kopia lustrzana https://gitlab.com/sane-project/website
150 wiersze
5.5 KiB
HTML
150 wiersze
5.5 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
|
|
"http://www.w3.org/TR/REC-html40/loose.dtd">
|
|
<HTML>
|
|
<HEAD>
|
|
<TITLE>sane-devel: Re: scsi command queuing</TITLE>
|
|
<META NAME="Author" CONTENT="Douglas Gilbert (dgilbert@interlog.com)">
|
|
<META NAME="Subject" CONTENT="Re: scsi command queuing">
|
|
</HEAD>
|
|
<BODY BGCOLOR="#FFFFFF" TEXT="#000000">
|
|
<H1>Re: scsi command queuing</H1>
|
|
<!-- received="Fri Jun 30 16:43:58 2000" -->
|
|
<!-- isoreceived="20000630234358" -->
|
|
<!-- sent="Fri, 30 Jun 2000 19:59:55 -0400" -->
|
|
<!-- isosent="20000630235955" -->
|
|
<!-- name="Douglas Gilbert" -->
|
|
<!-- email="dgilbert@interlog.com" -->
|
|
<!-- subject="Re: scsi command queuing" -->
|
|
<!-- id="395D347B.1E05897C@interlog.com" -->
|
|
<!-- inreplyto="20000630195917.B7623@hmg1.vortex.swb.de" -->
|
|
<STRONG>From:</STRONG> Douglas Gilbert (<A HREF="mailto:dgilbert@interlog.com?Subject=Re:%20scsi%20command%20queuing&In-Reply-To=<395D347B.1E05897C@interlog.com>"><EM>dgilbert@interlog.com</EM></A>)<BR>
|
|
<STRONG>Date:</STRONG> Fri Jun 30 2000 - 16:59:55 PDT
|
|
<P>
|
|
<!-- next="start" -->
|
|
<LI><STRONG>Next message:</STRONG> <A HREF="0240.html">Douglas Gilbert: "Re: scsi command queuing"</A>
|
|
<UL>
|
|
<LI><STRONG>Previous message:</STRONG> <A HREF="0238.html">Joachim Ansorg: "Re: Problems with mustek scanner"</A>
|
|
<LI><STRONG>In reply to:</STRONG> <A HREF="0232.html">Henning Meier-Geinitz: "Re: scsi command queuing"</A>
|
|
<!-- nextthread="start" -->
|
|
<LI><STRONG>Next in thread:</STRONG> <A HREF="0212.html">abel deuring: "Re: scsi command queuing"</A>
|
|
<!-- reply="end" -->
|
|
<LI><STRONG>Messages sorted by:</STRONG>
|
|
<A HREF="date.html#239">[ date ]</A>
|
|
<A HREF="index.html#239">[ thread ]</A>
|
|
<A HREF="subject.html#239">[ subject ]</A>
|
|
<A HREF="author.html#239">[ author ]</A>
|
|
</UL>
|
|
<HR NOSHADE><P>
|
|
<!-- body="start" -->
|
|
<P>
|
|
Henning Meier-Geinitz wrote:
|
|
<BR>
|
|
<EM>>
|
|
</EM><BR>
|
|
<EM>> Hi,
|
|
</EM><BR>
|
|
<EM>>
|
|
</EM><BR>
|
|
<EM>> On Thu, Jun 29, 2000 at 12:13:23AM +0200, Oliver Rauch wrote:
|
|
</EM><BR>
|
|
<EM>> > Henning Meier-Geinitz wrote:
|
|
</EM><BR>
|
|
<EM>> >
|
|
</EM><BR>
|
|
<EM>> > > Same here. I looked at the scanning times when the backend does nothing but
|
|
</EM><BR>
|
|
<EM>> > > getting data from the scanner and ignoring it. There was no big change in
|
|
</EM><BR>
|
|
<EM>> > > scanning time (about 5 %). With the original SCSI adapter the Mustek
|
|
</EM><BR>
|
|
<EM>> > > scanners are about twice as slow as with Windows despite large (4 MB) SCSI
|
|
</EM><BR>
|
|
<EM>> > > buffers and tweaking the Linux SCSI driver.
|
|
</EM><BR>
|
|
<EM>> >
|
|
</EM><BR>
|
|
<EM>> > 4 MB images are not the problem of the umax backend.
