[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20191011123105.s6qjwrlgugszk73j@linutronix.de>
Date: Fri, 11 Oct 2019 14:31:07 +0200
From: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To: Jan Kara <jack@...e.cz>
Cc: Ted Tso <tytso@....edu>, linux-ext4@...r.kernel.org,
Thomas Gleixner <tglx@...utronix.de>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Steven Rostedt <rostedt@...dmis.org>,
Anna-Maria Gleixner <anna-maria@...utronix.de>,
Julia Cartwright <julia@...com>
Subject: Re: [PATCH 0/7 v2] jbd2: Bit spinlock conversions
On 2019-08-09 14:42:26 [+0200], Jan Kara wrote:
> Hello,
Hi,
> This series is derived from Thomas' series to get rid of bit spinlocks in
> buffer head code. These patches convert BH_State bit spinlock to an ordinary
> spinlock inside struct journal_head and somewhat reduce the critical section
> under BH_JournalHead bit spinlock so that it is fine for RT.
>
> Motivation from original Thomas' series:
>
> Bit spinlocks are problematic if PREEMPT_RT is enabled. They disable
> preemption, which is undesired for latency reasons and breaks when regular
> spinlocks are taken within the bit_spinlock locked region because regular
> spinlocks are converted to 'sleeping spinlocks' on RT.
>
> Bit spinlocks are also not covered by lock debugging, e.g. lockdep. With
> the spinlock substitution in place, they can be exposed via a new config
> switch: CONFIG_DEBUG_BIT_SPINLOCKS.
>
> Ted, can you pick up these patches? Thanks!
Has this series been postponed?
> Changes since v1:
> * Fixed up compilation breakage on UP due to missing linux/spinlock.h include
>
> Honza
Sebastian
Powered by blists - more mailing lists