Talk:Solid-state drive/Archive 1
This is an archive of past discussions about Solid-state drive. Do not edit the contents of this page. If you wish to start a new discussion or revive an old one, please do so on the current talk page. |
Archive 1 | Archive 2 | Archive 3 | → | Archive 5 |
old
This article:
- Does not conform to WP:MOS and therefore needs to be wikified, hence {{wikify}}
- Has no categories, hence {{uncat}}
- Does not give sources, hence {{sources}}, and
- Has been proposed for merging. The merging should be discussed, tag cannot be removed before it is discussed. Rich257 09:11, 11 October 2006 (UTC)
This article now has Category:Solid-state computer storage media. It still needs the other tags. Athaenara 01:51, 10 November 2006 (UTC)
History Missing
The history section seems to be covering the non-mainframe usage of SSD. Cray Research sold / included a SSD (Cray IOS) drive with many of its units to increase performance. IBM and Amdahl mainframes supported SSD drives also for increased performance. —Preceding unsigned comment added by Bmoshier (talk • contribs) 03:41, 25 June 2008 (UTC)
As far as I know, first SSD units were at use before drum units appeared - I met one for the first Russuan serial Dnepr tube mainframe - so it noted in the main body Stasdm (talk) 16:44, 17 August 2008 (UTC)
Merge completed
The merge was advertized on one talk page for 3 months (Oct 2006) with no objections, and agreed 5-0 on the other. I have therefore merged them fully, see Talk:Solid state disk. FT2 (Talk | email) 01:34, 18 January 2007 (UTC)
The decision to move this article with opinions of five people without basing it on actual research was wrong. It violates the no original research principle. Since you already achieved this thetan level why don't you move RAM disk too? While you're at it, pay a visit to logical disk as well since logical disks are not actual circular objects. SSG (talk) 00:30, 11 March 2008 (UTC)
Reference
"Subsequent investigations into this field, however, have found that data can be recovered from SSD memory." I think it's appropiate to put a reference for that statement. —Preceding unsigned comment added by 72.50.39.149 (talk) 23:29, 11 November 2007 (UTC)
Giga versus Gibi ?
Hard drives are measured in giga bytes, memory is measured in gibi bytes, what are SSD disks measured in? —Preceding unsigned comment added by 62.95.76.2 (talk) 15:01, 18 January 2008 (UTC)
- I second that question. There seems to be evidence that SSD is measures using decimal notation like HDD, but I'm unsure if there is more that is required for formatting a SSD which would account for this variance. pattersonc (talk) 01:56, 2 March 2008 (UTC)
- The answer is: Both SSD & HDD manufactures use decimal notation where 1MB = 1 million bytes. (SOURCE) pattersonc (talk) 02:04, 2 March 2008 (UTC)
"For example, some x86 architectures have a 4 GB limit"
I thought ALL x86 architectures had a 4GB limit because that's the limit of combinations of a 32bit memory address, wasn't that one of the prime reasons for switching to 64bit standard.--KX36 14:57, 8 February 2007 (UTC)
- I think not, modern x86 CPUs support PAE (although 32-bit Windows generally doesn't, except for some rare drivers) so they can address more than 4 GB at the cost of lower performance.
However, you CAN'T extend the 4 GB limit with a swap file. Allocated pages on swap file are no different than allocated pages in RAM, their address must still be within the 4 GB total. Once you have 4 GB of RAM you don't even need a swap file, it will not be used.
Agreed. Operating systems don't just re-address memory pell-mell when they swap it to disk. Here's a good article on the 4GB limit and memory addressing in general: Understanding Address Spaces and the 4GB Limit ◗●◖ falkreon (talk) 05:30, 10 December 2007 (UTC)
"First company"
The section on history was both inaccurate and remains full of holes.
The first company to launch a flash-based solid state drives did certainly not do so as late as 1995, since Psion PLC was already selling its "SSD" units from 1989 onwards. See for example http://3lib.ukonline.co.uk/historyofpsion.htm
I have no idea who was the first company to do so, but Psion sold "solid state" drives from 1984. The earlier ones were UV-EPROMs or battery-backed static RAM, with flash models introduced later. —The preceding unsigned comment was added by CecilWard (talk • contribs) 21:19, 24 February 2007 (UTC).
Campbridge Computing had one in their Z88 portable computers (EEPROM based) as early as 1988 also, and was viewed at the time as one of the most innovative products on the market. - John Hancock
Read/Write Cycles
I'm not sure if this is marketing talk or not, but since there's no source cited in the disadvantages section I think this is apt:
"Q: Is there currently some sort of technical limitation on the creation of SSDs other than cost, and what about the reliability of flash media?
A: Historically SSDs were limited in the number of R/W cycles. However, with modern flash technology and error correction, the reliability of the flash in a PC exceeds 10 years. " [1]
The Compact_Flash article states a read/write cycle up to 300,000.
The Read-only_memory#EPROM.2FEEPROM.2FEAROM_lifetime article states up to 100,000.
