[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Darwin disk I/O question

Subject: Re: Darwin disk I/O question
From: John Clark <email@hidden>
Date: Sat, 20 Jan 2001 08:46:30 -0800
Organization: Disorganization

Stuart Smith wrote:

> Darwin's disk drivers are single-threaded (per device) and do not implement
> any reordering of requests. This is left as an exercise for the developer.

What do you mean by 'single threaded'. The SCSI disconnect permits
the driver to have 'simultaneous' SCSI transfers going and upon
reconnect, the driver services the reconnecting device by updating
pointers/buffers/etc as required.

I don't believe IDE has such a concept, and by extension would
suspect that ATA may not either.

While this may not be implemented as a 'kernel' thread or the like,
various implementations of drivers to hand such call the transfer
requests 'threads'...

--
Copyright 2000, John Clark all rights reserved, in particular
permission for use in reference to any commercial product
is denied.
Copyright 2000, John Clark alle Rechte vorbehalten,
insbesondere kommerzieller Gebrauch ist nicht gestattet.

References:
	>Darwin disk I/O question (From: Dave Yost <email@hidden>)

Prev by Date: Re: Release note inaccuracies?
Next by Date: Re: Darwin disk I/O question
Previous by thread: Re: Release note inaccuracies?
Next by thread: Re: Darwin disk I/O question
Index(es):
- Date
- Thread

Home