Re: Linux scalability?
Sean Hunter wrote: > On Sat, May 19, 2001 at 10:31:01AM +0200, Sasi Peter wrote: > > On Fri, 18 May 2001, Sean Hunter wrote: > > > > > Why would you want to run a web server with 8 processors rather than four > > > webservers with 2 each? > > > > As you might already know, after the interviews to Mingo I assumed, that a > > major portion of the achievements was enabled by the 2.4 scalability > > enhacements. That is why I wrote to LKML, to ask about the 2.4 > > scalability, if anybody out there could tell us about the linux kernel's > > scalability possibily compared to W2k scalability... > > Yup. The problem is that you're trying to measure scalability in performance > of an i/o-bound task by comparing a machine with greater i/o resource but less > processing power with one with greater processing but poorer i/o. Surprisingly > enough, the one with the best i/o wins. This isn't really a fair comparison > between the two platforms. The document tree (21 - 26 GB) is small enough to fit in RAM (32 GB), so the speed of the disk is not likely to have a noticable impact. (See http://boudicca.tux.org/hypermail/linux-kernel/2001week20/1276.html ) A lot of people during the Mindcraft discussion made the mistake of calling the test unfair. Regardless of whether the initial test was fair, it actually showed interesting performance weaknesses in Linux, ones the kernel team has successfully addressed. > My point was that in the real world having this configuration for a webserver > is unlikely to be sensible at all. That's certainly true. On the other hand, worrying about how many nanoseconds a system call takes isn't really an issue in the real world, but kernel hackers love to optimize system call overhead anyway. This is the same sort of intellectual challenge. Plus, it impresses the beancounters, and they're the ones who buy the systems and keep us all employed. - Dan - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
Yup. The problem is that you're trying to measure scalability in performance of an i/o-bound task by comparing a machine with greater i/o resource but less processing power with one with greater processing but poorer i/o. Surprisingly enough, the one with the best i/o wins. This isn't really a fair comparison between the two platforms. If you put the same disk array on both machines and got the same results, then you'd have a point. My point was that in the real world having this configuration for a webserver is unlikely to be sensible at all. Sean On Sat, May 19, 2001 at 10:31:01AM +0200, Sasi Peter wrote: > On Fri, 18 May 2001, Sean Hunter wrote: > > > Why would you want to run a web server with 8 processors rather than four > > webservers with 2 each? > > As you might already know, after the interviews to Mingo I assumed, that a > major portion of the achievements was enabled by the 2.4 scalability > enhacements. That is why I wrote to LKML, to ask about the 2.4 > scalability, if anybody out there could tell us about the linux kernel's > scalability possibily compared to W2k scalability... > > -- > SaPE - Peter, Sasi - mailto:[EMAIL PROTECTED] - http://sape.iq.rulez.org/ > > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to [EMAIL PROTECTED] > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ > - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
On Fri, 18 May 2001, Sean Hunter wrote: > Why would you want to run a web server with 8 processors rather than four > webservers with 2 each? As you might already know, after the interviews to Mingo I assumed, that a major portion of the achievements was enabled by the 2.4 scalability enhacements. That is why I wrote to LKML, to ask about the 2.4 scalability, if anybody out there could tell us about the linux kernel's scalability possibily compared to W2k scalability... -- SaPE - Peter, Sasi - mailto:[EMAIL PROTECTED] - http://sape.iq.rulez.org/ - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
On 18 May 2001, reiser.angus wrote: > not really the same box > look at the disk subsystem > 7 x 9GB 10KRPM Drives and 1 x 18GB 15KRPM (html+log & os) for Win2000 > 5 x 9GB 10KRPM Drives (html+log+os) for TUX 2.0 > this is sufficient for a such difference Don't you think that all the really needed stuff could just fit in the enormous ram of the boxes? -- SaPE - Peter, Sasi - mailto:[EMAIL PROTECTED] - http://sape.iq.rulez.org/ - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [OT] Re: Linux scalability?