Read/Write Cycles
The claim that was on this page that endurance is not a problem, with the reference to storagesearch, is incorrect. It is true that if the hard disk were overwritten as a whole, over and over and over again, it would last a very long time. The problem is that's not a common access pattern. Under GNU/Linux, if you're running a web server, /var/log/apache/access.log will get written with each access. If you're getting an access once every second, that means you're overwriting the same spot on the hard disk 86,400 times per day, and your SSD fails after 2-3 days tops (real-world Flash gets 100,000 write cycles typically, and 300,000 on the high-end. 1-5 million are slightly exaggerated marketing figures, and at least the high-end of that is not actually achieved with today's technology). With a desktop GNU/Linux box, there are log files that get written many times per day. Access times get marked on common files every couple of minutes at most. Similar issues exist with Windows. Flash drives used naively will fail after at most a few months use on the desktop. Many embedded network devices come with Flash for log files, but the Flash is a replaceable part, and typically wears out after some use and needs to be replaced.
I've seen both the desktop and the embedded failures occur (on the desktop, with a naive user, using a CF-IDE converter, and in the embedded case, replacing Flash was just standard maintenance). I haven't seen the server case occur, because all the sysadmins I know using SSDs are intelligent enough to manage the endurance issues.
The failures can be mitigated through the use of intelligent software. OLPC spurred the rapid development of Flash-optimized files systems for GNU/Linux. These intentionally stagger writes over the whole drive, so that no single block gets worn down. Hybrid Flash/non-Flash drives use the Flash as a cache, and again, can intelligently manage the part of the Flash that gets used with each write. All-Flash drives have their place, and can be managed to not fail, but the endurance issue does occur, and does need to be managed. Many SSDs have firmware to manage this, but many of the SSDs I have dealt with do not. It is an issue the user needs to be aware of. I have corrected the page to reflect that. 68.160.152.190 21:32, 4 June 2007 (UTC)
Is there any citation for
1-5 million are slightly exaggerated
value. Disclaimer: I am NOT working in any company - just curious.
Can you list models or names of SSDs with and without "wear-leveling" ? —Preceding unsigned comment added by Whyagainwiki (talk • contribs) 18:52, 27 March 2008 (UTC)
Merging RAM disc article
- The following discussion is closed. Please do not modify it. Subsequent comments should be made in a new section. A summary of the conclusions reached follows.
- Did not merge
I am against it, as RAM discs are different. SSDs use non volatile memory. RAM is not non volatile. --soum talk 16:35, 7 June 2007 (UTC)
- I'm against too, they're completely different things. - 83.116.205.167 07:52, 17 June 2007 (UTC)
- Against it. Second above, and add that ram disks are virtual; SSD are physical. Arosa 21:43, 18 June 2007 (UTC)
- Same here - not the same thing at all (although the RAM disk article contradicts what Arosa said...)! I'll remove the tag. Spamsara 22:07, 24 June 2007 (UTC)
- Against it here, for Soumyasch's reasons. Makes no sense to combine the two when they are inherently different technologies, even if they share some common applications. Would be like combining 'car' and 'bike' because they could both be used to get to work, and had wheels. - 203.206.177.188
- Same here - they are completely different, SSD are hardware allocated, where RAM Disks can be created from system ram, or hardware allocated. SSD are hybrid memory. Ram Disks are volatile memory.
I am in favor of merging RAM-disk and Solid State Drive. They are essentially the same devices. They both use Ram to act like a disk drive. The fact that one is volatile and the other not does not seem to be a significant difference. In which section would you put a RAM-disk with a battery backup? --FromageDroit 13:59, 28 August 2007 (UTC)
RAM-disk and Solid State Drive are not the same, as RAM is Volatile, SSD is not. so Merging not needed, maybe an Link to Ram-disks at the bottem of the page if its not all ready there. Leexgx 15:53, 24 October 2007 (UTC)
We're arguing over symantics. On the "RAM disk" page that's marked for possible merging, the article itself states that it can be one of two things. So we're talking about two different things here. I suggest that a disambiguation page is created. It will point to either this SSD page, which could be merged with half the RAM disk article; or the RAM disk's "software abstraction that treats a segment of random access memory (RAM) as secondary storage". I used the latter extensively and can attest to it being a different beast entirely. And yes, SSD's that use volatile memory as a hardware component are indeed the same thing, just volatile.◗●◖ falkreon (talk) 05:49, 10 December 2007 (UTC)
I think they may be merged now, else where to put RIndMA Disk - on one side it is a software RAM disk, on the other - a remote hardware appliance. —Preceding unsigned comment added by Stasdm (talk • contribs) 16:51, 17 August 2008 (UTC)
- They are still separate. I think SSD is probably the more appropriate article for the usage you mention, since it is an implementation of a DRAM based SSD using off the shelf hardware/software. (I did move it to the implementations section from history, since citations were not provided to establish when the idea originated.) Zodon (talk) 17:52, 17 August 2008 (UTC)
The idea originated in July 24 2008 - see the mentioned site main page. Might be you restore it in "history"?78.36.39.135 (talk) 19:41, 17 August 2008 (UTC)
- To establish something like when something originated would need a reliable source WP:RS that established a basis for the claim (e.g. patents, literature search, etc.). The site mentioned is not reliable for establishing this. It is easy to disprove the assertion of the idea originating in July/Aug '08. For instance, this thread [2] has a posting of the idea from January of '08, and some of the posts in it refer to earlier implementations of the idea. Since as the cited website mentions this is a pretty trivial "invention," and the necessary components have been around for a few decades, it would probably be difficult to trace back and prove a first use/inception. Any claim to originating a very simple idea like this would be extraordinary, and therefore require extraordinary proof. 20:09, 17 August 2008 (UTC)
Well, the idea itself is even more old. The "RIndMA disk" name for it is absolutly new (there are talks on RDMA disks for some years, still not implemented)Stasdm (talk) 20:25, 17 August 2008 (UTC)
Made some editing in the RAM-based SDD section - mainly for better literary presentation.Stasdm (talk) 21:04, 17 August 2008 (UTC)
Read/Write Cycles (another one)
When calculating the endurance level of the hardware, the article claims "blocks are typically on the order of 1kb and an 8 GB disk will have 8,192 blocks", which unless I'm very much mistaken is out by a factor of 2^10, i.e. 8,192 * 1Kb = 8Mb, not 8Gb.
