Re: Compression of full-page-writes

Hello,

Below are performance numbers in case of synchronous replication with and
without fpw compression using latest version of patch(version 14). The patch
helps improve performance considerably.

Both master and standby are on the same machine in order to get numbers
independent of network overhead.
The compression patch helps to increase tps by 10% . It also helps reduce
I/O to disk , latency and total runtime for a fixed number of transactions
as shown below.
The compression of WAL is quite high around 40%.

pgbench scale :1000
pgbench command : pgbench -c 16 -j 16 -r -t 250000 -M prepared

To ensure that data is not highly compressible, empty filler columns were
altered using
alter table pgbench_accounts alter column filler type text using
gen_random_uuid()::text

checkpoint_segments = 1024
checkpoint_timeout = 5min
fsync = on

Compression on
off

WAL generated 23037180520(~23.04MB)
38196743704(~38.20MB)

TPS 264.18
239.34

Latency average 60.541 ms 66.822
ms

Latency stddev 126.567 ms 130.434
ms

Total writes to disk 145045.310 MB 192357.250
MB

Runtime 15141.0 s
16712.0 s

Server specifications:
Processors:Intel® Xeon ® Processor E5-2650 (2 GHz, 8C/16T, 20 MB) * 2 nos
RAM: 32GB
Disk : HDD 450GB 10K Hot Plug 2.5-inch SAS HDD * 8 nos
1 x 450 GB SAS HDD, 2.5-inch, 6Gb/s, 10,000 rpm

Thank you,
Rahila Syed

--
View this message in context: http://postgresql.nabble.com/Compression-of-full-page-writes-tp5769039p5833315.html
Sent from the PostgreSQL - hackers mailing list archive at Nabble.com.