RedHat 8.0 Sluggish...

Taking Back · 10-25-2002, 06:35 PM

I just installed RedHat 8.0 yesterday, and overall it's
pretty good. However, it seems to be running VERY sluggishly. My hardware is AMD K6/2 500 mhz, 128 MB ram, 20 GB 7200 rpm Fujistsu HD. My swap size is 256 MB.
Any ideas on why this may be?

jdc2048 · 10-25-2002, 07:57 PM

Need some more info.

Run "top" in a term window and post top resource hogs.

dnar · 10-25-2002, 08:47 PM

Run as root:

/sbin/hdparm -tT /dev/hdx

where hdx is your drive (typically hda).

Post the results...

Taking Back · 10-26-2002, 02:00 PM

Ok, so this is what I got when I ran top:

2:59pm up 8 min, 1 user, load average: 0.47, 0.43, 0.20
61 processes: 58 sleeping, 2 running, 1 zombie, 0 stopped
CPU states: 33.8% user, 5.4% system, 0.0% nice, 60.6% idle
Mem: 126448K av, 114444K used, 12004K free, 0K shrd, 948K buff
Swap: 262040K av, 0K used, 262040K free 50504K cached

PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME COMMAND
932 root 15 0 25620 25M 13808 S 21.7 20.2 0:39 mozilla-bin
811 root 5 -10 19764 15M 5388 S < 9.9 12.1 0:18 X
957 root 16 0 9096 9092 7120 R 2.9 7.1 0:07 gnome-terminal
914 root 15 0 11340 11M 8436 S 1.9 8.9 0:06 gnome-panel
985 root 16 0 1012 1012 820 R 1.3 0.8 0:01 top
894 root 15 0 6588 6588 5348 S 0.5 5.2 0:03 metacity
822 root 15 0 8304 8300 6396 S 0.1 6.5 0:01 gnome-session
898 root 15 0 7292 7288 5684 S 0.1 5.7 0:02 gnome-settings-
916 root 15 0 16088 15M 10056 S 0.1 12.7 0:08 nautilus
1 root 15 0 460 460 408 S 0.0 0.3 0:04 init
2 root 15 0 0 0 0 SW 0.0 0.0 0:00 keventd
3 root 15 0 0 0 0 SW 0.0 0.0 0:00 kapmd
4 root 34 19 0 0 0 SWN 0.0 0.0 0:00 ksoftirqd_CPU0
5 root 15 0 0 0 0 SW 0.0 0.0 0:00 kswapd
6 root 25 0 0 0 0 SW 0.0 0.0 0:00 bdflush
7 root 15 0 0 0 0 SW 0.0 0.0 0:00 kupdated
8 root 25 0 0 0 0 SW 0.0 0.0 0:00 mdrecoveryd
12 root 15 0 0 0 0 SW 0.0 0.0 0:00 kjournald
107 root 15 0 0 0 0 SW 0.0 0.0 0:00 kjournald
421 root 17 0 1024 1024 736 S 0.0 0.8 0:00 dhclient
476 root 15 0 532 532 444 S 0.0 0.4 0:00 syslogd
480 root 15 0 432 432 376 S 0.0 0.3 0:00 klogd
497 rpc 15 0 528 528 452 S 0.0 0.4 0:00 portmap
516 rpcuser 18 0 816 816 696 S 0.0 0.6 0:00 rpc.statd
597 root 16 0 488 488 436 S 0.0 0.3 0:00 apmd
635 root 16 0 1428 1428 1208 S 0.0 1.1 0:00 sshd
649 root 15 0 916 916 788 S 0.0 0.7 0:00 xinetd

and from /sbin/hdparm -tT /dev/hda:

Timing buffer-cache reads: 128 MB in 3.37 seconds = 37.98 MB/sec
Timing buffered disk reads: 64 MB in 5.19 seconds = 12.33 MB/sec

Any help would be appreciated...

Flibble · 10-26-2002, 03:21 PM

That buffer-cache stat looks a little bogus to me. I just run this on my P270 Compaq laptop with 96MB of RAM (running RH8) and my results are:

/dev/hda:
Timing buffer-cache reads: 128 MB in 1.86 seconds = 68.98 MB/sec
Timing buffered disk reads: 64 MB in 8.15 seconds = 7.85 MB/sec

Bearing in mind this is a _very_ old machine your stats look bizarre.

Flibble

dnar · 10-26-2002, 07:50 PM

Looks like your not running any DMA on that drive.

Do:- /sbin/hdparm /dev/hda to see whats enabled.

