Re: [bitfolk] Interesting (?) Linux RAID-10 performance caveat

Author: Andy Smith
Date:
To: users
Subject: Re: [bitfolk] Interesting (?) Linux RAID-10 performance caveat

gpg: Signature made Fri May 31 02:36:40 2019 UTC
gpg: using DSA key 2099B64CBF15490B
gpg: Good signature from "Andy Smith <andy@strugglers.net>" [unknown]
gpg: aka "Andrew James Smith <andy@strugglers.net>" [unknown]
gpg: aka "Andy Smith (UKUUG) <andy.smith@ukuug.org>" [unknown]
gpg: aka "Andy Smith (BitFolk Ltd.) <andy@bitfolk.com>" [unknown]
gpg: aka "Andy Smith (Linux User Groups UK) <andy@lug.org.uk>" [unknown]
gpg: aka "Andy Smith (Cernio Technology Cooperative) <andy.smith@cernio.com>" [unknown]

On Thu, May 30, 2019 at 11:47:01PM +0000, Andy Smith wrote:
> Clearly it is the imbalance (of device performances) because it
> won't happen if they both perform the same. The question is why can't
> RAID-10 cope with the unbalanced devices? Is it by design? Is it
> generally known? Can it be fixed? etc.

Well here's some of the answer!

    https://marc.info/?l=linux-raid&m=155926702609282&w=2

This allows RAID-1 to pick most idle device to do a read from:

    https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/drivers/md/raid1.c?id=9dedf60313fa4dddfd5b9b226a0ef12a512bf9dc

So that explains how Linux RAID-1 is able to prefer fastest device
to read from. Same improvement was never done for Linux RAID-10.
Don't know if it could be.

Cheers,
Andy

--
https://bitfolk.com/ -- No-nonsense VPS hosting

This message is part of the following thread:
	the complete thread tree sorted by date
	Andy Smith at

Re: [bitfolk] Interesting (?) Linux RAID-10 performance cave…