Read/Write Cycles (yet another one)
As the previous comment indicated, the description of wear leveling in the text is not only very naive but also very wrong.
The nature of NAND flash is such that one typically must erase whole 128KB blocks, and then consecutively write 64 2KB pages within that block. There are no rewrites, so in order to rewrite a single 2KB page, the entire 128KB block must be erased. So, with a naive implementation the endurance of a single block drops 64 times (to about 160 rewrites?).
The main problem is not wear leveling itself, but how to avoid the need to rewrite existing data, that is how to avoid fragmentation. This problem is not 100% solvable in general unless once can predict the future. One hardware solution is to cache some data in a battery-backed RAM to avoid immediately rewriting it.
24.4.151.152 17:24, 29 September 2007 (UTC)
The problem can be solved by more innovative filesystem designs, such as Log-structured file systems. Segmentation is a non-problem for such file systems. You can always predict with 100% certainty where you're going to write next, although you still can't predict when you're doing so.
202.71.231.218 (talk) 2008-02-21T06:54 —Preceding comment was added at 06:57, 21 January 2008 (UTC)
Server mentions
There is insufficient mention of SSD usage in servers. Because the primary bottleneck on many types of servers is I/O from many users (and thus random I/O), SSDs are often considered superior to RAID HDD, assuming one is willing to pay the price.
128.113.167.175 17:15, 1 October 2007 (UTC)
- Unfortunately, word of mouth is not enough for Wikipedia. We need published sources to cite. Can you help?--soum talk 17:41, 1 October 2007 (UTC)
- A google for "random i/o bottleneck" shows plenty of sources for this, i'm not experienced enough to edit this, please be my guest to help with this :)
Talrinys (talk) 23:50, 2 January 2008 (UTC)
MacBook Air
The high-end version of the macbook air uses a 64 GB solid state drive. Some mention of this application might be warranted. —Preceding unsigned comment added by 67.116.239.156 (talk) 19:03, 15 January 2008 (UTC)
- The mention of the Air under Availability states that the 64 GB SSD "Boasts better reliability.... 80GB PATA drive." A couple of problems here. I haven't looked into it yet, but I seriously doubt that they aren't using SATA in new macbooks. Secondly, and more importantly, where is it said that the SSD offers better reliability? I don't necessarily doubt it, but is there a source for this statement? Ferrariman60 (talk) 22:44, 15 January 2008 (UTC)
- http://store.apple.com/Apple/WebObjects/dkstore?node=home/shop_mac/family/macbook_air&cid=OAS-EMEA-KWG-DK_LAPTOP-DK&aosid=p202&esvt=GODKE&esvadt=999999-1200820-1079263-1&esvid=100504 says it's PATA. No harddrives even need SATA yet, so doesn't really matter, except for the ancient standard, cables etc. SSDs just are plain more reliable, it's in the technology itself. Unless it has bad chips chips it simply just can't crash randomly as a mechanical harddrive can. However it will die after a specific amount of transfers. This will be a lot easier to account for than the random failures we have now. Talrinys (talk) 12:06, 26 January 2008 (UTC)
Lots of other laptops have 64 GB SSDs - yet this article is now sprinkled with references specifically to MacBook Air. Most of these references look rather redundant to me. --Romanski (talk) 22:05, 29 January 2008 (UTC)
Solid State and Tubes
Please take out the line in the intro refering to vacuum tubes. The term "Solid State" has always refered to semiconductors and only semiconductors, not tubes. It has to do with the fact that dopants are difused into the silicon while in a solid state in a way that mimics diffusion in liquid. 75.55.39.21 (talk) 21:25, 15 January 2008 (UTC) Sandy
Disadvantage? - "Vulnerability to certain types of effects,...magnetic fields..."
