I think they're probably right there.

I think we've reached the end of this conversation. Nice meeting you, I'll stick you in my friends so I see you around :)

Re:paging benefits?

[bluefoxlucid]

bash scripting does make 'rm -rf /' perfectly legal...

Fusion-io's iodrive is faster!!!

[Anonymous Coward]

Fusion-io's iodrive blows this thing away... this is junk.

Re:Fusion-io's iodrive is faster!!!

[denis-The-menace]

[citation needed]

Re:Fusion-io's iodrive is faster!!!

[Anonymous Coward]

[citation needed]

I was not the original poster - and I can't cite anything - but I can quote some numbers from our testing:

I can't remember the hardware, but memory or cpu was never the bottleneck. Easily seen with iostat -x 1.

Repair of a large MySQL table:
14 SAS disks in RAID-10: ~45 minutes.
2 X25-E in RAID-1: ~30 minutes.
1 IODrive: ~2 minutes.

QPS (70% read, 30% write) for a database consisting mostly of MyISAM tables:
14 SAS disks in RAID-10: ~4.500.
2 X25-E in RAID-1: ~6.000.
1 IODrive: ~15.000.

- This is not very scientific, but our numbers confirms it.

I have a feeling that Intel's Extreme disks suffer the same problem as MTron's higher end disks, namely very bad random write speeds.

Re:Fusion-io's iodrive is faster!!!

[DJKC]

http://www.engadget.com/2008/12/11/fusion-ios-iodrive-tested-worlds-fastest-storage-confirmed/ , etc. We do HPC stuff at work, the Fusion IO guys are cool. Their products also run 3000-15000$ so it's not exactly a fair comparison.

If I keep my current 15K drives that long

[Shivetya]

I will be surprised.

See, in the enterprise environment that I work in the majority of our big hardware is leased. I am quite willing to use what I can to maintain performance and reliability. That being said my system is built entirely on 15K drives of various sizes. I am not worried about five years or so of read/write that SSD drives have, all I want to see is a track record. I expect to replace most of the drives I have now within five years so this "five year limit" many like to toss out is immaterial to me. Reliability over that lifetime is of more importance.

Besides, the nice benefit of SSD drives is I don't need special enclosures (read: ones that can handle the torque these puppies can put out)

Redundant Array of what?

[telchine]

This is a very expensive solution. What part of Redundant Array of Inexpensive Disks don't they understand?

Re:Redundant Array of what?

[evilbessie]

RAID 0 is not redundant, they are not really 'disks' any more and they could be independent disks rather than inexpensive. Sorry I know you were trying to be funny but I felt you could have more fully reduced the issue.

Re:Redundant Array of what?

[Anonymous Coward]

lurn 2 akcronym: The "I" in RAID can also stand for "Independent"

Re:Redundant Array of what?

[grub]

Independent disks. And remember that some high end SCSI or Fiberchannel RAIDs have never fit the antiquated "Inexpensive" bit.

Re:Redundant Array of what?

[Ioldanach]

That's right. Marketing switched "Inexpensive" for "Independent" years after the term was coined, because they couldn't convince people to buy their non-Inexpensive disks for RAID use as easily under the old meaning.

Re:Redundant Array of what?

[afidel]

Dude, 4 of these drives can keep up with my 110 spindle FC SAN segment for IOPS. Here's a hint, 110 drives plus SAN controllers is about two orders of magnitude more expensive than 4 SSD's and a RAID card. If you need IOPS (say for the log directory on a DB server) these drives are hard to beat. The applications may be niche, but they certainly DO exist.

Re:Redundant Array of what?

[Artraze]

Yes, well, that, or maybe it's just that the notion of "expensive" disks is gone. These days, you pay a tiny amount per GB, which usually goes down with increasing size. Oh sure, you may pay a bit more at the top, but it's not much.

It used to be that you could get huge drives. I'm not just talking about the fact that they would store like 20+MB, but they were also physically huge. I used to have one that was 5 platters and two 3.5" slots high (though my memory is fuzzy). These suckers were EXPENSIVE; multiple times what the same capacity would cost across standard disks, thus the creation of RAID.

