CPU count (May 13 2009)

Message boards : Technical News : CPU count (May 13 2009)

Author	Message
Matt Lebofsky Volunteer moderator Project administrator Project developer Project scientist Send message Joined: 1 Mar 99 Posts: 1379 Credit: 74,079 RAC: 0	Message 894273 - Posted: 13 May 2009, 19:24:37 UTC
	No real server news today, but I'll respond to a couple things mentioned in the previous thread. I said we have about 150 CPUs in our server fold. Of course, looking at the list of machines on the server status page you see about 40. First, this isn't a complete list - it only contains public facing or critical servers. We have a lot of other systems that are doing tangential tasks or behind-the-scenes stuff. We also have several appliances (like the NAS's) which contain multiple CPUs as well. Still, this number may be inflated a bit due to hyperthreading on some servers. I think the actual number of physical CPUs is still above 100 though. Plus, as I was calculating this just now I found that two of the CPUs on sidious have apparently died. This is no surprise - it's a used/experimental machine and had CPU issues since day one, which is why it is the replica mysql server and not the master. The talk (which happens next week) should be viewable over the net after it happens. I don't think we're going to do live streaming or anything like that. We're going to meet and discuss early next week what our options are. - Matt ____________ -- BOINC/SETI@home network/web/science/development person -- "Any idiot can have a good idea. What is hard is to do it." - Jeanne-Claude
	ID: 894273 ·

Johnney Guinness Volunteer tester Send message Joined: 11 Sep 06 Posts: 2946 Credit: 2,306,100 RAC: 24	Message 894278 - Posted: 13 May 2009, 19:38:10 UTC
	Matt, I'm looking forward to hearing your speech, i know you put a lot of time and effort into it. Programming is easy, writing public speeches is difficult...LOL Thanks Matt, John. ____________
	ID: 894278 ·

Matt Lebofsky Volunteer moderator Project administrator Project developer Project scientist Send message Joined: 1 Mar 99 Posts: 1379 Credit: 74,079 RAC: 0	Message 894299 - Posted: 13 May 2009, 20:27:29 UTC - in response to Message 894278.
	writing public speeches is difficult... Actually writing public speeches is easy for me. The hard part is shutting up once I start speaking. Anyway, I get only 20 minutes, saving time so Jeff could talk about the NTPCkr. And most of the time so far has been spent fighting with OpenOffice Impress. - Matt ____________ -- BOINC/SETI@home network/web/science/development person -- "Any idiot can have a good idea. What is hard is to do it." - Jeanne-Claude
	ID: 894299 ·

Danny Sosebee Send message Joined: 10 Jun 02 Posts: 53 Credit: 1,022,592 RAC: 0	Message 894311 - Posted: 13 May 2009, 21:01:31 UTC - in response to Message 894299.
	The hard part is shutting up once I start speaking. ROFLMAO I too am looking forward to hearing your talk. I am assuming it'll be made available somewhere on the S@H web site, or at least a link to it. Thanks for all the great work you guys do! ____________
	ID: 894311 ·

Speedy Volunteer tester Send message Joined: 26 Jun 04 Posts: 587 Credit: 3,628,391 RAC: 4,500	Message 894343 - Posted: 13 May 2009, 22:36:01 UTC
	Thanks for all the hard work Matt, Jeff & team in the lab. I'm the opposite I find it really hard to write a speach, best of luck with your speach I look ford to reading or viewing. Out of all the CPUs you have in the server room are any used solely to processes Seti? If the answer is yes how many workunits a day does it process? ____________ Live in NZ y not join Smile City?
	ID: 894343 ·

John McLeod VII Volunteer developer Volunteer tester Send message Joined: 15 Jul 99 Posts: 22343 Credit: 440,201 RAC: 100	Message 894469 - Posted: 14 May 2009, 2:07:23 UTC - in response to Message 894273.
	{SNIP] Plus, as I was calculating this just now I found that two of the CPUs on sidious have apparently died. - Matt [SNIP] Is this, perhaps, one of the causes of the problems with the replica DB? ____________ BOINC WIKI
	ID: 894469 ·

