Re: [lopsa-tech] High density servers

2013-04-04 Thread bergman
In the message dated: Thu, 04 Apr 2013 12:58:49 -0700, The pithy ruminations from Robert Hajime Lanning on were: => On 04/04/13 07:12, Leon Towns-von Stauber wrote: => Some observations: => The data center I am at, I have provisioned 4x 20A 120V circuits (billed => as 2x HA pair) per rack f

Re: [lopsa-tech] High density servers

2013-04-04 Thread Doug Hughes
They have deep racks if you have super deep servers, but 90% of the time the standard, run of the mill 40" deep rack is fine. Also, brackets exist to rotate the 0U PDUs 90 degrees (as shown in one of my earlier pictures), but by and large it's not a problem. We've only had to go with the 48" deep r

Re: [lopsa-tech] High density servers

2013-04-04 Thread Robert Hajime Lanning
On 04/04/13 07:12, Leon Towns-von Stauber wrote: I've been in datacenters like that: single circuit per rack, maybe 15- or 20-amp, maybe even 110V. (I'm thinking of a particular one in Fremont right now) I don't consider that kind of power density acceptable these days. Two or three 30A circ

Re: [lopsa-tech] High density servers

2013-04-04 Thread Doug Hughes
Re: pictures.. Yes I do, but I'm not sure that everybody can see them. !@$(&% facebook isn't letting me select public from the dropdown. I have pictures of a microcloud (8 servers in 3U) and a twin-squared (4 servers in 2U). No issues with cabling interrupting air flow and quite pretty to look at w

Re: [lopsa-tech] High density servers

2013-04-04 Thread Leon Towns-von Stauber
On Apr 3, 2013, at 2:58 PM, Nicholas Tang wrote: > What I will say, though, is that if anyone is considering blades, I'd > seriously consider Seamicro: http://seamicro.com/SM15000 > > This is an unsponsored, non-employee plug: I used one of their systems for > several months at my last job, an

Re: [lopsa-tech] High density servers

2013-04-04 Thread Leon Towns-von Stauber
On Apr 3, 2013, at 12:34 PM, Robert Hajime Lanning wrote: > Last time I evaluated going with the high density chassis (both 4x1 and > blades), I found that unless I went into a brand new data center that > had enough power to light a city, I was limited to about 16 actual > servers per rack. ("ac

Re: [lopsa-tech] High density servers

2013-04-03 Thread Nicholas Tang
A few comments from my perspective... while I'm not a huge fan of the 4 systems in 2u boxes, a lot of them are more dense, power-wise, than 1u boxes (at least in my experience - ours used shared power supplies, which helped) and so that makes up for some of the frustration (but also means that if o

Re: [lopsa-tech] High density servers

2013-04-03 Thread Andrew Hume
i am OCDish enough to fuss over cabling so i normally try to do my own. the one thing i did in this arena that people found remarkable (in the sense of making remarks, not necessarily earthshaking) was setting up a third vertical bar in the back of the rack. this really helped routing cables. (near

Re: [lopsa-tech] High density servers

2013-04-03 Thread Jeff Wasilko
On Wed, Apr 03, 2013 at 12:19:04PM -0700, Adrian Luff wrote: > Depending on the blade manufacturer you're talking about (sounds like HP) the > likelihood of the passive enclosure backplane causing a failure is near zero. > We have 4+ years of ~20,000 blades in c-class enclosures without a single

Re: [lopsa-tech] High density servers

2013-04-03 Thread bergman
In the message dated: Wed, 03 Apr 2013 13:46:03 -0500, The pithy ruminations from Matt Lawrence on <[lopsa-tech] High density servers> were: => This is a bit of a rant, so adjust your filters accordingly. => => I'm currently doing some work not really production datacenter

Re: [lopsa-tech] High density servers

2013-04-03 Thread Derek Balling
On Apr 3, 2013, at 3:34 PM, Robert Hajime Lanning wrote: > Last time I evaluated going with the high density chassis (both 4x1 and > blades), I found that unless I went into a brand new data center that > had enough power to light a city, I was limited to about 16 actual > servers per rack. ("act

Re: [lopsa-tech] High density servers

2013-04-03 Thread Robert Hajime Lanning
On 04.03.2013 11:46, Matt Lawrence wrote: This is a bit of a rant, so adjust your filters accordingly. I'm currently doing some work not really production datacenter (unless you ask the developers) that has a variety of systems. Some of the systems I'm dealing with are the 4 servers in 2U varie

Re: [lopsa-tech] High density servers

2013-04-03 Thread Adrian Luff
A few thoughts and observations from a longtime blade admin… Depending on the blade manufacturer you're talking about (sounds like HP) the likelihood of the passive enclosure backplane causing a failure is near zero. We have 4+ years of ~20,000 blades in c-class enclosures without a single inst

[lopsa-tech] High density servers

2013-04-03 Thread Matt Lawrence
This is a bit of a rant, so adjust your filters accordingly. I'm currently doing some work not really production datacenter (unless you ask the developers) that has a variety of systems. Some of the systems I'm dealing with are the 4 servers in 2U variety. It's a neat idea, but great care ne