Kernel Newbies archive on lore.kernel.org
 help / color / Atom feed
From: hariprasad kelam <hariprasad.kelam@gmail.com>
To: Subhashini Rao Beerisetty <subhashbeerisetty@gmail.com>
Cc: kernelnewbies <kernelnewbies@kernelnewbies.org>
Subject: Re: How to debug throughput issues?
Date: Wed, 26 Jun 2019 11:17:23 +0530
Message-ID: <CACFYQXPQ7yyo5RNwpxwwU2vViGwYhktnhdUzVhemEDWaFR=3Yw@mail.gmail.com> (raw)
In-Reply-To: <CAPY=qRRKzYYT6r55KgMhQGvMAjqg0TNEGik29y7NE=gnpUtQhw@mail.gmail.com>

[-- Attachment #1.1: Type: text/plain, Size: 2191 bytes --]

Hi subhashini,

On Wed, 26 Jun, 2019, 10:56 AM Subhashini Rao Beerisetty, <
subhashbeerisetty@gmail.com> wrote:

> On Wed, Jun 26, 2019 at 7:44 AM Hariprasad Kelam
> <hariprasad.kelam@gmail.com> wrote:
> >
> > On Tue, Jun 25, 2019 at 10:26:54PM +0530, Subhashini Rao Beerisetty
> wrote:
> > Hi  Subhashini,
> >
> > Please see inline,
> > >  Hi All,
> > >
> > >  I’ve two Bluetooth dongles and connected to two Linux
> > > systems(hostname1, hostname2). I’ve a test executable and it creates a
> > > BT link does the file transfer and calculates the throughput.
> > >
> > Are these dongle supports classic mode or Ble?
> It supports classic mode.
>
> > Which profile are you using to establish connection between these two? (
> > PAN, ..etc)
> > >  I repeated the same test with the same BT dongles on another
> > > different Linux systems(hostname3, hostname4), here I’m getting less
> > > data rate.
> > >
> > After inserting dongles to host are you getting serial interface
> > /dev/tty* or hci interface ?
> Using serial interface /dev/tty*
> If it's inbuilt serial profile ..kernel simply creates serial interface.
>
    You may focus on serial driver .




> If its hci interface ,you can use hcidump to see packets  and check MTU
> > size
> > > Here first I want to narrow down whether the issue is below device
> > > driver level or above device driver level and where the bottleneck is?
> > > which tools will help me to debug this kind of issue?
> > >
> > I think before jumping into driver level ,its better to ensure all
> > bluetooth parameters are same on both the setups.
> Except the kernel version(hostname1 & 2 are having same kernel and it
> differs with hostname3 & 4 kernel version) rest all other stuff is
> same. So I'd like to know how to know which part of kernel mode
> functions causing more delay and any tools are there to debug these
> issues?
>
> >
> > Thanks,
> > Hariprasad k
> > > Thanks
> > >
> > > _______________________________________________
> > > Kernelnewbies mailing list
> > > Kernelnewbies@kernelnewbies.org
> > > https://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>

[-- Attachment #1.2: Type: text/html, Size: 3502 bytes --]

