10 minutes to unpack linux kernel source? hmmm... :-)

[Luca Maranzano]

Hi all,

I've installed Linux 2.0.33 (red hat 5.0) on a machine with the
following hardware:

CPU AMD K6 200Mhz
64 MB RAM
Chipset Triton
Controller Adaptec 2940UW
Hard disk Quantum Atlas III XP39100W 8.4Giga
3Com 590 PCI

I've experienced the following strange thing:

If I try to extract the source of the Linux Kernel from the .tgz archive
to the file system it is terribly slow! And this to me is unbelievable,
since the machine seems to perform quite well (it is one of our proxy
server running squid). I've tryed to compile the kernel and the time
was quite good (some minutes). If I try to extract whichever package
from a .tgz (operation that obviously involves a lot of write operations)
the machine seems to sleep every few seconds, and the load average
doesn't increase (~ 0.0x). 
Look at this:

[root at artemide xxx]# time tar zxf ~liuk/linux-2.0.33.tar.gz 
5.06user 4.97system 9:11.08elapsed 1%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (1451major+4571minor)pagefaults 0swaps

Almost 10 minutes!!! Isn't it incredible?

Removing the same files just unpacked (~26M) seems to be reasonably fast:

0.17user 0.77system 0:06.04elapsed 15%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (84major+17minor)pagefaults 0swaps

Here is the output about the controller:

dmesg reports this:
aic7xxx: <Adaptec AHA-294X Ultra SCSI host adapter> at PCI 20
aic7xxx: Warning - detected auto-termination.  Please verify driver
         detected settings and use manual termination if necessary.
aic7xxx: BIOS enabled, IO Port 0x6400, IO Mem 0xe4000000, IRQ 11, Revision B
aic7xxx: Wide Channel, SCSI ID 7, 16/16 SCBs, QFull 16, QMask 0x1f
scsi0 : Adaptec AHA274x/284x/294x (EISA/VLB/PCI-Fast SCSI) 4.1.1/3.2.1
scsi : 1 host.
scsi0: Scanning channel A for devices.
  Vendor: QUANTUM   Model: XP39100W          Rev: LXY4
  Type:   Direct-Access                      ANSI SCSI revision: 02
Detected scsi disk sda at scsi0, channel 0, id 6, lun 0
scsi : detected 1 SCSI disk total.
SCSI device sda: hdwr sector= 512 bytes. Sectors= 17781520 [8682 MB] [8.7 GB]

cat /proc/scsi/aic7xxx/0 reports this:

Adaptec AIC7xxx driver version: 4.1.1/3.2.1
Compile Options:
  AIC7XXX_RESET_DELAY    : 15
  AIC7XXX_TAGGED_QUEUEING: Enabled
  AIC7XXX_PAGE_ENABLE    : Disabled
  AIC7XXX_PROC_STATS     : Disabled

Adapter Configuration:
           SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
                         (AIC-788x chipset)
               Host Bus: Wide
                Base IO: 0x6400
         Base IO Memory: 0xe4000000
                    IRQ: 11
                   SCBs: Used 8, HW 16, Page 16
             Interrupts: 64748
          Serial EEPROM: True
   Extended Translation: Enabled
         SCSI Bus Reset: Enabled
             Ultra SCSI: Enabled
Disconnect Enable Flags: 0xffff

Do I have to set up some special parameters on the BIOS Config of the
controller?

May the AMD CPU be involved in this strange thing?

Any hint is very appreciated! Tell me more if you need some other infos...

Thank you in advance.
Best regards from Italy.
Luca



To Unsubscribe: send mail to majordomo at FreeBSD.org
with "unsubscribe aic7xxx" in the body of the message