Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Hybrid Storage Solutions Compared

Soulskill posted more than 2 years ago | from the mules-go-in-the-barn dept.

Data Storage 61

Vigile writes "While few would argue with the performance advantages of solid state drives, the relative cost compared to spindle-based disks still make them a luxury item. The promise of hybrid storage solutions is to combine the benefits of both — large capacities with standard drive technology and performance advantages of solid state. PC Perspective published an article comparing several different solutions that vary in their approach to hybrid storage. The OCZ RevoDrive Hybrid combines a standard 2.5-in drive with a PCI Express-based SSD that offers the best overall performance and largest cache size. Seagate's new Momentus XT 2.5-in solution embeds the cache on the PCB of the drive, allowing notebook users to install this solution easily. Finally, the Intel chipset-based caching option combines either a 2.5-in or mSATA SSD with a standard hard drive on either desktop or mobile platforms, allowing the most flexibility of any other hybrid solution. All three have advantages for specific consumers, though, and varying performance levels to go along with them."

Sorry! There are no comments related to the filter you selected.

Um (0)

masternerdguy (2468142) | more than 2 years ago | (#38285842)

Doesn't the disk fail if that SSD cache dies? Correct me if I'm wrong, but SSD technology still has a severely limited number of max writes.

Re:Um (2, Informative)

Anonymous Coward | more than 2 years ago | (#38285896)

The limit of an ssd's max writes is high enough that time wise a mechanical hard drive is more likely to fail during the normal lifespan.

Wrong approach. (1)

ResidentSourcerer (1011469) | more than 2 years ago | (#38292624)

Putting both in the same can is the wrong way to do it.

A better way is to have SSD and hard disk as tiered storage. The OS is more likely to be able to make better decisions for what to store where. So think in terms of overmounting the SSD onto the HD file system.

The OS on reading a file from the HD looks at the access pattern and if it gets accessed frequently, it writes it out to the SDD. If a file hasn't been accessed for a while it gets deleted from the SSD if it's clean, written to the HD and deleted if it's dirty.

When a file is created it's written to the SSD. If it's not accessed for X hours, it's flushed to HD. If it's not accessed for Y hours (Y>X) it's deleted from HD.

With separate SSD/HD you can pick your components. You can also do things like mirror your SSD and RAID your HDs.

Surprised this sort of FS access not available on Linux/BSD yet.

Re:Wrong approach. (1)

badkarmadayaccount (1346167) | more than 2 years ago | (#38422250)

ZFS

Re:Um (1)

MrMista_B (891430) | more than 2 years ago | (#38285990)

Re:Um (1)

Anonymous Coward | more than 2 years ago | (#38286306)

That analysis is for high-end enterprise-class SSDs that use SLC memory. The lifespan for consumer-class MLC-based SSDs is much worse.

Re:Um (1)

Christian Smith (3497) | more than 2 years ago | (#38286580)

That analysis is for high-end enterprise-class SSDs that use SLC memory. The lifespan for consumer-class MLC-based SSDs is much worse.

And consumer drives are generally less write heavy as well. Newer enterprise class SSDs are MLC as well. Given the cheapness of MLC, you can increase the amount of FLASH available to make up for the lack of erase cycles, and using deduplication like the SandForce drives, you write less anyway (I wonder how SF drives do GC.)

Simple fact is that firmware errors or user errors will lose your data before the FLASH wears out.

Re:Um (3, Insightful)

mollymoo (202721) | more than 2 years ago | (#38286550)

That article talks about enterprise drives which use SLC flash. SLC has 20 - 30 times the write endurance of the MLC flash you get in consumer-grade SSDs.

SSD controllers are good enough now that I wouldn't worry about the MLC flash in my laptop's SSD for general use, but I'd take a very close look at the numbers if I was using it to do anything that was write heavy (like video work or building a big codebase).

Re:Um (0)

Anonymous Coward | more than 2 years ago | (#38290188)

Well, issues here:

-) hdds on mobile devices tend to fail quite often (when you travel often enough), I've got used to replacing the hdd every 12 months on my subnotebook, to avoid these "OMG, have to run to get a new hdd to try to recover the data on the failing hdd" moments.

