Forums
New posts
Search forums
News
Security News
Technology News
Giveaways
Giveaways, Promotions and Contests
Discounts & Deals
Reviews
Users Reviews
Video Reviews
Support
Windows Malware Removal Help & Support
Inactive Support Threads
Mac Malware Removal Help & Support
Mobile Malware Removal Help & Support
Blog
Log in
Register
What's new
Search
Search titles only
By:
Search titles only
By:
Reply to thread
Menu
Install the app
Install
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Forums
Software
General Apps
System utilities
SSD Fresh, anyone heard of this?
Message
<blockquote data-quote="MacDefender" data-source="post: 918900" data-attributes="member: 83059"><p>Sure, bugs happen but in the time it takes for issues like this to be discovered and fixed, you aren't going to lose that much SSD capacity. TRIM calls on already-trimmed areas of SSDs generally incur no cost. (Again, I've worked on firmware for popular SSDs for 5+ years... I am well aware of what the SSD does in response to these commands)</p><p></p><p></p><p>SuperFetch and Prefetch info is directly from Microsoft, an optimization they introduced in Windows 8 and carried to Windows 10 will benchmark your SSD for random access performance and use that to guide what aspects of prefetch/superfetch to enable: <a href="https://www.howtogeek.com/256859/dont-waste-time-optimizing-your-ssd-windows-knows-what-its-doing/" target="_blank">Don’t Waste Time Optimizing Your SSD, Windows Knows What Its Doing (howtogeek.com)</a></p><p></p><p>On the systems I own, most of them do not have any Superfetch activity but do maintain Prefetch for a small set of applications, which is usually the behavior you want. Prefetch isn't just about HDD/SSD latency, it's about applications that interleave IO with CPU activity, and being able to predict the future set of IOs.</p><p></p><p>If you have an old generation SATA SSD from like the days of OCZ Vertexes, sure, you might need to be careful if those SSDs are miraculously still alive. But if you have any reasonable SSD made in the last 5 years, trying to tune it this way is a total waste of time. We used to put on the data sheet the most prematurely failing numbers on our racks because of how ridiculously large those numbers already are. It wasn't at all unusual that drives we rate to a few hundred TBWs actually survive dozens of PBWs and still had not failed.</p></blockquote><p></p>
[QUOTE="MacDefender, post: 918900, member: 83059"] Sure, bugs happen but in the time it takes for issues like this to be discovered and fixed, you aren't going to lose that much SSD capacity. TRIM calls on already-trimmed areas of SSDs generally incur no cost. (Again, I've worked on firmware for popular SSDs for 5+ years... I am well aware of what the SSD does in response to these commands) SuperFetch and Prefetch info is directly from Microsoft, an optimization they introduced in Windows 8 and carried to Windows 10 will benchmark your SSD for random access performance and use that to guide what aspects of prefetch/superfetch to enable: [URL='https://www.howtogeek.com/256859/dont-waste-time-optimizing-your-ssd-windows-knows-what-its-doing/']Don’t Waste Time Optimizing Your SSD, Windows Knows What Its Doing (howtogeek.com)[/URL] On the systems I own, most of them do not have any Superfetch activity but do maintain Prefetch for a small set of applications, which is usually the behavior you want. Prefetch isn't just about HDD/SSD latency, it's about applications that interleave IO with CPU activity, and being able to predict the future set of IOs. If you have an old generation SATA SSD from like the days of OCZ Vertexes, sure, you might need to be careful if those SSDs are miraculously still alive. But if you have any reasonable SSD made in the last 5 years, trying to tune it this way is a total waste of time. We used to put on the data sheet the most prematurely failing numbers on our racks because of how ridiculously large those numbers already are. It wasn't at all unusual that drives we rate to a few hundred TBWs actually survive dozens of PBWs and still had not failed. [/QUOTE]
Insert quotes…
Verification
Post reply
Top