Paul Davis wrote:
> 
> nobody can comment much on these graphs when they are generated with
> an IDE disk system for which the hdparms set up is not reported.

Now those are reported, see below.

> however, it would appear that there are potential problems with the
> video adaptor that you have when used with XFree 4.1.99-cvs. it
> wouldn't be the first such case.

I did some driver hacking and managed to fix it, results with 2.4.16-ll
kernel and fixed radeon driver:

http://www.pp.song.fi/~visitor/latencytest3/3x256.html

> the rest of your results appear OK, though also hard to comment on
> because its not clear how the audio interface was configured by
> latencytest (2 channels? 10? etc.)

2 channels, 44.1 kHz as the default is.

> as a footnote, 2.4.12-ac3 still used the vanRiel VM system, which is
> known to perform poorly under extreme system load.

Results with 2.4.16-ll are at:

http://www.pp.song.fi/~visitor/latencytest2/3x256.html

There is nasty problem with disk IO (cache) which I think is fixed in 2.4.17
so I'm not going to hack 2.4.16.


 - Jussi Laako


----- 8< ------

/dev/hdb:
 multcount    = 16 (on)
 I/O support  =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 nowerr       =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 40020624, start = 0

----------VIA BusMastering IDE Configuration----------------
Driver Version:                     3.29
South Bridge:                       VIA vt82c686b
Revision:                           ISA 0x40 IDE 0x6
Highest DMA rate:                   UDMA100
BM-DMA base:                        0xb800
PCI clock:                          33MHz
Master Read  Cycle IRDY:            0ws
Master Write Cycle IRDY:            0ws
BM IDE Status Register Read Retry:  yes
Max DRDY Pulse Width:               No limit
-----------------------Primary IDE-------Secondary IDE------
Read DMA FIFO flush:          yes                 yes
End Sector FIFO flush:         no                  no
Prefetch Buffer:              yes                  no
Post Write Buffer:            yes                  no
Enabled:                      yes                 yes
Simplex only:                  no                  no
Cable Type:                   80w                 80w
-------------------drive0----drive1----drive2----drive3-----
Transfer Mode:       UDMA      UDMA       DMA      UDMA
Address Setup:       30ns      30ns      60ns      30ns
Cmd Active:          90ns      90ns      90ns      90ns
Cmd Recovery:        30ns      30ns      90ns      90ns
Data Active:         90ns      90ns      90ns      90ns
Data Recovery:       30ns      30ns      90ns      30ns
Cycle Time:          30ns      20ns     180ns      30ns
Transfer Rate:   66.0MB/s  99.0MB/s  11.0MB/s  66.0MB/s

-- 
PGP key fingerprint: 161D 6FED 6A92 39E2 EB5B  39DD A4DE 63EB C216 1E4B
Available at PGP keyservers

Reply via email to