patches for DPDK stable branches
 help / color / mirror / Atom feed
From: Stephen Hemminger <stephen@networkplumber.org>
To: "Zhou, YidingX" <yidingx.zhou@intel.com>
Cc: Ferruh Yigit <ferruh.yigit@xilinx.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"Zhang, Qi Z" <qi.z.zhang@intel.com>,
	"stable@dpdk.org" <stable@dpdk.org>
Subject: Re: [PATCH] net/pcap: reduce time for stopping device
Date: Wed, 31 Aug 2022 09:42:19 -0700	[thread overview]
Message-ID: <20220831094219.74f5aa6c@hermes.local> (raw)
In-Reply-To: <DM5PR1101MB2107A250EC67513C52E95D5885769@DM5PR1101MB2107.namprd11.prod.outlook.com>

On Mon, 29 Aug 2022 11:50:29 +0000
"Zhou, YidingX" <yidingx.zhou@intel.com> wrote:

> I draw a diagram to describe it more clearly
> 
>  fwrite                             fclose/fflush                                                   fclose/fdatasync
> --------->| libc buffer  |----------------> |    disk cache in RAM          |---------------------> |disk|  
>               | 4096 Bytes |                         | size is determined by OS |                                |       |
> 
> When the libc buffer is full, the system will automatically sync it to the disk cache.
> It is easily full as it's only 4096 B size. so there is no need to call 'fflush()' every time.
> The real time consuming action is syncing the disk cache to disk.
> Because the disk cache is very large, it will take a long time to sync all at one time during 'fclose()',
> so need to call 'fdatasync()' periodically to amortize the time.

If you want to speed up this, then get rid of stdio and use a faster
API like io_uring. What you tried can help but using a better API
would make bigger gains.

  reply	other threads:[~2022-08-31 16:42 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-25  7:20 Yiding Zhou
2022-08-25 10:09 ` Ferruh Yigit
2022-08-25 11:17   ` Zhou, YidingX
2022-08-25 12:21     ` Ferruh Yigit
2022-08-29 11:50       ` Zhou, YidingX
2022-08-31 16:42         ` Stephen Hemminger [this message]
2022-09-01  7:40         ` Zhou, YidingX
2022-09-06  8:05 ` [PATCH v2] net/pcap: fix timeout of " Yiding Zhou
2022-09-06 14:57   ` Stephen Hemminger
2022-09-06 16:21     ` Zhou, YidingX
2022-09-21  7:14     ` Zhou, YidingX
2022-10-03 15:00       ` Ferruh Yigit
2022-11-22  9:25       ` Zhou, YidingX
2022-11-22 17:28         ` Stephen Hemminger
2022-12-02 10:22           ` Zhou, YidingX
2022-11-29 14:11         ` Ferruh Yigit
2022-12-02 10:13           ` Zhou, YidingX
2022-12-02 11:19             ` Ferruh Yigit
2022-12-05  1:58               ` Zhou, YidingX
  -- strict thread matches above, loose matches on Subject: below --
2022-08-25  6:27 [PATCH] net/pcap: reduce time for " Yiding Zhou

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=20220831094219.74f5aa6c@hermes.local \
    --to=stephen@networkplumber.org \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@xilinx.com \
    --cc=qi.z.zhang@intel.com \
    --cc=stable@dpdk.org \
    --cc=yidingx.zhou@intel.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;
as well as URLs for NNTP newsgroup(s).