Working with some of the largest magnetic fields found in the industrial world, SSDs are the only allowed hard-drive replacement in a production environment. Mechanical hard drives die pretty much instantly or are rendered un-usable/erased.
Maximum gauss is ~ 2,000. With an average of 40-80 Gauss in normal walkway area's. Some equipment is under ~ 80-400 Gauss, all flash based storage. Magnetic field source is a DC current at ~200-350kA.
Main issues are with DC-DC converters under such conditions, so the potential for power supply in the SSD to fail rather than the flash itself.
Hard-Disks will NOT survive this environment. Flash based SSDs are the only storage device able to withstand these conditions.
Should this "disadvantage" be moved to an "advantage"?
The mentioned disadvantage is ridiculous. "Compared to normal HDDs (which store the data inside a Faraday cage).". Is there anything preventing SSD's from being put in the same cage? Are there any references that say no SSD is put in those? I hate seeing such ridicule creep through, and more importantly, stay. SSG (talk) 00:02, 11 March 2008 (UTC)
I definitely agree. I put a [dubious] mark on the sentence, but it probably should be moved to "advantages".151.65.45.84 (talk) 20:01, 19 August 2008 (UTC)
Vandalism
Semi-protection vandalism lock needs to be placed.--Kozuch (talk) 21:13, 5 February 2008 (UTC)
Overall quality
Hi!
I apologize for the critical view of my post and I respect the people who contributed to this article. However I feel that it does not meet the minimal criteria for a respected Wikipedia article.
First of all the article seems fragmented. When we say SSD we mean permanent solid storage, not battery-aided DRAM. It's just like saying DRAM is non-volatile just because you own a UPS. Flash sticks or other solid state media (SD, CF, MS) even they are technically solid-state storage, they are not solid-state-DRIVES -- they're memory cards. So, first of all, FOCUS on the subject.
Secondly article lacks of scientific information or any data a technically curious or a computer science student or researcher may find of any value.
Thirdly I believe *links* (not actual figures, we're not a HW review site, unless numbers are solid and confirmed) to benchmarks should be included, many potential SSD byers may advise this page.
Forth: Sections are fragmented, article lacks of an overall coherence. It seems that it was written by an uncoordinated team, by separate people with their ideas popping here and then. Sorry to say that but article is messy.
Regrettably I believe that it should be marked for quality review in order to meed minimal quality standards.
Thank you and I apologize for criticizing other's hard work.
Galanom (talk) 07:36, 12 February 2008 (UTC)
- Thank you for your suggestion. When you feel an article needs improvement, please feel free to make those changes. Wikipedia is a wiki, so anyone can edit almost any article by simply following the Edit this page link at the top. The Wikipedia community encourages you to be bold in updating pages. Don't worry too much about making honest mistakes — they're likely to be found and corrected quickly. If you're not sure how editing works, check out how to edit a page, or use the sandbox to try out your editing skills. New contributors are always welcome. You don't even need to log in (although there are many reasons why you might want to). -- ShinmaWa(talk) 18:38, 18 February 2008 (UTC)
Market analysis
Some "price per MB/time" or other graph would be nice...--Kozuch (talk) 00:12, 24 March 2008 (UTC)
Plagiarism
Most of the History section of this article seems to be lifted verbatim from the first cited source. See http://www.storagesearch.com/chartingtheriseofssds.html Notably, certain phrases have been removed, such as "In Q1 2002 - SSDs were 4th most popular subject with our readers." —Preceding unsigned comment added by 71.198.65.9 (talk) 14:51, 23 April 2008 (UTC)
- Undid the revision that put in copied history. Zodon (talk) 06:02, 24 April 2008 (UTC)
This is an archive of past discussions about Solid-state drive. Do not edit the contents of this page. If you wish to start a new discussion or revive an old one, please do so on the current talk page. |
Archive 1 | Archive 2 | Archive 3 | → | Archive 5 |
Merging Flash drive into Solid-state drive
- The following discussion is closed. Please do not modify it. Subsequent comments should be made in a new section. A summary of the conclusions reached follows.
- The result was merge into Solid-state drive. -- Zodon (talk) 04:46, 10 September 2008 (UTC)
NOTE: The proposal is to merge the article Flash drive into Solid-state drive, the proposed merge has nothing to do with the USB flash drive article. (This clarification added part way through the discussion Zodon (talk) 18:53, 18 August 2008 (UTC)).
