[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87h69igyc3.ffs@tglx>
Date: Fri, 11 Oct 2024 22:48:44 +0200
From: Thomas Gleixner <tglx@...utronix.de>
To: "Leizhen (ThunderTown)" <thunder.leizhen@...wei.com>, LKML
<linux-kernel@...r.kernel.org>
Cc: Waiman Long <longman@...hat.com>
Subject: Re: [patch 21/25] debugobjects: Implement batch processing
On Thu, Oct 10 2024 at 17:39, Leizhen wrote:
> On 2024/10/8 0:50, Thomas Gleixner wrote:
>> Adding and removing single objects in a loop is bad in terms of lock
>> contention and cache line accesses.
>>
>> To implement batching, record the last object in a batch in the object
>> itself. This is trivialy possible as hlists are strictly stacks. At a batch
>> boundary, when the first object is added to the list the object stores a
>> pointer to itself in debug_obj::batch_last. When the next object is added
>> to the list then the batch_last pointer is retrieved from the first object
>> in the list and stored in the to be added one.
>>
>> That means for batch processing the first object always has a pointer to
>> the last object in a batch, which allows to move batches in a cache line
>> efficient way and reduces the lock held time.
>
> It seems that adding a helper function hlist_cut_position() can make the code
> look more concise and clear. But there's a lot of patches now. We can do it
> later, and maybe I can do it then.
>
> Similar to the current list_cut_position():
Yes. Thought about that, but then ran out of cycles. Feel free to look
at that. Help is welcome.
Thanks,
tglx
Powered by blists - more mailing lists