Go Back   AnandTech Forums > Hardware and Technology > Memory and Storage

Forums
· Hardware and Technology
· CPUs and Overclocking
· Motherboards
· Video Cards and Graphics
· Memory and Storage
· Power Supplies
· Cases & Cooling
· SFF, Notebooks, Pre-Built/Barebones PCs
· Networking
· Peripherals
· General Hardware
· Highly Technical
· Computer Help
· Home Theater PCs
· Consumer Electronics
· Digital and Video Cameras
· Mobile Devices & Gadgets
· Audio/Video & Home Theater
· Software
· Software for Windows
· All Things Apple
· *nix Software
· Operating Systems
· Programming
· PC Gaming
· Console Gaming
· Distributed Computing
· Security
· Social
· Off Topic
· Politics and News
· Discussion Club
· Love and Relationships
· The Garage
· Health and Fitness
· Home and Garden
· Merchandise and Shopping
· For Sale/Trade
· Hot Deals with Free Stuff/Contests
· Black Friday 2014
· Forum Issues
· Technical Forum Issues
· Personal Forum Issues
· Suggestion Box
· Moderator Resources
· Moderator Discussions
   

Reply
 
Thread Tools
Old 04-25-2010, 04:54 PM   #1
BTRY B 529th FA BN
Lifer
 
BTRY B 529th FA BN's Avatar
 
Join Date: Nov 2005
Posts: 13,019
Default Check disk on an SSD?

Do SSD drives need Check Disk?
__________________
Rig1: Xeon X5660 6core 32nm (2.8GHz stock), Asrock X58, Geforce 210 0db, Samsung 128Gb 840 Pro, Vertex2 100Gb, Cherry MX Blacks, 2009 Seasonic X 650w, Aluminum Full tower
Rig2: i7 970 6core 32nm @ 4.4GHz 1.365v, EVGA 760 Classified,
GTX 670, Samsung Evo 120Gb, Vertex LE 100Gb, Cherry MX Reds, Sidewinder X5, Enermax Revo 950w, Obsidian 800D
BTRY B 529th FA BN is offline   Reply With Quote
Old 04-25-2010, 04:59 PM   #2
flamenko
Senior Member
 
flamenko's Avatar
 
Join Date: Apr 2010
Location: Niagara, Canada
Posts: 349
Default

No.... SSDs all have wear levelling technology which ensures all "blocks" (if you will) are checked automatically and wear evenly. In fact, even stored information will be moved from location to location throughout the life of your ssd quite unlike that of the hard drive. This is different than a hard drive where it is possible that areas are never used or checked, thus necessitating the checkdisk function.

Last edited by flamenko; 04-25-2010 at 05:06 PM.
flamenko is offline   Reply With Quote
Old 04-25-2010, 05:06 PM   #3
BTRY B 529th FA BN
Lifer
 
BTRY B 529th FA BN's Avatar
 
Join Date: Nov 2005
Posts: 13,019
Default

TY sir
__________________
Rig1: Xeon X5660 6core 32nm (2.8GHz stock), Asrock X58, Geforce 210 0db, Samsung 128Gb 840 Pro, Vertex2 100Gb, Cherry MX Blacks, 2009 Seasonic X 650w, Aluminum Full tower
Rig2: i7 970 6core 32nm @ 4.4GHz 1.365v, EVGA 760 Classified,
GTX 670, Samsung Evo 120Gb, Vertex LE 100Gb, Cherry MX Reds, Sidewinder X5, Enermax Revo 950w, Obsidian 800D
BTRY B 529th FA BN is offline   Reply With Quote
Old 04-25-2010, 07:33 PM   #4
Mark R
Diamond Member
 
Mark R's Avatar
 
Join Date: Oct 1999
Posts: 8,296
Default

Quote:
Originally Posted by BTRY B 529th FA BN View Post
Do SSD drives need Check Disk?
Yes. All drives have the potential for file system corruption, due to corruption by the drive - (very rare on SSDs, but can still happen), power failure, system crash, etc.

What is more important, rather than drive technology, is the format used. Formats like FAT32 are unstable, and system crashes, power failures, etc. can severely corrupt the files and directories on the drive. You may need to use checkdisk software in order to repair the corruption.

Modern formats like NTFS are very stable, and highly resistant to system crashes and power failures. However, SSDs with a write-back cache but without a supercapacitor backup, can still allow NTFS partitions to be corrupted in a power failure situation. [SSDs without write-caching (e.g. Intel) or a write-cache with backup supercapacitor (e.g. Sandforce controller), are safe].

There is no need to regularly perform a surface scan, with SSDs - as the internal processor will periodically move data around as part of 'wear levelling'. When it is moved, it is checked for accuracy, and defective parts of the flash memory are deactivated and the data moved to a spare area.

That said, there is no need to perform surface scans of conventional HDs. The internal processor in normal HDs will regularly scan the data when idle, to ensure that all the data is readable, and weakening areas of data will be 'repaired' by moving the data to a spare area automatically.

--

Summary. SSDs are no different to HDs in terms of getting errors.