I agree that the merge seems like a good idea. Zodon (talk) 21:25, 25 June 2008 (UTC)
- I concur. --Laser brain (talk) 21:26, 25 June 2008 (UTC)
Disagree: All flash drives are solid state drives, but not all solid state drives are flash drives. They're still different things and should be kept seperate. Lightblade (talk) 23:29, 27 June 2008 (UTC)
Yah but flash could be its own topic under SSD, and still have its differences noted. JMAN1156
- Flash drives are already covered in the solid-state drive article, it is not clear that they have enough unique features to warrant a separate article. It isn't necessary to have an article about every subtype of an item. Please explain why they should be separated out from the other solid-state drives. Thanks. Zodon (talk) 00:30, 2 July 2008 (UTC)
Disagree: Flash drives imply portability and "hot swappable" type behaviour, like a USB pen, whereas talking about solid state drives implies usage as permanent hard disks - I think this means that they are 2 seperate things. Merging these would be like merging CD's and Floppy Disks, because they are both types of disk... —Preceding unsigned comment added by 62.255.249.197 (talk) 08:48, 8 July 2008 (UTC)
- Acutally SSD are hot swappable, if you use raid and sata hot swappable drives teh SSD can be used instead of traditonal hard disks.Andrewcrawford (talk) 20:23, 17 August 2008 (UTC)
- Please observe that the article in question for merging is Flash drive, not USB Flash drive. The Flash drive article even states "Unlike USB flash drives and memory cards, flash drives tend to physically imitate conventional hard drives in size, shape, and interface so that they may act as a replacement for hard drives." The article about flash drive makes none of the distinctions you mention for flash drives. (There is no reason a SSD can't be hot swappable, using an external enclosure, E-SATA, etc.)
- There are so many little articles about similar devices that it makes sense to combine a few of them. Since flash drive is a subset of SSD, and the article overlaps a lot with this one, it makes sense to merge them. The see also section of the Flash drive article has a reasonable summary of a few of the different related types. The flash drive entry should probably become a disambiguation page (pointing to USB flash drive, or SSD, etc.). Zodon (talk) 01:22, 9 July 2008 (UTC)
- I agree with Zodon. The "Flash Drive" article is confusing: The common use of the term "Flash Drive" implies "USB." Merging "Flash Drive" with this article and creating a disambiguation page for "Flash Drive" is an excellent idea. Horseadmonition (talk) 16:56, 5 August 2008 (UTC)
Strongly Agree Do not see any difference for USB / other bus drives. They all need software support (driver) to operate. Also there are conventional USB HDDs at hand. The article must be more sructured and there should be separate parts for RAM/"standard" flash/USB flash drives (else we'll have to distinguish IDE/SATA/SAS/InfiniBand/other buses SSDsStasdm (talk) 17:07, 17 August 2008 (UTC)
Strongly Agree There are already USB RAID (RAID 0 actually, but it's only the beginning). Once again - do we describe technology or use/application and bus differences? Most flash SSDs (exept for newest ones)are IDE - any native RAID for them? And EDE/SATA SSDs are quite often used to transfer data - especially in publishing industry, where seem to be a standard already. Stasdm (talk) 12:46, 18 August 2008 (UTC)
- One why give your agurement twice? and second there is no IDE ssd that i know of mostly because the interface can not handle it correctly. USB can not be used as raid, it can be used to elimated raid on linux but that quite hard to do. windows can not handle it nor do it. RAID also requires teh drives are fixed ;) which last time i checked usb flash drive arentAndrewcrawford (talk) 13:47, 18 August 2008 (UTC)
- Please clarify how your argument against relates to the articles in question. The article on Flash drive says. "Unlike USB flash drives and memory cards, flash drives tend to physically imitate conventional hard drives in size, shape, and interface so that they may act as a replacement for hard drives." So both flash drive and SSD are primarily disk replacements.
- What does whether USB drives can be used in RAID or not have to do with the merger proposal? Neither article proposed for merger deals with USB to any great extent. (Whether it is a discussion of features of USB drives, or evolving into a proposal to merge the USB flash drive article, please either relate it back to the topic of this discussion, or start another thread for it.)