Peter Rival wrote: > "David S. Miller" wrote: > > > J Sloan writes: > > > Microsoft finally managed to get a better result using > > > an all-out, "bet the farm", "benchmark buster" setup > > > with a special web cache in front of iis. > > > > I haven't heard anyone talk about the fact that their 8-cpu numbers > > got disqualified and aren't even mentioned on the SPEC site on the > > main tables anymore. > > > > Really? I just checked and it's still there from what I see. We're talking > about the Dell 8450/700 w/ IIS & SWC 3.0 result, right? I'm hoping that > they're deemed NC, but I don't see it yet... > IIRC they did have some results disqualified, but them these latest results have been submitted since then - perhaps they will be disqualified as well, once the facts come to light... cu jjs - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
On Fri, May 18, 2001 at 09:17:11AM +0100, Sean Hunter wrote: [Discussion of SPECWeb results] > Why would you want to run a web server with 8 processors rather than four > webservers with 2 each? Because you want to win benchmarketing exercises, not demonstrate that your architecture has any value in the real world whatsoever. Because you know that you can induce people with financial approval to make stupid and irrational decisions based on irrelevant data. -- Rodger Donaldson[EMAIL PROTECTED] Klingons do *not* make good programmers. They make good PFWs and abuse staff, though. "You have dishonoured our Ascend! I should kill you where you stand!" -- Malcolm Ray - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [OT] Re: Linux scalability?
"David S. Miller" wrote: > Peter Rival writes: > > Really? I just checked and it's still there from what I see. We're talking > > about the Dell 8450/700 w/ IIS & SWC 3.0 result, right? I'm hoping that > > they're deemed NC, but I don't see it yet... > > Sorry, they are there in the table, but marked as NC. > > Maybe you need to hit reload in your browser :-) > Yup, one of them is marked as NC. But the other one is still there (and I hit reload and even shift-reload). So either you're missing the second one or something is not behaving nicely with our web proxies here. While I'd probably be more inclined to believe the latter... ;) - Pete - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [OT] Re: Linux scalability?
Peter Rival writes: > Really? I just checked and it's still there from what I see. We're talking > about the Dell 8450/700 w/ IIS & SWC 3.0 result, right? I'm hoping that > they're deemed NC, but I don't see it yet... Sorry, they are there in the table, but marked as NC. Maybe you need to hit reload in your browser :-) Later, David S. Miller [EMAIL PROTECTED] - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [OT] Re: Linux scalability?
"David S. Miller" wrote: > J Sloan writes: > > Microsoft finally managed to get a better result using > > an all-out, "bet the farm", "benchmark buster" setup > > with a special web cache in front of iis. > > I haven't heard anyone talk about the fact that their 8-cpu numbers > got disqualified and aren't even mentioned on the SPEC site on the > main tables anymore. > Really? I just checked and it's still there from what I see. We're talking about the Dell 8450/700 w/ IIS & SWC 3.0 result, right? I'm hoping that they're deemed NC, but I don't see it yet... - Pete - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [OT] Re: Linux scalability?
J Sloan writes: > Microsoft finally managed to get a better result using > an all-out, "bet the farm", "benchmark buster" setup > with a special web cache in front of iis. I haven't heard anyone talk about the fact that their 8-cpu numbers got disqualified and aren't even mentioned on the SPEC site on the main tables anymore. Later, David S. Miller [EMAIL PROTECTED] - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[OT] Re: Linux scalability?