Most errors are software errors, caused by saving to the drive being interrupted by a serious system crash or power failure. Checkdisk will be required to check that the files are OK under some circumstances (very few on NTFS or other advanced formats).
Normal HDs can be protected from corruption by system crash and power-failure by disabling 'write caching' - but this is very slow. Some SSDs have ways of getting around this.

Errors on the drive (bad sectors) can occur on SSDs and HD (but are rare on SSDs). Both types of drive technology regularly scan the data automatically to check for bad sectors.
Mark R is online now   Reply With Quote
Old 04-25-2010, 08:02 PM   #5
flamenko
Senior Member
 
flamenko's Avatar
 
Join Date: Apr 2010
Location: Niagara, Canada
Posts: 349
Default

Nice add on!!!
flamenko is offline   Reply With Quote
Old 04-25-2010, 11:44 PM   #6
capeconsultant
Senior Member
 
Join Date: Aug 2005
Posts: 454
Default

Think I'll check disk my SSD right now
__________________
Mac mini - 2.3ghz - core i7-16GB Ram | 24 inch Dell IPS monitor | OCZ Vector 512GB SSD | 2TB WD External | CapeWP.com
capeconsultant is offline   Reply With Quote
Old 04-25-2010, 11:57 PM   #7
jimhsu
Senior Member
 
Join Date: Mar 2009
Posts: 702
Default

Quote:
Originally Posted by Mark R View Post
Yes. All drives have the potential for file system corruption, due to corruption by the drive - (very rare on SSDs, but can still happen), power failure, system crash, etc.

What is more important, rather than drive technology, is the format used. Formats like FAT32 are unstable, and system crashes, power failures, etc. can severely corrupt the files and directories on the drive. You may need to use checkdisk software in order to repair the corruption.

Modern formats like NTFS are very stable, and highly resistant to system crashes and power failures. However, SSDs with a write-back cache but without a supercapacitor backup, can still allow NTFS partitions to be corrupted in a power failure situation. [SSDs without write-caching (e.g. Intel) or a write-cache with backup supercapacitor (e.g. Sandforce controller), are safe].

There is no need to regularly perform a surface scan, with SSDs - as the internal processor will periodically move data around as part of 'wear levelling'. When it is moved, it is checked for accuracy, and defective parts of the flash memory are deactivated and the data moved to a spare area.

That said, there is no need to perform surface scans of conventional HDs. The internal processor in normal HDs will regularly scan the data when idle, to ensure that all the data is readable, and weakening areas of data will be 'repaired' by moving the data to a spare area automatically.

--

Summary. SSDs are no different to HDs in terms of getting errors.

Most errors are software errors, caused by saving to the drive being interrupted by a serious system crash or power failure. Checkdisk will be required to check that the files are OK under some circumstances (very few on NTFS or other advanced formats).
Normal HDs can be protected from corruption by system crash and power-failure by disabling 'write caching' - but this is very slow. Some SSDs have ways of getting around this.

Errors on the drive (bad sectors) can occur on SSDs and HD (but are rare on SSDs). Both types of drive technology regularly scan the data automatically to check for bad sectors.
To be precise, individual bit errors on SSDs are actually fairly common (on the order of 10^-7 or something) but due to error recovery, actual uncorrected bit errors are extremely low (10^-15 to 10^-18 [with SandForce's claims]). Similar to how human DNA replication is fairly error prone (10^-3 bases without any 3'-5' exonuclease activity) but with proofreading, excision repair, homologous recombination and whatnot becomes much more accurate (10^-8 or more). The amount of machinery and effort the typical cell devotes to DNA repair is frankly impressive ... the same can be said of IO devices in the modern day world.

Apologies for the lack of references. There was a whitepaper by Supertalent that covered this well ... I don't seem to have it for some reason.

PS I can't believe I just used a biology example in a post about IO storage devices. Lol.

Last edited by jimhsu; 04-26-2010 at 12:03 AM.
jimhsu is offline   Reply With Quote
Old 04-26-2010, 02:59 AM   #8
RebateMonger
Super Moderator
Elite Member
 
RebateMonger's Avatar
 
Join Date: Dec 2005
Location: Tempe, Arizona, USA
Posts: 11,592
Default

As noted by Mark R, Chkdsk can perform two different functions:

1) Check for logical errors
2) Check for physical errors

While they can be related, a logical error doesn't necessarily mean there's anything physically "wrong" with the disk. Win98, with its FAT operating system, often presented logical errors with scrambled directories and other niceties. NTFS is much more resistant to logical corruption. I don't thiink I've EVER seen a scrambled NTFS directory.
__________________
MCSE:Security:2003 - MCTS:SBS 2008 - Arizona's 1st Microsoft Small Business Specialist
--- In loving memory of my beautiful Australian Shepherd, Skye. July 2001-January 2010 ---
War on Terror 2000-2010 ~ Terrorist-caused Deaths < 10,000 ~ Bush's Wars > 1,000,000 ~ Winning?
RebateMonger is offline   Reply With Quote
Reply

Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -5. The time now is 06:43 PM.


Powered by vBulletin® Version 3.8.7
Copyright ©2000 - 2014, vBulletin Solutions, Inc.