| Lists: | pgsql-performance |
|---|
| From: | Ricardo Humphreys <ricardoainati(at)gmail(dot)com> |
|---|---|
| To: | pgsql-performance(at)postgresql(dot)org |
| Subject: | Avoid using swap in a cluster |
| Date: | 2005-09-02 01:04:10 |
| Message-ID: | 3aa4c10905090118046e81b107@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Lists: | pgsql-performance |
Hi all.
In a cluster, is there any way to use the main memory of the other nodes
instead of the swap? If I have a query with many sub-queries and a lot of
data, I can easily fill all the memory in a node. The point is: is there any
way to continue using the main memory from other nodes in the same query
instead of the swap?
Thank you,
Ricardo.
| From: | Richard Huxton <dev(at)archonet(dot)com> |
|---|---|
| To: | Ricardo Humphreys <ricardoainati(at)gmail(dot)com> |
| Cc: | pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: Avoid using swap in a cluster |
| Date: | 2005-09-02 09:42:59 |
| Message-ID: | 43181EA3.3010302@archonet.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Lists: | pgsql-performance |
Ricardo Humphreys wrote:
> Hi all.
> In a cluster, is there any way to use the main memory of the other nodes
> instead of the swap? If I have a query with many sub-queries and a lot of
> data, I can easily fill all the memory in a node. The point is: is there any
> way to continue using the main memory from other nodes in the same query
> instead of the swap?
I don't know of any clustered version of PG that can spread queries over
multiple machines. Can I ask what you are using?
--
Richard Huxton
Archonet Ltd
| From: | Alex Stapleton <alexs(at)advfn(dot)com> |
|---|---|
| To: | Richard Huxton <dev(at)archonet(dot)com> |
| Cc: | Ricardo Humphreys <ricardoainati(at)gmail(dot)com>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: Avoid using swap in a cluster |
| Date: | 2005-09-02 11:18:22 |
| Message-ID: | 1C0688FA-8D0D-4862-B416-C2574FD284BC@advfn.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Lists: | pgsql-performance |
On 2 Sep 2005, at 10:42, Richard Huxton wrote:
> Ricardo Humphreys wrote:
>
>> Hi all.
>> In a cluster, is there any way to use the main memory of the
>> other nodes instead of the swap? If I have a query with many sub-
>> queries and a lot of data, I can easily fill all the memory in a
>> node. The point is: is there any way to continue using the main
>> memory from other nodes in the same query instead of the swap?
>>
>
> I don't know of any clustered version of PG that can spread queries
> over multiple machines. Can I ask what you are using?
IIRC GreenPlums DeepGreen MPP (Version 2) can do it. It does cost
money though, but it is a very nice product.
> --
> Richard Huxton
> Archonet Ltd
>
> ---------------------------(end of
> broadcast)---------------------------
> TIP 9: In versions below 8.0, the planner will ignore your desire to
> choose an index scan if your joining column's datatypes do not
> match
>