[mythtv-users] MySQL on SSD 99% Utilization

[Matthew McClement]

On 03/02/11 18:46, Rob Smith wrote:
> On Thu, Feb 3, 2011 at 10:38 AM, Matthew McClement <mythtv at macker.co.uk> wrote:
>> Eh? SSD's are significantly slower at writes than reads, especially if
>> you're writing to a non-GC'd cell, which with how the Toshiba controller
>> handles TRIM is entirely possible(GC isn't continuous but rather seems
>> to be demand triggered). If you then add non-aligned sub-page sized
>> writes, things can get bad pretty quickly.
>>
>> It's buffering and other tricks which make SSD's faster today over the
>> early versions, rather than slower.
>>
>> And it's not like that result is an oddity. Just look at any benchmark
>> for the early JMicron based SSDs to see SSDs that were often *slower*
>> than hard disks at random writes.
>>
>> Matt
> 
> Those benchmarks do look incorrect. For example:
> 4KB Random Reads:
> Kingston SSDNow V Series (30GB) - 9.1 MB/s
> Western Digital VelociRaptor (600GB) - 68 MB/s
> 
> 4KB Random Read (4K Aligned)
> Kingston SSDNow V Series (30GB) - 9.4 MB/s
> Western Digital VelociRaptor (600GB) - 68 MB/s
> That is just wrong or a really really crappy SSD

Considering that the rest of the graphs are to scale, that *might* just
suggest that the rendering layer is dropping/hiding the decimal place?

Matt