Deluge (Jan 27 2010)


log in

Advanced search

Message boards : Technical News : Deluge (Jan 27 2010)

Author Message
Profile Matt Lebofsky
Volunteer moderator
Project administrator
Project developer
Project scientist
Avatar
Send message
Joined: 1 Mar 99
Posts: 1388
Credit: 74,079
RAC: 0
United States
Message 966228 - Posted: 27 Jan 2010, 23:23:25 UTC

As predicted, the science secondary did indeed catch up to the primary again, so all's well on that front (for now). And in case anybody noticed, we quickly turned the splitters/assimilators off for a bit to replace the failing drive on thumper - something we planned to do during the outage yesterday but couldn't. Easy squeasy - I'm glad we pay for Sun service on that system as drives are going fast. I can safely say the rumors that SATA drives fail frequently are true.

What you may notice is our servers being clogged for a spell, as Eric just turned the astropulse splitters back on (hooray!). We'll see if all goes well on that front - it's been a while and certain parts of the engine may need oil.

- 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

Profile BilBg
Volunteer tester
Avatar
Send message
Joined: 27 May 07
Posts: 2563
Credit: 5,855,911
RAC: 2,336
Bulgaria
Message 966379 - Posted: 28 Jan 2010, 12:39:22 UTC - in response to Message 966228.


..... I can safely say the rumors that SATA drives fail frequently are true. ...
- Matt


You mean all brands of SATA drives?!

Or are they just Western Digital?
What brand/model/capacity?

I don't think Seagate will "fail frequently".

____________



- ALF - "Find out what you don't do well ..... then don't do it!" :)

Cosmic_Ocean
Avatar
Send message
Joined: 23 Dec 00
Posts: 2233
Credit: 8,422,106
RAC: 4,049
United States
Message 966410 - Posted: 28 Jan 2010, 15:28:44 UTC - in response to Message 966379.


..... I can safely say the rumors that SATA drives fail frequently are true. ...
- Matt


You mean all brands of SATA drives?!

Or are they just Western Digital?
What brand/model/capacity?

I don't think Seagate will "fail frequently".

I don't have any problems with WD. True, I've seen a lot of comments on newegg about some batches that are prone to premature failure, but out of the 50+ that I've bought in the past 7 years, I've only had one failure, and it was in a raid5, so I didn't lose anything.
____________

Linux laptop uptime: 1484d 22h 42m
Ended due to UPS failure, found 14 hours after the fact

OzzFan
Volunteer tester
Avatar
Send message
Joined: 9 Apr 02
Posts: 13541
Credit: 29,277,181
RAC: 15,237
United States
Message 966428 - Posted: 28 Jan 2010, 17:05:10 UTC - in response to Message 966410.


..... I can safely say the rumors that SATA drives fail frequently are true. ...
- Matt


You mean all brands of SATA drives?!

Or are they just Western Digital?
What brand/model/capacity?

I don't think Seagate will "fail frequently".

I don't have any problems with WD. True, I've seen a lot of comments on newegg about some batches that are prone to premature failure, but out of the 50+ that I've bought in the past 7 years, I've only had one failure, and it was in a raid5, so I didn't lose anything.


I've had nothing but problems with WD. Out of the two dozen I've owned over the years (from giving them another try, or because they were given to me), every single one of them has failed. On every system I've worked on, it has always been a WD when it's a hard drive failure (once it was a Fujitsu, but that is the only other HDD to have died). This is all normal use, non-RAID systems.

By comparison, I still have some Conner 80MB and Maxtor 400MB HDDs in use that work flawlessly.
____________

Profile Matt Lebofsky
Volunteer moderator
Project administrator
Project developer
Project scientist
Avatar
Send message
Joined: 1 Mar 99
Posts: 1388
Credit: 74,079
RAC: 0
United States
Message 966439 - Posted: 28 Jan 2010, 18:15:46 UTC
Last modified: 28 Jan 2010, 18:15:58 UTC

The drives in thumper are Hitachis. That's what Sun chose to use. I'll never touch WDs or Maxtors for heavy production use.

Also, Eric years ago discovered a bug in WD drives being used by linux systems where memory maps to disk greater than 4GB introduced random corruption. He even wrote a little C program to prove this, and recreate the problem continuously. For all I know this hasn't yet been fixed. Seems like a major problem, but then again, who is using WD drives on a system that has processes taking up more than 4GB of actual memory (and memory maps to disk)? If you're running a big instance of mysqld... beware!

- 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

Profile ignorance is no excuse
Avatar
Send message
Joined: 4 Oct 00
Posts: 9529
Credit: 44,433,274
RAC: 0
Korea, North
Message 966440 - Posted: 28 Jan 2010, 18:20:01 UTC - in response to Message 966439.

