[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: On very different journalling activity on 2 servers.

Nico Morrison <nico morrison micronicos com> wrote:
> Hello Folks,
> We have 2 (identical hardware) busy public 2U rack servers, both have
> several hundred users & peak email (for example) deliveries at 300/5min
> during the daytime.
> Both servers run RAID1 over 2 EIDE disk drives.
> One server is fine - it never has problems - it is running RH7.3 and CPU
> loads are normal.
> The other server has constant disk activity & kjournald at CPU load of
> 50/60/70% most of the time!  this machine is running RH7.2
> The same processes & loads are on both machines - can anyone tell me why one
> machine should have so much kjournald activity & the other not?
> Is it a difference between 7.2 & 7.3 or must it be another factor?

Usually, this is due to IDE drives running in PIO mode and not DMA mode.

> How can I find out?

Look at the output of `hdparm -i':

# hdparm -i /dev/hda


 Model=Maxtor 5T040H4, FwRev=TAH71DP0, SerialNo=T4J0N9BC
 Config={ Fixed }
 RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57
 BuffType=DualPortCache, BuffSize=2048kB, MaxMultSect=16, MultSect=16
 CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=80043264
 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 
 AdvancedPM=yes: disabled (255) WriteCache=enabled
 Drive conforms to: ATA/ATAPI-6 T13 1410D revision 0:  1 2 3 4 5 6

See the "*" next to UDMA2?  This disk is doing DMA.

You can manually force DMA mode, which is considered risky.  Or upgrade the
kernel, perhaps.

[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]