Date:   Fri, 17 Mar 2023 18:10:50 +0530
From:   Ojaswin Mujoo <ojaswin@linux.ibm.com>
To:     Andreas Dilger <adilger@dilger.ca>
Cc:     Jan Kara <jack@suse.cz>,
        Ext4 Developers List <linux-ext4@vger.kernel.org>,
        "Theodore Ts'o" <tytso@mit.edu>,
        Ritesh Harjani <riteshh@linux.ibm.com>,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
        rookxu <brookxu.cn@gmail.com>,
        Ritesh Harjani <ritesh.list@gmail.com>
Subject: Re: [PATCH v3 7/8] ext4: Use rbtrees to manage PAs instead of inode
 i_prealloc_list
Message-ID: <ZBRf0i+hR2lDvi/P@li-bb2b2a4c-3307-11b2-a85c-8fa5c3a69313.ibm.com>
References: <Y8Z413XTPMr//bln@li-bb2b2a4c-3307-11b2-a85c-8fa5c3a69313.ibm.com>
 <20230117110335.7dtlq4catefgjrm3@quack3>
 <Y8jizbGg6l2WxJPF@li-bb2b2a4c-3307-11b2-a85c-8fa5c3a69313.ibm.com>
 <20230127144312.3m3hmcufcvxxp6f4@quack3>
 <Y9zHkMx7w4Io0TTv@li-bb2b2a4c-3307-11b2-a85c-8fa5c3a69313.ibm.com>
 <Y+OGkVvzPN0RMv0O@li-bb2b2a4c-3307-11b2-a85c-8fa5c3a69313.ibm.com>
 <20230209105418.ucowiqnnptbpwone@quack3>
 <Y+UzQJRIJEiAr4Z4@li-bb2b2a4c-3307-11b2-a85c-8fa5c3a69313.ibm.com>
 <20230210143753.ofh6wouk7vi7ygcl@quack3>
 <542D3378-3214-4D0D-AA63-5A149E2B00EE@dilger.ca>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <542D3378-3214-4D0D-AA63-5A149E2B00EE@dilger.ca>
Precedence: bulk

On Thu, Feb 16, 2023 at 10:07:39AM -0700, Andreas Dilger wrote:
> On Feb 10, 2023, at 7:37 AM, Jan Kara <jack@suse.cz> wrote:
> > So I belive mballoc tries to align everything (offsets & lengths)
> > to powers of two to reduce fragmentation and simplify the work for
> > the buddy allocator.  If ac->ac_b_ex.fe_len is a power-of-two, the
> > alignment makes sense. But once we had to resort to higher allocator
> > passes and just got some random-length extent, the alignment stops
> > making sense.
> 
> In addition to optimizing for the buddy allocator, the other reason that
> the allocations are aligned to power-of-two offsets is to better align
> with underlying RAID stripes.  Otherwise, unaligned writes will cause
> parity read-modify-write updates to multiple RAID stripes.  This alignment
> can also help (though to a lesser degree) with NAND flash erase blocks.
> 
> Cheers, Andreas
> 
Got it, thanks. So from my limited understanding of RAID, if the write
is stripe aligned and the (length % stripe == 0) then we won't need a 
RMW cycle for parity bits and thats one of the reasons to pay attention
to alignment and length in mballoc code. 

Then I think Jan's reasoning still holds that if ac_b_ex.fe_len is already
not of a proper size then we'll anyways be ending with a RMW write in
RAID so no point of paying attention to its alignment, right?

Regards,
ojaswin