Re: Systeme lent.

トップ ページ

このメッセージに返信
著者: Jean-Pierre Morin
日付:  
To: guilde
題目: Re: Systeme lent.
Le Samedi 31 Juillet 2004 20:48, Jerome KIEFFER a écrit :
> Le Sat, 31 Jul 2004 18:56:42 +0200
>
> Jean-Pierre Morin <jeanpierre.morin@???> a écrit :
> > Depuis quelques temps, il y a des moments ou mon
> > systeme est très lent.
> > Je suis en Mandrake 9.0, carte mère MSI VIAKT3,
> > processeur AMD XP1800 et 256 MO de memoire
> > et 2 disques IDE hda=20GO, hdb= 40GO.
> > J'ai fini par faire un hdparm -t -T dont voici le resultat:
> > ---------------
> > [root@duron dev]# hdparm -t -T /dev/hdb
> >
> > /dev/hdb:
> > Timing buffer-cache reads: 128 MB in 0.57 seconds =224.56 MB/sec
> > Timing buffered disk reads: 64 MB in 1.39 seconds = 46.04 MB/sec
>
> performances très honorables ....
>
> > [root@duron dev]# hdparm -t -T /dev/hda
> >
> > /dev/hda:
> > Timing buffer-cache reads: 128 MB in 0.56 seconds =228.57 MB/sec
> > Timing buffered disk reads: 64 MB in 581.82 seconds =112.64 kB/sec
>
> effectivement il y a un probleme.
> peux tu donner
> -le chipset (lspci)
> -les refs du disque (smartctl -a /dev/hda)
>
>
> Ca sent la fin de vie du disque dur ... commence par faire un backup de
> ce qui est important.
>
> ensuite ca peut être un probleme de DMA, correctible avec hdparm.


Pour répondre à Jerome et à Alain
lspci donne :
[root@duron tmp]# cat lspci.log
00:00.0 Host bridge: VIA Technologies, Inc. VT8367 [KT266]
00:01.0 PCI bridge: VIA Technologies, Inc. VT8367 [KT266 AGP]
00:06.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8139/8139C
(rev 10)
00:07.0 Multimedia audio controller: Ensoniq ES1371 [AudioPCI-97] (rev 08)
00:08.0 SCSI storage controller: Tekram Technology Co.,Ltd. TRM-S1040 (rev 01)
00:11.0 ISA bridge: VIA Technologies, Inc. VT8233A ISA Bridge
00:11.1 IDE interface: VIA Technologies, Inc. Bus Master IDE (rev 06)
00:11.2 USB Controller: VIA Technologies, Inc. USB (rev 23)
00:11.3 USB Controller: VIA Technologies, Inc. USB (rev 23)
01:00.0 VGA compatible controller: S3 Inc. 86c368 [Trio 3D/2X] (rev 02)

Je ne connais pas la cmd smartcl mais cat /proc/ide/ide0/hda donne :
Maxtor 52049H3

hdparm -ivtT /dev/hda? donne :
[root@duron tmp]# cat hdparm.log

/dev/hda1:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 3903732, start = 63
 Timing buffer-cache reads:   128 MB in  0.56 seconds =228.57 MB/sec
 Timing buffered disk reads:  64 MB in  3.94 seconds = 16.24 MB/sec


/dev/hda2:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 546210, start = 3903795
 Timing buffer-cache reads:   128 MB in  0.57 seconds =224.56 MB/sec
 Timing buffered disk reads:  64 MB in  3.28 seconds = 19.51 MB/sec


/dev/hda4:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 2, start = 4450005
 Timing buffered disk reads:  
/dev/hda5:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 3919797, start = 4450068
 Timing buffer-cache reads:   128 MB in  0.57 seconds =224.56 MB/sec
 Timing buffered disk reads:  64 MB in  2.10 seconds = 30.48 MB/sec


/dev/hda6:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 2040192, start = 8369928
 Timing buffer-cache reads:   128 MB in  0.57 seconds =224.56 MB/sec
 Timing buffered disk reads:  64 MB in  2.25 seconds = 28.44 MB/sec


/dev/hda7:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 6136767, start = 10410183
 Timing buffer-cache reads:   128 MB in  0.57 seconds =224.56 MB/sec
 Timing buffered disk reads:  64 MB in  2.21 seconds = 28.96 MB/sec


/dev/hda8:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 6136767, start = 16547013
 Timing buffer-cache reads:   128 MB in  0.57 seconds =224.56 MB/sec
 Timing buffered disk reads:  64 MB in 18.44 seconds =  3.47 MB/sec


/dev/hda9:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 2491/255/63, sectors = 6136767, start = 22683843
 Timing buffer-cache reads:   128 MB in  0.56 seconds =228.57 MB/sec
 Timing buffered disk reads:  64 MB in  2.26 seconds = 28.32 MB/sec


La racine etant sur /dev/hda9

Si c'est un probleme de DMA, que faut-il faire avec hdparm
pour tester et corriger ?

Bon dimanche.