[squid-users] Data tricking implementation is on ICAP side or Squid side?

[Alex Rousskov]

On 1/20/21 3:21 PM, John Zhu wrote:

> I implemented ICAP in java. I have questions regarding the “data
> trickling” to handle slow response for large file scanning from ICAP.

> 1) Java libraries available for data trickling at ICAP side, if any?

FWIW, implementing a production ICAP server from scratch (in any
language) is usually a bad idea -- there are too many poorly documented
and barely understood protocol areas. There are production ICAP servers
that support data trickling.

Unfortunately, I am not familiar with Java libraries, but there were two
ICAP projects in Java:
https://wiki.squid-cache.org/Features/ICAP#ICAP_Servers


> 2) Need any configuration change for trickling feature on Squid side?
> 3) Need any code change on Squid side?

I do not recall any required changes. Squid itself can be unaware that
data trickling is going on. However, it is possible that, in some
extreme cases (e.g., trickling one byte at a time), some configuration
or code adjustments would be needed to force "flushing" of that data
through Squid or to fix Squid metadata parsing bugs.


> 3) The trickling (in a very slow speed data send to Squid) is
> implemented only ICAP server side, correct?

The ICAP client side must not buffer (as in "delay to aggregate") data
trickled by the ICAP server.


HTH,

Alex.