Since RAID because popular, the expensive disk died leaving us with only 'inexpensive' ones. Yes, WD Raptors are pricey, but they've got performance to back that up (usually). And yes, "RAID" versions are usually slightly (10%) more expensive, but they usually come with a longer warranty and are modified to work better in a RAID (which is a smaller market).

In short, you cynicism is misplaced. Expensive disks don't exist anymore so it only makes sense to update the acronym.

Re:Redundant Array of what?

[wastedlife]

I've never understood why they call it RAID 0. Striped Array would suffice. Why is it a Redundant Array of In(expensive|dependent) Disks 0(as in NOT)?

Re:Redundant Array of what?

[NSIM]

It's nice to see someone who actually gets it. Yes, SSD is epxensive, but not when you compare it to the price you'd pay for a similar number of hard drives that can match the IOPs performance

Re:Redundant Array of what?

[Anonymous Coward]

if you think raptor are pricey, then learn about those SAS disk, before posting your layman comment about what is expensive and what not.

Re:Redundant Array of what?

[Bearhouse]

The performance part.

Re:Redundant Array of what?

[Anonymous Coward]

Mod the parent up. My understanding is that inexpensive meant that the array provided space/performance that was cheaper than a comparable 1-disk option. There isn't a 1 disk, 128 GB, very fast SSD out there, is there? So, if the GP has to be a misguided pedant, he can be comforted that 4 of these expensive disks are inexpensive relative to something which is unavailable (and so costs $infinity?).

Re:Redundant Array of what?

[SanityInAnarchy]

So, what is it now? Random Assortment of Independent Datastores?

Re:Redundant Array of what?

[sexconker]

It's Inexpensive.
Marketing got away with the fucking KB = 1000 bytes bullshit too. Doesn't make them right.

Re:Redundant Array of what?

[Siffy]

You mean like this? http://www.newegg.com/Product/Product.aspx?Item=N82E16820231242 Or did you mean SLC? There's also a 256GB version for $500. Pure Si has announced a 1TB 2.5" drive. http://www.marketwire.com/press-release/Puresilicon-936099.html

Also, your parent was wrong on about everything he said. Go compare the prices of WD Black (WD1001FALS 1TB $119.99) vs RE3 (WD1002FBYS 1TB $189.99) & RE2 GP (WD1000FYPS 1TB $199.99)drives, then Cuda AS (ST31000340AS 1TB $109.99) vs ES/NS (ST31000340NS 1TB $169.99) drives, and finally VR vs Savvio 15k.2 (ST9146852SS) or Cheetah 15k.6 (ST3300656SS). You're looking at a 50% premium for drives certified to just work in RAID, not even work better. And you're looking at at least 100% more/GB for an enterprise performance drive. Calling a Raptor expensive in '09 is just silly. Hell, calling a Raptor a performance drive in '09 is silly.

Re:Redundant Array of what?

[drsmithy]

That's right. Marketing switched "Inexpensive" for "Independent" years after the term was coined, because they couldn't convince people to buy their non-Inexpensive disks for RAID use as easily under the old meaning.

The original reason for 'inexpensive' is because collections of smaller disks in an array used to cost appreciably less than a single larger drive.

Occasionally you see this today, with brand new drives (eg: the new WD 2T drive is more than twice as much as two 1T drives), but generally it doesn't last long and the price disparity is much smaller. Used to be a RAID10 array (at least 4 drives) would cost less than a single drive of the same capacity.

Re:Redundant Array of what?

[TooMuchToDo]

So will SSDs eventually be replaced with battery-backed RAM-based drives? SSD is fast, but DRAM is faster.

Re:Redundant Array of what?

[Anonymous Coward]

That's why such a thing's called RAVED: Redundant Array of Very Expensive Disks!

Re:Redundant Array of what?

[Bigjeff5]

Back in the Day, when RAID was new, those massive server hard drives were the size of your walk-in closet, used robots to run the platters, and cost $100k+ for a score or two of megabytes.

With RAID, you could put together 20ish 1mb disks and get MORE performance for your 20mb for well below half of what the Expensive drive costs.

There IS no such thing as an "Expensive" drive anymore, RAID killed them. The equivalent today would be building a giant, 40tb drive the size of a small desk. It just doesn't work, and it'd cost about 10x what putting 40 1tb drives together in a RAID would cost.

