From: Martin Honermeyer <maze@strahlungsfrei.de>
To: linux-kernel@vger.kernel.org
Subject: Re: [Fwd: Re: 3w-9xxx status in kernel]
Date: Wed, 19 Apr 2006 14:04:19 +0200 [thread overview]
Message-ID: <e258sa$5n1$1@sea.gmane.org> (raw)
In-Reply-To: 1145445387.3085.27.camel@laptopd505.fenrus.org
Arjan van de Ven wrote:
> -------- Forwarded Message --------
>> From: Martin Honermeyer <maze@strahlungsfrei.de>
>> To: linux-kernel@vger.kernel.org
>> Subject: Re: 3w-9xxx status in kernel
>> Date: Wed, 19 Apr 2006 13:02:42 +0200
>>
>> Hi,
>>
>> same problem over here. Why does the newest kernel contain an old version
>> of the 3w-9xxx driver?
>
> because nobody bothered to submit it??
Okay, now I know how it works.
>
>>
>> We are having performance problems using a 9550SX controller. Read
>> throughput (measured with hdparm)
>
> hdparm is not a good measurement tool at all for performance.
> At least use something like tiobench (tiobench.sf.net)
Thanks for the hint. Here is tiobench output:
$ tiobench
No size specified, using 2000 MB
Run #1: /usr/bin/tiotest -t 8 -f 250 -r 500 -b 4096 -d . -TTT
Unit information
================
File size = megabytes
Blk Size = bytes
Rate = megabytes per second
CPU% = percentage of CPU used during the test
Latency = milliseconds
Lat% = percent of requests that took longer than X seconds
CPU Eff = Rate divided by CPU% - throughput per cpu load
Sequential Reads
File Blk Num Avg
Maximum Lat% Lat% CPU
Identifier Size Size Thr Rate (CPU%) Latency
Latency >2s >10s Eff
---------------------------- ------ ----- --- ------ ------ ---------
----------- -------- -------- -----
2.6.15-19-amd64-xeon 2000 4096 1 46.63 7.159% 0.083
484.49 0.00000 0.00000 651
2.6.15-19-amd64-xeon 2000 4096 2 34.65 10.11% 0.223
386.04 0.00000 0.00000 343
2.6.15-19-amd64-xeon 2000 4096 4 15.14 8.629% 1.016
1128.07 0.00000 0.00000 175
2.6.15-19-amd64-xeon 2000 4096 8 23.56 23.09% 1.209
2051.28 0.00020 0.00000 102
Random Reads
File Blk Num Avg
Maximum Lat% Lat% CPU
Identifier Size Size Thr Rate (CPU%) Latency
Latency >2s >10s Eff
---------------------------- ------ ----- --- ------ ------ ---------
----------- -------- -------- -----
2.6.15-19-amd64-xeon 2000 4096 1 3.76 0.626% 1.037
99.77 0.00000 0.00000 601
2.6.15-19-amd64-xeon 2000 4096 2 4.88 1.654% 1.545
97.82 0.00000 0.00000 295
2.6.15-19-amd64-xeon 2000 4096 4 5.40 3.389% 2.673
208.84 0.00000 0.00000 159
2.6.15-19-amd64-xeon 2000 4096 8 6.51 11.20% 4.013
261.38 0.00000 0.00000 58
Sequential Writes
File Blk Num Avg
Maximum Lat% Lat% CPU
Identifier Size Size Thr Rate (CPU%) Latency
Latency >2s >10s Eff
---------------------------- ------ ----- --- ------ ------ ---------
----------- -------- -------- -----
2.6.15-19-amd64-xeon 2000 4096 1 13.05 6.946% 0.274
34488.77 0.00098 0.00039 188
2.6.15-19-amd64-xeon 2000 4096 2 6.99 14.91% 0.432
57601.25 0.00352 0.00039 47
2.6.15-19-amd64-xeon 2000 4096 4 7.10 53.92% 1.360
69873.41 0.00957 0.00176 13
2.6.15-19-amd64-xeon 2000 4096 8 7.07 78.44% 2.813
71698.67 0.02441 0.00684 9
Random Writes
File Blk Num Avg
Maximum Lat% Lat% CPU
Identifier Size Size Thr Rate (CPU%) Latency
Latency >2s >10s Eff
---------------------------- ------ ----- --- ------ ------ ---------
----------- -------- -------- -----
2.6.15-19-amd64-xeon 2000 4096 1 0.44 0.142% 0.010
11.50 0.00000 0.00000 306
2.6.15-19-amd64-xeon 2000 4096 2 0.43 0.324% 0.009
0.07 0.00000 0.00000 131
2.6.15-19-amd64-xeon 2000 4096 4 0.42 1.979% 0.031
0.50 0.00000 0.00000 21
2.6.15-19-amd64-xeon 2000 4096 8 0.41 4.640% 0.077
1.33 0.00000 0.00000 9
I am especially scared of the high CPU usage in sequential writes! Btw: this
server sits idle at the moment. Just some webserver processes running!
Specs:
Dual-Xeon 3 GHz, Ubuntu Dapper 64bit with 2.6.15 Ubuntu kernel.
Martin
prev parent reply other threads:[~2006-04-19 12:02 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-04-19 11:16 [Fwd: Re: 3w-9xxx status in kernel] Arjan van de Ven
2006-04-19 12:04 ` Martin Honermeyer [this message]
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='e258sa$5n1$1@sea.gmane.org' \
--to=maze@strahlungsfrei.de \
--cc=linux-kernel@vger.kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.