Velocity Reviews - Computer Hardware Reviews

Velocity Reviews > Newsgroups > Computing > NZ Computing > new subject What makes a Server a Server?

Reply
Thread Tools

new subject What makes a Server a Server?

 
 
Robert Cooze
Guest
Posts: n/a
 
      03-05-2005
In the bad old days a Server was a big room filling device with plenty
of teckie type in white dust coats milling around. previous threads talk
about desk tops running server app's. There are some hosting companys
using shop bought machines running XXXXdist or XXXXXos of some form or
another unattended in some office or NOC or converted shed. and what
about some home machines I have a machine that does samba file and print
sharing, Mail (bagging), it streams mp3 to other machines on the
network and also has a local web site on it.

comments? and HO

ps let the flame war start putting on asbestos suite
--
http://cooze.co.nz home of the RecyclerMan aka Robert Cooze

/ __/ / / / / /__ / / ___/ / __/ / / / |/ / /__ /
/ / / /_/ / / /_/ / _-' / __/ / / / /_/ / / /| / _-'
___\ ____/ ____/ /___/ /____/ /_/ ___\ ____/ /_/ /_/ |_/ /___/

----== Posted via Newsfeeds.Com - Unlimited-Uncensored-Secure Usenet News==----
http://www.newsfeeds.com The #1 Newsgroup Service in the World! 120,000+ Newsgroups
----= East and West-Coast Server Farms - Total Privacy via Encryption =----
 
Reply With Quote
 
 
 
 
Shane (aka froggy)
Guest
Posts: n/a
 
      03-05-2005
On Sun, 06 Mar 2005 10:15:25 +1300, Robert Cooze wrote:

> In the bad old days a Server was a big room filling device with plenty
> of teckie type in white dust coats milling around. previous threads talk
> about desk tops running server app's. There are some hosting companys
> using shop bought machines running XXXXdist or XXXXXos of some form or
> another unattended in some office or NOC or converted shed. and what
> about some home machines I have a machine that does samba file and print
> sharing, Mail (bagging), it streams mp3 to other machines on the
> network and also has a local web site on it.
>
> comments? and HO
>
> ps let the flame war start putting on asbestos suite


hehehe..
Something similar caught my attention recently..
Google runs ye olde pc (in clusters) with IDE drives (they were
bragging/commenting on the fact their FS has to cope with X amount of
drives failing everyday because they were IDE)
also I read somewhere yesterday they use a stripped down Red Hat (which
they have hacked/modifyed the hell out of)
--

Hardware, n.: The parts of a computer system that can be kicked

 
Reply With Quote
 
 
 
 
Robert Cooze
Guest
Posts: n/a
 
      03-05-2005
Shane (aka froggy) wrote:

> On Sun, 06 Mar 2005 10:15:25 +1300, Robert Cooze wrote:
>
>
>>In the bad old days a Server was a big room filling device with plenty
>>of teckie type in white dust coats milling around. previous threads talk
>>about desk tops running server app's. There are some hosting companys
>>using shop bought machines running XXXXdist or XXXXXos of some form or
>>another unattended in some office or NOC or converted shed. and what
>>about some home machines I have a machine that does samba file and print
>> sharing, Mail (bagging), it streams mp3 to other machines on the
>>network and also has a local web site on it.
>>
>>comments? and HO
>>
>>ps let the flame war start putting on asbestos suite

>
>
> hehehe..
> Something similar caught my attention recently..
> Google runs ye olde pc (in clusters) with IDE drives (they were
> bragging/commenting on the fact their FS has to cope with X amount of
> drives failing everyday because they were IDE)
> also I read somewhere yesterday they use a stripped down Red Hat (which
> they have hacked/modifyed the hell out of)

Clustering that's what I want to pay with never had enough working
machines spare to play with.