Basically, if you can RAID it, it isn't an Expensive disk in the same sense as when the term was coined. $400 for the fastest 128gb SSD hard drive is cheap man, crazy cheap.

Comparisons a little unfair in places

[heffrey]

It seemed a little unfair that they only used the nice hardware RAID controller with the Intel SSDs. I would have liked to see them use it with all the other disks to get a more level playing field.

Re:Comparisons a little unfair in places

[Anonymous Coward]

The "nice little hardware RAID controller" actually increases seek time and reduces performances by adding delays.

In several enthusiasts home-made comparison tests, the raid card usually gives worse results than the ICH10r controller.

Apparently, not a single engineer at Areca or Adaptec figured this out ages ago and so now there are no real options for "good" SSD-oriented raid cards.

Re:Comparisons a little unfair in places

[Nick Ives]

Indeed, telling us to ignore the extra minute in the X25-E RAID0 boot times compared to the other setups is highly disingenuous. RAID setups are slower to boot because you have to load the RAID BIOS first, if you really care about fast booting it's something you need to be aware of. There were also CPU bound case where the RAID0 setup performed slightly worse than the single disk, an obvious sign of a performance hit due to the RAID card.

Re:Comparisons a little unfair in places

[afidel]

Or LSI, we get half the IOPS from our LSI based HP P400 than we do from the ICH in our HP workstations when using the X25-e's. Reports on the web lead me to believe that there are NO hardware raid cards that can keep up with these beasts which is a shame because I can't see using them without battery backed write cache. I'm going to look into the big boy P800 and possibly the new P410 but right now I'm kind of underwhelmed by the fact that $5-600 raid cards get beaten badly by the 'free' ICH controllers on motherboards =(

What was the target for this test???

[LWATCDR]

Doom levels????
Office tasks???
Okay folks I can only see a few groups using this kind of set up.
Not one Database test?
I mean a real database like Postgres, DB2, Oracle, or even MySQL. Doom3... yea those are some benchmarks.

Re:What was the target for this test???

[JohnnyBigodes]

Look in the later pages of the review. There's a bit of everything. There are IOMeter benches there, with very enligthening results.

Re:What was the target for this test???

[LWATCDR]

I did see the IOMeter tests. That was some what useful but the rest of it was pretty useless and I would really like to see some actual database benchmarks.
A RAID of SSDs really only makes sense to me for database servers, video editing workstations, and for rugged systems that would kill hard drives.

Terrible review

[Anonymous Coward]

Cheap RAID controller... check
CPU-bound benchmarks... check
Couldn't be bothered reading any more... check

What's on TV?

Re:Terrible review

[Kushieda Minorin]

What's on TV?

An all new Fringe is on FOX tonight at 9pm Eastern. This week, the team deals with a computer virus that is able to infect humans and turn their brains into liquid. I figure this episode should be of interest to many Slashdotters.

Test it on a better system then a OLD P4 cpu

[Joe The Dragon]

Test it on a better system then a OLD P4 cpu.

Re:Test it on a better system then a OLD P4 cpu

[JCSoRocks]

Hey, I have a P4 running my home server you insensitive clod!

Re:Test it on a better system then a OLD P4 cpu

[Ant P.]

I've got a P3 running mine. It saved 100 watts.

Re:Test it on a better system then a OLD P4 cpu

[DMalic]

Yeaaaaaah. Gotta love doom3 level loads taking as long as Crysis would with that configuration on a modern PC.

Re:Test it on a better system then a OLD P4 cpu

[Anonymous Coward]

The Thunderbird 1GHz I built for my mother in 2000 has run 24x7 since as her home office desktop. She is an author and does all her writing on the machine. Every Christmas and birthday she refuses to let me upgrade it for her - she believes it's somehow uniquely indestructible.

Fusion-io's iodrive is faster

[dragonbladex]

Fusion-io's SSD the iodrive is faster than this by far, I would suggest looking at their speeds on fusionio.com

Re:Fusion-io's iodrive is faster

[Anonymous Coward]

Astroturf much?

Re:Fusion-io's iodrive is faster

[afidel]

Fusion-IO is about $30/GB, these are about $20/GB and get about the same IOPS/$ so unless you don't have physical space the Intel SSD's win.

