Forgot your password?
typodupeerror

Comment: Re:Gurus: will this affect high-SMP workstations? (Score 1) 135

by isolationism (#34790264) Attached to: Linux 2.6.37 Released

Yes, I have a BBU (battery back-up unit) installed, and have the write cache enabled and "Performance" mode set for the "StorSave" profile.

I don't think 3ware actually prevents you from setting it without a BBU installed anyway, but they certainly don't recommend it for obvious reasons. In any case, write cache performance isn't the bottleneck. It seems to be -- strange as it sounds -- something to do with the combination of high disk IO and high network IO.

Comment: Re:Not enough information (Score 1) 135

by isolationism (#34775042) Attached to: Linux 2.6.37 Released

Linux mars 2.6.36-gentoo-r6 #1 SMP PREEMPT Sun Jan 2 15:46:06 EST 2011 x86_64 Intel(R) Xeon(R) CPU X5670 @ 2.93GHz GenuineIntel GNU/Linux

I am indeed using 2.6.36, and I'm using the "patchless" alternative cgroups approach (which involves creating some new nodes and stuffing a few lines into ~/.bashrc. I was thinking it was less likely that the BKL would make a difference and hoping maybe some of the other things mentioned in the article would make a difference, like the cgroup io-throttling integration and SMP scalability improvements to XFS -- although I guess it depends whether the scalability refers to the size of the array (which is quite small, only 1TB) or the processor threads (which is quite large, at 24).

Comment: Re:Gurus: will this affect high-SMP workstations? (Score 1) 135

by isolationism (#34775008) Attached to: Linux 2.6.37 Released

As stated in another post above, it's a 3ware 9690SA -- Not a very expensive controller but not a piece of crap either -- I would expect that this thing is well-travelled enough that it wouldn't perform so bad as to freeze the system for seconds at a time during high io ops.

As for XFS, I'm sorry for your pain -- I've run XFS on 5 workstation and server RAIDs for years and never had anything close to as many problems as I've had with this (relatively new) machine. I've never once had any superblock corruption problems, but admittedly the risk exists -- I keep the computers on a UPS and have BBU's on the RAID controllers themselves as a last resort and have kept out of trouble despite increasingly frequent brownouts and 15+ minute power outages around here. Knock on wood.

Comment: Re:Gurus: will this affect high-SMP workstations? (Score 1) 135

by isolationism (#34774990) Attached to: Linux 2.6.37 Released

No -- as stated in my original post, it is a hardware RAID controller. Specifically, it is a 3ware 9690SA (SAS/SATA) model; the drives are all enterprise-grade Seagate SAS2 models.

It's not what I would quantify as a "very expensive" controller (it ballparks around $500 USD), but it's definitely dedicated hardware with cache write-through and other "performance" options enabled.

Comment: Re:Gurus: will this affect high-SMP workstations? (Score 1) 135

by isolationism (#34774966) Attached to: Linux 2.6.37 Released
Yes, I do all of my larger copy operations via terminal window instead of a file manager in X, although I honestly didn't think there'd be much difference. I'm not sure if "smoothness" is really so much the case as outright stalling though; if I didn't know it was coming back I'd have thought my machine has crashed. Thanks for taking the time to reply -- I will check it out once things cool down with work and decide for myself.

Comment: Gurus: will this affect high-SMP workstations? (Score 3, Informative) 135

by isolationism (#34771512) Attached to: Linux 2.6.37 Released
I have dual-processor Xeon with six cores each, meaning there are effectively 24 threads (2 physical * 6 cores * 2 hyperthreading) and the system will lock up for SECONDS at a time during large IO operations. The file system is XFS over an 8-disc hardware RAID10 on 15K RPM drives. Seems to be most noticeable when copying to/from the network, although I'm not convinced the network is the problem here. For such a high-end machine these stalls are unbearable; I had (a lot) less difficulty with only 4 cores and less/slower drives in a hardware RAID 0.

Comment: Re:It sucks I agree (Score 1) 472

by isolationism (#34018614) Attached to: The State of Linux IO Scheduling For the Desktop?

Very opportune timing as I have a brand-spanking new workstation where this problem has become surprisingly much more visible than it ever was on my older machine. I went from:

  • Core2 Quad @ 3GHz (overclocked)
  • 3ware 9500MI
  • 3x WD Raptor 150GB in RAID 0

to:

  • 2x Xeon X5670 @ ~2.9GHz
  • 3ware 9690SA
  • 8x Seagate 15.7K in RAID 10

... And there was a whole lot of "freezing" -- mostly in the sub-1000ms range -- while copying files on 2.6.34-35 kernels (I haven't tried any lower versions for comparison, sorry). On your advice I switched to 2.6.36 which I had compiled but not used as it requires a more "bleeding edge" nVidia driver -- but interestingly enough, my entire konsole session freezes up for 10-20 seconds at a time while trying to do an `ls` during a big file copy to an NFS share which it didn't do before -- but the mouse cursor is completely unaffected, as is surfing in Firefox. So I'm guessing whatever commits were made did make a difference in making the machine more usable Thank you for telling us!

