Slashdot Log In
Intel Responds To X25-M Fragmentation Issue
Posted by
Soulskill
on Mon Apr 13, 2009 07:22 PM
from the problem-what-problem dept.
from the problem-what-problem dept.
Vigile writes "In mid-February, news broke about a potential issue with Intel's X25-M mainstream solid state drives involving fragmentation and performance slow-downs. At that time, after having the news picked up by everyone from CNet to the Wall Street Journal, Intel stated that it had not seen any of these issues but was working with the source to replicate the problem and find a fix if at all possible. Today Intel has essentially admitted to the problem by releasing a new firmware for the X25-M line that not only fixes the flaws found in the drive initially, but also increases write performance across the board."
Related Stories
[+]
Long-Term Performance Analysis of Intel SSDs 95 comments
Vigile writes "When the Intel X25-M series of solid state drives hit the market last year, there was little debate that they were easily the best performing MLC (multi-level cell) offerings to date. The one area in which they blew away the competition was with write speeds — initial reviews showed consistent 80MB/s results. However, a new article over at PC Perspective that looks at Intel X25-M performance over a period of time shows that write speeds are dramatically reduced from everyday usage patterns. Average write speeds are shown to drop to half (40MB/s) or less in the worst cases, though the author does describe ways that users can recover some of the original drive speed using standard HDD testing tools."
Reader MojoKid contributes related SSD news that researchers from the University of Tokyo have developed a new power supply system which will significantly reduce power consumption for NAND Flash memory.
[+]
Intel 34nm SSDs Lower Prices, Raise Performance 195 comments
Vigile writes "When Intel's consumer line of solid state drives were first introduced late in 2008, they impressed reviewers with their performance and reliability. Intel gained a lot of community respect by addressing some performance degradation issues found at PC Perspective by quickly releasing an updated firmware that solved those problems and then some. Now Intel has its second generation of X25-M drives available, designated by a "G2" in the model name. The SSDs are technically very similar though they use 34nm flash rather than the 50nm flash used in the originals and reduced latency times. What is really going to set these new drives apart though, both from the previous Intel offerings and their competition, are the much lower prices allowed by the increased memory density. PC Perspective has posted a full review and breakdown of the new product line that should be available next week."
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Good for them (Score:4, Insightful)
Re:Good for them (Score:5, Insightful)
Makes an interesting contrast to intel's response to the FDIV bug, eh? Between this and the whole linux driver thing I'm almost inclined to suspect that intel has learned that you have to serve your customers.
Parent
Re: (Score:2)
Please gents, think logically here. This is something fixed ~three weeks after reproducing the problem. And it was something that could easily be fixed with a firmware update. It's not like the hardware was broken.
So, good job Intel for fixing it, but patting them on the back for admitting a problem [on a tiny user base] that was easily fixed is a delusion.
-bullseye
Re:Good for them (Score:4, Funny)
So, good job Intel for fixing it, but patting them on the back for admitting a problem [on a tiny user base] that was easily fixed is a delusion.
You're inferring things from my post that aren't implied. What I'm saying is that intel is perhaps no longer pure, concentrated evil -- not that I want to go start sucking dicks in the executive washroom.
Parent
Re: (Score:2)
How do you know, that is was easy to fix? Did you fix it? Do you know someone who fixes it?
Or are you perhaps talking out of the wrong orifice? ^^
Re:Good for them (Score:4, Insightful)
Parent
Re: (Score:2)
Re:Good for them (Score:5, Insightful)
There's a big difference between admitting to a bug that you can fix with a low/no-cost firmware upgrade, and admitting to a bug which requires a massive recall, and announcing to the market you'll be taking a multi-million dollar loss.
Parent
Re: (Score:2)
There's a big difference between admitting to a bug that you can fix with a low/no-cost firmware upgrade, and admitting to a bug which requires a massive recall, and announcing to the market you'll be charging them more for '486 chips until you pay for the replacements.
There, fixed that for you.
