<div class="moz-cite-prefix">On 02/11/2013 07:27 AM, Jeff Janes wrote:<br /></div><blockquote
cite="mid:CAMkU=1xV3tYKoHD8U2mQzfC5Kbn_bdcVf8br-EnUvy-6Z=B47w@mail.gmail.com"type="cite"><pre wrap="">I created
doBenchMarkConnect()to segregate bench-marking connections from
utility connections. At first I thought of adding the startup code to only
the normal path and leaving support for -C in the wind, but decided that
was just lazy.
</pre></blockquote><br /> That sounds very useful and would've eased some recent pgbench work I've been doing too.<br
/><br/> I've put some patches together to make pgbench capable of talking to multiple servers. I needed it for
benchmarkingwork on bidirectional replication, but it's also useful if you want to benchmark a group of hot standbys in
read-onlymode, and it may be useful with various 3rd pty replication solutions. As written it uses one or more threads
perserver, with all clients managed by a given thread using the same server. Multiple servers are specified by using
connstringstyle syntax, eg:<br /><br /> pgbench -T 600 -j 4 -c 64 "host=server1 user=postgres" "host=server2
user=postgresport=5433"<br /><br /> It isn't ready for a commitfest yet as I need to tidy up a few things and I still
haven'tadded an extra set of timings to measure how long the DB takes to return to a steady state after the pgbench
run,but once that's done I'll send it in. The after-run timings are intended for things like measuring how much lag an
asynchronousreplica has built up and how long it takes to catch up after the write flood stops, or how long a
CHECKPOINTtakes after the pgbench run.<br /><br /> I also have a patch that adds a flag to force a CHECKPOINT after
vacuumand before running its tests. This makes pgbench results _vastly_ more stable over short runs.<br /><br /> The
workis currently lurking in the 'multibench' branch of git://github.com/ringerc/postgres.git ; see <a
href="https://github.com/ringerc/postgres/tree/multibench">https://github.com/ringerc/postgres/tree/multibench</a>.Only
pgbench.cis actually changed. Comments appreciated.<br /><pre class="moz-signature" cols="72">-- Craig Ringer
<a class="moz-txt-link-freetext" href="http://www.2ndQuadrant.com/">http://www.2ndQuadrant.com/</a>PostgreSQL
Development,24x7 Support, Training & Services</pre>