DPDK patches and discussions
 help / color / mirror / Atom feed
From: Thomas Monjalon <thomas@monjalon.net>
To: rahul gupta <rahulrgupta27@gmail.com>,
	Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>,
	Rahul Gupta <rahulgupt@linux.microsoft.com>,
	dev@dpdk.org, sovaradh@linux.microsoft.com, okaya@kernel.org,
	sujithsankar@microsoft.com, sowmini.varadhan@microsoft.com,
	Rahul Gupta <rahulgupt@microsoft.com>
Subject: Re: [RFC] eal: RFC to refactor rte_eal_init into sub-functions
Date: Wed, 08 Nov 2023 16:40:07 +0100	[thread overview]
Message-ID: <2246568.HovnAMPojK@thomas> (raw)
In-Reply-To: <20231108165331.61eef3e0@sovereign>

08/11/2023 14:53, Dmitry Kozlyuk:
> 2023-11-07 23:03 (UTC+0530), rahul gupta:
> > > > From: Rahul Gupta <rahulgupt@linux.microsoft.com>
> > > > To: dev@dpdk.org,  thomas@monjalon.net
> > > > Cc: sovaradh@linux.microsoft.com, okaya@kernel.org,  
> > > sujithsankar@microsoft.com,  sowmini.varadhan@microsoft.com,
> > > rahulrgupta27@gmail.com,  Rahul Gupta <rahulgupt@microsoft.com>,  Rahul
> > > Gupta <rahulgupt@linux.microsoft.com>  
> > > > Subject: [RFC] eal: RFC to refactor rte_eal_init into sub-functions
> > > > Date: Thu,  2 Nov 2023 11:19:24 -0700
> > > > X-Mailer: git-send-email 1.8.3.1
> > > >
> > > > From: Rahul Gupta <rahulgupt@microsoft.com>
> > > >
> > > > Initialization often requires rte_eal_init + rte_pktmbuf_pool_create
> > > > which can consume a total time of 500-600 ms:
> > > > a) For many devices FLR may take a significant chunk of time
> > > >    (200-250 ms in our use-case), this FLR is triggered during device
> > > >    probe in rte_eal_init().
> > > > b) rte_pktmbuf_pool_create() can consume upto 300-350 ms for
> > > > applications that require huge memory.
> > > >
> > > > This cost is incurred on each restart (which happens in our use-case
> > > > during binary updates for servicing).
> > > > This patch provides an optimization using pthreads that appplications
> > > > can use and which can save 200-230ms.
> > > >
> > > > In this patch, rte_eal_init() is refactored into two parts-
> > > > a) 1st part is dependent code ie- it’s a perquisite of the FLR and
> > > >    mempool creation. So this code needs to be executed before any
> > > >    pthreads. Its named as rte_eal_init_setup()
> > > > b) 2nd part of code is independent code ie- it can execute in parallel
> > > >    to mempool creation in a pthread. Its named as rte_probe_and_ioctl().
> > > >
> > > > Existing applications require no changes unless they wish to leverage
> > > > the optimization.
> > > >
> > > > If the application wants to use pthread functionality, it should call-
> > > > a) rte_eal_init_setup() then create two or more pthreads-
> > > > b) in one pthread call- rte_probe_and_ioctl(),
> > > > c) second pthread call- rte_pktmbuf_pool_create()
> > > > d) (optional) Other pthreads for  any other independent function.
> > > >
> > > > Signed-off-by: Rahul Gupta <rahulgupt@linux.microsoft.com>  
> 
> I doubt that the new API is required.
> It is already possible to block all devices from automatic probing
> with EAL options and then probe explicitly in any threads desired.
> At the same time, this RFC shows a valuable optimization pattern,
> so maybe it is worth having in DPDK as an example.
> There are DPDK use cases when probing is completely unnecessary.

It seems here we want to do the device probing,
but start it in parallel of other tasks.

> Exposing the initialization process stages makes it harder to refactor
> and requires precise documentation of when and what is initialized
> (for example, in this RFC rte_eal_init_setup()
> does not make service core API usable yet).

Yes the init order is sensitive, that's why we have a big init function.
But in general I would agree to try splitting it with necessary warnings
and explanations.

> P. S. You may be also interested in using `--huge-unlink=never`
> to speed rte_pktmbuf_pool_create() during restarts:
> 
> https://doc.dpdk.org/guides/linux_gsg/linux_eal_parameters.html#id3

Yes good tip :)




  reply	other threads:[~2023-11-08 15:40 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-02 18:19 Rahul Gupta
2023-11-02 18:37 ` Stephen Hemminger
2023-11-07 17:33   ` rahul gupta
2023-11-08 13:53     ` Dmitry Kozlyuk
2023-11-08 15:40       ` Thomas Monjalon [this message]
2023-11-09 17:26         ` Rahul Gupta
2023-11-09 17:32           ` Bruce Richardson
2023-11-10 17:25             ` Rahul Gupta
2023-11-08  4:38   ` Rahul Gupta
2023-11-08 11:51 ` Bruce Richardson
2023-11-08 15:40   ` Thomas Monjalon

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=2246568.HovnAMPojK@thomas \
    --to=thomas@monjalon.net \
    --cc=dev@dpdk.org \
    --cc=dmitry.kozliuk@gmail.com \
    --cc=okaya@kernel.org \
    --cc=rahulgupt@linux.microsoft.com \
    --cc=rahulgupt@microsoft.com \
    --cc=rahulrgupta27@gmail.com \
    --cc=sovaradh@linux.microsoft.com \
    --cc=sowmini.varadhan@microsoft.com \
    --cc=stephen@networkplumber.org \
    --cc=sujithsankar@microsoft.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).