PS & OT I think that Orcon is not in the news game any more just by
looking at the advertising put on my original post is that spam? or am
I paying money to Orcon so they can put adds on my thoughts

--
http://cooze.co.nz home of the RecyclerMan aka Robert Cooze

/ __/ / / / / /__ / / ___/ / __/ / / / |/ / /__ /
/ / / /_/ / / /_/ / _-' / __/ / / / /_/ / / /| / _-'
___\ ____/ ____/ /___/ /____/ /_/ ___\ ____/ /_/ /_/ |_/ /___/

----== Posted via Newsfeeds.Com - Unlimited-Uncensored-Secure Usenet News==----
http://www.newsfeeds.com The #1 Newsgroup Service in the World! 120,000+ Newsgroups
----= East and West-Coast Server Farms - Total Privacy via Encryption =----
 
Reply With Quote
 
The Other Guy
Guest
Posts: n/a
 
      03-06-2005
Robert Cooze wrote:
> PS & OT I think that Orcon is not in the news game any more just by
> looking at the advertising put on my original post is that spam? or am
> I paying money to Orcon so they can put adds on my thoughts


Orcon outsources their news service to newsfeeds.com who add the message
to all their incoming posts.

Most Orcon users now use a free tect-only service to post their
messages. Orcon could provide a good full-text newsfeed at almost no
cost to them, instead they outsource to a crappy binary provider at
minimal cost.

The Other Guy
 
Reply With Quote
 
Enkidu
Guest
Posts: n/a
 
      03-06-2005
Shane (aka froggy) wrote:
> On Sun, 06 Mar 2005 10:15:25 +1300, Robert Cooze wrote:
>
> hehehe..
> Something similar caught my attention recently..
> Google runs ye olde pc (in clusters) with IDE drives (they were
> bragging/commenting on the fact their FS has to cope with X amount of
> drives failing everyday because they were IDE)
> also I read somewhere yesterday they use a stripped down Red Hat (which
> they have hacked/modifyed the hell out of)
>

Google runs rack servers. I can't remember where I read it.
If one of their servers dies, they don't bother to try to
find it though! They are not so much clusters as *hundreds*
of servers running parallel tasks.

What makes you think that disks fail because they are IDE?
I've had more than enough SCSIs fail to know that they are
not immune.

Cheers,

Cliff

--

Barzoomian the Martian - http://barzoomian.blogspot.com
 
Reply With Quote
 
Robert Cooze
Guest
Posts: n/a
 
      03-06-2005
The Other Guy wrote:
> Robert Cooze wrote:
>
>> PS & OT I think that Orcon is not in the news game any more just by
>> looking at the advertising put on my original post is that spam? or
>> am I paying money to Orcon so they can put adds on my thoughts

>
>
> Orcon outsources their news service to newsfeeds.com who add the message
> to all their incoming posts.
>
> Most Orcon users now use a free tect-only service to post their
> messages. Orcon could provide a good full-text newsfeed at almost no
> cost to them, instead they outsource to a crappy binary provider at
> minimal cost.
>
> The Other Guy

That has been on my to do list is to find a good text news source...
pref in nz,



--
http://cooze.co.nz home of the RecyclerMan aka Robert Cooze

/ __/ / / / / /__ / / ___/ / __/ / / / |/ / /__ /
/ / / /_/ / / /_/ / _-' / __/ / / / /_/ / / /| / _-'
___\ ____/ ____/ /___/ /____/ /_/ ___\ ____/ /_/ /_/ |_/ /___/

----== Posted via Newsfeeds.Com - Unlimited-Uncensored-Secure Usenet News==----
http://www.newsfeeds.com The #1 Newsgroup Service in the World! 120,000+ Newsgroups
----= East and West-Coast Server Farms - Total Privacy via Encryption =----
 
Reply With Quote
 
David Preece
Guest
Posts: n/a
 
      03-06-2005
The Other Guy wrote:

> Orcon could provide a good full-text newsfeed at almost no
> cost to them, instead they outsource to a crappy binary provider at
> minimal cost.


I always get the impression that newsfeeds of any real scale are a bitch
to administer. There's also the bigger question of whether or not it's
worth sucking down a 50GB/day (or however big it is) news feed for the
100 or so users that actually use it, when you could just outsource the
problem to someone else.

