Hi,
On 2024-11-01 14:10:54 -0400, Andres Freund wrote:
> I still don't like this idea a whole lot - but perhaps we could get reduce the
> overhead of my proposal some, to get closer to yours. When setting hint bits
> for many tuples on a page the overhead of my approach is neglegible, but when
>
Hi,
On 2024-10-30 09:58:30 -0400, Andres Freund wrote:
> On 2024-10-30 14:16:51 +0200, Heikki Linnakangas wrote:
> > Could we put the overhead on the FlushBuffer()
> > instead?
> >
> > How about something like this:
> >
> > To set hint bits:
> >
> > 1. Lock page in SHARED mode.
> > 2. Read BM_IO_I
On 24/09/2024 18:55, Andres Freund wrote:
What I'd instead like to propose is to implement the right to set hint bits as
a bit in each buffer's state, similar to BM_IO_IN_PROGRESS. Tentatively I
named this BM_SETTING_HINTS. It's only allowed to set BM_SETTING_HINTS when
BM_IO_IN_PROGRESS isn't al
Hi,
On 2024-10-30 10:47:35 -0700, Jeff Davis wrote:
> On Tue, 2024-09-24 at 11:55 -0400, Andres Freund wrote:
> > What I suspect we might want instead is something inbetween a share
> > and an
> > exclusive lock, which is taken while setting a hint bit and which
> > conflicts
> > with having an IO
On Tue, 2024-09-24 at 11:55 -0400, Andres Freund wrote:
> What I suspect we might want instead is something inbetween a share
> and an
> exclusive lock, which is taken while setting a hint bit and which
> conflicts
> with having an IO in progress.
I am starting to wonder if a shared content locks
Hi,
On 2024-10-30 13:29:01 +0200, Heikki Linnakangas wrote:
> On 30/10/2024 04:21, Andres Freund wrote:
> > Attached is a, unfortunately long, series of patches implementing what I
> > described upthread.
>
> Review of the preparatory patches:
>
> > 0001 Add very basic test for kill_prior_tuples
Hi,
Thanks for the quick review!
On 2024-10-30 14:16:51 +0200, Heikki Linnakangas wrote:
> On 24/09/2024 18:55, Andres Freund wrote:
> > What I'd instead like to propose is to implement the right to set hint bits
> > as
> > a bit in each buffer's state, similar to BM_IO_IN_PROGRESS. Tentatively
On 30/10/2024 04:21, Andres Freund wrote:
Attached is a, unfortunately long, series of patches implementing what I
described upthread.
Review of the preparatory patches:
0001 Add very basic test for kill_prior_tuples
We currently don't exercise this patch for gist and hash, which seems
Hi,
Attached is a, unfortunately long, series of patches implementing what I
described upthread.
0001 Add very basic test for kill_prior_tuples
We currently don't exercise this patch for gist and hash, which seems
somewhat criminal.
0002 heapam: Move logic to handle HEAP_MOVED into a
On Wed, Sep 25, 2024 at 12:45 PM Thomas Munro wrote:
> On Wed, Sep 25, 2024 at 8:30 AM Andres Freund wrote:
> > However, our habit of modifying buffers while IO is going on is
> > causing issues with filesystem level checksums as well, as evidenced by the
> > fact that debug_io_direct = data on b
Antonin Houska wrote:
> Andres Freund wrote:
>
> > What I'd instead like to propose is to implement the right to set hint bits
> > as
> > a bit in each buffer's state, similar to BM_IO_IN_PROGRESS. Tentatively I
> > named this BM_SETTING_HINTS. It's only allowed to set BM_SETTING_HINTS when
>
Andres Freund wrote:
> What I'd instead like to propose is to implement the right to set hint bits as
> a bit in each buffer's state, similar to BM_IO_IN_PROGRESS. Tentatively I
> named this BM_SETTING_HINTS. It's only allowed to set BM_SETTING_HINTS when
> BM_IO_IN_PROGRESS isn't already set and
On Tue, Sep 24, 2024 at 04:30:25PM -0400, Andres Freund wrote:
> On 2024-09-24 12:43:40 -0700, Noah Misch wrote:
> > On Tue, Sep 24, 2024 at 11:55:08AM -0400, Andres Freund wrote:
> > > Besides that, the need to copy the buffers makes checkpoints with AIO
> > > noticeably slower when checksums are
On Wed, Sep 25, 2024 at 8:30 AM Andres Freund wrote:
> Just ran that. There probably is a performance difference, but it's small
> (<0.5%) making it somewhat hard to be certain. It looks like the main reason
> for that is ConditionVariableBroadcast() on the iocv shows up even though
> nobody is wa
Hi,
On 2024-09-24 12:43:40 -0700, Noah Misch wrote:
> On Tue, Sep 24, 2024 at 11:55:08AM -0400, Andres Freund wrote:
> > So far the AIO patchset has solved this by introducing a set of "bounce
> > buffers", which can be acquired and used as the source/target of IO when
> > doing
> > it in-place i
On Tue, Sep 24, 2024 at 11:55:08AM -0400, Andres Freund wrote:
> So far the AIO patchset has solved this by introducing a set of "bounce
> buffers", which can be acquired and used as the source/target of IO when doing
> it in-place into shared buffers isn't viable.
>
> I am worried about that solu
Hi,
Currently we modify pages while just holding a share lock, for hint bit
writes. Writing a buffer out only requires a share lock. Because of that we
can't compute checksums and write out pages in-place, as a concurent hint bit
write can easily corrupt the checksum.
That's not great, but not aw
17 matches
Mail list logo
