[squid-users] Questions around https transparent chained proxy

Walid A. Shaari walid.shaari at linux.com
Sat Feb 16 08:18:17 UTC 2019


Greetings,

The end goal is enforcing an appliance(s) tls traffic to go through
the corporate proxy, as I understand it (splice, not interested in
decrypting)

http traffic works fine. however not clear 100% regarding https traffic.

1) does the order of the below directives (ssl_bump, never_direct, and
cacher_peer,..etc) matter where it is in the squid.conf file, or is it
just the ACLs and ssl_bump that are order strict in squid.conf?

------ partial squid.conf  # is that order ok----
ssl_bump peek all     # or should I just peek at step1
ssl_bump splice  all
#ssl_bump bump all   # not necessary in that case, traffic should have
been already spliced
never_direct allow all

cache_peer  upstream-proxy parent 8118 0 no-query no-digest
---------------------------

2) What does the only-proxy option really means for cache-peer?
3) if the parent proxy is not using SSL/tls, however, the clients are
using tls/SSL, is that an issue?
4) in an https transparent chained proxy scenario, is there a way I
can get rid of exporting the squid proxy certificates to the clients?
as the clients are part of an appliance that I do not have control
over and not all traffic is actually originating from browsers?
5)  Is squid 3.5 out of the Linux distro good enough, or should I
upgrade to latest 4.x for a guaranteed splice functionality? the
unofficial binary package for RHEL available is 3.5.27, while centos
package is 4.5-1. shouldn't both be the same?

TIA

Walid



ReplyForward


More information about the squid-users mailing list