Dave
 
Reply With Quote
 
Shane (aka froggy)
Guest
Posts: n/a
 
      03-06-2005
On Sun, 06 Mar 2005 15:42:23 +1300, Enkidu wrote:

> Shane (aka froggy) wrote:
>> On Sun, 06 Mar 2005 10:15:25 +1300, Robert Cooze wrote:
>>
>> hehehe..
>> Something similar caught my attention recently..
>> Google runs ye olde pc (in clusters) with IDE drives (they were
>> bragging/commenting on the fact their FS has to cope with X amount of
>> drives failing everyday because they were IDE)
>> also I read somewhere yesterday they use a stripped down Red Hat (which
>> they have hacked/modifyed the hell out of)
> >

> Google runs rack servers. I can't remember where I read it.
> If one of their servers dies, they don't bother to try to
> find it though! They are not so much clusters as *hundreds*
> of servers running parallel tasks.
>
> What makes you think that disks fail because they are IDE?
> I've had more than enough SCSIs fail to know that they are
> not immune.
>
> Cheers,
>
> Cliff


I er googled for the info
http://www.zdnet.co.uk/print/?TYPE=s...445t-20000012c
<Q>
As the scale of the operation increases, it introduces some particular
problems that would not be an issue on smaller systems. For instance,
Google uses IDE drives for all its storage. They are fast and cheap, but
not highly reliable. To help deal with this, Google developed its own file
system -- called the Google File System, or GFS -- which assumes an
individual unit of storage can go away at any time either because of a
crash, a lost disk or just because someone stepped on a cable.
</Q>
<Q>
There are no disk arrays within individual PCs; instead Google stores
every bit of data in triplicate on three machines on three racks on three
data switches to make sure there is no single point of failure between you
and the data.
</Q>
to be honest Im not sure if that second quote aids my cause or yours
(seems they call their machines w/ever takes their fancy)
or it could be calling them peecee's to make it easier to read fer simple
folk like me

--

Hardware, n.: The parts of a computer system that can be kicked

 
Reply With Quote
 
Shane (aka froggy)
Guest
Posts: n/a
 
      03-06-2005
On Sun, 06 Mar 2005 18:36:45 +1300, Shane (aka froggy) wrote:

> On Sun, 06 Mar 2005 15:42:23 +1300, Enkidu wrote:
>
>> Shane (aka froggy) wrote:
>>> On Sun, 06 Mar 2005 10:15:25 +1300, Robert Cooze wrote:
>>>
>>> hehehe..
>>> Something similar caught my attention recently..
>>> Google runs ye olde pc (in clusters) with IDE drives (they were
>>> bragging/commenting on the fact their FS has to cope with X amount of
>>> drives failing everyday because they were IDE)
>>> also I read somewhere yesterday they use a stripped down Red Hat (which
>>> they have hacked/modifyed the hell out of)
>> >

>> Google runs rack servers. I can't remember where I read it.
>> If one of their servers dies, they don't bother to try to
>> find it though! They are not so much clusters as *hundreds*
>> of servers running parallel tasks.
>>
>> What makes you think that disks fail because they are IDE?
>> I've had more than enough SCSIs fail to know that they are
>> not immune.
>>
>> Cheers,
>>
>> Cliff

>
> I er googled for the info
> http://www.zdnet.co.uk/print/?TYPE=s...445t-20000012c
> <Q>
> As the scale of the operation increases, it introduces some particular
> problems that would not be an issue on smaller systems. For instance,
> Google uses IDE drives for all its storage. They are fast and cheap, but
> not highly reliable. To help deal with this, Google developed its own file
> system -- called the Google File System, or GFS -- which assumes an
> individual unit of storage can go away at any time either because of a
> crash, a lost disk or just because someone stepped on a cable.
> </Q>
> <Q>
> There are no disk arrays within individual PCs; instead Google stores
> every bit of data in triplicate on three machines on three racks on three
> data switches to make sure there is no single point of failure between you
> and the data.
> </Q>
> to be honest Im not sure if that second quote aids my cause or yours
> (seems they call their machines w/ever takes their fancy)
> or it could be calling them peecee's to make it easier to read fer simple
> folk like me


er.. scrolling up the page a bit I found this
<Q>
Google runs its systems on cheap, no-name IU and 2U servers -- so cheap that
Google refers to them as PCs. After all each one has a standard x86 PC
processor, standard IDE hard disk, and standard PC reliability - which
means it is expected to fail once in three years.
</Q>
so it appears thats why I was confused
(and you were right)



