Re: SQUID I/O

Alex Rousskov wrote:

> Right! However, looks like it is not supported on "many" systems.
> Otherwise, we would not see such a dependency on that buffer in
> real life measurements.

Not entirely true. TCP_NODELAY does not disable the buffer, it only
disable one possible delay. Normal TCP flow control is still there so
for fast data (disk reads, or faster server than client connection) the
buffer very fast filled with unsent data.

And how did you measure? You can't measure the latency based on how fast
Squid can process a request since the buffer will swallow any request up
to buffer size regardless if it is delivered or not. The only reliable
measure is to measure a client on a network connection. Squid considers
the transfer done, as soon as the data is delivered to the TCP/IP stack
(put in the TCP send buffer).

---
Henrik Nordström