linux-kernel - Re: Slow I/O performance on SAS1064

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>] [day] [month] [year] [list]

Message-ID: <20140308201450.GA18581@localhost.localdomain>
Date:	Sat, 8 Mar 2014 21:14:50 +0100
From:	markus <markus@...a.li>
To:	Purush Gupta <purush.gupta@...anix.com>
Cc:	Nagalakshmi Nandigama <Nagalakshmi.Nandigama@....com>,
	Sreekanth Reddy <Sreekanth.Reddy@....com>, support@....com,
	DL-MPTFusionLinux@....com, linux-scsi@...r.kernel.org,
	Linux Kernel List <linux-kernel@...r.kernel.org>
Subject: Re: Slow I/O performance on SAS1064

On Fri, Mar 07, 2014 at 08:24:48AM -0800, Purush Gupta wrote:
> I noticed you had benchmarked only sda target, is the behavior same on
> other targets?
> 
Yes the other disk are equal to sda , but they are used with zfs and there were other preformance problems because of the multible disk access.
config:

        NAME        STATE     READ WRITE CKSUM
        home        ONLINE       0     0     0
          raidz1-0  ONLINE       0     0     0
            sdb     ONLINE       0     0     3
            sdc     ONLINE       0     0     0
            sdd     ONLINE       0     0     0



> Since they are SCSI targets, have you explored sg_utils [
> http://sg.danny.cz/sg/uu_index.html]
> 
> And for benchmarking I also recommend FIO https://github.com/axboe/fio
> 
Thanks for the tips.
> Good luck,
> Purush
> 

Download attachment "signature.asc" of type "application/pgp-signature" (820 bytes)