[Top] [All Lists]

Re: Intel X25-E running Linux using XFS

To: Pavel Machek <pavel@xxxxxxx>
Subject: Re: Intel X25-E running Linux using XFS
From: Justin Piszcz <jpiszcz@xxxxxxxxxxxxxxx>
Date: Fri, 12 Dec 2008 15:23:19 -0500 (EST)
Cc: smartmontools-support@xxxxxxxxxxxxxxxxxxxxx, smartmontools-database-owner@xxxxxxxxxxxxxxxxxxxxx, linux-raid@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, linux-ide@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx, Alan Piszcz <ap@xxxxxxxxxxxxx>
In-reply-to: <20081212185803.GE11974@xxxxxxxxxx>
References: <alpine.DEB.1.10.0811271257470.2233@xxxxxxxxxxxxxxxx> <20081212185803.GE11974@xxxxxxxxxx>
User-agent: Alpine 1.10 (DEB 962 2008-03-14)

On Fri, 12 Dec 2008, Pavel Machek wrote:


Due to the 100k write cycle lifetime, I will not be performing any more
benchmarks on the SSD itself, such benchmarks are available on
techreport.com but just wanted to send out the smart data for the
smartmontools list and point out it is working with linux+ich7+xfs.

Overall, whenever I do anything now its just like the entire machine is
sitting in a ramdisk (similar when you boot knoppix and load to ramdisk).

The techreport benchmarks are here:

Actually I'd like to know... how does it behave during powerfails
while it is being written to?

Flashes I seen (USB / SD) developed bad sectors in that case, and
ext2/ext3 can't handle that. (And I don't think xfs can handle that

I have a UPS for all of my machines, so that will not be a problem in my case. I do not wish to trash a $720 SSD or my current install, if someone else wants to try feel free though :)

With barriers, presumably it would be safe-- but as always, a UPS/and barriers and/or RAID, there is no excuse not to have regular backups incase of a failure at any time..

I do recall however one instance where there was an apt-get dist-upgrade going and the power was cut to a machine on purpose (before/not using barriers) and suffice to say-- it got mucked/suffered many corruptions
all over the place.


<Prev in Thread] Current Thread [Next in Thread>