Ronald Bultje wrote: > On 18 May 2001 10:12:34 +0200, reiser.angus wrote: > > > However, taking a closer look, it turns out, that the above statement > > > holds true only for 1 and 2 processor machines. Scalability already > > > suffers at 4 processors, and at 8 processors, TUX 2.0 (7500) gets beaten > > > by IIS 5.0 (8001), and these were measured on the same kind of box! > > not really the same box > > look at the disk subsystem > > 7 x 9GB 10KRPM Drives and 1 x 18GB 15KRPM (html+log & os) for Win2000 > > 5 x 9GB 10KRPM Drives (html+log+os) for TUX 2.0 > > > > this is sufficient for a such difference > > I read an article about TUX in the dutch C'T a few months ago (nov/dec > 2000, I think) - the real difference (according to the article) was the > 2.2.x kernel used in TUX. Look at the stats of the website, they used > Redhat 7.0 as base, with kernel 2.2.16. In the C'T, they also used a > 2.4-test kernel for TUX, and this one didn't have these "scalibility > problems". The problem seemed to be SMP problems with systems with more > than two cpus in the 2.2.x-based kernel series. 2.4.x kernels didn't > seem to have this problem. All Tux webservers have run on a 2.4 or 2.4-pre kernel. > And as far as I know, TUX with 2.4.x kernel was faster than win2k on all > SMP-combinations. Tux held the record for most of the time since last summer, when Linux vaulted into 1st place Microsoft finally managed to get a better result using an all-out, "bet the farm", "benchmark buster" setup with a special web cache in front of iis. However, they haven't heard the last of Linux either. cu jjs - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
Sasi Peter <[EMAIL PROTECTED]> wrote: > I am just writing an essay, an have mentioned TUX as a performance and > scalability linearity recort holder with TUX, referencing the specweb99 > website summary page: > > http://www.spec.org/osg/web99/results/web99.html > > However, taking a closer look, it turns out, that the above statement > holds true only for 1 and 2 processor machines. Scalability already > suffers at 4 processors, and at 8 processors, TUX 2.0 (7500) gets beaten > by IIS 5.0 (8001), and these were measured on the same kind of box! > > How come, TUX is s good at the lowend (1 and 2 CPUs), and scales this > bad? Let's look at the scores. (BTW, SPECweb99 gets harder as the scores get better; the document tree required to achieve a score of 3222 is twice as large as that required to achieve a score of 1438.) SPECweb99 result summary: date#cpu #nics L2 cache/cpu RAM tree score sw modelMHz 1/2001 1 1 256K 2G5G 1438 tux2 Compq Proliant DL320 800 6/2000 1 1 256K 2G4G 1270 tux1 Dell Poweredge 6400 667 6/2000 2 2 256K 4G7G 2200 tux1 Dell Poweredge 4400 800 3/2001 2 4 256K 4G10G 3222 tux2 Dell Poweredge 2500 1000 2/2001 1 3 2M8G9G 2700 tux2 IBM xSeries 370 900 2/2001 2 4 2M16G 13G 3999 tux2 IBM xSeries 370 900 6/2000 4 4 2M8G14G 4200 tux1 Dell Poweredge 6400 700 7/2000 8 8 2M32G 21G 6387 tux1 Dell Poweredge 8450 700 11/2000 8 8 2M32G 24G 7500 tux2 Dell Poweredge 8450 700 12/2000 8 8 2M32G 21G 6407 tux1 IBM Netfinity 8500R 700 3/2001 2 3 256K 4G8G 2499 IIS5/SWC HP NetserverLP2000r 1000 4/2001 8 8 2M32G 26G 8000 IIS5/SWC Dell Poweredge 8450 700 IIS5/SWC only has two results on record, at 2 and 8 CPUs. They're hard to compare, because they have different cache and RAM sizes and CPU speeds, but it's safe to say that it performs poorly at 2 CPUs (compared to the 3/2001 results from Dell) and scales nearly linearly to perform comparatively well at 8 CPUs. Looking at the IBM 1 and 2 CPU results, twice the CPU only got 1.4 times the performance. Not sure TUX is scaling especially well even at 2 CPU's. (And you can't blame this on disk drives, please don't try.) So I agree, Tux doesn't seem to scale as well to multiple CPUs as does IIS5/SWC. About comparing the Tux and IIS/SWC results on the Dell 8 CPU box: the Tux measurement is 5 months older than the IIS/SWC measurement. It's interesting to speculate how tux2 would do if tested today; It looks like tux2 is about 12% faster than tux1 on 8-CPU machines. In other words, 5 months of further development on tux and the 2.4 kernel yielded a 12% speedup. Since IIS was only 4% faster than TUX, If Tux were measured today, it might have improved enough to beat IIS/SWC, who knows. - Dan - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
