I can't see the report your link is pointing at, but I guess that the "more-data-to-client" event is a big part of total waittime.
Basically the event indicates, that the server is trying to send data to the client for a second, third.... time. Meaning that the it is sending consecutive packets of data to the client. The P2 column of the wait is the bytesize sent.
More data to client is often seen when either (or both) the server is sending a lot of data to the client, or/and the the TCP/IP packet size on the server and client is not the same.
If the client and the server is on the same machine (batch etc) you could use BEQ instead of TCP/IP.
If the TCP/IP packetsize is different on the two systems (on the OS level) they should be adjusted to the same.
If the the problem still occurs it might be possible to adjust the SDU-size based on the values in P2, to enable the server to get bigger but fewer packets sent.
Jakob
Suhen Pather wrote:
Hi,
I am tuning a system at a client site and notice lots of waits for SQL*Net more data to client (97%) for a fraction
of the CPU consumed by the system.
I know this is not to be characterized as an idle wait event and can yield better performance if we increase
the packet size.
The database is Oracle 7.3.4 (SQL Net 2.3). What effect will increasing TDU and SDU have
on this wait to increase packet size.
It seems that if we can reduce this wait then we can save lots of time (I Think).
Will using BEQ protocol help at all.
Regards
Suhen
--
Castle Cove
AU - 2069 NSW
Phone: (+61 2) 9882 1099
Fax: (+61 2) 9882 1098
Cell: (+61) 0404146110
Email: [EMAIL PROTECTED]
Best regards/Venlig hilsen
Jakob Hammer-Jakobsen
Miracle Australia
Pty Ltd
Castle Cove
AU - 2069 NSW
Phone: (+61 2) 9882 1099
Fax: (+61 2) 9882 1098
Cell: (+61) 0404146110
Email: [EMAIL PROTECTED]
smime.p7s
Description: application/pkcs7-signature