-) SSDs (even good consumer grade devices) have enough write cycles that they'll keep quite a bit of time even under heavy write load.

-) SSDs tend to have electronic failures implying completely dead device => that's just because they don't do the bit by bit physical deterioration thing. So backups are important. (Is helped by the fact that SSD tends to be smaller, HDDs are nice backup media, and reading/writing serially works well enough with hdds.

-) Actually, for basically anything write intensive (that is not >99% serial writing/reading) a SSD is a must. So what if you have to replace the SSD every 12-24 months, if the stuff you are doing gets drastically faster. Random access is where SSDs shine, e.g. the rule of thumb is that you get ~70 transactions (write, DBA speak) per hdd spindle. So using high end discs (which means btw going into price ranges that are very SSD-ish) you manage say ~100 iops. So a 10 disc array maxes out in the best case around ~1000 iops. Sounds great. Till you look at a conservative consumer grade SSD and notice that even the slowest one specify way more write iops.

So basically in practice, as the $/GB metric is still to big, you end up with OS/Apps/data on the SSD and multimedia files (huge) on HDD.

Re:Um (2)

BagOBones (574735) | more than 2 years ago | (#38286060)

According to Seagate the Momentus XT will fail back to being a regular hard drive if flash failure is detected by the controller. All data in flash is also stored on the drive, the SSD part only caches a copy of already stored data for faster read performance.

Re:Um (2)

sexconker (1179573) | more than 2 years ago | (#38286176)

According to Seagate the Momentus XT will fail back to being a regular hard drive if flash failure is detected by the controller. All data in flash is also stored on the drive, the SSD part only caches a copy of already stored data for faster read performance.

That's obviously true for reads, but is it true for writes?

These hybrid devices typically have a battery (excuse me, "super capacitor") to flush any cached writes out to disk.
But what if the OS thinks data was written (because it went to the SSD cache successfully), but flushing from cache to disk fails because something broke on the SSD side?

SSD controllers haven't been exactly stellar in terms of reliability so far.

For my money, I just got two 256 GB Crucial M4s, and I do daily full-image backups (excluding *.bt! and any steam games) to an external 2 TB drive.

Re:Um (1)

nabsltd (1313397) | more than 2 years ago | (#38286338)

That's obviously true for reads, but is it true for writes?

The Momentus XT only caches reads. Writes (i.e., data from the computer to the drive) completely bypass the cache.

If you can add 4-8GB of RAM, you're better off spending your money on that and a standard 3-1/2" mechanical hard drive. The Momentus XT really is only useful in laptops.

Re:Um - really good for laptops (0)

Anonymous Coward | more than 2 years ago | (#38286826)

Yes, it is a godsend in a laptop where you're likely to be limited to 4GB or 8GB of RAM. I put a 500GB XT in my mid-2010 15" macbook pro about three months ago. The 8GB of cache is about 10% of the working space I'm likely to use while processing photos during one sitting. It helps a lot when working with RAW camera images and HDR compositing after shooting on location wherever.

Re:Um - really good for laptops (0)

Anonymous Coward | more than 2 years ago | (#38287808)

A mid-2010 macbook is limited to 4-8 GB RAM? I could install 8 GB in my nearly five year old ThinkPad X61 tablet.

Re:Um (1)

dargaud (518470) | more than 2 years ago | (#38288764)

SSD controllers haven't been exactly stellar in terms of reliability so far.

Yeah. This post is quasi a dupe of a few days ago [slashdot.org] where this eye opening message was posted [slashdot.org] .
I have converted most of my systems to SSDs for the system disk and now I'm scared. I'm sure there's an OCZ somewhere in there... Add to this the risk of mechanical failure and added complexity ,and I'm really not sure I want an hybrid.

Re:Um (0)

Anonymous Coward | more than 2 years ago | (#38289372)

According to Seagate the Momentus XT will fail back to being a regular hard drive if flash failure is detected by the controller.

