ber, 2019 12:46
>To: SQLite mailing list
>Subject: Re: [sqlite] Theoretical write performance for low-throughput
>devices
>
>>and only one thread accesses that connection at a time. The target
>>lacks mmap(), posix file locks, and multiple address spaces, so this
>>se
>and only one thread accesses that connection at a time. The target
>lacks mmap(), posix file locks, and multiple address spaces, so this
>seemed like the right settings to use.
So what happens to the shm file? Is in not normally just an ordinary file that
is mmap'ped?
What would be the
On Mon, Oct 21, 2019 at 5:47 PM Richard Hipp wrote:
>
> On 10/21/19, Jonathan Brandmeyer wrote:
> >
> > No significant change. The target filesystem only caches non-aligned
> > writes, so there usually isn't anything for it to do on fsync anyway.
> >
>
> OK. I don't have any more ideas at the
On Tue, Oct 22, 2019 at 2:03 AM Wout Mertens wrote:
> This probably won't change a thing, but I wonder why you wouldn't set the
> sqlite page size to 2KB? Hopefully this means lots of aligned writes.
At one point, the row blobs were exactly 1024 bytes. This isn't great
for 4kB pages, but it is
On Mon, Oct 21, 2019 at 5:28 PM Jonathan Brandmeyer <
jbrandme...@planetiq.com> wrote:
> I'm working on an embedded system that uses a log-structured
> filesystem on raw NAND flash. This is not your typical workstation's
> managed flash (SATA/NVMe), or portable managed flash (SD/USB). It's a
>
On Mon, 21 Oct 2019 at 23:28, Jonathan Brandmeyer
wrote:
> Or, how many times is each page written by SQLite for an insert-heavy
> test? The answer appears to be "4", but I can only account for two of
> those four.
>
> I'm working on an embedded system that uses a log-structured
> filesystem on
On 10/21/19, Jonathan Brandmeyer wrote:
>
> No significant change. The target filesystem only caches non-aligned
> writes, so there usually isn't anything for it to do on fsync anyway.
>
OK. I don't have any more ideas at the moment, and without access to
your code, and your platform, I can't
On Mon, Oct 21, 2019 at 5:00 PM Richard Hipp wrote:
>
> On 10/21/19, Jonathan Brandmeyer wrote:
> > On Mon, Oct 21, 2019 at 10:31 AM Richard Hipp wrote:
> >>
> >> On 10/21/19, Jonathan Brandmeyer wrote:
> >> > Or, how many times is each page written by SQLite for an insert-heavy
> >> > test?
On 10/21/19, Jonathan Brandmeyer wrote:
> On Mon, Oct 21, 2019 at 10:31 AM Richard Hipp wrote:
>>
>> On 10/21/19, Jonathan Brandmeyer wrote:
>> > Or, how many times is each page written by SQLite for an insert-heavy
>> > test? The answer appears to be "4", but I can only account for two of
>>
On Mon, Oct 21, 2019 at 10:31 AM Richard Hipp wrote:
>
> On 10/21/19, Jonathan Brandmeyer wrote:
> > Or, how many times is each page written by SQLite for an insert-heavy
> > test? The answer appears to be "4", but I can only account for two of
> > those four.
>
> Are you measuring writes at
On 10/21/19, Jonathan Brandmeyer wrote:
> Or, how many times is each page written by SQLite for an insert-heavy
> test? The answer appears to be "4", but I can only account for two of
> those four.
Are you measuring writes at the OS-interface layer, or writes at the
hardware layer? SQLite
Or, how many times is each page written by SQLite for an insert-heavy
test? The answer appears to be "4", but I can only account for two of
those four.
I'm working on an embedded system that uses a log-structured
filesystem on raw NAND flash. This is not your typical workstation's
managed flash
12 matches
Mail list logo
