Hmmm interesting, as an owner of a late 2009 MB Pro, what I'd really love to see is whether there would be any difference with a brand new "out of the box" SSD compared to the one you guys received in the Air. I've got a mechanical HD in the lappie at the mo, but would really love to see a 256GB SSD in there.
Is it "possible" that the SSD you tested was so thrashed by other reviews, it was suffering as a result? I don't know, maybe some built in "wear leveling" at it's maximum?
It feels to me though that TRIM isn't really needed on a MB (At least with the SSDs apple use). I wonder if that statement still stacks up when installing your own SSD.
I assume being a mac that you cannot take the SSD out and repeat the tests on a PC?
Also, being Apple, you will not get specific answers to performance unless it is a positive result. Believe me, I have worked with them for many years. If it doesn't make them look good, no-one seems to know.
Originally Posted by Guinevere Is it "possible" that the SSD you tested was so thrashed by other reviews, it was suffering as a result? I don't know, maybe some built in "wear leveling" at it's maximum?
It feels to me though that TRIM isn't really needed on a MB (At least with the SSDs apple use). I wonder if that statement still stacks up when installing your own SSD.
It's possible, but we did reformat the Air using an option in the OS X installer that sets all the bytes in the disk to zero - it's effectively the same low level format we do for SSDs when testing them under Win 7.
Definitely need to see what happens when you put a retail, new, modern SSD in that 2008 MacBook Pro you have sitting around for podcasts. The Air is well due for an update, so I'm not suprised its SSD is dating from 2008...
As a side note, you can get off the shelf SSDs for the Air, but they're not exactly common due to the size (The Air uses physically smaller drives, think the old iPod 1.8" HDDs).
It would probably be a good idea to install Windows on the Mac using bootcamp and test (using all of your usual Windows tools) just to see if it's OSX being good or the SSD doing something freaky.
TRIM is unimportant is when deleting files the OS actually deletes them. I.e. resets the data on the SSD to 0s rather than just deleting the file's pointer in the filesystem's File Allocation Table.
As a followup, you could test a non-TRIM enabled SSD under Linux with an ext3/ZFS filesystem (filesystems that never need to be defragmented too).
Quote:
Originally Posted by TFA Consider the Indilinx powered OCZ Vertex: without TRIM, its sequential read speed of 1,024KB files plummeted by astonishing 87 per cent - from 258MB/sec to 138MB/sec.
Uhhhh what? 138 is like 53% of 258. Performance plummeted by an astonishing 47%.
I did wonder if it might be related to file structure in the way that Linux's ext 3/4 copes much better with fragmentation than Window's NTFS/FAT therefore needing significantly less defragging, if indeed any at all is needed.
However checking back over a few articles from Linux magazine it would seem earlier SSDs still struggled with early kernels due to a lack of TRIM support. I would guess therefore that the logical explanation is either that OSX has TRIM or the SSD is too slow to notice any significant changem which I guess in a way is an astonishingly long way of saying.... what he said!
Word from a Mac engineer: even swapping an off-the-shelf SSD into any form of Mac won't give you decent results. Because Mac OS X and it's file system treat the actual hardware so differently (as you discovered) Apple supply all their hard drives and SSDs with custom firmware, optimised for the specific differences in cache usage patterns between OS X and Windows, the OS pretty much all hardware is primarily designed and supplied to to perform best on.
I've personally seem some quite startling differences in performance differences between Apple-supplied hard drives and seemingly identical 3rd-party units. I replaced 2 failing drives in an X-Raid, sourcing drives identical to the originals before Apple rebadged (and reflashed) them, placed them in the original Apple caddies and rebuilt the entire raid structure from scratch. Performance writing large contiguous files to the raid dropped around 20%.
Originally Posted by StoneyMahoney Word from a Mac engineer: even swapping an off-the-shelf SSD into any form of Mac won't give you decent results. Because Mac OS X and it's file system treat the actual hardware so differently (as you discovered) Apple supply all their hard drives and SSDs with custom firmware, optimised for the specific differences in cache usage patterns between OS X and Windows, the OS pretty much all hardware is primarily designed and supplied to to perform best on.
