Dear Waitman,
Testing the SSD drive, before installing it on the squid, showed huge
performance advantage in IOPS, read/write. So, I thought that this will
solve the problems I had with HDD.
But it was not so, look at this output:
12:39:35 PM CPU %user %nice %sys %iowait %irq %soft %steal
%idle intr/s
12:39:37 PM all 2.87 0.00 2.25 44.44 0.12 3.50 0.00
46.82 11666.50
12:39:37 PM 0 0.00 0.00 0.00 0.00 0.50 4.50 0.00
95.00 4764.00
12:39:37 PM 1 0.00 0.00 0.50 4.98 0.00 2.49 0.00
92.04 2097.50
12:39:37 PM 2 11.56 0.00 8.54 76.88 0.00 3.02 0.00
0.00 1977.50
12:39:37 PM 3 0.50 0.00 0.00 95.52 0.50 3.48 0.00
0.00 2827.50
This is a moment before the system went down, the IO is up high.
Waitman Gobble-2 wrote:
>
>
> smaugadi wrote:
>> Dear ALL,
>> We have a squid server with high volume of traffic, 200 – 300 MB.
>> The server is in transparent mode and using 18GB of ramdisk. With this
>> configuration performance is very good (after optimizing the squid and
>> the linux machine).
>> The problem is the small size of cache directory.
>> Since IO is a big issue with squid we purchased the intel ssd x25-m 160gb
>
> hmmmm, i have not yet experimented with an ssd, but i've read that it's
> advised to disable swap because heavy reads/writes kill the thing. the
> information was in regards to using an ssd on a netbook running linux -
> (for example running windows on the netbook with an ssd is certain
> death, unavoidable doom - as you probably know windows machines read and
> write to the disk like there's no tomorrow, and for no real good reason
> - they swap just for the heck of it, even just turning the thing on it
> starts swapping)
>
> so... it would make sense to me that you're going to experience troubles
> running a high traffic cache on an ssd.
>
> Waitman
>
>
>
>
>
>
-- View this message in context: http://www.nabble.com/Squid-high-bandwidth-IO-issue-%28ramdisk-SSD%29-tp24775448p24776249.html Sent from the Squid - Users mailing list archive at Nabble.com.Received on Sun Aug 02 2009 - 09:43:21 MDT
This archive was generated by hypermail 2.2.0 : Sun Aug 02 2009 - 12:00:02 MDT