It remains to be seen if that really works. There's so many failure points. Will it actually catch the flash failure, will there be corrupted data, a confused state of disk, and so on.

Re:Um (5, Informative)

Misch (158807) | more than 2 years ago | (#38286190)

Doesn't really matter.

Anand from Anandtech writes [anandtech.com] :

My personal desktop sees about 7GB of writes per day. That can be pretty typical for a power user and a bit high for a mainstream user but it's nothing insane. ...
If I never install another application and just go about my business, my drive has 203.4GB of space to spread out those 7GB of writes per day. That means in roughly 29 days my SSD, if it wear levels perfectly, I will have written to every single available flash block on my drive. Tack on another 7 days if the drive is smart enough to move my static data around to wear level even more properly. So we're at approximately 36 days before I exhaust one out of my ~10,000 write cycles. Multiply that out and it would take 360,000 days of using my machine for all of my NAND to wear out; once again, assuming perfect wear leveling. That's 986 years. Your NAND flash cells will actually lose their charge well before that time comes, in about 10 years.

Re:Um (1)

bill_mcgonigle (4333) | more than 2 years ago | (#38292826)

Multiply that out and it would take 360,000 days of using my machine for all of my NAND to wear out

The number to be concerned about isn't when all of the cells wear out, it's when one more than you need for cell redundancy wears out.

Flashcache (2, Interesting)

Anonymous Coward | more than 2 years ago | (#38285906)

Facebook released, some time ago, their Flashcache solution. It works similar to ReadyBoost, et al, except it works on Linux, and "pairs" an SSD with a hard drive. Very useful.

http://www.facebook.com/note.php?note_id=388112370932

A question for Slashdotters. (-1)

Anonymous Coward | more than 2 years ago | (#38286018)

I was surfing the internet the other day, and I came across this question: "Ohhhhhh, Jeeeeesus, caaaan youuuu seeeeee... what's insiiiiiide myyyyyy underweeeeeeeeeear?"

And it got my thinking: if Jesus exists, can he see inside my underwear?

Seagate Momentus XT *not* new (2)

devleopard (317515) | more than 2 years ago | (#38286038)

Seagate's new Momentus XT 2.5-in solution

Had a 500 GB version in my laptop since they came out last year (Summer I think) And yes, it's much faster than a typical 7200 rpm drive.

Re:Seagate Momentus XT *not* new (0)

Anonymous Coward | more than 2 years ago | (#38286106)

They just released their second generation drives, so the description is accurate, if misleading.

Re:Seagate Momentus XT *not* new (0)

Anonymous Coward | more than 2 years ago | (#38286224)

I just installed the new 750GB Momentus XT, and it's noticeably faster than the 500GB Momentus XT. No word yet on the reliability.

Re:Seagate Momentus XT *not* new (1)

devleopard (317515) | more than 2 years ago | (#38287044)

Yes, but the technology is essentially the same (as the article summary described it) - Flash memory on the PCB (the changes are to an upgraded SATA 6G interface)

Filesystem (3, Interesting)

Anonymous Coward | more than 2 years ago | (#38286162)

What I want is a filesystem that can use a partition of an SSD and a partition of a rotating magnetic disk. Metadata, directories and small files on the SSD, big files on the rotating disk.

This ought to be fairly simple - anyone fancy hacking ext4?

Re:Filesystem (1)

Anonymous Coward | more than 2 years ago | (#38287994)

Since it ought to be fairly simple: Simply do it and mail the diffs.

Re:Filesystem (0)

Anonymous Coward | more than 2 years ago | (#38289394)

This ought to be fairly simple - anyone fancy hacking ext4?

It would actually be quite a challenging project. Not necessarily impossible, though.

Re:Filesystem (1)

GNious (953874) | more than 2 years ago | (#38290918)

Mirror an SSD and HDD, with either interleaving-reads or exclusively reading from the SSD - voilá.

