On 05/03/19, Kenneth Marshall (ktm@rice.edu) wrote:
> >
> > Consequently we're thinking of the following replacement servers:
> >
> > postgres 11 (planned)
> > supermicro 113TQ-R700W
> > LSI MegaRAID 9271-8i SAS/SATA RAID Controller, 1Gb DDR3 Cache (PCIE- Gen 3)
> > 500gb raid 1 /
> > 2tb raid 10 /db
> > with "zero maintenance flash cache protection"
> > 256GB RAM (2666MHz DDR4)
> > 2x E5-2680 v4 Intel Xeon, 14 Cores, 2.40GHz, 35M Cache,
> >
> > This configuration gives us lots more storage, double the RAM (with 8
> > slots free) and just under 4x CPU (according to passmark) with lots more
> > cores.
> >
> > We're hoping to get two to three years of service out of this upgrade,
> > but then will split the cluster between servers if demand grows more
> > than we anticipate.
> >
> > Any comments on this upgrade, strategy or the "zero maintenance" thingy
> > (instead of a BBU) would be much appreciated.
> Is there a reason not to consider an all flash solution? The AMD EPYC
> processor series supports enough NVMe channels to support your sizing.
> The 7401P single processor is a good value proposition.
Hi Ken
Thanks very much for your response.
I'm completely naive about the uses of NVMe. Does it support RAID, for
instance? Since we are not IO-bound at the moment, do you believe NVMe
would relieve our RAM/CPU problems?
I'd be grateful for some pointers to database-related NVMe info.
Many thanks
Rory