Re: (Score:3, Insightful)
Well to be fair to Intel as you can see here [wikipedia.org] the odds of anybody hitting the bug(hell the odds of Intel accidentally hitting the bug) were pretty much slim to none. Nobody(including Intel) would have probably ever found out it even HAD a bug if Thomas Nicely hadn't written a program to hunt for primes and ran it on a Pentium. Let's face it: It was 1994. Most folks were running simple spreadsheets and simple games on Windows 3.11 at the time. The odds that they would have actually been doing enough floating
Re:Good for them (Score:5, Insightful)
Parent
In Other News.. (Score:2, Funny)
In other news, Microsoft has responded to reports that Windows Vista is slow, buggy, insecure and horribly bloated by releasing DOS 3.2
Fragmentation issue? (Score:4, Funny)
At first I read fragmentation as in "frag grenade".
Guess I've been playing too many violent games. Oh, that reminds me - tax reports are due tomorrow, right?
Least we could do for the readers! (Score:4, Informative)
Guys,
You're welcome :).
Kidding aside, it was great to have a manufacturer as large as Intel work with us and have something good come from it.
Allyn Malventano
Storage Editor, PC Perspective
Re: (Score:2)
Get all over the OCZ please, we need as much info as possible.
We're right at the cusp of SSD's becoming reasonably priced for enthusiasts now (not just ultra-rich enthusiasts) and I for one would like to know about the 120 and 240gb OCZ drives anand has dabbled with.
Also future products might be nice too, I am almost positive OCZ will have learnt a lot in the past month, we'll see some seriously good products come out within 3 to 6 months in the SSD scene, I'm sure of it
Re: (Score:2)
I touched on this at the end of this page:
http://www.pcper.com/article.php?aid=691&type=expert&pid=8 [pcper.com]
OCZ is getting there, but they are trying to keep up with the IOPS of Intel's 10 channel controller with their own 4 channel controller. Something has to give. In this case it is their Vertex fragments fairly quickly and won't come back on its own. It *requires* a TRIM utility to be run on it to restore full write speed.
It's a tradeoff. With the new firmware, the X25 goes *slightly* slower with ra
Re:Least we could do for the readers! (Score:4, Insightful)
Based on your examination of the situation along with anandtechs and the fact that both OCZ and Intel seem to be aggressively improving these products, it seems to me it might be silly to even consider the X25-M or the Vertex.
Something tells me the SSD scene is moving so fast that within literally 6 months one of these 2 companies (or a competitor taking note) will have a product superior in size, speed and price to those 2 very very soon.
It's a good time to have a little bit of patience I think.
- Scott
Parent
Pace of progress (Score:3, Insightful)
"Something tells me the SSD scene is moving so fast that within literally 6 months one of these 2 companies (or a competitor taking note) will have a product superior in size, speed and price to those 2 very very soon."
And this is different from the rest of the computer hardware world how? :) Everything is always getting bigger, faster, cheaper, smaller, whatever.
One thing I've learned is that, in general, one should decide on a budget and make your purchase based on what's available today. Something better is *always* coming down the pike. :)
Allyn Malventano Theory - It Can Write Faster! (Score:4, Interesting)
The most interesting thing is the last section on the last page.
PC Perspective: Intel Responds to Fragmentation with New X25-M Firmware - My Theory - It Can Write Faster [pcper.com]
by Allyn Malventano 2009-04-13
I think that Allyn is onto something because if you look at the graph for write speed of the X25-M (MLC) it seems utterly perfect at 80 MB/s, almost like there is an artificial cap on the speed, while the one from the X25-E (SLC) series it produces a standard waveform, like Allyn pointed out, and not an artificial flat line.
I too believe that Intel is artificially capping the performance of this drive and they might decide to uncap it sometime in the future once the competitors start snapping at their heels or if enough time goes by and they decide to introduce a new SSD MLC based performance/server oriented product line and remove the cap then. This is very similar to the situation with processor multiplier locks that they remove in their performance oriented Extreme processor lines.
I frankly don't like this kind of behavior from Intel since they know that they have the upper hand so they are just doling out enough performance to beat the competitors and to satisfy the current customers but at the same time holding back to create a market for their X25-E product line with slightly higher performance.