Re:Fusion-io's iodrive is faster

[beaviz]

Fusion-IO is about $30/GB, these are about $20/GB and get about the same IOPS/$ so unless you don't have physical space the Intel SSD's win.

I would say that the Intel Extremes win by the fact that they can be hot-swapped. Not for performing nearly as good as IODrives.

If we take their own specs:
IODrive 160GB: 102.000iops random read, 101.000iops random write.
Intel X25-E: >35,000iops random read, >3,300iops random write.

That is in no way the same performance.

We have both in our servers, I like the Intel's because they are cheap, you can buy them at the local grocery store (well, almost) and they hotswap. But I simply love the IODrives for their performance. There is no practical difference of running a database completely in memory and from IOdrives.

But hey! Buy some and judge for yourself :)

Re:Fusion-io's iodrive is faster

[afidel]

I'm getting 70K IOPS@ 4K 100% random write with the ICH on my HP desktop, only 35K from the P400 controller in my server though.

Re:Fusion-io's iodrive is faster

[RightSaidFred99]

Note he didn't say you get the same performance. He said about the same IOPS/$.

New acronym: RAVED?

[RTHilton]

Redundant Array of Very Expensive Disks?

Re:New acronym: RAVED?

[CompMD]

No, its got a cooler acronym, RAVEN: Redundant Array of Very Expensive Not-disks-but-some-silly-stack-of-flash-memory-chips.

Re:New acronym: RAVED?

[RTHilton]

I like it, but it seems a bit long. Maybe we can just abbreviate Expensive

Re:New acronym: RAVED?

[Anonymous Coward]

Extremely
eXpensive
Portable
Erasable
Non-volatile
Storage
Intel
inVigorates with
Electricity?

Re:New acronym: RAVED?

[MBCook]

That was me, I accidentally checked "post anonymously".

I want my karma! *sobs*

Re:New acronym: RAVED?

[lazyforker]

No, its got a cooler acronym, RAVEN: Redundant Array of Very Expensive Not-disks-but-some-silly-stack-of-flash-memory-chips.

This is /.:
RAMEN - Redundant Array of More Expensive Not-disks-but-some-silly-stack-of-flash-memory-chips.

Re:New acronym: RAVED?

[Anonymous Coward]

fail.

Re:New acronym: RAVED?

[sean4u]

Since there are no longer any discs in these disks, I thought we might go back to yesteryear for RAVEAC: Redundant Array of Very Expensive Aluminium Castings. But then, if there are no moving parts, then there's no need for that Expensive Aluminium Casting is there? How about RAVEO: Redundant Array of Very Expensive Oblongs?

Exactly

[Ritz_Just_Ritz]

I suspect the performance would have been a LOT better if they'd used something like the 3Ware 9690SA. 3Ware is also a LOT more Linux friendly.

Cheers,

Re:Exactly

[MBCook]

Of course, they ran all their tests in Windows. I wonder how much of the results in some of the tests (like program installation) are really due to how fast NTFS can handle lots of little files and not due to the drives they were testing.

It would have been nice to see some quick tests under Linux with ext3 / XFS / reiser / ext4 / btrfs / flavor_of_the_month just to see if that was really the drives or a vastly sub-optimal access pattern.

Re:Exactly

[setagllib]

Windows filesystems don't even have an optimal access pattern. At least with ext2/3 you can optimise for RAID stripe and stride in a way that works regardless of the underlying RAID implementation, and significantly reduces the number of disks involved in reading/writing metadata.

Doom 3

[Anonymous Coward]

Well to be fair Doom 3 still runs like shit on my rig

Re:Doom 3

[SanityInAnarchy]

But likely not due to disk. If I remember, that was a heavily CPU-bound process.

Software RAID and a modern rig

[Anonymous Coward]

Here is a test with 4-5 drives and Linux software RAID 0:
http://21stcenturystorage.cebis.net

Re:Software RAID and a modern rig

[keeboo]

Interesting.
But, from what I saw there, you didn't make a real RAID0, you benchmarked several mountpoints simultaneously instead.
A md0-like benchmark will be nice to see.

performance per dollar rather than gigabytes

[Anonymous Coward]

No one looks at just IOPS/$ without looking at size. It's probably something like IOPS/$/GB with different weights depending on the circumstances. No business is going to pay the same price for a 3x faster drive if it has 1/10,000 of the size unless money is no object. Then you're just concerned with IOPS, not IOPS/$.

