Linux MIPS Architecture development
 help / color / mirror / Atom feed
From: Matej Kupljen <matej.kupljen@ultra.si>
To: David Daney <ddaney@avtrex.com>
Cc: linux-mips@linux-mips.org
Subject: Re: Where is op_model_mipsxx.c ?
Date: Wed, 26 Oct 2005 08:35:02 +0200	[thread overview]
Message-ID: <1130308502.4656.5.camel@localhost.localdomain> (raw)
In-Reply-To: <435E48CB.6040607@avtrex.com>

[-- Attachment #1: Type: text/plain, Size: 721 bytes --]

Hi

> If there are no performance counters, OProfile can still use the system 
> timer to take samples each clock tick.  This is the way I am using it.

Thanks for the info.

> To use it in this manner you have to hack up the code a bit so that the 
> return value of oprofile_arch_init() (in oprofile/common.c) is -ENODEV.

I'll try that and let you know the results.

I want to use the profiler, because the network performance of dbau1200
is very poor (with 2.6.14-rc2 and smc91x driver I get around 12Mbit/s!).

I check the traffic of netperf with ethereal and I see quite a lot
of duplicated packets (see the attached file with a few packets).
I think think this is also the reason that NFS is so slow.

BR,
Matej



[-- Attachment #2: netperf_dump.txt --]
[-- Type: text/plain, Size: 2621 bytes --]

No.     Time        Source                Destination           Protocol Info
     50 5.759336    172.18.1.53           172.18.1.57           TCP      37994 > 32772 [ACK] Seq=28961 Ack=1 Win=5840 Len=1448 TSV=111254184 TSER=2217426
     51 5.759342    172.18.1.53           172.18.1.57           TCP      37994 > 32772 [ACK] Seq=30409 Ack=1 Win=5840 Len=1448 TSV=111254184 TSER=2217426
     52 5.761884    172.18.1.57           172.18.1.53           TCP      [TCP Dup ACK 49#1] 32772 > 37994 [ACK] Seq=1 Ack=14481 Win=34752 Len=0 TSV=2217427 TSER=111254176 SLE=17377 SRE=18825
     53 5.761894    172.18.1.53           172.18.1.57           TCP      37994 > 32772 [ACK] Seq=31857 Ack=1 Win=5840 Len=1448 TSV=111254186 TSER=2217427
     54 5.762052    172.18.1.57           172.18.1.53           TCP      [TCP Dup ACK 49#2] 32772 > 37994 [ACK] Seq=1 Ack=14481 Win=34752 Len=0 TSV=2217429 TSER=111254176 SLE=17377 SRE=20273
     55 5.762063    172.18.1.53           172.18.1.57           TCP      [TCP Retransmission] 37994 > 32772 [ACK] Seq=14481 Ack=1 Win=5840 Len=1448 TSV=111254186 TSER=2217429
     56 5.762214    172.18.1.57           172.18.1.53           TCP      [TCP Dup ACK 49#3] 32772 > 37994 [ACK] Seq=1 Ack=14481 Win=34752 Len=0 TSV=2217429 TSER=111254176 SLE=17377 SRE=21721
     57 5.762223    172.18.1.53           172.18.1.57           TCP      [TCP Retransmission] 37994 > 32772 [ACK] Seq=15929 Ack=1 Win=5840 Len=1448 TSV=111254187 TSER=2217429
     58 5.764745    172.18.1.57           172.18.1.53           TCP      [TCP Dup ACK 49#4] 32772 > 37994 [ACK] Seq=1 Ack=14481 Win=34752 Len=0 TSV=2217432 TSER=111254176 SLE=17377 SRE=23169
     59 5.764754    172.18.1.53           172.18.1.57           TCP      37994 > 32772 [ACK] Seq=33305 Ack=1 Win=5840 Len=1448 TSV=111254189 TSER=2217432
     60 5.764911    172.18.1.57           172.18.1.53           TCP      [TCP Dup ACK 49#5] 32772 > 37994 [ACK] Seq=1 Ack=14481 Win=34752 Len=0 TSV=2217432 TSER=111254176 SLE=26065 SRE=27513 SLE=17377 SRE=23169
     61 5.765074    172.18.1.57           172.18.1.53           TCP      [TCP Dup ACK 49#6] 32772 > 37994 [ACK] Seq=1 Ack=14481 Win=34752 Len=0 TSV=2217432 TSER=111254176 SLE=26065 SRE=28961 SLE=17377 SRE=23169
     62 5.765083    172.18.1.53           172.18.1.57           TCP      [TCP Retransmission] 37994 > 32772 [PSH, ACK] Seq=23169 Ack=1 Win=5840 Len=1448 TSV=111254189 TSER=2217432
     63 5.766842    172.18.1.57           172.18.1.53           TCP      [TCP Dup ACK 49#7] 32772 > 37994 [ACK] Seq=1 Ack=14481 Win=34752 Len=0 TSV=2217434 TSER=111254176 SLE=26065 SRE=30409 SLE=17377 SRE=23169

  reply	other threads:[~2005-10-26  9:23 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-10-05  4:11 Where is op_model_mipsxx.c ? David Daney
2005-10-05 10:44 ` Ralf Baechle
2005-10-25 11:25   ` Matej Kupljen
2005-10-25 15:01     ` David Daney
2005-10-26  6:35       ` Matej Kupljen [this message]
2005-10-26 12:15     ` Ralf Baechle
2005-10-07 18:13 ` Mike C. Ward
2005-10-07 18:13   ` Mike C. Ward

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=1130308502.4656.5.camel@localhost.localdomain \
    --to=matej.kupljen@ultra.si \
    --cc=ddaney@avtrex.com \
    --cc=linux-mips@linux-mips.org \
    /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