In the last episode (Oct 05), Philip Brown said:
> Server: SCO OpenServer V3.2 R5.0.5, AMD K6-2 350Mhz CPU, 128Mb RAM
> mySQL: 3.23.39, compiled by me to avoid use of libraries, using latest
> available pthreads
> Clients: Win32 machines (more detail later).
> There are 2 times I am interested in, the time to execute a query, and the
> time required to fetch the results across the network (100Mbps LAN, 3
> isolated workstations in test setup).
> Basically I have been timing the mysql_query() and the mysql_store_result()
> calls on the client. I have been getting some very bizarre results, that are
> 100% reproducible:
I suppose your test program connects, and loops the same query multiple
times in the same session? (Just to rule out connect/disconnect
What are your timings if you run your client on the SCO box? If all
your queries are instantaneous, I'd say start dumping packets on the
network. 200ms sounds a lot like Nagle's Algorithm kicking in (which
shouldn't happen assuming the mysql libs are written right).