Fantastic Slashvertising

[damn_registrars]

Intel's X25-E Extreme SSD is easily the fastest flash drive on the market, and contrary to what one might expect, it actually delivers compelling value if you're looking at performance per dollar rather than gigabytes

I hope someone got a healthy commission from Intel for writing that...

Re:Fantastic Slashvertising

[RightSaidFred99]

Let me get this straight. Is it possible to do any kind of article on a commercial product without it being "astroturfing" of some form or another? Or is it only the negative articles that can be done? I just want to know the SlashDweeb rules.

Re:Fantastic Slashvertising

[citizenr]

Intel's X25-E Extreme SSD is easily the fastest flash drive on the market, and contrary to what one might expect, it actually delivers compelling value if you're looking at performance per dollar rather than gigabytes

I hope someone got a healthy commission from Intel for writing that...

commission? no, he just kept the drives :)

Re:Fantastic Slashvertising

[damn_registrars]

Is it possible to do any kind of article on a commercial product without it being "astroturfing" of some form or another?

Yes, it is. They didn't need to write it as

Intel's X25-E Extreme SSD is easily the fastest flash drive on the market, and contrary to what one might expect, it actually delivers compelling value if you're looking at performance per dollar rather than gigabytes

When they could have just as easily said

We tested Intel's X25-E Extreme SSD drive in a four-disk RAID configuration

There was no need to tout the product like that on the front page.

I just want to know the SlashDweeb rules

There was no need for that, either. I rather doubt that someone is forcing you to read anything on this website. You could read something completely different if you prefer, or not read anything technical at all.

I stand by my criticism of this article. The headline did not need to be such blatant advertising of the Intel drives.

Re:Fantastic Slashvertising

[BobMcD]

I stand by my criticism of this article. The headline did not need to be such blatant advertising of the Intel drives.

Particularly because their own data doesn't always support the conclusion of 'easily the fastest'. Not without a lot of emphasis on the word 'flash'.

Re:Fantastic Slashvertising

[Anonymous Coward]

I assume that means that you know of a faster flash drive?

Because what they said sounded to me like "these things are crazy fast, so for the fun of it lets see what kind of performance we get with several in raid".

They could have been paid to say that, but who cares if they were paid to say it if it's true?

SATA/Flash for RAM?

[Doc Ruby]

Other than just using one of these Flash RAIDs as a swap volume, is there a way for a machine running Linux to use them as RAM? There are lots of embedded devices that don't have expandable RAM, or for which large RAM banks are very expensive, but which have SATA. Rotating disks were too slow to simulate RAM, individual Flash drives probably too slow, but a Flash RAID could be just fast enough to substitute for real RAM. So how to configure Linux to use it that way?

Re:SATA/Flash for RAM?

[Shadow-isoHunt]

It's called swap, but at the prices for SSDs(and limited write cycles) you'd be better of getting *real* RAM. If you're at the limit for your board, UPGRADE!

Re:SATA/Flash for RAM?

[Doc Ruby]

I said no swap.

The PS3 (running Linux), for example, can't take any more RAM, but it has SATA. There is only a single product that plugs RAM into SATA, and it's expensive (and a HW kluge). A really fast Flash RAID might be suitable for storing running programs as "RAM", with the real RAM used for data fed to the super-fast SPEs.

If someone actually knows how to config a Flash RAID like that (not swap), instead of telling me to change my requirements, I'd like to hear about it.

Re:SATA/Flash for RAM?

[jareds]

This is a hardware issue, not an OS issue. If you truly want to use a SATA device in the same way you use RAM, rather than as swap, the hardware must support this. This is an extremely general issue, not an architecture-specific quirk. If you have a CPU with address and data pins, to treat something as RAM there has to be some range of addresses that it can put out and get the contents directly back, and there must be hardware to do this. If hardware can't do this, and you don't want the data swapped into a spare page of RAM by the OS, then there is no physical address the OS can ever use to have virtual addresses mapped to the device, so the best you can do is have unmapped virtual addresses, where every access causes an exception and the OS emulates the instruction (i.e., reads in the necessary data, figures out what the instruction would do, and then updates registers, writes to memory, writes the device, etc.). This is far, far, far worse than swap.