Writes are slow (but may look fast, depending on the mirroring-algorithm), but reads are going to be either faster-than-HDD (when interleaving) or alot-faster-than-HDD (when only reading from SSD).

To ensure they remain identical, some reads should be from both drives, so don't expect everything to be SSD-speed, though.

Re:Filesystem (0)

Anonymous Coward | more than 2 years ago | (#38307122)

What you are looking for is a journaling filesystem with the journal itself stored on a separate device. This is available.

hybrid vs SSD+HDD (0)

Anonymous Coward | more than 2 years ago | (#38286170)

Why bother?

For the price of one of these you could buy a larger ssd and a larger hdd (shortages not widthstanding)

The time for hybrid drives has passed with ssd approaching $1 per gb.

Adaptec Hybrid RAID (2)

cffrost (885375) | more than 2 years ago | (#38286258)

Adaptec has a new technology called Hybrid RAID, which uses 50% SSD/50% HDD in RAID 1 or RAID 10. Reads are serviced by the SSD(s) only. It seems to me you might need to short-stroke the HDD in order to make this a reasonable approach.

Their new 6E series is very inexpensive for 6Gb SAS cached (128MB) hardware RAID; 6805E is (8 int. ports) is about $225 retail:
https://www.adaptec.com/en-us/products/controllers/hardware/sas/entry/sas-6805e [adaptec.com]

I'm no shill or fanboy; I just found this interesting and relevant.

Re:Adaptec Hybrid RAID (1)

drinkypoo (153816) | more than 2 years ago | (#38286700)

It seems to me you might need to short-stroke the HDD in order to make this a reasonable approach.

Well gee, I'll install a shortened crank just as soon as I finish my valve job.

I'm no shill or fanboy; I just found this interesting and relevant.

Well, when you get done short-stroking, maybe you could explain what you were talking about.

Re:Adaptec Hybrid RAID (1)

cffrost (885375) | more than 2 years ago | (#38287102)

Well gee, I'll install a shortened crank just as soon as I finish my valve job.

For what purpose? Please elaborate.

Well, when you get done short-stroking, maybe you could explain what you were talking about.

Did I say I was going to short-stroke a disk? I was talking about anyone who buys an Adaptec 6E controller for Hybrid RAID.

The reason I suggested short-stroking the HDDs, is due to the capacity and price/capacity differences between SSDs and HDDs... SSDs and HDDs of equal capacity will likely be either very slow or very expensive. Given that the 6E series is aimed at budget workstations, both of those options are probably not ideal.

Re:Adaptec Hybrid RAID (1)

Thing 1 (178996) | more than 2 years ago | (#38287262)

"Hi, I'm going to respond to your comment (which uses jargon in one area), by using jargon in another area. You know, I'm hip and all that, and cannot look up jargon I do not understand. Perhaps, by repeating the word 'jargon' often enough, I might think of it as some sort of reptile or something. You know, 'cuz I'm hip."

Re:Adaptec Hybrid RAID (1)

Alphadecay27 (1277022) | more than 2 years ago | (#38288006)

Short-stroking is restricting a HD to the outer area of the disk which is higher performance. This also makes access times better since the max distance the head has to travel is shorter. The capacity of the drive is decreased significantly depending on how much you restrict the area e.g. 1 TB > 100 GB might cut access times by 50% and bring your minimum and average transfer rates close to your max rate.

Tom's hardware article here: http://www.tomshardware.com/reviews/short-stroking-hdd,2157.html [tomshardware.com]

This was more viable when HDs were dirt cheap. I don't think you would want to do it in a hybrid setup since the point is to get capacity + speed. If you just want speed, use the SSD on it's own.

Re:Adaptec Hybrid RAID (1)

batkiwi (137781) | more than 2 years ago | (#38288584)

Short Stroking a HDD refers to telling the firmware that a disk has less sectors than it really has. An easy example is setting a 1.5TB drive as a 500gb. That means that you only use the INNER 1/3 of the disk (the fastest part). Additionally you reduce head movement.

