From: "McCaffity, Ray" <ray.mccaffity@wcg.com>
To: linux-ia64@vger.kernel.org
Subject: RE: [Linux-ia64] New Red Hat Linux Beta release for ia64 availabl
Date: Tue, 01 May 2001 19:47:46 +0000 [thread overview]
Message-ID: <marc-linux-ia64-105590693005505@msgid-missing> (raw)
In-Reply-To: <marc-linux-ia64-105590678205864@msgid-missing>
Just a lot of little questions here, not really directed at anyone in
particular.
1. I know with all the hub-bub surrounding BogoMips the last few years on
the x86
platforms, the number doesn't mean a whole lot. But I still use it as a
"close-enough"
baseline for some of my servers. Anyway, the output from cat
/proc/cpuinfo is
slightly different from the bogoMips in the dmesg. Which one is more
reliable?
2. For my 733Mhz IA64's, my BogoMips is around 730, which is slower than 1
bogo per
MHz. This is a long way from what I get with x86 processors. Perhaps
it's mostly
because I haven't been able to optimize my kernel yet, (typically my x86
kernels will
fit on a floppy pretty easily after recompiling, and then my benchmarks
are sometimes
as much as 50% faster depending on what I'm trying to do)
I am finally able to download the new redhat/wolverine as I'm
typing this.
Hopefully I'll have better luck compiling it.
3. If the strength of the IA64 isn't really speed, I suspect it's power is
in the
number of multiple threads? For example, on some of my Solaris servers I
run
apache bench against a certain file (single URL). But I can't have more
than
256 connections to that single file without making some changes to kernel
parameters,
if I go too far the server starts getting unstable. What are the number
of
file handles supported by Linux 2.4.x ? Is is different for IA64? I
have been
able to run over 1000 concurrent connections on my IA64 server and it
doesn't seem
to slow it down much.
4. I know everything we are talking about here is beta, but another area I
have problems
with is 32-bit emulation. I have seen questions about Oracle and JAVA
for IA64 Linux
on other threads, and who knows when they'll happen. Has anyone had much
luck trying
to get these to run under Linux-IA64?
Not really meaning to take up peoples important time with trivial questions.
But
some of this affects plans our IT dept has over the 6 months to a year.
Ray
next prev parent reply other threads:[~2001-05-01 19:47 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2000-12-19 17:04 [Linux-ia64] New Red Hat Linux Beta Release for IA-64 available Bill Nottingham
2001-04-27 22:09 ` [Linux-ia64] New Red Hat Linux Beta release for ia64 available Bill Nottingham
2001-05-01 19:47 ` McCaffity, Ray [this message]
2001-05-01 19:55 ` [Linux-ia64] New Red Hat Linux Beta release for ia64 availabl e Bill Nottingham
2001-05-01 20:42 ` Don Dugger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=marc-linux-ia64-105590693005505@msgid-missing \
--to=ray.mccaffity@wcg.com \
--cc=linux-ia64@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox