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>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <adae6bff-8401-b641-438c-d212b20a7430@huaweicloud.com>
Date: Wed, 13 Nov 2024 09:18:14 +0800
From: Yu Kuai <yukuai1@...weicloud.com>
To: Dragan Milivojević <galileo@...-inc.com>,
 Yu Kuai <yukuai1@...weicloud.com>, "yukuai (C)" <yukuai3@...wei.com>
Cc: Song Liu <song@...nel.org>, linux-raid@...r.kernel.org,
 linux-kernel@...r.kernel.org, yi.zhang@...wei.com, yangerkun@...wei.com,
 "Luse, Paul E" <paul.e.luse@...el.com>
Subject: Re: [PATCH md-6.13] md: remove bitmap file support

Hi,

在 2024/11/11 22:07, Dragan Milivojević 写道:
> Reads are fine but writes are many times slower ...
> 
> 
>>
>> I still can't believe your test result, and I can't figure out why
>> internal bitmap is so slow. Hence I use ramdisk(10GB) to create a raid5,
>> and use the same fio script to test, the result is quite different from
>> yours:
>>
>> ram0:            981MiB/s
>> non-bitmap:        132MiB/s
>> internal-bitmap:    95.5MiB/s
>>>

So, I waited for Paul to have a chance to give it a test for real disks,
still, results are similar to above.
> 
> I don't know, I can provide full fio test logs including fio "tracing" 
> for these iodepth 8
> tests if that would make any difference.
> 

No, I don't need fio logs.
> 
> 
>> There is absolutely something wrong here, it doesn't make sense to me
>> that internal bitmap is so slow. However, I have no idea until you can
>> provide the perf result.
> 
> I may be able to find time to do that over the weekend, but don’t hold 
> me to it.
> The test setup will not be the same, server is in production ...
> I did leave some "spare" partitions on all drives to investigate this 
> issue further
> but did not find the time.
> 
> Please send me an example of how would you like me to run the perf tool, 
> I haven't used
> it much.

You can see examples here:

https://github.com/brendangregg/FlameGraph

To be short, while test is running:

perf record -a -g -- sleep 10
perf script -i perf.data | ./stackcollapse-perf.pl | ./flamegraph.pl

BTW, you said that you're using production environment, this will
probably make it hard to analyze performance.

Thanks,
Kuai


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