From: | Vinicius Segalin <vinisegalin(at)gmail(dot)com> |
---|---|
To: | Oleksandr Shulgin <oleksandr(dot)shulgin(at)zalando(dot)de> |
Cc: | pgsql general <pgsql-general(at)postgresql(dot)org> |
Subject: | Re: Predicting query runtime |
Date: | 2016-09-12 15:59:04 |
Message-ID: | CAAeH1nBeFX6j=DL-fVy_ThiHhgaxx46fch5ADwaCkyA2Ng8FdQ@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-general |
2016-09-12 12:08 GMT-03:00 Oleksandr Shulgin <oleksandr(dot)shulgin(at)zalando(dot)de>:
> On Mon, Sep 12, 2016 at 4:03 PM, Vinicius Segalin <vinisegalin(at)gmail(dot)com>
> wrote:
>
>> Hi everyone,
>>
>> I'm trying to find a way to predict query runtime (I don't need to be
>> extremely precise). I've been reading some papers about it, and people are
>> using machine learning to do so. For the feature vector, they use what the
>> DBMS's query planner provide, such as operators and their cost. The thing
>> is that I haven't found any work using PostgreSQL, so I'm struggling to
>> adapt it.
>> My question is if anyone is aware of a work that uses machine learning
>> and PostgreSQL to predict query runtime, or maybe some other method to
>> perform this.
>>
>
> Hi,
>
> I'm not aware of machine-learning techniques to achieve that (and I don't
> actually believe it's feasible), but there you might find this extension
> particularly useful: https://www.postgresql.org/docs/9.5/static/
> pgstatstatements.html
>
I'll read about it and see how it can help me. Thank you
> Can you share some links to the papers you are referring to (assuming
> these are publicly available)?
>
I don't have them all now, but these are some of them:
http://dl.acm.org/citation.cfm?id=1845166
https://people.eecs.berkeley.edu/~jordan/papers/ganapathi-etal-icde09.pdf
From | Date | Subject | |
---|---|---|---|
Next Message | Patrick B | 2016-09-12 18:09:33 | Re: 2.5TB Migration from SATA to SSD disks - PostgreSQL 9.2 |
Previous Message | Oleksandr Shulgin | 2016-09-12 15:08:14 | Re: Predicting query runtime |