🔗 Feature: Collapsed Forwarding
- Status: completed in 2.6, 2.7, and ported to Squid-3.5
- Version: 2.6+ and 3.5+
- Developer: HenrikNordstrom, AlexRousskov
- More: Bugs 1614 and 3495
This performance enhancement feature enables multiple client requests for the same URI to be processed as one request to the backend server. Normally disabled to avoid increased latency on dynamic content, but there can be benefit from enabling this in accelerator setups where the web servers are the bottleneck but are reliable and return mostly cacheable information.
It was left out of Squid-3.0 due to time and stability constraints. The max_stale part of this feature was added to Squid-3.2, collapsed_forwarding part to Squid-3.5, refresh_stale_hit is still awaiting re-implementation.
The stale-while-revalidate part of the original Squid-2.6 feature has since been turned into an official HTTP/1.1 extension by RFC 5861. The protocol header should now be used instead of the squid configuration option.
In accelerator setups it is desirable if the number of connections to the backend web servers is minimized. However, Squid being designed primarily for forward proxy operation does not take this into consideration. As a result there may be storms of requests to the backend server if a very frequently accessed object expires from the cache or a new very frequently accessed object is added.
To remedy this situation this feature adds a new tuning knob
to squid.conf, making Squid delay further requests while a cache
revalidation or cache miss is being resolved. This sacrifices general
proxy latency in favor for accelerator performance and thus should not
be enabled unless you are running an accelerator.
Squid-2.6 and Squid-2.7 in addition contain a stale-while-revalidate option on refresh_pattern to shortcut the cache revalidation of frequently accessed objects is added, making further requests immediately return as a cache hit while a cache revalidation is pending. This may temporarily give slightly stale information to the clients, but at the same time allows for optimal response time while a frequently accessed object is being revalidated. This too is an optimization only intended for accelerators, and only for accelerators where minimizing request latency is more important than freshness.
This option enables collapse of multiple requests for the same URI to be processed as one request. Normally disabled to avoid corner cases with hung requests, but there can be large benefit from enabling this in accelerator setups where the web servers are reliable.
refresh_stale_hit interval (default 0)
This option decreases latency on collapsed forwarding by initiating a revalidation request some time before the object becomes stale. This avoid having more than one client wait for the revalidation to finish.
🔗 Known issues and shortcomings
- The 30 second window should be tuneable; see Bug 2504.
- At least in the 2.6 implementation, non-successful responses are not collapsed, leading to the potential for overwhelming the back-end server; see Bug 1918.
- Might even be suitable for the general Internet proxy situation, not only reverse proxies.
- Fails to occur when memory-only cache is used and no cache_dir are present.
Categories: FeatureNavigation: Site Search, Site Pages, Categories, 🔼 go up