I've personally seem some quite startling differences in performance differences between Apple-supplied hard drives and seemingly identical 3rd-party units. I replaced 2 failing drives in an X-Raid, sourcing drives identical to the originals before Apple rebadged (and reflashed) them, placed them in the original Apple caddies and rebuilt the entire raid structure from scratch. Performance writing large contiguous files to the raid dropped around 20%.
So what is the answer if I want to put an SSD in my MacBook? :)
if it's using different firmware, i would be very interested in what happens if you partition the test Macbook Air and install Windows onto the SSD. this should tell if it's running self-TRIM firmware or just plain Samsung.
very interesting read, it appears i have got exact same Samsung drive in my desktop. but don't have TRIM support
It would be interesting to see an off the shelf SSD in a MacBook Pro. Drive Genius does some sort of performance testing though I've never looked deeply into it.
I'm not sure about the SSD's specifics, but Apple named/branded drives have custom firmware on them, which may effect abilities or performance. I know in the case of server/raid drives, Apple's engineers have worked with the drive manufacturers to optimize the firmware for the way OS X and HFS+ accesses and caches data.
Comments 1 to 25 of 58
ReplyIs it "possible" that the SSD you tested was so thrashed by other reviews, it was suffering as a result? I don't know, maybe some built in "wear leveling" at it's maximum?
It feels to me though that TRIM isn't really needed on a MB (At least with the SSDs apple use). I wonder if that statement still stacks up when installing your own SSD.
Also, being Apple, you will not get specific answers to performance unless it is a positive result. Believe me, I have worked with them for many years. If it doesn't make them look good, no-one seems to know.
It's possible, but we did reformat the Air using an option in the OS X installer that sets all the bytes in the disk to zero - it's effectively the same low level format we do for SSDs when testing them under Win 7.
Retail SSDs in Macs is next up I think :)
Did you try disabling journaling to see if it had any effect on the performance?
Cos the Air doesn't have a 2.5in SATA connection of course :p
Surely you can get your hands on a macbook pro
As the drives will keep themselves tidy regardless of the OS or filesystem?
eg. the OCZ Vertex and similar.
The firmware supports TRIM and GC.
As a side note, you can get off the shelf SSDs for the Air, but they're not exactly common due to the size (The Air uses physically smaller drives, think the old iPod 1.8" HDDs).
Earlier Airs used a sata-LIF connection (pretty much only used by Apple AFAIK) but the rev B's used a Micro Sata which you can get adapters for
As a followup, you could test a non-TRIM enabled SSD under Linux with an ext3/ZFS filesystem (filesystems that never need to be defragmented too).
Uhhhh what? 138 is like 53% of 258. Performance plummeted by an astonishing 47%.
Gah, sorry, fixed. :S
However checking back over a few articles from Linux magazine it would seem earlier SSDs still struggled with early kernels due to a lack of TRIM support. I would guess therefore that the logical explanation is either that OSX has TRIM or the SSD is too slow to notice any significant changem which I guess in a way is an astonishingly long way of saying.... what he said!
I've personally seem some quite startling differences in performance differences between Apple-supplied hard drives and seemingly identical 3rd-party units. I replaced 2 failing drives in an X-Raid, sourcing drives identical to the originals before Apple rebadged (and reflashed) them, placed them in the original Apple caddies and rebuilt the entire raid structure from scratch. Performance writing large contiguous files to the raid dropped around 20%.
Nice :) You can always drop me an email (editor [at] bit-tech.net) if you have any more info to share...
So what is the answer if I want to put an SSD in my MacBook? :)
very interesting read, it appears i have got exact same Samsung drive in my desktop. but don't have TRIM support
edit: ah yes, Garbage Collection. So what everyone else said. Ignore me!
I'm not sure about the SSD's specifics, but Apple named/branded drives have custom firmware on them, which may effect abilities or performance. I know in the case of server/raid drives, Apple's engineers have worked with the drive manufacturers to optimize the firmware for the way OS X and HFS+ accesses and caches data.
-
« Previous
-
1
-
2
-
3
-
Next »
Discuss in the forums