Strategies for splitting load across varnish instances? And avoiding single-point-of-failure?

[Poul-Henning Kamp]

In message <8C3F8D23-3E20-4E2C-BA7C-902D843FF964 at dynamine.net>, "Michael S. Fis
cher" writes:
>On Jan 18, 2010, at 1:52 PM, Poul-Henning Kamp wrote:

>Can you describe in more detail your comparative analysis and plans? =20

First of all, the major player in this are the 'stevedores' like
"malloc", "file" and "persistent".

I'm trying to apply what I have learned so far to the persistent
stevedore and it has much more VM-hintable behaviour than the "file"
stevedore, and hopefully a much more disk-scheduling friendly (ie:
sequential) layout policy.

In particular, I'm trying to make the "persistent" stevedore as
"cheap-SSD" friendly as possible, by optmising for sequential
writes where at all possile.

Exactly how much help this will be, depends on everything in your
world, including what your kernel does for madvise(), and if you
have a usable sendfile() syscall, and therefore giving any specific
promises is pretty impossible for me.

Poul-Henning

-- 
Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG         | TCP/IP since RFC 956
FreeBSD committer       | BSD since 4.3-tahoe    
Never attribute to malice what can adequately be explained by incompetence.