Re:Adaptec Hybrid RAID (1)

jones_supa (887896) | more than 2 years ago | (#38291528)

Short Stroking a HDD refers to telling the firmware that a disk has less sectors than it really has. An easy example is setting a 1.5TB drive as a 500gb. That means that you only use the INNER 1/3 of the disk (the fastest part). Additionally you reduce head movement.

But but but...how is the situation when the HDD has multiple platters? Assuming that this 1.5TB disk has 3 x 500GB platters, wouldn't short-stroke like that mean that the whole disk area is used, but only one platter? Or is the data interleaved across platters?

Re:Adaptec Hybrid RAID (1)

Alphadecay27 (1277022) | more than 2 years ago | (#38292772)

But but but...how is the situation when the HDD has multiple platters? Assuming that this 1.5TB disk has 3 x 500GB platters, wouldn't short-stroke like that mean that the whole disk area is used, but only one platter? Or is the data interleaved across platters?

The data is interleaved across the platters. If you look at the access times Tom's hardware got from short-stroking, you can see that they drop considerably. This is because the head moves over a much shorter range.

http://www.tomshardware.com/reviews/short-stroking-hdd,2157-5.html [tomshardware.com]

Re:Adaptec Hybrid RAID (1)

Coren22 (1625475) | more than 2 years ago | (#38294142)

One criticism. It is the outer edge of the disk that is used, because it is faster.

Re:Adaptec Hybrid RAID (0)

Anonymous Coward | more than 2 years ago | (#38288672)

Has Adaptec come up with a *usable* utility to manage these HBA's? Last I'd checked, all they had was arcconf which, if you could find it, sucked even worse than LSI's megacli.

Re:Adaptec Hybrid RAID (1)

cffrost (885375) | more than 2 years ago | (#38289036)

Has Adaptec come up with a *usable* utility to manage these HBA's? Last I'd checked, all they had was arcconf which, if you could find it, sucked even worse than LSI's megacli.

I'm sorry, I have no idea; I want a 6805E but I don't have one yet. I've only used Adaptec's x64 Windows GUI utility with a Supermicro-branded Adaptec 3Gb SAS ZCR adapter. I had no complaints with Adaptec's software; the ZCR card's performance was bad enough to keep me from noticing. The non-RAID LSI U320 and Tekram U160 cards I used before that had firmware-based configuration only.

In what way were Adaptec and LSI's CLI utilities deficient (reliability, lack of control, etc.)?

Re:Adaptec Hybrid RAID (1)

TheTyrannyOfForcedRe (1186313) | more than 2 years ago | (#38290322)

You can do the same with Linux software raid for $0. Check out mdadm --write-mostly and --write-behind options.

Pointless (1)

lucm (889690) | more than 2 years ago | (#38286382)

Reading from SSD is insanely faster than reading from SAS. Writing to SSD is much slower. There is no way around that.

Those hybrids products are simply a futile tentative to come up with a cheap alternative to what is really needed: adding a decent cache on SSD controllers so the write buffer is big enough to mitigate the write penalty, and adding enough processing power to perform destaging properly.

This being said - if someone comes up with a way to read from SSD and write to SAS, then it's a winner... but the magic part that brings the written bit from the SAS to be read by the SSD is the million-dollar catch.

Until then, those hybrids are just a Fisher Price implementation of sub-volume tiering.

Re:Pointless (1)

Local ID10T (790134) | more than 2 years ago | (#38287154)

Reading from SSD is insanely faster than reading from SAS. Writing to SSD is much slower. There is no way around that.

Those hybrids products are simply a futile tentative to come up with a cheap alternative to what is really needed: adding a decent cache on SSD controllers so the write buffer is big enough to mitigate the write penalty, and adding enough processing power to perform destaging properly.

This being said - if someone comes up with a way to read from SSD and write to SAS, then it's a winner... but the magic part that brings the written bit from the SAS to be read by the SSD is the million-dollar catch.

Until then, those hybrids are just a Fisher Price implementation of sub-volume tiering.

