Researchers Sour on Vista Service Pack 1 Performance 339
Stony Stevenson passed us a link indicating that a group of researchers has described Microsoft's upcoming Windows Vista Service Pack 1 as basically a performance dud. Researchers from the Devil Mountain Software group is claiming that a series of in-house benchmark tests showed that users hoping to receive a speed boost from the update will be disappointed. "Devil Mountain ran its DMS Clarity Studio framework on a laptop Barth described as a "barn burner" -- dual-core processor, dedicated graphics, and either 1GB or 2GB of memory -- to compare performance of the SP1 release candidate that Microsoft released last week with the RTM version that hit general distribution last January. The Vista RTM was not updated with any of the bug fixes, patches or performance packs that Microsoft has pushed through Windows Update since the operating system's debut. 'One gigabyte, 2GB [of memory], it didn't make a difference,' said [CTO Craig] Barth. 'SP1 was never more than 1% or 2% faster.'"
Anonymous King Sours on Slashdot (Score:2, Informative)
Re:Straw Man? (Score:5, Informative)
How to "speed up" Vista (Score:5, Informative)
Turn off: Volume Shadow Copy (files won't be versioned automatically any more), indexing service (rapid searching won't work any more), and SuperFetch (apps wont be pre-loaded and so will start slower, but you'll have more "free memory" on average - a debatable benefit anyway).
You'll notice XP levels of disc activity (barely any) and lot's more free memory. That's because Vista's not doing anything. Personally, I like to be able to search instantly, have apps load instantly, and have my critical files backed up transparently; so I don't mind the "bloat".
Anyway, if you actually know how Windows works, you'll know what you don't want running and what you do. Turn off the stuff you don't want, but most people are fine with the defaults even if it means using more resources.
Fixed the headline for you (Score:5, Informative)
Re:How to "speed up" Vista (Score:4, Informative)
I agree...Black Viper [blackviper.com] to the rescue. I printed out his list of services for XP [blackviper.com] and still use it to this day when tweaking systems for friends/family.
Re:Straw Man? (Score:3, Informative)
Re:Straw Man? (Score:5, Informative)
No. It's fair to call a straw man when someone puts words in someone else's mouth and then defeats that argument. In this example, (I did not RTFA, nor anything else related to this btw)if Microsoft did not say anything about performance, but this group tore MS apart because of a lack of performance improvement, it would be a straw man because this group is attacking a claim MS never made. On the other hand, if MS did say performance would be improved, it wouldn't be. From what others have said, and my own personal expectations of this SP, this is probably a straw man. I wouldn't expect a service pack designed to fix security holes and other issues would by default improve performance significantly. Service packs are, generally, a roll up of all the previous security updates, plus any additional security or features they want to add.
An example from the wikipedia article [wikipedia.org]:
Re:Straw Man? (Score:5, Informative)
Perhaps you should google on logical fallacies. All that saying "straw man" means is that someone is making an argument against a claim that was never made. If Microsoft never claimed SP1 would improve performance, than it would truly be a "straw man" criticism to berate them because SP1 does not improve performance, and thus the "straw man" defense is valid. However, if MS *did* tout SP1 as improving performance, then the "straw man" accusation is invalid as the article would have a valid point in pointing out that performance gains appear to be dismal.
The guy who posted that MS *did* claim performance improvement makes an actual argument that the OP's "straw man" claim *is* invalid, which is perfectly fine. However, you are simply implying that *any* claim of "straw man" is a "diversion tactic", which is not.
Re:Straw Man? (Score:5, Informative)
Performance
The following list describes some of the performance improvements that Windows Vista SP1 will include
Improves the speed of copying and extracting files.
Improves the time to become active from Hibernate and Resume modes.
Improves the performance of domain-joined PCs when operating off the domain; in the current release
version of Windows Vista, users would experience long delays when opening the File dialog box.
Improves performance of Windows® Internet Explorer® 7 in Windows Vista, reducing CPU utilization and
speeding JavaScript parsing.
