Re: [squid-users] FreeBSD :Diskd ? (WAS: Compile Crash)

Terminology warning: async is heavily overlapped in this discussion.

A) It is a term used in relation to Squid to denote asyncronous disk I/O
for the application, where the application does not need to wait for
completetion. This applies to both reads and writes, and is completely
independent on how the underlying filesystem is mounted, underlying
filesystem or whatever.

B) It is also a term used in mounting filesystem, denoting that
filesystem updates are done asyncronously.

For Squid 'A' is the important thing.

If you mount the filesystem as "async" or "soft-updates" Squid does not
care about. It is your headache in terms of filesystem recoverability in
case of unexpected system failure (power loss or whatever). One of them
is generally recommendable to cut down on the disk I/O required and I'll
leave it to you to figure out which.

In any event, for good Squid performance Squid needs to be compiled with
one of the async I/O implementations, either diskd or aufs. For *BSD
OS:es diskd is generally recommended. If you want the technical reasons
to why diskd is recommended over aufs on *BSD then study the effect of
disk I/O and most *BSD thread implementations.

Regards
Henrik Nordström
Squid Hacker
MARA Systems AB

Dave Raven wrote:
>
> As I see it,
>
> Yes, soft-updates is highly recommended, but is _completely_ different to
> async disk io.
> I have softupdates turned on on the drive, but I run it in async mode.
> The default fBSD disk will run on noasync (not meaning NO async) but that:
> Metadata I/O should be done synchronously, while data I/O should be done
> asynchronously.
>
> To enable syncronous mode only is actually shooting yourself in the foot,
> (I would think)
> I can only see this being done for data safety, which is again pointless.
> The
> chance of you loosing data is about equal.
>
> Soft-updates has nothing to do with this, its more of a journaling method.
> It isnt actually journaling as it should be, but one has to weigh up the
> pros/cons
> of the soft-updates method.
>
> There are a few articles about this on freebsd.org; I have no links though.
>
> Feel free to comment anyone, as I feel there is a general lack of knowledge
> as to the correct file system and what to enable / disable.
>
> (I speak for myself - as I know very little of it)
>
> Dave.
> OpteqSec.
>
> ----- Original Message -----
> From: "Aaron Seelye" <AaronS@et-n-m.com>
> To: <squid-users@squid-cache.org>
> Sent: Thursday, December 20, 2001 1:06 AM
> Subject: RE: [squid-users] FreeBSD :Diskd ? (WAS: Compile Crash)
>
> > This may be a bit off-topic, but for the BSDs, soft-updates is *highly*
> > preferred over async, as it's neck-and-neck in speed, and guarantees state
> > of the drive.
Received on Thu Dec 20 2001 - 15:28:46 MST