Please see comment at the bottom of this post.
On 08/07/16 10:48, Pete Stevenson wrote:
Good info, thanks for the note. Agreed that it is difficult to pull
things apart to isolate these features for offload — so actually
running experiments with offload is not possible, as you point out
(and f
Peter Geoghegan wrote:
> Has anyone ever done any kind of write-up of the "TED" design that was
> discussed during FOSDEM (I hope I recall the name it was given
> correctly)? Apparently that's something that's been discussed a few
> times among senior community members, and I think it has promise.
On Thu, Jul 7, 2016 at 11:45 AM, Pete Stevenson
wrote:
> Hi postgresql hackers -
>
> I would like to find some analysis (published work, blog posts) on the
> overheads affiliated with the guarantees provided by MVCC isolation. More
> specifically, assuming the current workload is CPU bound (as o
On Fri, Jul 8, 2016 at 11:44 AM, Tom Lane wrote:
>> Sure, but we could *also* do it separately, splitting VACUUMs tasks of
>> tuple freezing, page compaction, and index entry removal each into
>> separate tasks.
>
> Uh ... wouldn't that tend to make things worse? The knocks on VACUUM are
> too mu
On Thu, Jul 7, 2016 at 11:45 AM, Pete Stevenson
wrote:
> I would like to find some analysis (published work, blog posts)
> on the overheads affiliated with the guarantees provided by MVCC
> isolation.
There are three levels of isolation implemented[1]; the incremental
cost of SERIALIZABLE isolat
Alvaro Herrera writes:
> Tom Lane wrote:
>> VACUUM in itself is an offloading optimization; the whole point of it
>> is to do maintenance in a background process not foreground queries.
> Well, if VACUUM worked so great, we wouldn't get so many trouble reports
> with it. There's substantial impr
Tom Lane wrote:
> Alvaro Herrera writes:
> > Pete Stevenson wrote:
> >> Maybe I could figure out the lines of code that add versions into a
> >> table and then those that collect old versions (they do get collected,
> >> right?). Anyway, thought being I could profile while running TPC-C or
> >> si
Alvaro Herrera writes:
> Pete Stevenson wrote:
>> Maybe I could figure out the lines of code that add versions into a
>> table and then those that collect old versions (they do get collected,
>> right?). Anyway, thought being I could profile while running TPC-C or
>> similar. I was hoping that som
Pete Stevenson wrote:
> Maybe I could figure out the lines of code that add versions into a
> table and then those that collect old versions (they do get collected,
> right?). Anyway, thought being I could profile while running TPC-C or
> similar. I was hoping that someone might be able to jump on
Good info, thanks for the note. Agreed that it is difficult to pull things
apart to isolate these features for offload — so actually running experiments
with offload is not possible, as you point out (and for other reasons).
Maybe I could figure out the lines of code that add versions into a tab
On 8 July 2016 at 03:50, Pete Stevenson wrote:
> Hi Simon -
>
> Thanks for the note. I think it's fair to say that I didn't provide enough
> context, so let me try and elaborate on my question.
>
Please reply in-line in posts to make it easier to follow conversations
with multiple people.
> It
On 7 July 2016 at 20:50, Pete Stevenson wrote:
> Hi Simon -
>
> Thanks for the note. I think it's fair to say that I didn't provide enough
> context, so let me try and elaborate on my question.
>
> I agree, MVCC is a benefit. The research angle here is about enabling MVCC
> with hardware offload.
Hi Simon -
Thanks for the note. I think it's fair to say that I didn't provide enough
context, so let me try and elaborate on my question.
I agree, MVCC is a benefit. The research angle here is about enabling MVCC
with hardware offload. Since I didn't explicitly mention it, the offload I
refer to
On 7 July 2016 at 17:45, Pete Stevenson wrote:
> Hi postgresql hackers -
>
> I would like to find some analysis (published work, blog posts) on the
> overheads affiliated with the guarantees provided by MVCC isolation. More
> specifically, assuming the current workload is CPU bound (as opposed to
14 matches
Mail list logo