1 |
On Thursday 22 July 2010 02:03:15 Dale wrote: |
2 |
> Alan McKinnon wrote: |
3 |
> > On Thursday 22 July 2010 00:18:05 Bill Longman wrote: |
4 |
> >> On 07/21/2010 12:39 PM, Alan McKinnon wrote: |
5 |
> >>> On Wednesday 21 July 2010 17:49:46 Bill Longman wrote: |
6 |
> >>>> And to play devil's advocate, I'll chime in with my experience. The |
7 |
> >>>> 4.4 GCC, at least on AMD CPUs, creates noticeably faster code. I |
8 |
> >>>> recompiled all my packages after I upgraded to 4.4 and it was a |
9 |
> >>>> noticeable difference. |
10 |
> >>>> |
11 |
> >>>> But, to make perfectly clear what Alan and Dale have stated |
12 |
> >>>> previously, it is not a requirement to recompile anything. The |
13 |
> >>>> binaries that are created still call the same system calls as they |
14 |
> >>>> did before. The kernel still publishes them in the same locations. |
15 |
> >>>> And to prove to yourself this is true, grab a statically linked |
16 |
> >>>> binary, compiled for a stock standard i686, and run it on your |
17 |
> >>>> machine. |
18 |
> >>> |
19 |
> >>> I'd love to be able to experience the speedups of gcc-4.4 and by rights |
20 |
> >>> I should be able to - my last "rip gentoo apart and put it back |
21 |
> >>> together again" stunt needed an emerge -e world to fix it all. |
22 |
> >>> |
23 |
> >>> But, and this is the bit that makes me cry, the slowdown from KDE-4.4.5 |
24 |
> >>> has obliterated all that advantage several times over..... |
25 |
> >>> |
26 |
> >>> raster *really* needs to hurrry up now and release e17 |
27 |
> >> |
28 |
> >> Might I suggest a small hardware upgrade: |
29 |
> >> http://www.supermicro.com/Aplus/motherboard/Opteron6100/SR56x0/H8QGi-F |
30 |
> >> .cfm |
31 |
> > |
32 |
> > Might I submit that that will be a tad difficult to squeez into this: |
33 |
> > |
34 |
> > # dmidecode | grep -B3 "Product Name" |
35 |
> > Handle 0x0100, DMI type 1, 27 bytes |
36 |
> > System Information |
37 |
> > |
38 |
> > Manufacturer: Dell Inc. |
39 |
> > Product Name: XPS M1530 |
40 |
> > : |
41 |
> > :-) |
42 |
> |
43 |
> Heck, the mobo most likely cost more than your whole laptop. Froogle |
44 |
> reports over $700.00 for that thing. O_O I wouldn't want the light |
45 |
> bill for that thing tho. I would like to see foldingathome running on |
46 |
> it. LOL Gkrellm would be fun to watch. |
47 |
|
48 |
Looks like a quad cpu, each one dual core. I've got one of those in the Data |
49 |
Centre next door and each core is running that new fancy hyper-threading that |
50 |
actually works: |
51 |
|
52 |
$ cat /proc/cpuinfo |
53 |
... |
54 |
processor : 15 |
55 |
vendor_id : GenuineIntel |
56 |
cpu family : 6 |
57 |
model : 26 |
58 |
model name : Intel(R) Xeon(R) CPU X5570 @ 2.93GHz |
59 |
stepping : 5 |
60 |
cpu MHz : 1596.000 |
61 |
cache size : 8192 KB |
62 |
|
63 |
$ free |
64 |
total used free shared buffers cached |
65 |
Mem: 98996716 95962284 3034432 0 1855976 32633760 |
66 |
-/+ buffers/cache: 61472548 37524168 |
67 |
Swap: 4192956 0 4192956 |
68 |
|
69 |
$ top |
70 |
top - 10:07:17 up 9 days, 10:01, 1 user, load average: 130.27, 134.99, |
71 |
122.32 |
72 |
Tasks: 246 total, 1 running, 245 sleeping, 0 stopped, 0 zombie |
73 |
Cpu(s): 18.9%us, 0.5%sy, 0.0%ni, 29.2%id, 51.2%wa, 0.0%hi, 0.2%si, 0.0%st |
74 |
Mem: 98996716k total, 96184800k used, 2811916k free, 1856248k buffers |
75 |
Swap: 4192956k total, 0k used, 4192956k free, 32848132k cached |
76 |
|
77 |
|
78 |
The grunt this thing has is unbelievable. Check the load - and the box is |
79 |
still completely responsive. It runs a database of traffic through all our |
80 |
routers so customers can check their traffic graphs going back 45 days. |
81 |
|
82 |
On the old hardware we used to have to pamper the bloody thing and do a |
83 |
juggling act with all the insert scripts. It was always running two hours |
84 |
behind (on a good day). With this new baby, we just let it rip and ram data in |
85 |
as fast as we can get it. It now runs 90 seconds behind :-0 |
86 |
|
87 |
Sometimes gigantic amounts of grunt are just the thing you need. |
88 |
|
89 |
|
90 |
|
91 |
|
92 |
|
93 |
-- |
94 |
alan dot mckinnon at gmail dot com |