linux-kernel - RE: [PATCH 2/2] aio: propogate post-EIOCBQUEUED errors to completion event

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <B41635854730A14CA71C92B36EC22AAC871E37@mssmsx411>
Date:	Wed, 21 Feb 2007 00:09:58 +0300
From:	"Ananiev, Leonid I" <leonid.i.ananiev@...el.com>
To:	"Chris Mason" <chris.mason@...cle.com>
Cc:	"Zach Brown" <zach.brown@...cle.com>, <linux-aio@...ck.org>,
	<linux-kernel@...r.kernel.org>,
	"Benjamin LaHaise" <bcrl@...ck.org>,
	"Suparna bhattacharya" <suparna@...ibm.com>,
	"Andrew Morton" <akpm@...ux-foundation.org>
Subject: RE: [PATCH 2/2] aio: propogate post-EIOCBQUEUED errors to completion event

-O I've missed:
aiostress -s 1200m -O -o 2 -i 1 -r 16k <test_file>

You are right I've used harness scripts.
i=0; while ((i++<50)); do ~/bm/bin/runs I2 -; done &

It runs bmrun harness script which is long for different hardware
configurations and test options.
The lines in aio-stress wrapper which could be useful for you are:
        gcc aiostress.c -Wall -o aiostress -lpthread -laio
2>>${file_log}
...
        sudo umount -f ${pdisk} ${ppath} > /dev/null 2>&1
        sudo /sbin/mke2fs -j ${pdisk} > /dev/null 2>>${file_log}
        sudo mount ${pdisk} ${ppath} > /dev/null 2>>${file_log}...
        export LD_LIBRARY_PATH=/lib:/usr/lib:$LD_LIBRARY_PATH
        all_files_size=1200             # in megabytes
...
        else
                num_disks=1
                ((file_size = all_files_size / num_disks))
                testfiles=${ppath}/test/testfile
                dd if=/dev/zero of=$testfiles bs=1M count=${file_size} >
/dev/null
        fi
        aiostress ${*} -v -o 2 -s ${file_size}m -i 1 -r 16k $testfiles >
${file_res} 2>&1
        if [ "$1" == "-S" ] ; then
                info="O_SYNC"
        elif [ "$1" == "-O" ] ; then
                info="O_DIRECT"
        fi
        awk .... ${file_res}
....
Which does 
1) mem=1G in kernel boot param if you have more
2) unmount; mk2fs; mount
3) dd if=/dev/zero of=<test_file> bs=1M count=1200
4) aiostress -s 1200m -O -o 2 -i 1 -r 16k <test_file>
5) if i++<50 goto 2).

Leonid
-----Original Message-----
From: Chris Mason [mailto:chris.mason@...cle.com] 
Sent: Tuesday, February 20, 2007 8:55 PM
To: Ananiev, Leonid I
Cc: Zach Brown; linux-aio@...ck.org; linux-kernel@...r.kernel.org;
Benjamin LaHaise; Suparna bhattacharya; Andrew Morton
Subject: Re: [PATCH 2/2] aio: propogate post-EIOCBQUEUED errors to
completion event

On Tue, Feb 20, 2007 at 08:17:51PM +0300, Ananiev, Leonid I wrote:
> aio-stress command lines used for test
> 1) mem=1G in kernel boot param if you have more
> 2) mk2fs for test_file
> 3) dd if=/dev/zero of=<test_file> bs=1M count=1200
> 4) aiostress -s 1200m -o 2 -i 1 -r 16k <test_file>
> 

Sorry, this aio-stress command line doesn't do O_DIRECT.  Do you have
this bundled into a test script that I can try?

-chris
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/