By: Doug S (foo.delete@this.bar.bar), December 8, 2014 2:04 pm
Room: Moderated Discussions
rwessel (robertwessel.delete@this.yahoo.com) on December 8, 2014 12:52 pm wrote:
> Brett (ggtgp.delete@this.yahoo.com) on December 8, 2014 10:00 am wrote:
> > Eric Bron (eric.bron.delete@this.zvisuel.privatefortest.com) on December 8, 2014 4:35 am wrote:
> > > > have huge working sets which would take too much memory, energy, and loading time to access.
> > >
> > > even without resorting to new technologies, SSD are vey fast already, something which need
> > > much attention for out of core processing is the file formats, legacy formats and many new
> > > formats (!) are based on serialization of the whole file which goes against parallelization
> >
> > A SSD has one set of pins you plug the device into, so ultimately the interface is serial.
> > The big mistake is not preallocating your disk blocks, a simple byte stream will have to update the file
> > table for each block added. This doubles the number of blocks written to and almost all those file table
> > blocks will need to be erased, which leads to a slow garbage collection wear leveling pass.
>
>
> Unless you specify immediate writes, better file systems do not need to commit the block indexes/pointers
> to disk for a file being sequentially written until the data is actually written to disk, or even
> until the file is actually closed. And considerable amounts of data can be buffered.
Not to mention, better SSDs include some SLC NAND write cache for small writes, so metadata updates don't get spooled out to MLC until evicted from the SLC cache.
This hasn't really made it to the consumer segment much yet, but flash lifetime is irrelevant at the consumer level. I've got a mirrored pair of Intel 320 SSDs in my home PC that are about two years old now. According to SMART the media wearout is at 99 - it starts at 100 and you get warnings around 5 or 10. I will replace them long before they wear out, despite not bothering with silly ideas to extend their life like preallocation.
In my laptop I use for work I have a Crucial MX100 that's about six months old. I run a Windows VM on it which is constantly badgering the filesystem with pointless small writes. Media wearout indicator is still 100 there, it too will last long beyond the point where I'll toss it aside.
> Brett (ggtgp.delete@this.yahoo.com) on December 8, 2014 10:00 am wrote:
> > Eric Bron (eric.bron.delete@this.zvisuel.privatefortest.com) on December 8, 2014 4:35 am wrote:
> > > > have huge working sets which would take too much memory, energy, and loading time to access.
> > >
> > > even without resorting to new technologies, SSD are vey fast already, something which need
> > > much attention for out of core processing is the file formats, legacy formats and many new
> > > formats (!) are based on serialization of the whole file which goes against parallelization
> >
> > A SSD has one set of pins you plug the device into, so ultimately the interface is serial.
> > The big mistake is not preallocating your disk blocks, a simple byte stream will have to update the file
> > table for each block added. This doubles the number of blocks written to and almost all those file table
> > blocks will need to be erased, which leads to a slow garbage collection wear leveling pass.
>
>
> Unless you specify immediate writes, better file systems do not need to commit the block indexes/pointers
> to disk for a file being sequentially written until the data is actually written to disk, or even
> until the file is actually closed. And considerable amounts of data can be buffered.
Not to mention, better SSDs include some SLC NAND write cache for small writes, so metadata updates don't get spooled out to MLC until evicted from the SLC cache.
This hasn't really made it to the consumer segment much yet, but flash lifetime is irrelevant at the consumer level. I've got a mirrored pair of Intel 320 SSDs in my home PC that are about two years old now. According to SMART the media wearout is at 99 - it starts at 100 and you get warnings around 5 or 10. I will replace them long before they wear out, despite not bothering with silly ideas to extend their life like preallocation.
In my laptop I use for work I have a Crucial MX100 that's about six months old. I run a Windows VM on it which is constantly badgering the filesystem with pointless small writes. Media wearout indicator is still 100 there, it too will last long beyond the point where I'll toss it aside.