It is just a little more code on the controller... directing writes to HD and reads from SSD, sync happens in the background, using a flag (toggle specific bit in the header) for the copy of the file on the SSD to indicate that changes are being written to the HD and reads must be directed there until the file is synced again.

Re:Pointless (1)

lucm (889690) | more than 2 years ago | (#38287610)

Reading from SSD is insanely faster than reading from SAS. Writing to SSD is much slower. There is no way around that.

Those hybrids products are simply a futile tentative to come up with a cheap alternative to what is really needed: adding a decent cache on SSD controllers so the write buffer is big enough to mitigate the write penalty, and adding enough processing power to perform destaging properly.

This being said - if someone comes up with a way to read from SSD and write to SAS, then it's a winner... but the magic part that brings the written bit from the SAS to be read by the SSD is the million-dollar catch.

Until then, those hybrids are just a Fisher Price implementation of sub-volume tiering.

It is just a little more code on the controller... directing writes to HD and reads from SSD, sync happens in the background, using a flag (toggle specific bit in the header) for the copy of the file on the SSD to indicate that changes are being written to the HD and reads must be directed there until the file is synced again.

Yeah, on paper, this is easy enough, anyone can draw a quick diagram... however, reality is much more tricky. Everything that is hidden under that "sync" concept is incredibly complex because both nodes are actively working on I/O and because of physics the backend spindle are slow; it's like reordering balls when you are juggling. You cannot just pick a source and a destination, or order things like a process scheduler; you need to take into account the evolving state and capabilities of many components (spindles, cache, bus) and do predictive work based on recent trends, otherwise the whole thing will get driven into the ground quickly.

It's like that experiment where people are asked to keep a room temperature between 15 and 20 Celsius, and all they have is a single controller that has a 5-minute delayed impact. Every participant feels that this will be easy, however most of them fail because once they see the temperature going down or up they tend to overreact, leading to a spiral of death.

Re:Pointless (1)

Local ID10T (790134) | more than 2 years ago | (#38294616)

Exactly. It is easy to do... but difficult to do well.

Re:Pointless (1)

drsmithy (35869) | more than 2 years ago | (#38287566)

Reading from SSD is insanely faster than reading from SAS. Writing to SSD is much slower. There is no way around that.

Where do I find a SAS drive that can do a couple of thousand write IOPS ?

Those hybrids products are simply a futile tentative to come up with a cheap alternative to what is really needed: adding a decent cache on SSD controllers so the write buffer is big enough to mitigate the write penalty, and adding enough processing power to perform destaging properly.

I wouldn't claim to be an SSD expert, but I'm pretty sure that happened a year or two ago.

Re:Pointless (0)

lucm (889690) | more than 2 years ago | (#38287686)

Reading from SSD is insanely faster than reading from SAS. Writing to SSD is much slower. There is no way around that.

Where do I find a SAS drive that can do a couple of thousand write IOPS ?

Those hybrids products are simply a futile tentative to come up with a cheap alternative to what is really needed: adding a decent cache on SSD controllers so the write buffer is big enough to mitigate the write penalty, and adding enough processing power to perform destaging properly.

I wouldn't claim to be an SSD expert, but I'm pretty sure that happened a year or two ago.

Enterprise-grade SSD will NOT give you 2000 IOPS. Best case scenario, 5-10x less. If all the planets are aligned and the wind is blowing from the right direction, in read you might get 1500 IOPS. Might. And we are talking here about a 5 digits price tag for that kind of drive. As for consumer-grade, well, you get what you pay for.

The only way to get 1000+ IOPS on write, on any storage technology that is not a military secret, is via some kind of cache (or a power surge...). There are just no controllers that can handle that kind of bandwidth and no device fast enough to catch up.

If you have some literature or benchmarks showing that a SSD drive (with no cache) can write more than 350-400 IOPS, please share, I would be thrilled to try one.

Re:Pointless (1)

drsmithy (35869) | more than 2 years ago | (#38287862)

If you have some literature or benchmarks showing that a SSD drive (with no cache) can write more than 350-400 IOPS, please share, I would be thrilled to try one.

