On Fri, 3 Nov 2000, Andres Kroonmaa wrote:
> OK, use digests for ICP. But digest generation? We do it currently quite
> rarely, because it has quite some cpu overhead? ICP is wanted when instant
> knowledge is wanted between peers that may be part of loadsharing setup.
> Delay between digest generations is not acceptable there. Can we add
> objects to digest as they arrive? Where we keep it between reloads?
Digests can be maintained incrementally if needed, with some RAM
penalty. An incremental digest will require, say, x4 more RAM.
However, the actual size will still be pretty small compared to the
traditional memory footprint. Moreover, the tradeoff can be controlled
at ./configure time or even at runtime.
> Based on what do we generate a digest, at startup?
Digests can be stored/loaded. If a digest is lost, it would need to be
rebuilt from scratch, but such a rebuilt does not have to block Squid
from serving misses and some hits.
Alex.
Received on Fri Nov 03 2000 - 09:33:44 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:12:55 MST