Обсуждение: hardware donation

Поиск
Список
Период
Сортировка

hardware donation

От
Benedikt Grundmann
Дата:
Jane Street has a spare server we would like to donate to the postgres community.  We originally planed to use it for one of our database clusters and it matches exactly what we use in production at the moment. 

Rough specs:
CPU: 8x Intel(R) Xeon(R) CPU           X5570  @ 2.93GHz
MEM: 48GB

The server will probably be most interesting for the disks in it.  That is where we spend the largest amount of time optimizing (for sequential scan speed in particular):

22x600GB disks in a Raid6+0 (Raid0 of 2x 10disk raid 6 arrays) + 2 spare disks. Overall size 8.7 TB in that configuration.

Is this something the community would find useful?  If so, who is the right person to talk to about shipping/delivery?

Cheers,

Bene

Re: hardware donation

От
Josh Berkus
Дата:
On 07/10/2013 09:53 AM, Benedikt Grundmann wrote:
> Jane Street has a spare server we would like to donate to the postgres
> community.  We originally planed to use it for one of our database clusters
> and it matches exactly what we use in production at the moment.
> 
> Rough specs:
> CPU: 8x Intel(R) Xeon(R) CPU           X5570  @ 2.93GHz
> MEM: 48GB
> 
> The server will probably be most interesting for the disks in it.  That is
> where we spend the largest amount of time optimizing (for sequential scan
> speed in particular):
> 
> 22x600GB disks in a Raid6+0 (Raid0 of 2x 10disk raid 6 arrays) + 2 spare
> disks. Overall size 8.7 TB in that configuration.
> 
> Is this something the community would find useful?  If so, who is the right
> person to talk to about shipping/delivery?

Mark, we can use this in the performance farm, no?

I know I could use it for testing ...

-- 
Josh Berkus
PostgreSQL Experts Inc.
http://pgexperts.com



Re: hardware donation

От
Mark Wong
Дата:
On Wed, Jul 10, 2013 at 10:00 AM, Josh Berkus <josh@agliodbs.com> wrote:
> On 07/10/2013 09:53 AM, Benedikt Grundmann wrote:
>> Jane Street has a spare server we would like to donate to the postgres
>> community.  We originally planed to use it for one of our database clusters
>> and it matches exactly what we use in production at the moment.
>>
>> Rough specs:
>> CPU: 8x Intel(R) Xeon(R) CPU           X5570  @ 2.93GHz
>> MEM: 48GB
>>
>> The server will probably be most interesting for the disks in it.  That is
>> where we spend the largest amount of time optimizing (for sequential scan
>> speed in particular):
>>
>> 22x600GB disks in a Raid6+0 (Raid0 of 2x 10disk raid 6 arrays) + 2 spare
>> disks. Overall size 8.7 TB in that configuration.
>>
>> Is this something the community would find useful?  If so, who is the right
>> person to talk to about shipping/delivery?
>
> Mark, we can use this in the performance farm, no?
>
> I know I could use it for testing ...

Yes, we certainly can.  I can be the contact for shipping/delivery.  Thanks!

Regards,
Mark



Re: hardware donation

От
Greg Smith
Дата:
On 7/10/13 12:53 PM, Benedikt Grundmann wrote:
> The server will probably be most interesting for the disks in it.  That
> is where we spend the largest amount of time optimizing (for sequential
> scan speed in particular):
> 22x600GB disks in a Raid6+0 (Raid0 of 2x 10disk raid 6 arrays) + 2 spare
> disks. Overall size 8.7 TB in that configuration.

What is the RAID controller used in the server?  That doesn't impact the 
donation, I'm just trying to fit this one into my goals for finding 
useful community performance testing equipment.

There are a good number of systems floating around the community with HP 
controllers--I have even one myself now--but we could use more LSI Logic 
and Adaptec based systems.

-- 
Greg Smith   2ndQuadrant US    greg@2ndQuadrant.com   Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com



Re: hardware donation

От
Benedikt Grundmann
Дата:
<div dir="ltr">The server is already turned off and in our nyc office (I'm based in the ldn one).  But I'm pretty sure
itsa LSI MegaRAID SAS 9285. <br /></div><div class="gmail_extra"><br /><br /><div class="gmail_quote"> On Thu, Jul 18,
2013at 11:58 PM, Greg Smith <span dir="ltr"><<a href="mailto:greg@2ndquadrant.com"
target="_blank">greg@2ndquadrant.com</a>></span>wrote:<br /><blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px#ccc solid;padding-left:1ex"><div class="im">On 7/10/13 12:53 PM, Benedikt Grundmann wrote:<br
/><blockquoteclass="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> The server will
probablybe most interesting for the disks in it.  That<br /> is where we spend the largest amount of time optimizing
(forsequential<br /> scan speed in particular):<br /> 22x600GB disks in a Raid6+0 (Raid0 of 2x 10disk raid 6 arrays) +
2spare<br /> disks. Overall size 8.7 TB in that configuration.<br /></blockquote><br /></div> What is the RAID
controllerused in the server?  That doesn't impact the donation, I'm just trying to fit this one into my goals for
findinguseful community performance testing equipment.<br /><br /> There are a good number of systems floating around
thecommunity with HP controllers--I have even one myself now--but we could use more LSI Logic and Adaptec based
systems.<spanclass="HOEnZb"><font color="#888888"><br /><br /> -- <br /> Greg Smith   2ndQuadrant US  
 greg@2ndQuadrant.com  Baltimore, MD<br /> PostgreSQL Training, Services, and 24x7 Support <a
href="http://www.2ndQuadrant.com"target="_blank">www.2ndQuadrant.com</a><br /></font></span></blockquote></div><br
/></div>