Commit graph

10 commits

Author SHA1 Message Date
Stefan Eßer
081930c498 Fix rawio for sequential read/write tests:
Revision 1.3 of patch-ad worked around the problem, that only one writer
is allowed to allow a partition through GEOM. The fix was not complete,
leading to the file position not been incremented during reads and writes,
thus not testing sequential performance, but performance of cached reads
and writes, in general.

This fix makes rawio report reasonable sequential performance again,
but I'm still very suspicious with regard to randomized start positions
working. The results do not show the expected variation of sequential
read/write performance. I have not had time to look into this any deeper,
though, and thus decidied to not delay the commit any further ...
2006-10-09 17:19:54 +00:00
Brian Feldman
19077a79c6 Re-support FreeBSD 4 (which has sys/disk.h as a kernel header, not a
userland/kernel header).  No PORTREVISION bump since this is a fix
for compilation.

PR:	ports/88319
Submitted by:	marck
2005-11-01 17:00:41 +00:00
Brian Feldman
33bf00180f Modify rawio(1) to work with GEOM by losing the multiple-open(2)
semantics.  As GEOM prevents actual concurrent accesses that are
deemed generally unsafe.  As we know, as a rawio(1) user, that we
are intending to do something ostensibly unsafe, we can use a single
open(2) shared among the worker children and then use pread(2) and
pwrite(2) instead of read(2), write(2) and lseek(2).  This properly
bypasses the sanity checks GEOM makes for concurrent access.

Additionally, sector size isn't and hasn't ever been necessarily 512
(or a multiple thereof), but we don't have many classical examples
of devices not the common case that we'd test rawio(1) with.  In my
particular case, I'm using graid3(8) and have an effective sector size
of 1024.  The program now attempts to use DIOCGSECTORSIZE to find
the correct base for a device and thus Works For Me.

Cursory review by:	MAINTAINER
2005-10-26 18:40:43 +00:00
Edwin Groothuis
04a340f14c [PATCH] benchmarks/rawio has a bug in commandline option parser
run rawio with -s option(size of raw disk device), as follows:
	    % rawio -a -s 30029328k -v 1 /dev/ad4c
	returned:
	    Invalid length specification: -v

	in source rawio.c, it skips parsing argument at one point.

PR:		ports/58567
Submitted by:	OOTOMO Hiroyuki <ootomo@za.wakwak.com>
Approved by:	maintainer timeout
2004-01-10 07:57:35 +00:00
Edwin Groothuis
9d2ba0bd5a Remove obsolete patch-files
PR:		ports/40535
Submitted by:	Tilman Linneweh <tilman@arved.de>
Approved by:	grog@freebsd.org
2002-11-05 00:32:54 +00:00
Greg Lehey
937e2cc97d Make this build again on systems with no MAP_INHERIT on mmap. 2002-03-29 06:27:12 +00:00
Greg Lehey
3aecce6126 Include sys/random.h, not machine/random.h.
This should fix the conditional build breakage introduced in revision
1.2
2001-01-04 06:58:01 +00:00
Steve Price
727779dfca Don't try to include machine/random.h on the Alpha. 2000-01-28 17:26:21 +00:00
Michael Haro
0f49af6984 fix bento build errors 2000-01-22 11:03:46 +00:00
Steve Price
b7e4c10bea Make this compile again in light of the recent signal changes. This is
no fault of Marcel's changes but rather poor style.   Bruce gives a much
longer version but I won't repeat that here. :)
1999-11-14 03:18:49 +00:00