Virtual Boss* Send message Joined: 4 May 08 Posts: 410 Credit: 5,822,037 RAC: 359	Message 894500 - Posted: 14 May 2009, 4:55:45 UTC - in response to Message 894469.
	{SNIP] Plus, as I was calculating this just now I found that two of the CPUs on sidious have apparently died. - Matt [SNIP] Is this, perhaps, one of the causes of the problems with the replica DB? Ahhhh . . . Sidious is becoming Insidious
	ID: 894500 ·

NewtonianRefractor Volunteer tester Send message Joined: 19 Sep 04 Posts: 495 Credit: 225,412 RAC: 0	Message 904601 - Posted: 7 Jun 2009, 0:33:10 UTC
	How does a CPU just die and the server continue to function? ____________
	ID: 904601 ·

Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 5291 Credit: 41,851,748 RAC: 32,525	Message 904610 - Posted: 7 Jun 2009, 1:06:31 UTC - in response to Message 904601.
	How does a CPU just die and the server continue to function? If there are 2, 4, 8 or 16 CPUs on a server, one can die & it will still function. If there is only one CPU & it dies, then the server dies with it. ____________ Grant Darwin NT.
	ID: 904610 ·

AlphaLaser Volunteer tester Send message Joined: 22 Aug 06 Posts: 262 Credit: 45,707 RAC: 0	Message 904669 - Posted: 7 Jun 2009, 7:11:39 UTC - in response to Message 904601. Last modified: 7 Jun 2009, 7:16:48 UTC
	How does a CPU just die and the server continue to function? Some very high end servers can also implement Lockstep processing. It's somewhat analogous to RAID 1 but for CPU's. Likewise, similar technology exists for RAM redundacy such as Chipkill, which enables recovery from a hardware failure of an entire RAM module. SETI doesn't necessarily use these but it goes to show that sometimes what makes server platforms unique and not just a rebranding of consumer chips is their certified ability to recover from disaster scenarios that are usually showstoppers for a normal desktop. In IT world it is called Reliability, Availability, and Serviceablity (RAS) and is important in mission critical and business mainframes. ____________
	ID: 904669 ·

Carl Send message Joined: 29 Jul 09 Posts: 6 Credit: 5,762 RAC: 0	Message 922445 - Posted: 30 Jul 2009, 15:13:02 UTC - in response to Message 894273.
	150 you know matt thats really not so many say if you worked out from helpers like me what would that bring your processing power up to. i fiddle and build pc,s if i were able to afford the power bill i have four quad core pc,s plus about twenty working 3gig cpu p5 units ad in a couple of dual core macs to that i have whoa at least 36 some on a network. here is a doozy over all us voulenteer,s what would you think we have its mind bogleing really. id let you use the lot but i cant afford the power and when gaming at friends while out for a smoke i really have seen sparks jumping across power lines. say thirty pc,s in one house. i admit a have three zeon quads but the cpu,s are at best 2.8gig. and they eat power. i would love to see some guess of the procesing power of all the voulenteers even a wild gues would be fun. sincerly carl portman perth wa
	ID: 922445 ·

zpm Volunteer tester Send message Joined: 25 Apr 08 Posts: 284 Credit: 975,677 RAC: 0	Message 922448 - Posted: 30 Jul 2009, 15:32:38 UTC - in response to Message 922445.
	xps 420, q6600 2.4GHZ , gtx 260 216 core. 32 bit vista P-mobile Dell Laptop 1.6 GHZ P4 HT, 3.06 GHZ, PCI-E 9400 GT, xp 32 bit. P4 2.8, pci 9400 gt, various projects ____________ I recommend Secunia PSI: http://secunia.com/vulnerability_scanning/personal/ Go Georgia Tech.
	ID: 922448 ·

Message boards : Technical News : CPU count (May 13 2009)