Re: fixing >4k reply header store reads

From: Henrik Nordström <henrik@dont-contact.us>
Date: Tue, 08 Jan 2008 18:34:01 +0100

tis 2008-01-08 klockan 02:17 +0900 skrev Adrian Chadd:
> I've been thinking about how to fix that particular issue whilst hacking on the
> s27_adri branch. The main requirement is modifying the store to allow arbitrary
> sized pages rather than just 4k pages, and then find a way to read the header
> data into that first page in store memory. Once its read then the whole lot can
> be parsed and fed through.

Or to not page the headers at all. All store clients discard them
anyway. (Squid-2)

> + read in the meta data
> + if we have no hdr_sz, hope it fits in 4k

hdr_sz is from finding the headers in the first 4k..

> Now, that should work, but its inefficient. Really guys, reading 4k is about
> as fast as reading 64k from a unix filesystem disk, so we should probably
> modify the store to do -that-.

I am fine with that, provided the buffer is released. However, releasing
that buffer do not work very well with your refcounted strings..

But maybe you'll find some clever way doing this with a chain of
refcounted buffers..

Regards
Henrik

Received on Tue Jan 08 2008 - 10:36:19 MST

This archive was generated by hypermail pre-2.1.9 : Wed Jan 30 2008 - 12:00:09 MST