I've had 1 hitachi and it didnt last a year. So that does fit with the high fail rate I guess
____________
In a rich man's house there is no place to spit but his face.
Diogenes Of Sinope

End terrorism by building a school

Grant (SSSF)
Send message
Joined: 19 Aug 99
Posts: 5683
Credit: 56,066,491
RAC: 49,870
Australia
Message 966442 - Posted: 28 Jan 2010, 18:30:05 UTC


Once upon a time, there were the Deathstars.
The problem with the drives was that IBM underestimated what was expected of a drive that was built for home/office use. If used as they expected, failure rates were very low- unfortunately for IBM by that time such use often meant the drives were on 24/5 or 24/7 instead of the (at most) 10/6 they were designed for & hence the high failure rates.

Most SATA drives are built for home/office use, and while designed to run 24/7 the actual amount of time the drives are active in such cases is really quite small. Runing in systems such as Seti the periods of inactivity would be very, very small. Hence drives such as Seagates ES series which are designed for 24/7 use in environments such as Seti.
____________
Grant
Darwin NT.

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 3841
Credit: 106,312,725
RAC: 88,876
United States
Message 966443 - Posted: 28 Jan 2010, 18:44:35 UTC

Google published the results of a study they did with 100,000 some odd of their hard drives. The report vaguely indicates that the manufacture doesn't seems to have any influence in the failures. I'd guess they didn't name any manufactures so they wouldn't have to show any preferences towards a specific brand.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

msattler
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38153
Credit: 555,543,550
RAC: 604,014
United States
Message 966444 - Posted: 28 Jan 2010, 18:44:54 UTC - in response to Message 966442.


Hence drives such as Seagates ES series which are designed for 24/7 use in environments such as Seti.


Agreed. I learned this the hard way. I have always sworn by Seagate. Had a bit of a problem with a batch that I bought a couple of years ago. But I think that was later confirmed to be a firmware problem rather than the hardware.

At that time, somebody pointed out to me that there was a difference between everyday hard drives and ones specifically engineered for 24/7 server use.

I got some ES's, and have not had a failure since (stroking the kitties for luck).

I don't think the Sata interface itself has much to do with the failure rate.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

I have met a few friends in my life.
Most were cats.

1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 966529 - Posted: 29 Jan 2010, 0:36:29 UTC - in response to Message 966442.

Once upon a time, there were the Deathstars.

The problem with the drives was that IBM underestimated what was expected of a drive that was built for home/office use.

IBM didn't talk much about the reasoning, I personally suspect that it had more to do with how they coated the magnetic media on the (glass) platters than the intended use: http://www.astro.ufl.edu/~ken/crash/index.html

The real problem was trying to make the warranty problem going away by "redefining" the warranty -- and sales suffered because it was easier to avoid all IBM drives than it was to avoid the specific troublesome deathstar models.

The short version of the story is that as a result, IBM chose to leave the hard disk market, and sold their drive business and manufacturing plants -- to Hitachi.
____________

Profile Widouxmaker
Avatar
Send message
Joined: 7 May 02
Posts: 12
Credit: 185,930
RAC: 0
United States
Message 966746 - Posted: 29 Jan 2010, 21:48:22 UTC - in response to Message 966529.

Yep. Seta in my acer croaked and I was offline for awhile. didn't make it 2 years. Level 55 on diablo2 lost. Back it up. What kind of beer did ya'll get?
____________
You talk'n to me?

archae86
Send message
Joined: 31 Aug 99
Posts: 886
Credit: 1,572,037
RAC: 0
United States
Message 966780 - Posted: 30 Jan 2010, 1:52:58 UTC - in response to Message 966443.

The report vaguely indicates that the manufacture doesn't seems to have any influence in the failures.
I think over the years every major manufacturer has had a bad patch or three. If you have the bad luck to get several drives out of a problem distribution, you'll have dreadful results, and may latch a permanent aversion to the manufacturer concerned.

Other folks, who happen to have sampled other bad portions, will naturally have grossly different opinions, held with equal fervor (and equal lack of adequate data).

I think the same Google study found drives marketed as "enterprise grade" not to do better either--but that won't stop people with a favorable experience on a tiny number of drives from fervently maintaining their vast superiority.

Unless you like to buy obsolete drives, and take the trouble somehow to accumulate vast field experience in the specific model and batch in advance, it is pretty hard to claim data based decision making on hard drive selection for reliability.

Disclosure: For four years of my varied electronics career I was a reliability professional--but it was at a semiconductor company, not a hard drive place. I did, on the other hand, play in a small recorder ensemble with a QA guy for Quantum, but that was so long ago that they not only built their own drives, but actually built them in California, so it really does not count.

____________

msattler
Volunteer tester
Avatar
Send message
Joined: 9 Jul 00
Posts: 38153
Credit: 555,543,550
RAC: 604,014
United States
Message 966788 - Posted: 30 Jan 2010, 2:30:22 UTC - in response to Message 966746.