<div dir="auto"><div>Hi subhashini,<br><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, 26 Jun, 2019, 10:56 AM Subhashini Rao Beerisetty, &lt;<a href="mailto:subhashbeerisetty@gmail.com">subhashbeerisetty@gmail.com</a>&gt; wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On Wed, Jun 26, 2019 at 7:44 AM Hariprasad Kelam<br>
&lt;<a href="mailto:hariprasad.kelam@gmail.com" target="_blank" rel="noreferrer">hariprasad.kelam@gmail.com</a>&gt; wrote:<br>
&gt;<br>
&gt; On Tue, Jun 25, 2019 at 10:26:54PM +0530, Subhashini Rao Beerisetty wrote:<br>
&gt; Hi  Subhashini,<br>
&gt;<br>
&gt; Please see inline,<br>
&gt; &gt;  Hi All,<br>
&gt; &gt;<br>
&gt; &gt;  I’ve two Bluetooth dongles and connected to two Linux<br>
&gt; &gt; systems(hostname1, hostname2). I’ve a test executable and it creates a<br>
&gt; &gt; BT link does the file transfer and calculates the throughput.<br>
&gt; &gt;<br>
&gt; Are these dongle supports classic mode or Ble?<br>
It supports classic mode.<br>
<br>
&gt; Which profile are you using to establish connection between these two? (<br>
&gt; PAN, ..etc)<br>
&gt; &gt;  I repeated the same test with the same BT dongles on another<br>
&gt; &gt; different Linux systems(hostname3, hostname4), here I’m getting less<br>
&gt; &gt; data rate.<br>
&gt; &gt;<br>
&gt; After inserting dongles to host are you getting serial interface<br>
&gt; /dev/tty* or hci interface ?<br>
Using serial interface /dev/tty*<br>
If it&#39;s inbuilt serial profile ..kernel simply creates serial interface.<br></blockquote></div></div><div dir="auto">    You may focus on serial driver .</div><div dir="auto"><br></div><div dir="auto"><br></div><div dir="auto"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"></blockquote></div></div><div dir="auto"><br></div><div dir="auto"><br></div><div dir="auto"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
&gt; If its hci interface ,you can use hcidump to see packets  and check MTU<br>
&gt; size<br>
&gt; &gt; Here first I want to narrow down whether the issue is below device<br>
&gt; &gt; driver level or above device driver level and where the bottleneck is?<br>
&gt; &gt; which tools will help me to debug this kind of issue?<br>
&gt; &gt;<br>
&gt; I think before jumping into driver level ,its better to ensure all<br>
&gt; bluetooth parameters are same on both the setups.<br>
Except the kernel version(hostname1 &amp; 2 are having same kernel and it<br>
differs with hostname3 &amp; 4 kernel version) rest all other stuff is<br>
same. So I&#39;d like to know how to know which part of kernel mode<br>
functions causing more delay and any tools are there to debug these<br>
issues?<br>
<br>
&gt;<br>
&gt; Thanks,<br>
&gt; Hariprasad k<br>
&gt; &gt; Thanks<br>
&gt; &gt;<br>
&gt; &gt; _______________________________________________<br>
&gt; &gt; Kernelnewbies mailing list<br>
&gt; &gt; <a href="mailto:Kernelnewbies@kernelnewbies.org" target="_blank" rel="noreferrer">Kernelnewbies@kernelnewbies.org</a><br>
&gt; &gt; <a href="https://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies" rel="noreferrer noreferrer" target="_blank">https://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies</a><br>
</blockquote></div></div></div>

[-- Attachment #2: Type: text/plain, Size: 170 bytes --]

_______________________________________________
Kernelnewbies mailing list
Kernelnewbies@kernelnewbies.org
https://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies

  reply index

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-25 16:56 Subhashini Rao Beerisetty
2019-06-26  2:14 ` Hariprasad Kelam
2019-06-26  5:26   ` Subhashini Rao Beerisetty
2019-06-26  5:47     ` hariprasad kelam [this message]
2019-06-26  5:52       ` Subhashini Rao Beerisetty

Reply instructions:

You may reply publically 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='CACFYQXPQ7yyo5RNwpxwwU2vViGwYhktnhdUzVhemEDWaFR=3Yw@mail.gmail.com' \
    --to=hariprasad.kelam@gmail.com \
    --cc=kernelnewbies@kernelnewbies.org \
    --cc=subhashbeerisetty@gmail.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

Kernel Newbies archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kernelnewbies/0 kernelnewbies/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kernelnewbies kernelnewbies/ https://lore.kernel.org/kernelnewbies \
		kernelnewbies@kernelnewbies.org kernelnewbies@archiver.kernel.org
	public-inbox-index kernelnewbies


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernelnewbies.kernelnewbies


AGPL code for this site: git clone https://public-inbox.org/ public-inbox