- Since several of the people commenting in this thread seem to have been confused about what articles are proposed for merger, I added a note at the top with links to which hopefully will help keep the discussion on track. Zodon (talk) 18:28, 18 August 2008 (UTC)
- I am merely asking why the previous person isung saying ot merge it on the fact of USB flash pens. This what was there arguemnt to merge for so i am quesiton it.Andrewcrawford (talk) 18:45, 18 August 2008 (UTC)
- I noticed the mention about no IDE SSD.. but what exactly is http://upload.wikimedia.org/wikipedia/en/d/df/Open_HDD_and_SSD.JPG showing then? Paril (talk) 07:14, 12 May 2009 (UTC)
Strongly AgreeOk after reviewing the the article in question rather than go on what is here, i say the articel should be merged here as it basically describing SSD.Andrewcrawford (talk) 19:43, 18 August 2008 (UTC) previous comment removed
Agree. It doesn't matter whether the two terms are identical - it is their overlap that matters, and they to appear to have a very large overlap. GregorB (talk) 13:03, 9 September 2008 (UTC)
i-RAM
I DO thing the i-RAM insertion is a kind of SPAM! Somone is triing to sell off the now obsolete product. If my note on tha i-RAM obsolete state will be deleted one more time, I surely will have to delete the whole paragraph!Stasdm (talk) 07:17, 13 October 2008 (UTC)
actualy i-RAM isnt quite obselete, it still has uses, i see it more as a way to have fast virtual memory, and temporary storage during system operation than a long term storage solution, for example loading important system files to it, or game files, or just as virtual memory. --Superchad (talk) 20:41, 29 December 2008 (UTC)
Disadvantage: Limited write (erase) cycles
I think this paragraph could use a rewrite. With proper write leveling techniques, the practical threat to your data is negligible. Before this starts to be a real risk-factor, you're likely to have had a disk failure for a completely unrelated reason or upgraded to a newer completely different system or whatever. Not saying we should sweep this source of errors under the carpet, but the paragraph could be rewritten to give off a more moderated impression of the risk level involved. CapnZapp (talk) 19:12, 22 December 2008 (UTC)
some info is not correct
{{ As a result of wear leveling and write combining, the performance of SSDs degrades with use . Eventually, wear leveling will use each page on the drive at least once, so further writes always involve a block erase. Although write combining (if supported by the device) offers advantages, it causes internal fragmentation in the SSD which degrades the sequential read speed. Such fragmentation cannot be mitigated by the operating system. }}
1. so further writes always involve a block erase, that does not allways happen (block is 4KB each page is 512KB each) when all blocks have been writen to is does an page wipe (block and pages look at page 5,6 and 7)
2. it causes internal fragmentation in the SSD which degrades the sequential read speed, SSDs Prefer fragmented files as then it can hit as many cells as it can when reading files as it can make them go read faster (2-10 depending on what type of ssd is it, intel is 10, Indilinx 4 (i think) Jmicron is 2-4 )
once all SSD pages have been writen to thay slow down as thay need to do an Page Erace before it can save but it will not allways erace every time something is saved as there is likey going to be spare blocks around from an erace that happened before
Leexgx (talk) 19:23, 21 April 2009 (UTC)
- For what it's worth, the AnandTech article you mention claims that sequential read was "largely unaffected" in the drives they tested. Ubernostrum (talk) 10:47, 16 August 2009 (UTC)
Needs a comparison to current mechanical hard drive wear standards to give meaning. Is a million writes more then a mechanical hard drive can currently do or less? --69.137.5.230 (talk) 19:16, 14 August 2009 (UTC)
progress on newer drives
I think it's about time to remove "capacity" from the disadvanteges of the SSD drives soon. Next month there will be 2TB SSDs available meeting the 2TB capacity of HDDs. Yes, the new drives will be ridiculously expensive ($10k?) but that is already covered by the cost disadvantage.
Also regarding volumetric density, The HDDs with best GB/cm2 drive are e.g Western Digital 2.5" drives at 1TB. Their physical size is about 80 cubic centimeters whereas http://www.tomshardware.com/news/puresilicon-ssd-1tb,6810.html#xtor=RSS-181 drives are about 65 cubic centimeters at the same capacity. Darin-0 (talk) 10:51, 17 September 2009 (UTC)
(Feb 16, 2010) The info about SSD prices in the article looks:
1) Outdated. $2 per GB? I don't know about small capacity (40-120GB) drives, but 250GB ones cost $3-4 per GB and 1TB ones are at $10/GB.
2) Misleading. Because for traditional 3,5" HDDs (non-SCSI) price per GB of storage is LOWER for higher capacity models. As of now 250GB HDDs cost $.25/GB and 1TB ones cost $.1/GB.
This makes SSDs much less competitive then they might seem from reading the article. Since 500GB+ HDDs are now mainstream, similar capacity SSDs would have to become 50-100 (!) times cheaper to fall into the same price range.
Rewrite of Quality and performance section
I really want to do a complete rewrite of this section. The information in that section is a) only applicable to the consumer market, as opposed to enterprise, b) Is manufacturer-biased, and most of all c) does not explain WHY the Intel drive (for instance) beats the other drives so badly (random write latency). I'm not a manufacturer or researcher, but I've studied SSD performance for a year and think I can contribute something. Jimhsu77479 (talk) 15:59, 27 October 2009 (UTC)
- Knock yourself out, if you haven't already :) This is a rapidly developing technology that should be kept up-to-date as much as possible. Thanks in advance! Publicly Visible (talk) 23:11, 17 December 2009 (UTC)
StorageTek - Year of SSD introduction
I am currently going through this article cleaning up as much as I can. I do have some experience in the storage industry, so I find it relatively easy to search for sources to this article because I am familiar with the technology. I have recently spent 3-4 hours searching for real sources on the StorageTek statement, but could only find one credible source that was not simply copying the current Wikipedia SSD article. That document was written by Fred Moore, the one time Corp VP of Strategic Planning at Storage Technology Corporation (StorageTek). [3] On page 1-9 there is mention of 1979 being the year that Storage Technology Corp introduced the fist SSD according to Fred. I have found no other sources that would likely be more accurate than a presentation from the one time VP or Strategic Planning at StorageTek. § Music Sorter § (talk) 04:13, 13 June 2010 (UTC)
Whether to merge Multi-level cell article into Solid-state drive section, etc.
