On Thu, Mar 3, 2016 at 6:20 AM, Mithun Cy <mithun.cy@enterprisedb.com> wrote: > I will continue to benchmark above tests with much wider range of clients.
Latest Benchmarking shows following results for unlogged tables.
Whoa. At 64 clients, we're hardly getting any benefit, but then by 88 clients, we're getting a huge benefit. I wonder why there's that sharp change there.
If you see, for the Base readings, there is a performance increase up till 64 clients and then there is a fall at 88 clients, which to me indicates that it hits very high-contention around CLogControlLock at 88 clients which CLog patch is able to control to a great degree (if required, I think the same can be verified by LWLock stats data). One reason for hitting contention at 88 clients is that this machine seems to have 64-cores (it has 8 sockets and 8 Core(s) per socket) as per below information of lscpu command.
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 128
On-line CPU(s) list: 0-127
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 8
NUMA node(s): 8
Vendor ID: GenuineIntel
CPU family: 6
Model: 47
Model name: Intel(R) Xeon(R) CPU E7- 8830 @ 2.13GHz