I think you need to expand a bit more on exactly what and how you're benchmarking, because even consumer-grade (ie: buy it from Newegg) SLC drives are reported to hit a couple of thousand IOPS in 4k random write benchmarks. 1500 read also seems ludicrously pessimistic.

(Not to mention even 350-400 IOPS is still twice the performance you'd get out of a 15k spindle.)

Re:Pointless (1)

lucm (889690) | more than 2 years ago | (#38288058)

If you have some literature or benchmarks showing that a SSD drive (with no cache) can write more than 350-400 IOPS, please share, I would be thrilled to try one.

I think you need to expand a bit more on exactly what and how you're benchmarking, because even consumer-grade (ie: buy it from Newegg) SLC drives are reported to hit a couple of thousand IOPS in 4k random write benchmarks. 1500 read also seems ludicrously pessimistic.

(Not to mention even 350-400 IOPS is still twice the performance you'd get out of a 15k spindle.)

WIse quote from Wikipedia here: "As with any benchmark, IOPS numbers published by storage device manufacturers do not guarantee real-world application performance". To get real numbers, what you need to do is call a vendor such as Hitachi or IBM, and ask them what they feel comfortable putting in a SLA as far as sustained IOPS goes (not theoretical maximum). If you get an answer, you will get the same numbers as any storage admin will give you:

SSD: Read 1500, Write 250-400
FC or SAS2: 200
SATA: 80

If you look at whitepapers, you will get crazy numbers like 200k IOPS for a single drive - but this is under very specific conditions, without the interface, without concurrency, using their specialized controller, etc etc. Lab numbers != real life.

I've seen thousands of live reports from enterprise-grade storage (IBM, HP, Hitachi); I've personally beat the sh*t out of a 2 millions dollar high-end SAN using G5 blades with each node running IOMETER ad SQLIOSIM 24x7 for days in order to test the sub-volume tiering behavior. And never did I see a spindle sustaining much more than the above figures. And even if a spindle was able to sustain that load, there is just no transport solid enough to handle the bandwidth.

Now if you want to get into the nano-second benchmarking where you take the very peak that can happen over a long-running, unrealistic workload, then yeah, put whatever number you want. But this is like saying that a Ford Explorer will do 2000MPG because you take a 2-second interval when it's going downhill on the Everest and you use that as a performance indicator.

If you want real figures instead of drinking the marketing kool-aid, use common IOPS simulators, such as "Disk Magic" (from Intellimagic) or typical web apps like this one:
http://www.wmarow.com/strcalc/ [wmarow.com]
(which I did not create and have no interest in promoting)

Re:Pointless (1)

mwvdlee (775178) | more than 2 years ago | (#38288834)

adding a decent cache on SSD controllers so the write buffer is big enough to mitigate the write penalty

You mean like using an HDD as a cache?

Re:Pointless (1)

lucm (889690) | more than 2 years ago | (#38294216)

adding a decent cache on SSD controllers so the write buffer is big enough to mitigate the write penalty

You mean like using an HDD as a cache?

The key word here would be "decent".

Performance numbers (2)

WaffleMonster (969671) | more than 2 years ago | (#38286516)

You can purchase 24 GB of ram for less than $200 today. I would love to see a side by side performance and energy consumption comparison with someone who decided to spend their extra money on DRAM.

I suspect what you'll see is that after a day all read operations are resolved instantly from the OS disk cache without the performance and power hit of flash. If you have write intensive workloads the current crop of SSDs would not be for you anyway.

Re:Performance numbers (4, Insightful)

Rockoon (1252108) | more than 2 years ago | (#38287306)

From a performance perspective it might be interesting, but from a power consumption perspective the SSD blows away a handful of DDR3 sticks.

Re:Performance numbers (1)

WaffleMonster (969671) | more than 2 years ago | (#38293148)

From a performance perspective it might be interesting, but from a power consumption perspective the SSD blows away a handful of DDR3 sticks

Higher density, process and lower operating voltages have been dropping DRAM power consumption many times over in the last few years. Latest DDR3 is able to run 24GB on 7 watts.