On 18 May 2001 10:30:40 +0200, reiser.angus wrote: > TUX does not exist on 2.2 kernel > They use a RedHat 7.0 with a 2.4 kernel patched by RedHat (with TUX, > zerocopy, etc..) I am pretty sure the C'T article mentioned that TUX did use a 2.2.x kernel - so it does exist. How else could they make a 2.2.x-kernel based TUX vs. 2.4-test-kernel based TUX comparison? Too bad the website doesn't mention the kernel number. -- Ronald - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
> I read an article about TUX in the dutch C'T a few months ago (nov/dec > 2000, I think) - the real difference (according to the article) was the > 2.2.x kernel used in TUX. Look at the stats of the website, they used > Redhat 7.0 as base, with kernel 2.2.16. TUX does not exist on 2.2 kernel They use a RedHat 7.0 with a 2.4 kernel patched by RedHat (with TUX, zerocopy, etc..) -David - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
On 18 May 2001 10:12:34 +0200, reiser.angus wrote: > > However, taking a closer look, it turns out, that the above statement > > holds true only for 1 and 2 processor machines. Scalability already > > suffers at 4 processors, and at 8 processors, TUX 2.0 (7500) gets beaten > > by IIS 5.0 (8001), and these were measured on the same kind of box! > not really the same box > look at the disk subsystem > 7 x 9GB 10KRPM Drives and 1 x 18GB 15KRPM (html+log & os) for Win2000 > 5 x 9GB 10KRPM Drives (html+log+os) for TUX 2.0 > > this is sufficient for a such difference I read an article about TUX in the dutch C'T a few months ago (nov/dec 2000, I think) - the real difference (according to the article) was the 2.2.x kernel used in TUX. Look at the stats of the website, they used Redhat 7.0 as base, with kernel 2.2.16. In the C'T, they also used a 2.4-test kernel for TUX, and this one didn't have these "scalibility problems". The problem seemed to be SMP problems with systems with more than two cpus in the 2.2.x-based kernel series. 2.4.x kernels didn't seem to have this problem. And as far as I know, TUX with 2.4.x kernel was faster than win2k on all SMP-combinations. -- Ronald - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
Why would you want to run a web server with 8 processors rather than four webservers with 2 each? Sean On Fri, May 18, 2001 at 09:24:48AM +0200, Sasi Peter wrote: > Hi! > > I am just writing an essay, an have mentioned TUX as a performance and > scalability linearity recort holder with TUX, referencing the specweb99 > website summary page: > > http://www.spec.org/osg/web99/results/web99.html > > However, taking a closer look, it turns out, that the above statement > holds true only for 1 and 2 processor machines. Scalability already > suffers at 4 processors, and at 8 processors, TUX 2.0 (7500) gets beaten > by IIS 5.0 (8001), and these were measured on the same kind of box! > > How come, TUX is s good at the lowend (1 and 2 CPUs), and scales this > bad? > > -- > SaPE - Peter, Sasi - mailto:[EMAIL PROTECTED] - http://sape.iq.rulez.org/ > > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to [EMAIL PROTECTED] > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ > - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Linux scalability?
> However, taking a closer look, it turns out, that the above statement > holds true only for 1 and 2 processor machines. Scalability already > suffers at 4 processors, and at 8 processors, TUX 2.0 (7500) gets beaten > by IIS 5.0 (8001), and these were measured on the same kind of box! not really the same box look at the disk subsystem 7 x 9GB 10KRPM Drives and 1 x 18GB 15KRPM (html+log & os) for Win2000 5 x 9GB 10KRPM Drives (html+log+os) for TUX 2.0 this is sufficient for a such difference -David - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/