Improves battery life by reducing CPU utilization by not redrawing the screen as frequently, on certain
computers.
Improves the logon experience by removing the occasional 10-second delay between pressing CTL-
ALT-DEL and the password prompt displaying.
Addresses an issue in the current version of Windows Vista that makes browsing network file shares
consume significant bandwidth and not perform as fast as expected.
Hmm, file shares are slow? Perhaps Microsoft should switch to Samba, which is fast.
Re:Are we shocked? (Score:4, Informative)
And yet another person who doesn't understand the new memory manager. High levels of allocated memory are a good thing for performance. Coding Horror [codinghorror.com] has a decent primer on all of this, but the short version of the story is that people who are used to how Windows has traditionally handled memory management rather than how an ideal memory manager should work love to complain about Vista being a memory hog when, in fact, I'd suggest that the Vista memory manager may arguably be one of the best out there right now.
Re:Are we shocked? (Score:1, Informative)
Samba is fast? (Score:3, Informative)
Re:Straw Man? (Score:3, Informative)
Therefore, this article cannot be, by any stretch of the imagination, considered a straw man argument.
Lots of people... (Score:3, Informative)
But there are a lot of people out there who mostly use their computer to read and write e-mails, surf the web, write some stuff on an editor that features spell-check. Whose most advanced needs in term of photos is the ability to open an SD card and display pictures by clicking on them. Maybe even IM a little bit.
Linux can bring every thing they need and even more (like reading multimedia) with the added benefit of good firewall function and separated privileges out-of-the-box. Most of those people with simple needs play games either in browser applets or on their gaming console (for which they'll have more cash available thanks to the low PC cost). They are the market for the Green PC, and there *ARE* a lot of them.
In fact, I personally use, as my everyday computer, a Pentium-III on a 440BX motherboard (nearly 10 years old Mobo !). Maxing out the memory to 1GB and upgraading HDD is the only thing I've needed to do the past few years. Linux runs perfectly on it and fulfils all my surfing/IMing/Mailing/GIMPing/etc. needs.
I guess I couldn't even get Vista to work on such old hardware.
The only reason a lot of people buy new machines is because the old one is "too slow", i.e. crawling under the number of viruses and spywares. And then they need to buy bigger hardware in those new machines, in order to support microsoft's bloatware-du-jour that powers it.
Re:Has it ever improved efficiency? (Score:3, Informative)
In fact, and I'm sure someone on Slashdot has raw data on this (that perhaps even shows I'm wrong), Apple are the only company who has ever achieved this on a regular basis.
And one should not lose sight of the fact the only reason Apple *could* do this was because OS X was so godawful slow to start with (and for years afterwards).
When OS X was released, it was a dog on even the fastest Macs available (and remained "slow" until the G5s). Vista runs happily on machines that were merely high-end (not even the best available) 4 years ago.
Re:Straw Man? (Score:3, Informative)
- Improves the speed of copying and extracting files.
- Improves the time to become active from Hibernate and Resume modes.
- Improves the performance of domain-joined PCs when operating off the domain; in the current release version of Windows Vista, users would experience long delays when opening the File dialog box.
- Improves performance of Windows® Internet Explorer® 7 in Windows Vista, reducing CPU utilization and speeding JavaScript parsing.
- Improves battery life by reducing CPU utilization by not redrawing the screen as frequently, on certain computers.
- Improves the logon experience by removing the occasional 10-second delay between pressing CTRL-ALT-DEL and the password prompt displaying.
- Addresses an issue in the current version of Windows Vista that makes browsing network file shares consume significant bandwidth and not perform as fast as expected.
You can't tell from the PCWorld article what the tests were, but there's no indication that they made substantial use of these specific features, and there's no reason to believe from this feature list that overall general system performance would improveRe:Straw Man? (Score:3, Informative)
The actual issue is that Microsoft claimed that Vista performance would improve, and it did not.
