On Thu, 2013-04-11 at 13:38 -0400, Egor Sanin wrote:
On 4/4/13, Len Ovens <len(a)ovenwerks.net> wrote:
I don't know if it makes any difference, but
hard drives stream off the
outside of the disk faster than the inside. So using a partition on the
high half of the drive will stream data faster.
The small print being that this is only true for a Hard Disk Drives
(HDD), not true for a Solid State Drive (SSD) which are not uncommon
these days.
True, but I still have doubts that the HDDs are the bottlenecks. They
aren't that slow and they've got several heads.
Other factors seem to be more important.
When I e.g. move a window, I get audible gaps without getting xruns,
while the audio session is that small, that everything is, resp. should
be in the RAM.
IOW I'm experiencing and I experienced all kinds of inexplicable issues
and IMO it's more likely that something is really fishy, than something
like using 1 instead of 2 drives does cause an issue.
It can't harm to use several drives, but I experienced using 1 drive
only doesn't cause (additional) issues. I own several drives myself and
usually I use 2 drives. Everybody with several drives could make tests
and use one drive only for a test. It shouldn't make a difference.
[rocketmouse@archlinux 02song.a]$ service rtirq status
PID CLS RTPRIO NI PRI %CPU STAT COMMAND
36 FF 90 - 130 0.0 S irq/8-rtc0
197 FF 85 - 125 0.0 S irq/18-snd_hdsp
234 FF 80 - 120 0.0 S irq/20-snd_ice1
236 FF 79 - 119 0.0 S irq/21-snd_ice1
90 FF 75 - 115 0.0 S irq/19-ehci_hcd
93 FF 75 - 115 0.0 S irq/16-ohci_hcd
107 FF 74 - 114 0.1 S irq/17-ohci_hcd
113 FF 73 - 113 0.0 S irq/17-ohci_hcd
34 FF 70 - 110 0.0 S irq/1-i8042
24 FF 50 - 90 0.0 S irq/9-acpi
50 FF 50 - 90 0.0 S irq/42-radeon
95 FF 50 - 90 0.0 S irq/14-pata_ati
96 FF 50 - 90 0.0 S irq/15-pata_ati
101 FF 50 - 90 0.1 S irq/22-ahci
195 FF 50 - 90 0.0 S irq/7-parport0
493 FF 50 - 90 0.0 S irq/43-enp3s0
3 FF 1 - 41 0.1 S ksoftirqd/0
13 FF 1 - 41 0.1 S ksoftirqd/1
[rocketmouse@archlinux 02song.a]$ grep 18: /proc/interrupts
18: 24 19924 IO-APIC-fasteoi snd_hdspm
Regards,
Ralf