mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Justin Piszcz" <jpiszcz@lucidpixels.com>
To: <linux-kernel@vger.kernel.org>, <e1000-devel@lists.sf.net>
Cc: <support@Supermicro.com>, <ap@solarrain.com>
Subject: RE: X9SCM-F/82574L/e1000e lag / high latency (e1000e/Intel bug)
Date: Wed, 10 Oct 2012 07:23:16 -0400	[thread overview]
Message-ID: <001f01cda6d9$a505d7b0$ef118710$@lucidpixels.com> (raw)
In-Reply-To: <001201cda6cf$d9de5480$8d9afd80$@lucidpixels.com>



-----Original Message-----
From: Justin Piszcz [mailto:jpiszcz@lucidpixels.com] 
Sent: Tuesday, October 09, 2012 6:15 PM
To: linux-kernel@vger.kernel.org; e1000-devel@lists.sf.net
Cc: support@Supermicro.com; ap@solarrain.com
Subject: X9SCM-F/82574L/e1000e lag / high latency (e1000e/Intel bug)

If you have > 16GB do not upgrade to 2.0b, I am writing up a page on this
and will post it shortly, the board will show 32GB with 2.0b but when it
tries to address it, the machine reboots.  Stick with 2.0a for now, I will
call Supermicro later, will post a page on all of these issues in a bit.

--

As promised:
https://sites.google.com/a/lucidpixels.com/web/blog/supermicrox9scm-fissues

Summary:

1. the board does not always address 32GB of ram if you are using an Ivy
Bridge chip on this motherboard
2. e1000e network problems
    a) During heavy network I/O (file copy) on eth0 the network latency
jumps to 300-1000ms+ every 4-5 seconds (it does not do this on a separate
card)
    b) During heavy network I/O (file copy) of over 600GB of files, the
kernel disabled the network IRQ on eth0 and took the server offline from a
network perspective (it has not done this on a separate card..yet)
3. Problems with PCI-e cards
    summary: Don't expect to use all four PCI-e slots if they use a lot of
power
4. clock drift issues:
  summary: expect some strangeness if you use gpsd/a gps to help sync your
time, due to what SM noted below
    http://lists.ntp.org/pipermail/pool/2012-July/006019.html

here is a picture of memtest86 showing "Unexpected Interrupt - Halting" when
2.0b BIOS is used with 32gb of ram:
http://home.comcast.net/~jpiszcz/20121010/x9scm-web-small.jpg

here is the issue with memtest86 (crashes/reboots host when you have 2.0b +
32gb of ram):
https://www.youtube.com/watch?feature=player_embedded&v=M2TWO5kFm9U

Justin.


      reply	other threads:[~2012-10-10 11:23 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-09 22:14 Justin Piszcz
2012-10-10 10:13 ` Justin Piszcz
2012-10-10 11:23   ` Justin Piszcz [this message]

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='001f01cda6d9$a505d7b0$ef118710$@lucidpixels.com' \
    --to=jpiszcz@lucidpixels.com \
    --cc=ap@solarrain.com \
    --cc=e1000-devel@lists.sf.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=support@Supermicro.com \
    /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

Powered by JetHome