The next question is whether any hardware supports having the contents of a SATA device mapped into memory like this. If you want to use a SATA device directly, the motherboard's chipset would need to support it. This is too unlikely to merit further discussion. With PCI/PCIe RAID, it's up to the card, but it seems very unlikely. Certainly it's not a normal feature or the intended way to use SATA. Finally, it doesn't seem like a useful feature. The fact you want to use something as RAM instead of as swap means you want to make a relatively larger number of relatively smaller accesses, which means that latency is just as important as bandwidth, and there's nothing to suggest the latency is that good (I think maybe the iPEAK benchmark corresponds the most to latency, and it's only 10 times better than hard drives). For the record, the normal way this works is you write commands to memory-mapped registers that cause the card to initiate a transfer from/to itself directly to/from RAM.

I don't mean to be condescending, it just sounded like you weren't inclined to believe that the problem is with your requirements. (I don't even understand your problem with swap.) The solution is to change your requirements, to find some mutant RAID card or motherboard chipset that supports this, or to design and fab your own.

seriously??

[poached]

We'll be focusing our attention on RAID 0 today, but the card supports a whole host of other array configurations, including RAID 1, 1E, 5, 5EE, 6, 10, 50, 60, and 36DD. Ok, so maybe not the last one.

I like Tech Report but, seriously? I found that joke to be very juvenile and I have a hard time reading the rest of the article without a prejudicial eye.

Re:seriously??

[Kneo24]

If a juvenile joke bothers you that much, I suggest you unclench. You can't tell me that neither you nor any of your friends ever make those type of jokes at least once in a while.

Re:seriously??

[daybot]

What poached actually typed:

I found that joke to be very arousi^H^H^H^H^H^Hjuvenile and I have a hard time reading the rest of the article without an erec^H^H^H^H^H^H prejudicial eye.

Re:seriously??

[poached]

I guess there is difference between making a joke between your friends and posting it to the web for millions to read. I still like these juvenile sites that review hardware, because not a lot of site will throw four expensive SSD drives together and benchmark them in such a silly way just to say, "there I did it". It's entertaining, but not very educational. As I was writing this reply, I said, "self, go find some educational tech/sci sites and waste your time on those instead". I think I'll go do that.

Re:seriously??

[uvajed_ekil]

I'm sorry, Captain Serious. From the viewpoint of someone without such a judgmental idea of what might constitute humor, I can assure you that the rest of the article is more sensible, though the testing methodologies could use some broadening. Now, is this a topic that interests your convent specifically, or one that you enjoy personally? Come on, it was a take on the varied capabilities of the hardware (or should I say product, so as not to offend you) and "alphabet soup" of jargon that we have to continually interpret, and was not terribly explicit or vulgar -- not terribly clever or especially funny, but was it THAT bad? I suspect you shouldn't drive a car, so you can keep your eyes off of any offensive bumper stickers you might encounter. Or is /. now available in North Korea and Utah?

Fail.

[Bearhouse]

MTBF is Mean Time Between Failures, (device is repairable).
For HDDs, you should really be talking about MTTF.
http://en.wikipedia.org/wiki/MTBF

RAIDing SSDs is a wimp solution

[klubar]

If you're really looking for high performance storage, you should go with a DRAM-based solution. This has almost no latency and can scale to any interface. Depending on your budget, you can get SAS 3GB/s 2 ports with 32GB capacity for a bargain $24,000 (URL:http://www.solidaccess.com/products.htm/> and if you need more performance or storage space, spring for the serious iron--a FC 4GB/2, 2 ports at a mere $375,000.

No need to raid this puppy. Make sure you spring for the redundant power supplies and rack-mountable UPS.

But!

[Weaselmancer]

Who shall watch the watch men?

Because Windows memory management sucks?

[SanityInAnarchy]

No matter how much RAM you give Windows, it will still page. It's to the point where people make ramdisks to put pagefiles on.

