1 |
On Sunday 25 June 2006 19:02, 张韡武 wrote: |
2 |
|
3 |
> Thank you for the answer. Just another smaller question: from pruely a |
4 |
> user's view (who simply wish to use it, rather then from developer |
5 |
> view who might gain knowledge and fun doing it), is it worthy to try |
6 |
> it (64bit sparc)? |
7 |
> |
8 |
> The original idea is the system as a print server is too slow (capable |
9 |
> of doing fast dithering for the inkjet printer, but not fast enough to |
10 |
> do real-time even-tone dithering to server the printer, usually cause |
11 |
> printer to wait for server), a rough gain of 20% to 30% CPU power, by |
12 |
> my guessing of observing top(1), should be enough for the printer. |
13 |
> Dithering is always a CPU intensive job and we do a lot of printing. |
14 |
> |
15 |
> I observed kernel is taking only a very small percentage of CPU usage, |
16 |
> if I try hours to get 64-bit kernel running but only obtain 5% speed |
17 |
> gain, that may not be worth. Or should I try Solaris 10? Should |
18 |
> Solaris provide better performance in this very case? (how much |
19 |
> performance gain might happen? 10%? 20%?) I don't need a very close |
20 |
> estimation, just if someone can give me a very rough estimation is |
21 |
> very helpful, for I am not techincally able to do the decision:) |
22 |
> |
23 |
> If switch to Solaris for performance (no offensive, I am a 5 year's |
24 |
> hardcore Linux user), generally speaking, is Solaris very compatible |
25 |
> with PCI cards like NEC USB controller, Promise IDE controller and |
26 |
> ethernet cards? |
27 |
|
28 |
Well, I'm not a sparc dev so probably I cannot give you the most accurate |
29 |
answer you could get; moreover, I cannot speak about solaris since I |
30 |
don't know it. Anyway... |
31 |
>From what I've read, the main reason gentoo stays 64 bit kernel/32 bit |
32 |
userland is that switching to a full 64 bit system (perhaps with |
33 |
multilib) will not be a considerable improvement, but rather just a |
34 |
waste of memory. This is different from what happens in the x86 world, |
35 |
where being 64-bit means getting a lot of benefits (like, for example, |
36 |
many more cpu registers). In the sparc world, for an userland app "being |
37 |
64-bit" means, basically, "wasting more memory" (due to larger |
38 |
executables binaries). In short, I think that (from the pure user's view |
39 |
you were talking about), it's not worth trying. |
40 |
However, I believe that a (highly experimental) userland 64-bit profile |
41 |
exists (but of course don't expect that to work flawlessly or to be |
42 |
usable in a production environment). |
43 |
Read this thread on the forums, which explains all: |
44 |
|
45 |
http://forums.gentoo.org/viewtopic-t-442194.html |
46 |
|
47 |
btw, AFAIK solaris uses a similar 64bit-kernel/32bit-userland approach |
48 |
(or, at least, *most* of the userland is 32bit). |
49 |
|
50 |
Hope this helps (and please somebody correct me if what I said is wrong). |
51 |
|
52 |
-- |
53 |
gentoo-sparc@g.o mailing list |