On Thu, 2015-07-09 at 11:28 +0200, Andres Freund wrote:
> That'd make some sense if there were other stuff going on - but here the
> same total budget in both cases leads to a 40% difference in throughput:
When I suspect that what I'm hearing is horse pookey, I instrument the
source and ask my si
On 2015-07-09 04:45:38 +0200, Mike Galbraith wrote:
> On Wed, 2015-07-08 at 17:45 +0200, Andres Freund wrote:
> > Workload:
> >
> > postgresql (multi-process via shared memory SQL server) and benchmark
> > client (pgbench, multi threaded) running on the same server. Connected
> > using unix socket
On Wed, 2015-07-08 at 17:45 +0200, Andres Freund wrote:
> Workload:
>
> postgresql (multi-process via shared memory SQL server) and benchmark
> client (pgbench, multi threaded) running on the same server. Connected
> using unix sockets. The statements are relatively simple (~1.5ms on
> average),
Hi,
while debugging a performance issue I noticed the following very odd
bit.
Kernel: 4.1.0-rc7-andres-00049-ge64f638
CPU: 2xE5520
Workload:
postgresql (multi-process via shared memory SQL server) and benchmark
client (pgbench, multi threaded) running on the same server. Connected
using unix so
4 matches
Mail list logo