I think the other shoe will drop sooner or later on the 80 MB/s cap.
Research
I've been doing research into Solid State Disks in the last few weeks and this article is yet another one of those for Required Reading in the course of learning about SSD. I've even wrote a detailed post with links to reviews and articles. You can read up on the linked articles to get a good primer on things.
Solid State Disk Benchmarks [slashdot.org]
Parent
Please, no more smokescreens. (Score:4, Interesting)
This was forseen: Intel will ultimately be forced to redesign their flash write algorithms [kerneltrap.org]
The point of this is, please please please if you are an engineering manager, when you make a collective booboo, no smoke screen please! It is unlikely to go unnoticed, and nothing positive will be achieved for you, your company, your potential customers or your tech audience. Instead, just come clean, admit the problem and get busy on the fix. Down that path lies increased trust, whereas the doublespeak path only erodes credibility. I certainly will be double checking any future claims, because of how this played out.
Anyway, big props to the team for implementing what appears to be a superior solution. Hey, how about just open sourcing that firmware and let everybody help make it even better? Just a thought.
Re: (Score:2)
Hey, how about just open sourcing that firmware and let everybody help make it even better? Just a thought.
Not going to happen.
They're in a competitive market of bleeding edge technologies such as SSD storage. They will want every advantage they can get. This will require both hardware and software optimizations make their product stand out among the competition.
I'm sure Intel will open up the open sourced spigot much like ATI has with older products. Just don't count on them from cutting edge products anyt
Re: (Score:2)
Ummm, what you were discussing in that link has nothing to do with what this firmware is fixing. You were discussing performance decreases over time through ordinary use. This firmware fixes a bug that (so far) has only been able to be replicated under certain benchmark conditions, and has not yet appeared under real world conditions.
Don't pat yourself on the back too hard.
Re: (Score:2)
The problems which that link discusses are general problems, not Intel's. Even in the worst case, the Intel drive is still better than all the other MLC drives. Anand did a very thorough analysis here [anandtech.com] and it's probably one of the best mainstream pieces of technical writing I've ever seen.
He basically justifies the whole existence of Anandtech with that one article.
Anandtech (Score:5, Interesting)
On this subject: I finally got around to reading Anandtech's very long article [anandtech.com] about the current crop of SSD drives. I feel like it was pretty educational, which is good because it took a long time to digest.
In its discussion of performance degradation as drives are used, the article explains that individual pages of NAND memory can't be rewritten. Early in a drive's life, page are remapped when they are rewritten by the OS. As the drive is used, the drive runs out of pages to remap and is forced to copy a block (typically a 512KiB collection of 4KiB pages) to cache, erase the block and then rewrite the block with the new pages. That explains pretty well why write performance degrades, since writing to a block that has data must perform a read and erase operation in addition to the write. However, that explanation also leaves open the question of how the drive prevents data loss if it loses power. Worst case, the OS issues a write and the drive copies a 512KiB block to cache and erases the block, and then loses power. Due to remapping, literally anything could be in that half a MiB. The data loss could corrupt the file that was being modified, obviously, but also any other file on the drive, or parts of the filesystem itself.
I figure there's got to be protection against data loss built-in, but I'm not able to find details regarding any individual drive or manufacturer's approach to solving that problem. Does anyone know more about this subject?
Re: (Score:3, Informative)
They have a large capacitor in the drive. The DRAM is on the ssd and behind the capacitor. If the drive detects a power failure the data in DRAM is written to the ssd memory before the capacitor loses it's charge. This is my understanding.
Cheaper ssd drives may not have the on chip DRAM chip. Research it before you put these in servers. Use the write optimized MLC ssd drives are better geared for logging like Suns ZFS intent log and database logs.
Re: (Score:2)
I figure there's got to be protection against data loss built-in, but I'm not able to find details regarding any individual drive or manufacturer's approach to solving that problem. Does anyone know more about this subject?
