OCZ Wants To Cache Your HDD With an SSD

sl4shd0rk writes "OCZ is coming out with Synapse Cache; an SSD cache for your hard drive. The SSD runs software that copies data into the cache from your hard drive as you work with it. The data sits on the SSD until it gets less activity and gets flushed to the hard disk. Aside from boosting your IOPS to 10k/75k (read/write), the SSD also supports AES encryption, SMART and TRIM."

Comments

Good idea, how will the implementation be ?

[zaibazu]

They need to make the controller logic bullet proof, Seagate had quiet some problems with their hybrid disks

Re:Good idea, how will the implementation be ?

[fuzzyfuzzyfungus]

A best I can tell, this is simply a basic SSD that is shipped with a bundled OEM copy of "dataplex" software from these guys(nice clip art...) (Here is a presentation by them about their product.

The SSD itself is a Sandforce 2281-based MLC drive with 50% overprovision for redundancy. Unless they've really screwed the firmware, it should be just fine, though no word on how it competes in price with other drives of similar size.

The caching function(unlike the Seagate hybrid units) is simply software: Supports Windows 7, no BIOS goo or specialized SATA features required; plugs into the OS somewhere in the storage handling area and shuffles data between the main mechanical HDD and the designated cache SSD.

On the plus side, that should(at least conceivably) give it considerably higher-level knowledge of what the OS is doing with which to make caching decisions(unlike caching firmware, which only has the SATA commands to go on). On the minus side, it means Win7 only, and your storage system is Not the place you want potentially flaky code, so if they aren't on the ball, we could see some serious bluescreening and/or OS hosing going on....

Re:So...

[Bill, Shooter of Bul]

Exactly! ....In the same way that a meatball is a golf ball for those playing the game of spaghetti.

SSD Cache and corruption

[DigiShaman]

Not sure I'm feeling the love for this concept. On the reads, sure. Nice idea. Writes however, not feeling the love. For whatever the reasons, PC hardware can lock up (CPU, video, motherboard, RAM etc) or because of buggy device drivers on the OS. In any event, how well can this device recover from a dirty-cache shutdown? What happens if the device just dies? Will I still be able to mount the HDD and recover data? It would be interesting to see how a journaling file system handles the abstraction of one volume read/written between two different drives. Were not talking about RAID5 here where you at least have parity data to recover from.

Re:SSD Cache and corruption

[fdawg]

Obv I have no idea how OCZ plans on doing this, but I can tell you what a standard journaling fs does.

In any event, how well can this device recover from a dirty-cache shutdown?

Chances are this cache is transparent. The blocks translate to vblocks which map to physical blocks on the rotational media. A "dirty" block is a vblock which hasn't been committed to the physical block. However, this is transparent to the filesystem. When the system comes back up and the journal is replayed at say, some operation 10, and we find the relevant blocks for op 10 which happen to be vblocks in the SSD, the write is stable. It's a NOOP from the filesystem perspective.

What happens if the device just dies? Will I still be able to mount the HDD and recover data?

This is the same as a single, non-tiered, drive dying. Same semantics- cache is dead is equivalent to the drive being dead. That is to say unless the journal and superblock live somewhere else. IIRC ext2/3 keeps the initial copy of the superblock in a few places on the drive. Depending on which you can recover, you'll get a version of the filesystem (likely the one when you first created the fs, i.e. an empty fs). In short, pay attention to your SMART data, and always (ALWAYS!) backup.

It would be interesting to see how a journaling file system handles the abstraction of one volume read/written between two different drives. Were not talking about RAID5 here where you at least have parity data to recover from.

Most journals arent like NVRAM and don't follow the copy on write semantic. Journal replay is usually a data-loss event if all writes weren't stable before the replay. With that in mind, most volume managers (the original "VM"!) allow your fs to write to as many drives as the vm allows. This seems no different. But yeah, maybe they're doing something smarter here.

Wouldn't it be great if it could be a USER add-on?

[wisebabo]

I mean did you know many people have laptops that can take a 12.5mm tall HDD? But most people only buy a 9mm drive?

So it would be nice if OCZ (or another manufacturer) could make a very thin (3mm) card that would piggyback on top of the HDD. It would also have to a SATA drive connector to attach it to the motherboard and then a loop through cable to attach to the drive. In this way the end user could add a SSD cache to their existing laptop!

Is this feasible or am I missing something?

Re:So...

[hairyfeet]

Well according to this answer by a developer you CAN use an SSD for readyboost, its just isn't as straight forward and you can't use the whole drive. personally I've been avoiding SSDs until they get the bugs out as the experience from my gamer customers (who spent waaaay more than i would have for top o' the line SSDs) is that Jeff Atwood at coding horror is correct that SSDs should be judged on a hot/crazy scale as while they are crazy fast the fail crazy often.

To me it isn't THAT they fail it is HOW they fail that has me avoiding them. With HDDs I can't remember the last time I had an HDD that failed without plenty of clear warnings something was up. Windows delayed write fails, or SMART errors, temp going nuts, there was ALWAYS a clear warning that there was trouble in HDD town. With both of the gamers there was NO WARNING with the SSDs, they just flipped the switch and....nothing. With the HDDs I was always able to get the data off before they bought the farm, minus a few bad sectors of course, but with the SSDs it was like they didn't exist, it was just...nothing.

so while using it as a cache (as long as the cache is ALWAYS backed up like Readyboost) sounds fine i really can't see recommending an SSD until they get the bugs out. you would have to spend all your time running back ups or RAIDing the drive constantly to remove the risk, and that is just more trouble than its worth. Besides with Superfetch and Readyboost if you have a large amount of RAM (and what geek don't right? hell even my netbook is gonna have 6Gb on it) then everything you use often is already preloaded into RAM so unless you boot daily i doubt you'd see much difference, as nothing yet beats RAM speed.