Since MLCs' and SLCs' applications go beyond that of use in SSDs alone (the example of Intel's 8087 processor given in the MLC article, for instance), and SLCs are significantly different from MLCs, it would seem appropriate to separate the SLC (Single-level cell) and MLC pages, and to link them each to the SSD one - and vice-versa. Valvicus (talk) 17:16, 27 June 2010 (UTC)
Surprisingly outdated
There seems to be at least a couple of competing factors here as tech sites try and grasp the latest technologies and then review it, and yet at the same time supposdely support the wiki initiative. As at 28 June 2010, there is scant, if any, realistic, objective comparisions of, for example, the Vertex 2, Vertex 2 Extended and the Z-Drive style PCIE SSD's. I was sloging thru Anand tech's most recent article on SSD's and noticed nothing recent. While I have the greatest respect for our people out there providing information in a timely fashion - you all risk jading the market by letting vendors write their own marketing hype and the potential customers running away after getting burned a few times. —Preceding unsigned comment added by 198.103.223.52 (talk) 17:20, 28 June 2010 (UTC)
- You bring up some good points. I think one problem is that Wikipedia is foremost a source of encyclopedic material based on secondary research. We have to be careful not to get into opinions about the products or technologies. We certainly can quote sources that have opinions on what is better than another, but we need to be sure to also cover opposing opinions. When we do that we still have to stay neutral. It is a careful balance.
- One option would be to create a section on notable reviewers and talk about their history on reviewing SSDs. The source citations can point to the sites referencing particular points being covered. That would create links to their sites in a way that would not be necessarily viewed as spam as long as the site was reputable or notable. § Music Sorter § (talk) 18:26, 31 July 2010 (UTC)
Unreferenced statement in Applications section
Currently in the Applications section of the article there is a statement (quite possibly made by me earlier), but I have been unable to find a supporting reference for it. I know it is true, but we are not about primary research. I will be deleting it if we cannot find a reference.
- "Flash-based Solid-state drives can be used to create network appliances from general-purpose PC hardware. A write protected flash drive containing the operating system and application software can substitute for larger, less reliable disk drives or CD-ROMs. Appliances built this way can provide an inexpensive alternative to expensive router and firewall hardware."
§ Music Sorter § (talk) 07:19, 9 August 2010 (UTC)
No mention of the security of data on SSDs!
There is no mention of the security (or not) of data on an SSD. Traditionally sectors on a conventional HDD are not cleared upon deletion (or fomat) but only by explicit over-write. I beleive that most SSDs are transitioning to FDE (Full Disk Encryption) with a random initial key or user generated password if specified which deals with much of this concern. How about some of this going into the article (BTW: I am looking for a laptop SDD or new HDD that MUST be FDE and therefore my data will be secure!) 122.148.41.172 (talk) 07:18, 31 October 2010 (UTC)
- It turns out some SSDs are headed to self-encryption, but many are not. The SandForce-based drives are all encrypted, but I am not sure about which of the others include it or not since they are slowly migrating it in. In either case we should add something on the security benefits of encryption. We just need a public source we can reference (otherwise I would write it up myself, but that would be primary research and not allowed here. If someone finds a public source and can post it here, I can add something to the article based on that source if the person does not want to write it themselves. § Music Sorter § (talk) 06:47, 1 November 2010 (UTC)
- Thanks for that link. I think I may settle on a Lenovo ThinkPad 43N3417 256GB FDE (AES 256bit) SSD. What pisses me off is that (laptop physical data) security is still not a major concern or easy value-addedd selling point for manufacturers/sellers and where it is that is only for Large Enterprises which manage secure drive access with enterprise key escrow software etc. These drives are hard to get and expensive OEM stuff. Some of the consumer level stuff out there is cheap chinese junk that is decidedly insecure even though the manufacturer advertises otherwise. I want to be able to trust a secure drive so I dont have to run TrueCrypt as my pre- i3/i5 series CPU doesnt have the AES extension instructions - running Truecrypt is a large performance hit and is less reliable than encyrtion performed transparently in the drive hardware. All disk and solid state drives should by now be FDE with AES 128-256 bit minimum. With software security issues a major growing issue on the internet I really do wonder sometimes about our species: god help the planet.Mattjs (talk) 07:07, 16 November 2010 (UTC)
Is anyone reviewing the SSD article,
Is anyone reviewing the SSD article, or this discussion page? This article might be useful to someone writing a report, but misleading at best to someone trying to buy a drive. I don't know much about Wikipedia, but is there a policy on adding links to the top of a page to a website? Specifically the articles that Anand has written over the last two years? (Monday March 22nd, 2010) (98.202.161.43 (talk) 06:08, 22 March 2010 (UTC))
- Also, the referenced article on performance between SSD and HDD is outdated... they didn't specify which SATA type... I'm personally looking for a speed comparison between SATA III 10krpm+ HDD vs SATA III SSD. Nathan (talk) 22:29, 18 May 2010 (UTC)
- I have been reviewing this article (and the other SSD related articles in Wikipedia) for some time now. I plan on updating this article over the next few weeks to address the numerous issues noted here and to hopefully improve this article.
