Are you using a hardware based raid controller with them?
Yes, of course. Hardware raid with cache and bbu is a must. You can't get fast fsync without it. Also mdadm is a pain in the ass and is suitable only on amazon and other cloud shit.
Den 11/12/2012 20.11 skrev "Evgeny Shishkin" < itparanoia@xxxxxxxxx>:
And what is your experience so far?
Increased tps by a factor of 10, database no longer a limiting factor of application. And it is cheaper than brand rotating drives.
Den 11/12/2012 18.16 skrev "Evgeny Shishkin" < itparanoia@xxxxxxxxx>:
On Dec 11, 2012, at 5:35 PM, Niels Kristian Schjødt <nielskristian@xxxxxxxxxxxxx> wrote:
>
> Den 11/12/2012 kl. 14.29 skrev Craig Ringer <craig@xxxxxxxxxxxxxxx>:
>
>> On 12/11/2012 06:04 PM, Niels Kristian Schjødt wrote:
>>>
>>> Maybe I should mention, that I never see more than max 5Gb out of my total 32Gb being in use on the server… Can I somehow utilize more of it?
>> For an update-mostly workload it probably won't do you tons of good so
>> long as all your indexes fit in RAM. You're clearly severely
>> bottlenecked on disk I/O not RAM.
>>> The SSD's I use a are 240Gb each which will grow too small within a
>>> few months - so - how does moving the whole data dir onto four of
>>> those in a RAID5 array sound?
>>
>> Not RAID 5!
>>
>> Use a RAID10 of four or six SSDs.
>>
>> --
>> Craig Ringer http://www.2ndQuadrant.com/
>> PostgreSQL Development, 24x7 Support, Training & Services
>>
> Hehe got it - did you have a look at the SSD's I am considering building it of? http://ark.intel.com/products/66250/Intel-SSD-520-Series-240GB-2_5in-SATA-6Gbs-25nm-MLC
> Are they suitable do you think?
>
I am not Craig, but i use them in production in raid10 array now.
>
>
> --
> Sent via pgsql-performance mailing list (pgsql-performance@xxxxxxxxxxxxxx)
> To make changes to your subscription:
> http://www.postgresql.org/mailpref/pgsql-performance
|
