From: Tristan <9p-st@imu.li>
To: 9fans@9fans.net
Subject: [9fans] usb slowness
Date: Sat, 3 Mar 2012 20:56:39 -0500 [thread overview]
Message-ID: <2579b6.8126cb52.62GS.mx@tumtum.plumbweb.net> (raw)
for a while now i've known that usb/ether runs slow for me. i thought it
was something to do with the specific situation or hardware, and that,
say, usb/disk would be alright. it isn't. and not just on the olpc. now,
my machines are fairly slow as machines go... but 2.5MB/s reads are a far
cry from 22MB/s (with the olpc on linux).
it turns out that _strayintr is taking up nearly all the time.
cpu% kprof /n/9fat/9cpcpuf /dev/kpdata
total: 24620 in kernel text: 23890 outside kernel text:730
RTZERO f0100000 PGSIZE 4Kb
ms % sym
21840 91.3 _strayintr
290 1.2 memmove
290 1.2 iunlock
180 0.7 sched
160 0.6 memset
150 0.6 sleep
...
my understanding is that _strayintr is glue between the interrupt vector
table and trap. and presumably includes the time spent in trap.
the short review of usbehci.c didn't provide any insight, so i guess i'm
asking, is this expected behavior? and what can i do?
enjoy,
tristan
--
All original matter is hereby placed immediately under the public domain.
next reply other threads:[~2012-03-04 1:56 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-04 1:56 Tristan [this message]
2012-03-05 15:46 ` erik quanstrom
2012-03-05 16:05 ` Richard Miller
2012-03-05 16:14 ` erik quanstrom
2012-03-05 16:20 ` Richard Miller
2012-03-06 13:19 ` Tristan
2012-03-06 15:36 ` Tristan
2012-03-06 16:10 ` Richard Miller
2012-03-06 18:55 ` erik quanstrom
2012-03-06 22:22 ` Tristan
2012-03-07 5:50 ` Tristan
2012-03-07 5:53 ` Tristan
2012-03-07 9:31 ` Charles Forsyth
2012-03-10 3:13 ` [9fans] donehead changed before ack Tristan
2012-03-10 12:33 ` erik quanstrom
2012-03-10 15:14 ` Tristan
2012-03-07 15:27 ` [9fans] usb slowness Richard Miller
2012-03-05 15:56 ` Richard Miller
2012-03-06 0:01 ` Tristan
2012-03-06 10:39 ` Richard Miller
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=2579b6.8126cb52.62GS.mx@tumtum.plumbweb.net \
--to=9p-st@imu.li \
--cc=9fans@9fans.net \
/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).