Write-ahead would be one simple technique. Keep at least a spare block around, and don't blow away the old block until you've copied what you need to keep.
Re: (Score:2)
Good question. I suppose a form of data journaling could be used. P
Re: (Score:2)
I'm too lazy to go back and reread the entire Anandtech article, but if I remember correctly, it speculates on the amount of memory on Intel's controller and specifically states that Intel doesn't use the controller memory the way you describe, for the exact reason you state. Or perhaps it was the other article they did about the hiccuping drive from... was it OCZ? Either way, I feel pretty confident power loss won't cause data loss (at least not at the fault of the SSD controller)
Every SSD has this problem (Score:5, Interesting)
We've all read this by now, right?
http://www.anandtech.com/storage/showdoc.aspx?i=3531 [anandtech.com]
The X25 has the same problem as all the other flash drives due to the need to erase in big chunks. Post-slowdown, the X25 is still faster than almost any other SSD that's brand new, and given the same usage, the X25 maintains the huge performance advantage it has from the start. I doubt Intel can really do much to improve this behavior without using TRIM.
I assume their "fix" will be slight tweaking of writing patterns done mostly to fool the mainstream press that had already been acting foolish by picked up this story without noticing the subtleties (such as the problem being present in all SSDs)
Re: (Score:2)
Re: (Score:2)
It's not how much you write to it, it's how you write to it. Write a bunch of small files to random locations and it will fragment, dropping subsequent write speed. There is a pic of the effect on the last page of my article:
http://www.pcper.com/article.php?aid=691&type=expert&pid=10 [pcper.com]
What you're thinking of is essentially the response time of the flash itself. Most drives appear to be engineered to assume the flash is at its end of life and keep their timings to that level. No drive I have tested
Re: (Score:2)
Re: (Score:2)
With 4k writes it was likely writing at a lower speed right off the bat and kept that lower value. Try it at higher queue depths and you will get increased parallelism within the drive. Then you should see higher initial speed that will fall off as the drive fragments.
Re: (Score:3, Interesting)
The problem Intel fixed is not the same thing you're thinking of. Anand's methodology was flawed, in that he was writing the OS back to the drive in sector-by-sector mode, which is effectively a large sequential write. This acts to heal drives that write combine and is not in line with how that OS would have got there in reality. The subsequent writes he did accomplished nothing more than seeing how far that particular drive could fill the 'holes' in the partition (i.e. how fast it can perform small rand
Re: (Score:2)
Re: (Score:3, Informative)
As AllynM mentioned, this fix addresses a different problem. If you read in that anandtech article, you will see this:
Need a bootable CD drive (Score:2)
Re: (Score:2)
Actually, Intel's x25 is designed for desktop/server/enterprise use, not laptop use. It's just that the form factor is the same as a 2.5" laptop SATA drive. Mostly because you can fit an affordable amount of flash and the controller i
Re: (Score:3, Informative)
Actually, the the X25-M is for "mainstream" usage, including laptops and desktops. The X25-E is for extreme workloads, including some server usages.
The X25-M is available both in 1.8" and 2.5" SATA form factors, which are the two most common laptop interfaces today.
PCIe is a bit more limited in a laptop typically, and if you go that route (as a laptop manufacturer) you're generally locking yourself into a single device vendor, since you'll need custom drivers for whichever PCIe board you choose. SATA, on
Customer Experience (Score:5, Insightful)
I once dined at a restaurant that took my order, but minutes later realised they couldnt make it due to stock shortage. I got a different meal, and they told me mine was for free!
The way a company recovers from a problem can actually turn into a net positive experience for the customer.
In my case, I'm turned from an unsatisfied customer, to an advocate. For sure, I've recommended friends dine there since then.
Every interaction is an opportunity to delight the customer. Even those events that at first feel like a disaster unrolling.
An easy fix for Intel (Score:2)
There is an easy fix that Intel may be able to implement in their flash file system. They just have to lookout for free space wipes.