|
|
</EM><BR>
|
|
<EM>>
|
|
</EM><BR>
|
|
<EM>> I am not talking about image size but about SCSI buffer size. With most
|
|
</EM><BR>
|
|
<EM>> Mustek scanners and the Mustek SCSI adapters the scan stops after each read
|
|
</EM><BR>
|
|
<EM>> command and backtracking occurs. So I am trying to scan with large buffers.
|
|
</EM><BR>
|
|
<EM>> Standard is 1 MB at the moment. The scan speed is dependant from the
|
|
</EM><BR>
|
|
<EM>> resolution and image with (but not from length).
|
|
</EM><BR>
|
|
<P>Henning,
|
|
<BR>
|
|
Some info on Linux sg buffer sizes. DMA (used by most but not the very low
|
|
<BR>
|
|
end SCSI adapters) requires continuous buffers. ["continuous" seen from the
|
|
<BR>
|
|
PCI/ISA bus.] Linux actively discourages drivers taking big continuous
|
|
<BR>
|
|
buffers. So sg takes 32 KB chunks (controlled by the SG_SCATTER_SZ define
|
|
<BR>
|
|
in sg.h) and builds a scatter gather list. The adapter dictates the maximum
|
|
<BR>
|
|
number of the scatter gather list elements which is further limited to
|
|
<BR>
|
|
255 elements. So that makes the maximum size of sg's reserve buffer
|
|
<BR>
|
|
(or any single command) just under 8 Megabytes. You can double
|
|
<BR>
|
|
SG_SCATTER_SZ, rebuild sg and perhaps get that number up to just under
|
|
<BR>
|
|
16 Megabytes.
|
|
<BR>
|
|
<P>Another consideration is that adapters using the ISA bus can only
|
|
<BR>
|
|
use the bottom 16 Megabytes of memory on a machine. ISA sound
|
|
<BR>
|
|
cards and just normal OS processes tend to eat up that lower 16
|
|
<BR>
|
|
MB so it is unlikely sg will always be successful grabbing large
|
|
<BR>
|
|
amounts of that low memory. This is not a problem with PCI based
|
|
<BR>
|
|
adapters (normally: some early PCI cards didn't use the full 32
|
|
<BR>
|
|
bit address space).
|
|
<BR>
|
|
<P>Doug Gilbert
|
|
<BR>
|
|
<P><PRE>
|
|
--
|
|
Source code, list archive, and docs: <A HREF="http://www.mostang.com/sane/">http://www.mostang.com/sane/</A>
|
|
To unsubscribe: echo unsubscribe sane-devel | mail <A HREF="mailto:majordomo@mostang.com?Subject=Re:%20scsi%20command%20queuing&In-Reply-To=<395D347B.1E05897C@interlog.com>">majordomo@mostang.com</A>
|
|
</PRE>
|
|
<P><!-- body="end" -->
|
|
<HR NOSHADE>
|
|
<UL>
|
|
<!-- next="start" -->
|
|
<LI><STRONG>Next message:</STRONG> <A HREF="0240.html">Douglas Gilbert: "Re: scsi command queuing"</A>
|
|
<LI><STRONG>Previous message:</STRONG> <A HREF="0238.html">Joachim Ansorg: "Re: Problems with mustek scanner"</A>
|
|
<LI><STRONG>In reply to:</STRONG> <A HREF="0232.html">Henning Meier-Geinitz: "Re: scsi command queuing"</A>
|
|
<!-- nextthread="start" -->
|
|
<LI><STRONG>Next in thread:</STRONG> <A HREF="0212.html">abel deuring: "Re: scsi command queuing"</A>
|
|
<!-- reply="end" -->
|
|
<LI><STRONG>Messages sorted by:</STRONG>
|
|
<A HREF="date.html#239">[ date ]</A>
|
|
<A HREF="index.html#239">[ thread ]</A>
|
|
<A HREF="subject.html#239">[ subject ]</A>
|
|
<A HREF="author.html#239">[ author ]</A>
|
|
</UL>
|
|
<!-- trailer="footer" -->
|
|
<HR NOSHADE>
|
|
<P>
|
|
<SMALL>
|
|
<EM>
|
|
This archive was generated by <A HREF="http://www.hypermail.org/">hypermail 2b29</A>
|
|
: <EM>Fri Jun 30 2000 - 16:45:31 PDT</EM>
|
|
</EM>
|
|
</SMALL>
|
|
</BODY>
|
|
</HTML>
|