Whether you will see better or worse power consumption depends on your workload (how much longer or shorter computer needs to run to get the same job done) under each SSD vs DRAM usage scenario.

Re:Performance numbers (1)

Rockoon (1252108) | more than 2 years ago | (#38296366)

The best SSDs (in terms of power consumption) use about 0.1W idle and 0.6W under load.

The DDR3 just can't compete. It might score favorably against specific SSDs, but that would be cherry picking bad SSDs in order to make stacking up DDR3 look better. Your proposition was that "after a day all read operations are resolved instantly from the OS disk cache" which means you've been burning 7W all day long on your cache. Its simply not possible in the propositional case for DDR3 to win on power consumption.

DDR3 is a lot faster tho, and that has value. You buy that value from your local power company.

The problem (1)

Gaygirlie (1657131) | more than 2 years ago | (#38287508)

The problem with most hybrid disks is the fact that they don't know about filesystems, they don't know about current working conditions of the rest of the system and they don't know of user and application preferences: they're working with a very limited set of data available to them and thus they can only base their operation on guesses of what is going to be needed next. The OCZ RevoDrive is the exception here in that it's actually two drives that are both accessible separately to the OS and/or applications if one doesn't install their caching software.

OS- and filesystem-agnostic system is always going to be somewhat limited so it would be beneficial if the rest of these hybrid systems also allowed the OS direct access to the flash so that the OS can optimize its behaviour accordingly. Like e.g. the user is reading several multi-gigabyte files, say, disc images for example; a OS- and filesystem-agnostic hybrid will start caching those files since it doesn't know how large those files are or how often they're needed, whereas if OS handled the caching it could determine that those files are accessed very rarely, usually in large sequences, and thus it would be better to skip caching them and instead save the cache for any related smaller files that are accessed more often. If you're familiar with the Windows ReadyBoost it actually works similarly: it skips caching large files as usually mechanical drives are more than fast enough for large sequential reads, but it instead caches a helluva lot of all kinds of small files since flash is absolutely terrific at random accesses and reading in even hundreds of small files from a slow flash is still faster than reading them in from the fastest mechanical one (I have a class10 16GB SD-card in my laptop as ReadyBoost drive and I've certainly noticed huge improvement in application startup times)

So yeah, sure, do create hybrids, they're a good idea in general. Just allow the OS to flip a bit and gain direct access to the flash part, too, for those OSes that are aware of such.

Re:The problem (1)

bill_mcgonigle (4333) | more than 2 years ago | (#38292886)

Just allow the OS to flip a bit and gain direct access to the flash part, too, for those OSes that are aware of such.

These products seem to be for people who can't do that.

I'm one - in my laptop anyway, I have a Momentus XT. It's a small boost, but I find it worthwhile. And I have nowhere else to put some flash.

But at the office, I have a few SSD's inside my servers. I use them for ZFS L2ARC and ZIL. They can also be used for bcache and ext4 journals. I have extra power and SATA headers in those things, though, and I understand how to read a man page.

thunk different (1)

pbjones (315127) | more than 2 years ago | (#38288524)

for some reason I thought this article may have been about Prius's or wind/solar power, but.....

Onboard SSD (1)

Translation Error (1176675) | more than 2 years ago | (#38293092)

It's also possible to get a motherboard with an SSD built-in and ready to operate with SRT. The $240 GIGABYTE GA-Z68XP-UD3-iSSD [newegg.com] has a 20GB SSD and, in the words of the manufacturer is (so feel free to take salt with them) is:

able to outperform hybrid drive systems by more than 2X (PC Mark Vantage HDD test) and HDD-only systems by as much as 4X (PC Mark Vantage HDD test) and deliver a 60% performance improvement over HDD-only systems in PC Mark Vantage Suite.

I just built a system with this motherboard, and while I haven't run any benchmarks, it does seem to be very fast.

Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?