linux-ext4 - Re: [PATCH 1/2] ext4: mballoc to prefetch groups ahead of scanning

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 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:   Thu, 14 May 2020 10:29:57 -0600
From:   Andreas Dilger <adilger@...ger.ca>
To:     Ritesh Harjani <riteshh@...ux.ibm.com>
Cc:     Alex Zhuravlev <azhuravlev@...mcloud.com>,
        "linux-ext4@...r.kernel.org" <linux-ext4@...r.kernel.org>
Subject: Re:  [PATCH 1/2] ext4: mballoc to prefetch groups ahead of scanning

On May 14, 2020, at 03:42, Ritesh Harjani <riteshh@...ux.ibm.com> wrote:
> 
> Hello Alex,
> 
> Few comments to understand the patch better.
> 
>> On 4/28/20 10:50 AM, Alex Zhuravlev wrote:
>> Together with the patch "ext4: limit scanning of uninitialized groups"
> Where is this patch which says ^^^^^ ?

I think that patch was eventually merged into this one?

>> the mount time of a 1PB filesystem is reduced significantly:
>>               0% full    50%-full unpatched    patched
>>  mount time       33s                9279s       563s
> 
> Looks good. Do you have perf improvement numbers with this patch alone?
> Wonder if this could show improvement if I make my FS image using dm-sparse?

That is hard to say, because the sparse image may not need seeking
when reading the bitmaps. You can test with an artificial delay via DM. 

>> Lustre-bug-id: https://jira.whamcloud.com/browse/LU-12988
> 
> Not sure if this is required.

This should be kept, as it i the same as existing Debian or Bugzilla tags.
It contains a lot more detail on history and earlier versions of the patches. 

Cheers, Andreas