--

Hardware, n.: The parts of a computer system that can be kicked

 
Reply With Quote
 
Enkidu
Guest
Posts: n/a
 
      03-06-2005
Shane (aka froggy) wrote:
> On Sun, 06 Mar 2005 18:36:45 +1300, Shane (aka froggy) wrote:
>
>
>>On Sun, 06 Mar 2005 15:42:23 +1300, Enkidu wrote:
>>
>>
>>>Shane (aka froggy) wrote:
>>>
>>>>On Sun, 06 Mar 2005 10:15:25 +1300, Robert Cooze wrote:
>>>>
>>>>hehehe..
>>>>Something similar caught my attention recently..
>>>>Google runs ye olde pc (in clusters) with IDE drives (they were
>>>>bragging/commenting on the fact their FS has to cope with X amount of
>>>>drives failing everyday because they were IDE)
>>>>also I read somewhere yesterday they use a stripped down Red Hat (which
>>>>they have hacked/modifyed the hell out of)
>>>
>>> >
>>>Google runs rack servers. I can't remember where I read it.
>>>If one of their servers dies, they don't bother to try to
>>>find it though! They are not so much clusters as *hundreds*
>>>of servers running parallel tasks.
>>>
>>>What makes you think that disks fail because they are IDE?
>>>I've had more than enough SCSIs fail to know that they are
>>>not immune.
>>>
>>>Cheers,
>>>
>>>Cliff

>>
>>I er googled for the info
>>http://www.zdnet.co.uk/print/?TYPE=s...445t-20000012c
>><Q>
>>As the scale of the operation increases, it introduces some particular
>>problems that would not be an issue on smaller systems. For instance,
>>Google uses IDE drives for all its storage. They are fast and cheap, but
>>not highly reliable. To help deal with this, Google developed its own file
>>system -- called the Google File System, or GFS -- which assumes an
>>individual unit of storage can go away at any time either because of a
>>crash, a lost disk or just because someone stepped on a cable.
>></Q>
>><Q>
>>There are no disk arrays within individual PCs; instead Google stores
>>every bit of data in triplicate on three machines on three racks on three
>>data switches to make sure there is no single point of failure between you
>>and the data.
>></Q>
>>to be honest Im not sure if that second quote aids my cause or yours
>>(seems they call their machines w/ever takes their fancy)
>>or it could be calling them peecee's to make it easier to read fer simple
>>folk like me

>
>
> er.. scrolling up the page a bit I found this
> <Q>
> Google runs its systems on cheap, no-name IU and 2U servers -- so cheap that
> Google refers to them as PCs. After all each one has a standard x86 PC
> processor, standard IDE hard disk, and standard PC reliability - which
> means it is expected to fail once in three years.
> </Q>
> so it appears thats why I was confused
> (and you were right)
>

No worries. I wasn't trying to score points or anything! I
wonder if they will or do use blade servers?

Frankly the logistics of keeping hundreds of beige boxes
around would be horrendous. I know from experience that just
one beige box in a rack disrupts everything.

Cheers,

Cliff

--

Barzoomian the Martian - http://barzoomian.blogspot.com
 
Reply With Quote
 
 
 
Reply

Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are On
Pingbacks are On
Refbacks are Off


Similar Threads
Thread Thread Starter Forum Replies Last Post
Understanding the DHCP Server Client conversation (very intresting subject) Weamfox MCSE 13 03-05-2008 10:00 AM
Subject: impersonate="True" gives login (null) for SQL Server acce Pedro Gonçalves ASP .Net Security 5 06-30-2006 02:04 PM
No Subject for this subject George MCAD 0 05-20-2005 10:19 AM
Add/Remove Programs Help Kinda Wierd Do Not Ignore Terrable Subject JustIgnore The Subject Oops Whatever Duh Samuel Townsend Computer Support 0 10-13-2004 12:49 AM
Can't see Subject when composing new message in Outlook 2002 Steve Freides Computer Support 0 11-17-2003 02:00 AM



Advertisments