On 06/07/16 07:17, Mkrtchyan, Tigran wrote:
Hi,
We had a similar situation and the best performance was with 64MB
background_bytes and 512 MB dirty_bytes.
Tigran.
On Jul 5, 2016 16:51, Kaixi Luo wrote:
Here are my server specs:
RAID1 - 2x480GB Samsung SSD with power loss protecti
Regarding the Nordeus blog Merlin linked.
They say:
"This doesn't mean the data was really written to disk, it can still remain in
the disk cache, but enterprise drives usually make sure the data was really
written to disk on fsync calls."
This isn't actually true for enterprise drives (when I
On Wed, Jul 6, 2016 at 12:13 PM, Merlin Moncure wrote:
> Disabling write back cache for write heavy database loads will will
> destroy it in short order due to write amplication and will generally
> cause it to underperform hard drives in my experience.
Interesting. We found our best performance
On Tue, Jul 5, 2016 at 9:50 AM, Kaixi Luo wrote:
> Hello,
>
> I've been reading Mr. Greg Smith's "Postgres 9.0 - High Performance" book
> and I have some questions regarding the guidelines I found in the book,
> because I suspect some of them can't be followed blindly to the letter on a
> server w
Well, our CPU\RAM configs are almost same...
The difference is - you're fetching\grouping 8 times less rows than I:
You scan 16.5 mln rows and fetch ~200k rows in 2 seconds and than spend
1.4 sec for aggregation
I'm scanning 3.5 mln rows and fetching 1.5 mln rows (8 times more than
you) in 1
On Mon, Jul 4, 2016 at 11:35 AM, Kouber Saparev wrote:
> I tried to DELETE about 7 million rows at once, and the query went up to 15%
> of the RAM (120 GB in total), which pushed some indexes out and the server
> load went up to 250, so I had to kill the query.
>
> The involved table does not have
On 06.07.2016 17:06, trafdev wrote:
Wondering what are your CPU\RAM characteristics?
Intel Core i7-2600 Quad Core
32 GB DDR3 RAM
2x 3 TB SATA III HDD
HDD is:
Model Family: Seagate Barracuda XT
Device Model: ST33000651AS
Firmware Version: CC45
User Capacity:3,000,592,982,016 bytes
Wondering what are your CPU\RAM characteristics?
On 07/06/16 01:35, Torsten Zuehlsdorff wrote:
On 05.07.2016 17:35, trafdev wrote:
[..]
Without TIMESTAMP cast:
QUERY PLAN
HashAggregate (cost=1405666.90..1416585.93 rows=335970 width=86)
(actual time=4797.272..4924.015 rows=126533 loops=1)
" G
On 05.07.2016 17:35, trafdev wrote:
> [..]
Without TIMESTAMP cast:
QUERY PLAN
HashAggregate (cost=1405666.90..1416585.93 rows=335970 width=86)
(actual time=4797.272..4924.015 rows=126533 loops=1)
" Group Key: subid, sid"
Buffers: shared hit=1486949
-> Index Scan using ix_feed_sub_aid_date