Not that I should talk... I have 1 gig of swap on Linux, and I'm thinking I could use more. Why? Because I have 4 gigs of RAM, and if I'm actually using even half of that, I can't hibernate.

Why Adaptec?

[Anonymous Coward]

It would make a lot more sense if the test was re-performed with different SATA controllers. Specifically, on-board Intel ICH9 or ICH10, Promise, HighPoint RocketRAID, and Areca.

Had I done the review, I would not have bothered using an Adaptec controller. I haven't used their garbage for years.

BAARF

[tepples]

Why not run RAID-5 (or 50 or 15) if it is seek-heavy?

Because four drives in a RAID-10 are three times as reliable as the same four drives in a RAID-5. Arrays of large drives are more vulnerable to drive failures during reconstruction than arrays of small drives, and RAID-5 is much more vulnerable to a double drive failure than RAID-10. In RAID-5, you lose data if any two drives fail. In RAID-10, you lose data only if the drives that fail are from the same mirrored pair, and there's only a 1 out of 3 chance that two randomly selected drives will be from the same pair. This makes it that much less likely that you'll have to roll back to the tapes.

That and you don't have to read-modify-write to calculate parity on RAID-10, as XanC pointed out.

USB flash drive RAID?

[hack slash]

When will someone come up with a hardware or software RAID solution to enable several USB flash drives to appear as a single drive on Windows? with relatively reliable & fast (12MB/s write, 30MB/s read) 16GB flash drives as cheap as £16 each I'd love to cram as many as I could inside my Eee and have them appear as a single drive instead of many individual drives.

Re:USB flash drive RAID?

[BobMcD]

Can you RAID eSATA?

http://www.kanguru.com/eflash.html

Re:USB flash drive RAID?

[Anonymous Coward]

When you write it. F/L/OSS works both ways

Incorrect: Not Fastest SSD

[Anonymous Coward]

The Fastest SSD on the planet is FusionIO.

I have personally benchmarked a SINGLE FusionIO drive in Redhat at 136,000 4k read IOPs and 96,000 4k random IOPs. Setup a Software RAID of four devices and get even better numbers.

Re:Incorrect: Not Fastest SSD

[Anonymous Coward]

You have four PCI-e slots available to do your software RAID of FusionIO drives?

Getting 20+ SATA ports is easy, PCI-e expansion is a bit more tricky.

FusionIO is nice, but not the most convenient of form factors if you're looking to upgrade SATA/SAS disks.

Hyperdrive4 or Hyperdrive5?

[Anonymous Coward]

Seriously folks, once you start stepping up to these kinds of things, getting a Hyperdrive actually starts to look attractive, though that does depend on the workload. Unless the FusionIO PCIe gear gets more reasonably priced, a Hyperdrive is a more realistic solution. The big problem with flash SSD's is the wear due to full block/cell writes. Arguably, a striped RAID only makes that situation worse, because you are potentially more likely to write less than a block size (depending on stripe block size, awareness at the RAID controller level, and at the OS level).

Now if somebody can bring back the concept of a RAM card using the guts of a Hyperdrive, we may have something here. PCIe 2.0 direct interface like the FusionIO stuff to skip the physical SATA interface limits, make it a full size card to give the necessary real estate for the DDR2 RAM sockets, an exterior PCI card cover opening to shove a CF card in for backup purposes, and a spot for the battery.

Drool starts when you think of putting such cards in an external PCIe chassis like the ones from Magma

http://www.magma.com/products/pciexpress/expressbox4-1u/index.html

especially if you double up the chassis capacity ( I don't see anything really stopping a 1U going from 4 to 8 hosted cards physically), and a double iPass cable to a HBA with twin outputs to give you PCIe x16 speed.

Or you could just go the ghetto route and do a poor man's Thumper with vertical Hyperdrive 5's in a 3x8 array in a 4U chassis (maybe 5U due to drive length?)

I hate to ask but...

[Douglas Goodall]

As SSD drives come into the market used, how will people know how close these drives are to "used up". That is to say, we will have to worry that these cheap drives on ebay will have lots of "bad" spots that can no longer be written. We are going to be needing a program or device of some kind that can certify the state of a drive so as to set a fair value on it. I expect a lot of unhappy people when used drives get installed and start failing soon after. There will have to be some pretty sleazy warrantees to cover used SSDs.

