| From: | Adrian von Bidder <avbidder(at)fortytwo(dot)ch> |
|---|---|
| To: | pgsql-general(at)postgresql(dot)org |
| Subject: | Re: database response slows while pg_dump is running (8.4.2) |
| Date: | 2010-06-11 06:43:53 |
| Message-ID: | 201006110843.53857@fortytwo.ch |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-general |
Heyho!
On Thursday 10 June 2010 23.49:58 Aleksey Tsalolikhin wrote:
> 3. We ARE disk bound. Disk utilization goes to 94% during
> the dump. There is an order of magnitude more reads than
> writes.
Just speculation, I've not tried this. Perhaps pipe the output of pg_dump
through a software that bandwidth-limits the throughput? (I don't know if
such a command exists, but it probably could be done in 4 lines of Perl or
30 lines of C if necessary.) Or are there so many buffers involved that
this would just cause data to pile up in memory, waiting to be written out?
cheers
-- vbi
--
There’s a big confusion in the terms, as the numbers used in Arabic are
the Hindu numbers and the numbers used in Latin languages are the Arabic
numbers.
-- Lior Kaplan, 1.4.2008
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Adrian von Bidder | 2010-06-11 06:48:42 | Re: Best way to store case-insensitive data? |
| Previous Message | Stephen Frost | 2010-06-11 01:18:42 | Re: Enforcing password standards |