If a block is written with all zeros (all the same byte) they could then free the flash sector and mark the sector as a 'monobyte' in the data structure. The advantage is that it wouldn't take any extra space at write time so the FFS wouldn't get into the state where it's got no space to defragment blocks and so normal ATA commands will be able to get it out of it's stuck sl
Re: (Score:3)
I also go back to the old x25 datacomm days. so I thought 'huh, what? x25 is coming back??'
what a poor choice of names. clearly, intel has some VERY young people working there that have no idea about past things by the same name.
(admittedly, x25 was not as popular in the US as, say, europe)
Re:Why'd they call it that? (Score:5, Informative)
The SWIFT and other banking networks still use x.25. It's a rule of information technology that nothing is ever thrown away.
Parent
Re: (Score:2)
No, that's the exception that proves the rule.
Re: (Score:2)
I don't think you understand that term...
http://www.snopes.com/language/notthink/exception.asp [snopes.com]
Re: (Score:2)
I also go back to the old x25 datacomm days. so I thought 'huh, what? x25 is coming back??'
what a poor choice of names. clearly, intel has some VERY young people working there that have no idea about past things by the same name.
(admittedly, x25 was not as popular in the US as, say, europe)
o/\o X.25 buddies
Re: (Score:2)
You should be looking at random I/O speeds (Score:5, Informative)
The new OCZ & Samsung drives are faster (and larger) than the X25-M.
For sequential read/write -- yes, they are faster than Intel's offerings. Random read and write operations, on the other hand, are another story [anandtech.com]. That's one of the biggest issues that SSDs solve versus spinning platters, and no one has gotten it right so far, except Intel.
Parent
Re:You should be looking at random I/O speeds (Score:4, Informative)
I have an OCZ VERTEX 250GB SSD, and it blows mechanical drives out of the water for random IO.
I noticed several reviews that indicated that the Samsung drives do have issues with random IO, but the OCZ drives appear to have no such problems. Yes, you lose performance with random IOs vs sequential IOs, but nowhere near as much as first-gen SSDs. I've seen 6000 random IOPS on a single drive, which is unattainable on anything short of a while tray of disks in a SAN.
I'm not pulling the SSD vs SAN comparison out of my ass, I tested my laptop with the SSD drive head-to-head with the same ~60GB database against two production servers, one with a 20-something spindle SAN volume (shared), and the other with a 3-drive 15K RPM SCSI RAID (dedicated). It won against both for all cases where IO was a significant bottleneck in the query. Obviously, my laptop lost out against the 8-CPU server with 32GB of memory for 'small' queries, but for un-cached data sets, it was usually faster.
Parent
Re:You should be looking at random I/O speeds (Score:5, Informative)
I think you misunderstood. Your experience vs. mechanical drives has nothing to do with the issue. The AC said that the OCZ was faster than the Intel. Chris Daniel was simply saying "yes the OCZ is a bit faster for sequential acces, but random access (which is what most users experience the most) is better on the Intel"
If you look at Anand's article [anandtech.com] You will see that the OCZ beats the Intel slightly at sequential read (about 5%), and by a decent margin on sequential write (slightly less than 3x). However, these aren't things most users typically do...especially the writes. You are only likely to be doing that if you are working with editing large a/v files or something, and since large a/v files take up tons of space, a SSD probably isn't the best candidate for that anyway, given its current cost/storage metric. The OCZ might make sense working in a something like a professional AV editing environment, where you can copy the file off the server, work on it locally, and then copy it back to the server when done.
On the other hand, random reads and writes are something that virtually 100% of users experience on a regular basis, and this is where Intel really shines. On reads, Intel wins by a decent margin (slightly less than 2x the speed, and nearly half the latency). But then look at sequential writes, and Intel really takes the decisive win in that category. While the OCZ is a healthy 4x faster than Velociraptor, the Intel is just shy of 10x the performance of the OCZ (and thus nearly 40x the Velociraptor).
So, when you compare the Intel and the OCZ, the Intel loses slightly and decently on 2 operations that are less common, and it wins decently and decisively on 2 operations that are more common. Thus it's a pretty good stretch to try and say the OCZ is faster than the Intel.
Parent