linux-kernel - 2.6 diskstats and 4096 sector block devices?

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: <c1bb56a2-c916-0bf2-96fd-017a8cc3bbd3@aeoncomputing.com>
Date:	Fri, 13 May 2016 12:15:30 -0700
From:	Jeff Johnson <jeff.johnson@...ncomputing.com>
To:	linux-kernel@...r.kernel.org
Subject: 2.6 diskstats and 4096 sector block devices?

Greetings,

I am analyzing output in /proc/diskstats for block devices that have a 
4096B physical and logical sector size. 4KN or 4K-native disk drives.

8      33 sdc1 1289 0 10312 5893 3258606 53 1668254992 16804002 31 
583987 16807101

Fields 3 and 7 are sectors read and written respectively. For operations 
on a 4KN device should fields 3 and 7 be interpreted as number of 4K 
sectors written (total transferred = N * 8) or is each 4K sector 
operation reflected as 8 ticks to N?

I am expecting 1MB transfers to the device and using 'delta[field7] / 
delta[field5]' getting 128 which would point to diskstats handling 
everything in terms of 512B operations.

To multiply by 8 or not to multiply by 8, that is the question.. :-)

Thanks,

--Jeff

------------------------------
Jeff Johnson
Co-Founder
Aeon Computing

jeff.johnson "dot" aeoncomputing.com
www.aeoncomputing.com

4170 Morena Boulevard, Suite D - San Diego, CA 92117

High-performance Computing / Lustre Filesystems / Scale-out Storage