Re:Are we shocked? (Score:2, Informative)
That is slow. I recently installed the new Mac OS 10.5.1 and it transferred data at 1738.1 MB/min from the internal drive to an external FW drive. I am using a 2Ghz dual G5 PPC I got in July 2004. I wonder how that compares with XP?
I do know that MS OS are ALWAYS slower on existing hardware whereas Apple's OS sees to get faster with each upgrade on existing equipment.
I bought a new Macbook pro and installed Win2K, XP and VISTA within 3 virtual machines under Parallels. Win2K is fastest, XP a little slower, but VISTA is glacial by comparison. It does look nice though. VISTA is also a battery hog. Checking with the Activity Monitor tells why.VISTA keeps both CPUs busy at 60-85% with no user apps running. Win2K runs at 50-55%, XP uses 20-23%, Parallels by itself, with no VM running uses about 2-3%
For example: Win2K boot time is 28 sec. Winxp boots in 38 sec, VISTA takes 1min 58 sec with memory allocation of 256M, 512M and 1000M respectively.
VISTA definitely need some serious improvement if that is possible without a total re-write.
Stay with XP if you must use Windows. If buying a new computer, check out the new Macs. Yes, they cost more, but you also get more.
wrong performance IMO (Score:2, Informative)
More relevantly are some of the general scheduling algorithm problems in vista which need to be addressed. Why does playing audio with a network running cause glitches? Anyone playing an MMO with VOIP (essepcially in game voip like tabula rasa and POTBS beta) can tell you this is a problem. When my backup is running, why are 3 of my cores idle, no matter what I'm doing and 1 nearly crippled? Why does it take so damn long to start a program? Now some of that is application level, not OS scheduler, but the time for an app to gain reasonable access to performance is strangely poor. Startup is the same sort of thing.
Ok so windows Vista has a transactional file system. Am I actually getting anything out of that I will ever use? Well truth be told probably, if it prevents partial writes to the system registry which leave it unstable (or any file leaving the OS or app unstable) then I guess it's good. But I'm not sure it's worth the cost, i guess that's a matter of opinion. Ok so supporting parallelism at an OS level is an odd balancing act, between trying to do it at the OS level and exposing cores to the app level. Sony's PS3 has probably the simplest idea, which is 1 cell core for the system processes and 6 cores up to the application to manage, but the PS3 has a limited set of programs it runs at once, Vista has at my count 78 running processes (including backup, excel, task manager and opera atm, with trillian, the NCsoft launcher, AlienFX for case lights, desktop icon manager (DIM), my palm pilot software and logitech mouse drivers), can't it load balance some of that crap around between cores?
If you want to start thinking about the not too distant future then there is definately something to say which is XP64 vs Vista64. Basically nothing works on XP64, and it's a nightmare, less of a nightmare than it was, but still a nightmare, whereas Vista64 seems a dramatic (if incomplete) improvement. I'm not sure it's even reasonable to compare these OS's since hardware vendors basically ignored XP64 when it came to life, whereas they're kinda forced to pay attention to vista64. The transition to windows 7, vienna or whatever the hell it's called is going to be painful when it's 64 bit only.
I think vista FEELs slow because of a poor scheduling algorithm for tasks getting control of the system and having a transactional file system. One of those things is fixable with a patch, one not, and the one that isn't fixable is probably not a bad idea, it's just an expensive one performance wise. That's a painful tradeoff between performance and reliablity, but most of us who've had to manage servers with virtualization and mission critical data understand the tradeoff all too well, as time goes on and the desktop PC begins to incorporate more and more of the HPC world of parallel machines with complicated interconnections and the database space of storing critical data (and while it may not seem like it is critical, no one wants to lose the last 5 years of pictures because of a bad file copy algorithm), it's going to slow the OS down. Autosave is a good example of this sort of tradeoff in the application world, and while the benefits are more obvious I'm not sure that a transactional file system is a bad thing really.
The other serious criticisms of (aside from file copy and game performance and general scheduling) such as too many versions, PIT
Re:Are we shocked? (Score:3, Informative)
I bet that if we could measure the L1 cache, we'd have idiots complaining it was too full.