On Tue, Mar 13, 2012 at 10:02 PM, Fujii Masao <masao.fujii@gmail.com> wrote:
> On Wed, Mar 14, 2012 at 7:20 AM, Robert Haas <robertmhaas@gmail.com> wrote:
>> On Tue, Mar 13, 2012 at 3:48 PM, Robert Haas <robertmhaas@gmail.com> wrote:
>>> On Mon, Mar 12, 2012 at 4:45 PM, Jeff Janes <jeff.janes@gmail.com> wrote:
>>>> Rerunning all 4 benchmarks (both 16MB and 32MB wal_buffers on both
>>>> machines) with fsync=off (as well as synchronous_commit=off still)
>>>> might help clarify things.
>>>
>>> I reran the 32-client benchmark on the IBM machine with fsync=off and got this:
>>>
>>> 32MB: tps = 26809.442903 (including connections establishing)
>>> 16MB: tps = 26651.320145 (including connections establishing)
>>>
>>> That's a speedup of nearly a factor of two, so clearly fsync-related
>>> stalls are a big problem here, even with wal_buffers cranked up
>>> through the ceiling.
>>
>> And here's a tps plot with wal_buffers = 16MB, fsync = off. The
>> performance still bounces up and down, so there's obviously some other
>> factor contributing to latency spikes
>
> Initialization of WAL file? Do the latency spikes disappear if you start
> benchmark after you prepare lots of the recycled WAL files?
The latency spikes seem to correspond to checkpoints, so I don't think
that's it.
--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company