- I also propose that since SSDs have rapidly become an option for nearly every system supplier it no longer makes sense that we keep adding announcements for systems that have SSDs available in Solid-state Drive#Availability. I believe we should keep or add any milestone would be relevant like
- First system to only ship with an SSD
- First system from each major system supplier to ship with an SSD
- First system to ship with RAIDed SSDs
- First Ultramobile system with an SSD
- First Netbook to ship with an SSD
- First system supplier to claim 1 million units shipped (or something similar)
- etc.
- (Note: I am not proposing exclusively firsts, but that was what came to mind)
- Further I plan to divide this section into "Availability:Shipped from system suppliers" and "Availability:Sold separately" to cover drives available for user upgrades of current systems. I think the separation of available drives between this section (sold in systems) and the Solid-state drive#Intermediate and Solid-state drive#Contemporary sections is hard to follow and they would make more sense closer together (which I plan on updating). I think the opening section on Solid-state drive#Development should stay focused on developments in the technology over time, not just every suppliers' product availability announcements.§ Music Sorter § (talk) 15:59, 3 June 2010 (UTC)
- I also propose that since SSDs have rapidly become an option for nearly every system supplier it no longer makes sense that we keep adding announcements for systems that have SSDs available in Solid-state Drive#Availability. I believe we should keep or add any milestone would be relevant like
- I have removed the "expert required" template on the article since we are working on it currently. I will leave up the other templates until we have concluded those items. § Music Sorter § (talk) 03:45, 9 August 2010 (UTC)
- I completed the reorganization on the Architecture section today. Now we can add more current information under the new organization. § Music Sorter § (talk) 20:06, 7 November 2010 (UTC)
- I think we have made significant updates and improvements to the article to make it very relevant and current. I am removing the "update" template.
i am writing report on SSD, please review this article
~~Davinder singh 5 march 2011 — Preceding unsigned comment added by Mrdragon333 (talk • contribs) 05:41, 9 March 2011 (UTC)
PATA or SCSI SSDs
These are listed as potential interfaces for SSDs. Can anyone cite a drive that nativel uses one of these old geezers? --Kvng (talk) 23:49, 23 January 2011 (UTC)
Early Asus Eee PCs and other netbooks used PATA wired to a mini PCIe connector. Upgrade drives are still available —Preceding unsigned comment added by 71.252.42.133 (talk) 04:41, 29 January 2011 (UTC)
Transcend makes some basic PATA SSDs. I don't recall seeing a SCSI one, probably very rare. 91.156.18.224 (talk) 13:12, 29 January 2011 (UTC)
- Thanks for the information. If removed {{dubious}} and added refs to the PATA entry. Still looking for any information on parallel SCSI SSDs. --Kvng (talk) 18:00, 30 January 2011 (UTC)
- SCSI SSD source added from http://www.storagesearch.com/scsi-ssd.html. § Music Sorter § (talk) 05:53, 21 June 2011 (UTC)
Removing {{Emerging technologies}} template
I see in the Emerging technologies template there are discussions around new "emerging" memory technologies, but currently shipping SSDs are not using them. Also there is no mention of SSDs in the template and I don't think it is relevant enough to add since they have already arrived with so many notebook computers already shipping with SSDs exclusively (no HDDs). Therefore I am removing it as unrelated. § Music Sorter § (talk) 22:37, 16 June 2011 (UTC)
Link to article on SSD operation and issues
Hello. This is my first Wikipedia post, and not fully sure how to make it useful.
I came to this article directly by searching for SSD. But the article barely touches on the technicals SSD operation. That information is covered extensively in the article linked as "Write Amplification", a well-written overview of the technical operation and issues of SSDs. This article is the one I needed to find in order to make an informed choice about SSD types and their issues and limitations. However it was largely by luck that I found it.
My suggestion is that the Write Amplification link be given higher prominence in the SSD article (in See Also?), and perhaps that article could be renamed to indicate that it serves as a comprehensive technical overview. I am sorry I am not a competent enough editor to tackle this myself, just an appreciative reader.
71.208.103.156 (talk) 19:42, 16 June 2012 (UTC)Doug M
Separate comparison page
The SSD/HDD comparison chart is getting rather long, should it be given a discrete page?
85.76.45.31 (talk) 16:39, 13 January 2012 (UTC)
I agree!--88.111.127.125 (talk) 18:07, 24 September 2012 (UTC)
- Disagree. I feel as though this comparison chart fits perfectly on this page and is not "too long" at all. I think it would not warrant any separate page. LogicalCreator (talk) —Preceding undated comment added 13:13, 7 October 2012 (UTC)