Mine gives:

Code:

[root@criten wayne]# /sbin/hdparm /dev/hda

/dev/hda:
 multcount    = 16 (on)
 IO_support   =  3 (32-bit w/sync)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  1 (on)
 readonly     =  0 (off)
 readahead    =  1 (on)
 geometry     = 4866/255/63, sectors = 78177792, start = 0

I have this drive setup using the RedHat8 / hdparm config script that is configured with /etc/sysconfig/harddisks :-

Code:

[root@criten wayne]# more /etc/sysconfig/harddisks
# These options are used to tune the hard drives -
# read the hdparm man page for more information

# Set this to 1 to enable DMA. This might cause some 
# data corruption on certain chipset / hard drive
# combinations. This is used with the "-d" option

USE_DMA=1

# Multiple sector I/O. a feature of most modern IDE hard drives,
# permitting the transfer of multiple sectors per I/O interrupt,
# rather than the usual one sector per interrupt.  When this feature
# is enabled, it typically reduces operating system overhead for disk
# I/O by 30-50%.  On many systems, it also provides increased data
# throughput of anywhere from 5% to 50%.  Some drives, however (most
# notably the WD Caviar series), seem to run slower with multiple mode
# enabled. Under rare circumstances, such failures can result in
# massive filesystem corruption. USE WITH CAUTION AND BACKUP.
# This is the sector count for multiple sector I/O - the "-m" option
#
 MULTIPLE_IO=16

# (E)IDE 32-bit I/O support (to interface card)
#
 EIDE_32BIT=3

# Enable drive read-lookahead
#
 LOOKAHEAD=1

# Add extra parameters here if wanted
# On reasonably new hardware, you may want to try -X66, -X67 or -X68
# Other flags you might want to experiment with are -u1, -a and -m
# See the hdparm manpage (man hdparm) for details and more options.
#
EXTRA_PARAMS=-u1a1m16

If your drive will handle DMA and also multi sector reads, then you have big gains ahead by turning them on.

Checkout your drives capabilities with /sbin/hdparm -i /dev/hda like so:-

Code:

[root@criten wayne]# /sbin/hdparm -i /dev/hda

/dev/hda:

 Model=MAXTOR 6L040J2, FwRev=A93.0500, SerialNo=662217243206
 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
 RawCHS=16383/16/63, TrkSize=32256, SectSize=21298, ECCbytes=4
 BuffType=DualPortCache, BuffSize=1819kB, MaxMultSect=16, MultSect=16
 CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=78177792
 IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
 PIO modes:  pio0 pio1 pio2 pio3 pio4 
 DMA modes:  mdma0 mdma1 mdma2 
 UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5 udma6 
 AdvancedPM=no WriteCache=enabled
 Drive conforms to: ATA/ATAPI-5 T13 1321D revision 1:  1 2 3 4 5

JesusCow · 10-27-2002, 12:47 AM

"top" results:

Code:

 12:41am  up 14 min,  1 user,  load average: 0.12, 0.30, 0.18
66 processes: 62 sleeping, 3 running, 1 zombie, 0 stopped
CPU states:  3.3% user,  0.7% system,  0.0% nice, 95.8% idle
Mem:   513952K av,  165212K used,  348740K free,       0K shrd,     620K buff
Swap:  995988K av,       0K used,  995988K free                   90928K cached

  PID USER     PRI  NI  SIZE  RSS SHARE STAT %CPU %MEM   TIME COMMAND
 1250 root      15   0  9372 9368  7068 R     1.7  1.8   0:01 gnome-terminal
  847 root       5 -10 82832  16M  5160 S <   1.3  3.3   0:17 X
 1095 root      15   0  6600 6600  5352 R     0.3  1.2   0:01 metacity
 1315 root      15   0  1028 1028   840 R     0.3  0.2   0:00 top
 1109 root      15   0 14408  14M  9596 S     0.1  2.8   0:01 nautilus
    1 root      15   0   480  480   428 S     0.0  0.0   0:04 init
    2 root      15   0     0    0     0 SW    0.0  0.0   0:00 keventd
    3 root      15   0     0    0     0 SW    0.0  0.0   0:00 kapmd
    4 root      34  19     0    0     0 SWN   0.0  0.0   0:00 ksoftirqd_CPU0
    5 root      15   0     0    0     0 SW    0.0  0.0   0:00 kswapd
    6 root      25   0     0    0     0 SW    0.0  0.0   0:00 bdflush
    7 root      15   0     0    0     0 SW    0.0  0.0   0:00 kupdated
    8 root      25   0     0    0     0 SW    0.0  0.0   0:00 mdrecoveryd
   65 root      15   0     0    0     0 SW    0.0  0.0   0:00 khubd
  511 root      15   0   540  540   460 S     0.0  0.1   0:00 syslogd
  515 root      15   0   428  428   376 S     0.0  0.0   0:00 klogd

and my "/sbin/hdparm -tT /dev/hda" results:

[root@localhost root]# /sbin/hdparm -tT /dev/hda

Code:

/dev/hda:
 Timing buffer-cache reads:   128 MB in  0.44 seconds =290.00 MB/sec
 Timing buffered disk reads:  64 MB in  1.87 seconds = 34.17 MB/sec

dnar · 10-27-2002, 01:46 AM

JesusCow -> hdparm is run on a drive not a partition. ie. /dev/hda

Looks good though, your running DMA obviously.

JesusCow · 10-27-2002, 01:18 AM

Quote:

Originally posted by dnar
JesusCow -> hdparm is run on a drive not a partition. ie. /dev/hda

Looks good though, your running DMA obviously.

oh ok, i didnt know if it made a differnce or not

im still learning at every step of the way

dnar · 10-27-2002, 01:21 AM

man hdparm, and heed the warnings!