Kexec Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "\"Zhou, Wenjian/周文剑\"" <zhouwj-fnst@cn.fujitsu.com>
To: Minfei Huang <mhuang@redhat.com>, Minoru Usui <min-usui@ti.jp.nec.com>
Cc: kexec@lists.infradead.org
Subject: Re: [PATCH v3] Improve the performance of --num-threads -d 31
Date: Mon, 7 Mar 2016 08:17:47 +0800	[thread overview]
Message-ID: <56DCC8AB.5090109@cn.fujitsu.com> (raw)
In-Reply-To: <56D95069.5030903@cn.fujitsu.com>

On 03/04/2016 05:07 PM, "Zhou, Wenjian/周文剑" wrote:
> Hello Minfei and Minoru,
>
> This is a reply to the previous letters.
> Sorry for so late.
> And it is also an introduction of the patch v3.
>
> About performance:
> I modified the patch after reading Minoru's code.
> Thanks Minoru, it has better performance now.
>
> About bugs:
> There are two bugs in the patch v2.
> First is reported by Minfei.
> Minoru's explanation and solution are right.
> But I used another solution.
> +            if (pfn >= kdump_thread_args->end_pfn) {
> +                page_data_buf[index].used = FALSE;
> +                page_flag_buf->ready = FLAG_READY;
> +                break;
> +            }
> The bug is caused by the above code.
> Just remove "page_flag_buf->ready = FLAG_READY;" is OK.
>
> Second bug is what I met.
> If run makedumpfile a lot of times, a few pages' data will not be correct.
> I fix it by using "volatile" and info->page_data_mutex.
> So I delete the original mutex in page_data_buf. It can also use less memory.
> I have run it 500 times and haven't got any wrong page data.
>

Sorry, the second bug still exists.


-- 
Thanks
Zhou



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

  reply	other threads:[~2016-03-07  0:19 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-04  8:35 [PATCH v3] Improve the performance of --num-threads -d 31 Zhou Wenjian
2016-03-04  9:07 ` "Zhou, Wenjian/周文剑"
2016-03-07  0:17   ` "Zhou, Wenjian/周文剑" [this message]
2016-03-07  5:53     ` Minfei Huang
2016-03-07  7:04 ` Minfei Huang
2016-03-07  7:36   ` Minoru Usui
2016-03-07  8:16     ` Minoru Usui
2016-03-07  8:39       ` Minfei Huang
2016-03-07  8:46         ` "Zhou, Wenjian/周文剑"
2016-03-07  8:22     ` "Zhou, Wenjian/周文?"
2016-03-07  8:43       ` "Zhou, Wenjian/周文剑"
2016-03-07  8:52         ` Minoru Usui
2016-03-07  9:03           ` "Zhou, Wenjian/周文剑"

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=56DCC8AB.5090109@cn.fujitsu.com \
    --to=zhouwj-fnst@cn.fujitsu.com \
    --cc=kexec@lists.infradead.org \
    --cc=mhuang@redhat.com \
    --cc=min-usui@ti.jp.nec.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox