Hi,
I installed a new disk to my small home server in order to have a
backup of the previous disk. The backup is intended to run during
late night hours using rsync.
First time, I rsynced some system directories to the second disk and
it worked quickly.
Now, I'm trying to rsync a big encrypted data partition to another
(almost same size) encrypted data partition in the second disk. And
speed is abysmal.
# iostat
tin tout KB/t t/s MB/s KB/t t/s MB/s KB/t t/s MB/s KB/t
t/s MB/s us ni sy in id
0 10 42.13 16 0.66 42.39 11 0.46 63.10 9 0.56 63.86
7 0.41 1 0 6 7 86
Both data partitions are using softraid, like
`bioctl -c C -l /dev/sdx.k softraid0`
# top
PID USERNAME PRI NICE SIZE RES STATE WAIT TIME CPU
COMMAND
11587 root 64 0 5700K 1708K run/0 - 264:28 51.07%
rsync
Which seems to me as a very high cpu usage for a simple
`rsync -a` command, no gzipped.
Both disks are SATA, 1TB, Samsung.
Origin: SAMSUNG HD103UJ
Destiny: SAMSUNG HD103SJ
sd2 at scsibus2 targ 1 lun 0: <OPENBSD, SR CRYPTO, 005> SCSI2 0/direct
fixed
sd2: 922747MB, 512 bytes/sector, 1889787792 sectors
softraid0: volume sd2 is roaming, it used to be sd1, updating metadata
syncing disks... done
My system:
OpenBSD 5.2-current (GENERIC.MP) #107: Mon Nov 19 12:58:00 MST 2012
[email protected]:/usr/src/sys/arch/i386/compile/GENERIC.MP
cpu0: Intel(R) Atom(TM) CPU N270 @ 1.60GHz ("GenuineIntel"
686-class) 1.60 GHz
Why does this happen? What can I do to improve the crawling speed?
--
Luis P. Mendes
