linux-kernel - Re: dm-ps-historical-service-time should probably set QUEUE_FLAG

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]

Date: Mon, 12 Feb 2024 14:39:06 -0800
From: Khazhy Kumykov <khazhy@...gle.com>
To: Mikulas Patocka <mpatocka@...hat.com>, Mike Snitzer <snitzer@...nel.org>, 
	Alasdair Kergon <agk@...hat.com>
Cc: dm-devel@...ts.linux.dev, 
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: dm-ps-historical-service-time should probably set QUEUE_FLAG_STATS

(urgh, apologies for the html)

We use io_start_time_ns in dm-mpath.c, but the only actual user is
historical-service-time currently. We need
blk_stat_enable_accounting()/blk_stat_disable_accounting() calls
somewhere.

I was considering adding a new multipath feature flag, but we already
have "DM_PS_USE_HR_TIMER", which seems similar in spirit. Would that
re-use make sense?

Khazhy

Download attachment "smime.p7s" of type "application/pkcs7-signature" (4010 bytes)