Re:I hate to ask but...

[BobMcD]

You've got a point, but I'm not sure this is really all that different from existing drives. I mean, you also have almost no idea what condition magnetics are in when you purchase them either. Likewise, ipods use SSD and still have a fairly strong resale value.

Re:I hate to ask but...

[Douglas Goodall]

On hard disks, there are two kinds of bad sectors. Those that were that way from the start because of manufacturing defects, and some dynamically occurring ones. In the industry, there are general guidelines about how many bad sectors per platter are considered reasonable. With SSD, all sectors start out useable and eventually (dynamically) fail. A used hard drive may have more dynamically failed sectors than it started out with, but that number would probably never increase past a few percent. The SSDs though eventually reach the point where the dynamically failed sectors are 100%. So I would buy a used hard drive expecting it might have a little more vibration, perhaps several dozen dynamically failed sectors, and the MTBF would be shorter. SSDs though are a different game. You are betting that the drive will last until you are ok simply replacing it, before it dies completely. Things will get very dicey towards the end, and you are hoping not to be there by then. SSDs are kind of like cars that last so long, then they start dying and you can't keep them running no matter how many repairs you make. Like cars, leasing SSDs and getting a new one each year would be the way to go, and buying used ones would be risky. If it sounds like I am down on them, maybe I am. If I had an application where I needed solid state storage and was willing to pay more and replace them often, they could be just the solution. When they become cheap enough, using them and discarding them when they get cranky would be fine.

Suspend-to-Swap

[spaceturtle]

I use a large pagefile so that I can use Suspend-to-Swap. I occasionally do swap out most of my 2GB of memory when running stress tests, but I don't need to swap all of it back in at once so my system remains usable. In any case, since 8GB of regular disk space is dirt cheap there is little need to change this behavior (although swapfiles may make more sense).The strongest argument for disabling swap on a regular harddisk would be to force the OOM killer to kill a misbehaving process that suddenly wants to allocate all memory, but there are other ways of doing this.

Re:Suspend-to-Swap

[Anonymous Coward]

it's not an issue of disk space
it's an issue of a poorly performing system when you're swapping out gigs of ram

Agreed

[LostMyBeaver]

My wife who loves me very much bought me the 28 port 512mb version of this hard drive controller for Christmas and I have loved it, but I feel like I'm wasting it by running it in a shitty Core 2 Quad motherboard instead of a Xeon motherboard.

I have actually run this exact controller in a Pentium M motherboard during my 3ware to Adaptec transition phase, and the results are entirely different. Especially since the Adaptec drivers are poorly suited for single core systems. After all, you just don't add a $300-$1700 controller to a computer that costs more to ship than to buy on eBay.

So far as I'm concerned, the test is entirely unrealistic and invalid. It's time these guys "rebooted" and got at least a quad core PC, at least using the x58 chipset, bus performance is less of an issue and peripherals should perform at their full potential.

ntfs vs ext2/3 Not....

[leuk_he]

The original poster was correct. Ik you look at the report you will notice that with most test the adaptec card is the "bottleneck". The test is really a comparison of different ways to connect a storeage device to a underpowered cpu.

using ntfs or a optimized raid FS will not change that bottleneck. Beside that, the raid optimizations you speak about are buffers and number of seeks, things where the ssd shines anyway.

If you want a good test ot get the last byte out of a ssd you need a test that shows where the bottlenecks are on this relatively new media. Did you niotice test where write amplicication shows up? (SSD are bad when down muliple small writes), did you notice that the XM-25 performs worse just after it was completely full?

I did not care to check, because these things are not in my personal budget.

A Pentium 4?

[Fishymachine]

Testing a SSD RAID 0 configuration on a system based around Pentium 4? I personally don't consider this a relevant test.

Not so fast there

[stonecypher]

"Intel's X25-E Extreme SSD is easily the fastest flash drive on the market,

Actually, according to pretty much every review I can find, FusionIO's IoDrive spanks the pants off of the Intel Extreme, even in raid-0 eight drive combinations. It can saturate PCIe x4.

It'd be great if citations were required for broad claims like this.