Yep. Seta in my acer croaked and I was offline for awhile. didn't make it 2 years. Level 55 on diablo2 lost. Back it up. What kind of beer did ya'll get?

Back in my day.......Stroh's was THE beer.......
And Wild Turkey was the whiskey.

Seagate were still the best on the block.......and still are as far as I'm concerned.......

It's ES's all the way down....
That's if any of my old Seagates ever fail.
____________
*********************************************
Embrace your inner kitty...ya know ya wanna!

I have met a few friends in my life.
Most were cats.

Profile KWSN THE Holy Hand Grenade!
Volunteer tester
Avatar
Send message
Joined: 20 Dec 05
Posts: 1893
Credit: 9,080,646
RAC: 9,357
United States
Message 967309 - Posted: 31 Jan 2010, 16:17:50 UTC

Alert! the "Workunits waiting for db purging" is over .5 million and the "Results waiting for db purging" are approaching 1.2 million. Both figures are unusually high, in my experience...
____________
.

Galadriel
Send message
Joined: 24 Jan 09
Posts: 42
Credit: 8,422,996
RAC: 0
Romania
Message 967394 - Posted: 1 Feb 2010, 3:07:54 UTC

regarding the hdd discussion i am always a mixing fan so i use harddrives from every major manufacturer. best solution imho combined with random backups and offsite data&drive storage .

i lost during the last 5 years: 1x fujitsu 1x seagate and 1x westerndigital drives.
all of them where 2.5" notebook drives. sensible little bastards.

Profile bloodrain
Volunteer tester
Avatar
Send message
Joined: 8 Dec 08
Posts: 94
Credit: 7,732,285
RAC: 3,425
Antarctica
Message 967667 - Posted: 2 Feb 2010, 8:43:19 UTC - in response to Message 967394.

yeah i have had 2 wd(1 died of a bt bug) and 1 seagate die on me. it the batches just like cpu,ram,blank media.
____________

John McLeod VII
Volunteer developer
Volunteer tester
Avatar
Send message
Joined: 15 Jul 99
Posts: 24050
Credit: 516,741
RAC: 128
United States
Message 967828 - Posted: 3 Feb 2010, 12:03:05 UTC

I have had 4 drives fail over the last 25 years. In two of the cases I discovered that the manufacturer was no longer in business. One was apparently done in by a hurricane in Florida, and one was done by quality control issues. They sent out drives that lasted about 4 to 8 hours before failure. I got two of those (not counted in the total as I had not gotten the OS installed from the stack of floppies when they failed). When the drive from them that finally did work failed 3 years later, the company was no longer to supply a replacement under their 5 year warranty...
____________


BOINC WIKI

C
Send message
Joined: 3 Apr 99
Posts: 240
Credit: 6,602,807
RAC: 782
United States
Message 967837 - Posted: 3 Feb 2010, 13:43:59 UTC

Something appears to be wrong with the Gigabiteathernet site:

http://fragment1.berkeley.edu:80/newcricket/grapher.cgi?target=/router-interfaces/inr-250/gigabitethernet2_3&ranges=d%3Aw&view=Octets It usually only flat-lines when SETI is down, such as on Tuesdays...

C
____________

Join Team MacNN

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 3841
Credit: 106,312,725
RAC: 88,876
United States
Message 967843 - Posted: 3 Feb 2010, 14:53:01 UTC - in response to Message 967837.

Something appears to be wrong with the Gigabiteathernet site:

http://fragment1.berkeley.edu:80/newcricket/grapher.cgi?target=/router-interfaces/inr-250/gigabitethernet2_3&ranges=d%3Aw&view=Octets It usually only flat-lines when SETI is down, such as on Tuesdays...

C

It looks more like the data collector isn't getting data from the router. Since that site is run by berkeleys IT department for their use. I'm sure they will work on it if they feel the need to.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Profile Keith T.
Volunteer tester
Avatar
Send message
Joined: 23 Aug 99
Posts: 738
Credit: 231,168
RAC: 0
United Kingdom
Message 967923 - Posted: 3 Feb 2010, 20:27:34 UTC - in response to Message 967843.

Something appears to be wrong with the Gigabiteathernet site:

http://fragment1.berkeley.edu:80/newcricket/grapher.cgi?target=/router-interfaces/inr-250/gigabitethernet2_3&ranges=d%3Aw&view=Octets It usually only flat-lines when SETI is down, such as on Tuesdays...

C

It looks more like the data collector isn't getting data from the router. Since that site is run by berkeleys IT department for their use. I'm sure they will work on it if they feel the need to.


I just tried looking at a few other routers randomly from that site. It looks like they have data problems with all of them for the same period, so it is not just SETI or SSL that is affected.

Message boards : Technical News : Deluge (Jan 27 2010)

Copyright © 2014 University of California