Re: RAID-10 initial sync is CPU-limited

[John Robinson <john.robinson@anonymous.org.uk>]

On 04/01/2011 16:41, Jan Kasprzak wrote:
> John Robinson wrote:
[...]
> 	Yes, I am aware of this. A single disk is able to do about
> 147 MB/s according to hdparm -t. However (a big "however"),
> my usage pattern rarely issues big/sequential requests, and for more
> random load the total throughput generated by all disks will be
> much lower and the disks themselves become the bottleneck.

Sure, but doing a resync does require huge sequential reads and writes.

> 	I have just been suriprised that for initial RAID-10 resync
> the bottleneck is in the (single) CPU.
>
> : but because you're throttled by the PCIe x4 interface, you're only
> : getting about half of what your discs could do.
>
> 	I have not talked about PCIe x4, but SAS 4-way multichannel.

My bad. Same effect in this situation though.

> Anyway, my SAS controller is connected by PCIe 2.0 x8, which equals
> to (if I read Wikipedia correctly :-) 32 Gbit/s, i.e. 2 GByte/s.
> So PCIe is not a bottleneck here. SAS is, and I am aware of that.

Which is why the the md kernel threads appear to be using 100% of CPU, 
they're blocked waiting for I/O. (And possibly RAM, per my other reply 
to this thread.)

Cheers,

John.