Anyone else tried switching from 2.6.36 and see any difference?

Comment: I've been expecting this to happen for a while. (Score 1) 436

by isolationism (#32664616) Attached to: Developers Expect iOS and MacOS To Merge

It only makes sense. They're both effectively the same OS, just different UI veneers. And Apple customers are eating up apps on the platform and most don't seem to be bothered by the lack of choice/competition thing; Steve would have been remiss not to at least try the waters with the iPad, and look how well it's selling. I'm one of those guys who would only even consider buying the thing only if it had actually shipped with OS X proper, but clearly I'm in the minority.

I own a couple older iPod Touches and a 2nd generation Mac Mini -- which is pretty much nothing but an HTPC that allows for some light surfing/VNC while my kid watches a cartoon or two for the hundredth time.

Disclosure: The Mac Mini replaced a really sweet 1GHz EPIA-based Freevo box that I had custom built both the hardware and software for; it was bliss. Totally diskless operation with netboot, very low power consumption, and ran everything from DirectFB so X wasn't even required. It was however quickly replaced as soon as I bought an HDTV as it could barely play h264 video at DVD resolution, and the motherboard didn't even have a DVI port. I might have done it again for a replacement, but I spent many long days setting the thing up -- The Mac Mini on the other hand came out of the box, got put on the stand, some cables plugged into it, and I was done.

Once upon a time I might have thought, "You know what, that's fine, let them do that, I'll just keep running my old OS and not upgrade" -- but I'm sure I'm not alone in realizing this isn't really an option at all anymore; no more bug fixes, security patches, and third-party software support disappears shortly thereafter (problematic for a media player). There is also the seemingly greater likelihood that the Mac Mini will die sooner than later as the design appears to favour quiet vs. cool operation, which probably isn't an unrealistic expectation based on their target audience.

Long story short, though -- if Apple wants to do this, let them. Given their recent business activities I've already decided to put a moratorium on buying any more Apple products, which is fine as I've always been a white-box guy anyway. I will admittedly miss running Plex as it is a beautiful media player, but I would rather have the freedom of choice than spend that much on hardware and have a vendor decide what's best for me to be allowed to run.

Comment: Re:Another nail in their coffin (for me). (Score 1) 483

by isolationism (#31426818) Attached to: Apple's iPhone Developer License Agreement Revealed

Thank you for the clarification. I haven't bought a replacement battery for a cell phone since the last time I owned a Nokia (which was about 10 years ago, as you say); the battery that came with the phone was Ni-cad and a larger aftermarket one I bought was a Li-ion. I honestly had no idea that all virtually all gadget batteries were lithium-based now; I assumed there were reasons for choosing one over the other but honestly have no idea what they are/were.

The concern over the battery is mainly over the reports that the phone requires a daily charge to operate, and didn't know how many charge cycles to reasonably expect. After talking with a few other people it sounds like moderate use of an iPhone results in a similar recharge frequency and I need to get my head out of the "it's just a phone, stupid, and lasts on standby for a week," mentality.

I realized I was being a pedant shortly after posting that because of my "Apple" state of mind; Having to send your whole device away (or taking matters into your own hands) is a bit more of an ordeal than ordering trivial replacement of a clip-on battery pack.

Comment: Re:Another nail in their coffin (for me). (Score 1) 483

by isolationism (#31416748) Attached to: Apple's iPhone Developer License Agreement Revealed

Are you an N900 owner? I hate to bug you, but could you chime in on battery life? Both my wife and I would use it as I don't want to pay for two wireless devices/contracts, but she isn't great about remembering to charge the phone, and reports I've read suggest I'll be lucky to get a day out of the N900 at a time.

The biggest question for me, I guess, is whether there is a "standby" mode that can accept phone calls and SMS messages where the phone would be able to go for longer than ~18 hours without recharging if it's not actually used as a tablet, or whatever. I get that if it is fully booted up with the screen on etc. that it's only going to get a few hours of play time before needing more juice.

Comment: Re:Another nail in their coffin (for me). (Score 1) 483

by isolationism (#31416694) Attached to: Apple's iPhone Developer License Agreement Revealed

Thank you for the recommendation, especially given the price tag as it's not something I would do often.

For what it's worth, this was a very rare case where I needed to copy a network driver to the machine in question and didn't have an actual USB stick handy, and thought, "Hey, I'll just download it from Safari using my iTouch." Then, when that didn't work, I thought, "Um, okay, I'll just use it as a USB mass storage device!" You get where I'm coming from.

I am not surprised there are applications out there to do this -- less now that I have had it pointed out to me by several people (although yours was the most constructive of the bunch; thank you) and in retrospect I might have looked for one at the time had I not been fighting exhaustion and just trying to get it done so I could go to bed -- I was just astounded that I was prevented from being able to perform what I mistakenly assumed would be a trivial operation given my experience with other similar devices.

Real Users find the one combination of bizarre input values that shuts down the system for days.

Working...