Ed Cashin | 17 Jun 03:25 2015
Picon

aoetools-37 on github

Hi.

There's a new aoetools release.  Please try it and provide feedback if 
you can.

https://github.com/OpenAoE/aoetools/archive/aoetools-37.tar.gz

Here is a snippet from the NEWS file:

2015-06-16 Ed Cashin <ed.cashin@...>
     update documentation for OpenAoE
     clean up code based on set-not-used compiler warnings
     release 37

--

-- 
   Ed

------------------------------------------------------------------------------
Daofeng Li | 16 Jun 18:12 2015
Picon

end_request: I/O error

Dear list,

I was trying to relocating my storage from 1 server to another, the old one has aoe driver version 81 installed, the new has 85 installed, I see this error message on the new system only. Is there a way to fix them? Thanks a lot.

Jun 15 17:11:01 cluster kernel: [ 1243.965424] end_request: I/O error, dev etherd/e50.23, sector 1953523728 Jun 15 17:11:01 cluster kernel: [ 1243.965436] aoe: device 52.23 is not up Jun 15 17:11:01 cluster kernel: [ 1243.965440] end_request: I/O error, dev etherd/e52.23, sector 1953524240 Jun 15 17:11:01 cluster kernel: [ 1243.965443] aoe: device 52.23 is not up Jun 15 17:11:01 cluster kernel: [ 1243.965445] end_request: I/O error, dev etherd/e52.23, sector 528 Jun 15 17:11:01 cluster kernel: [ 1243.965447] aoe: device 52.23 is not up Jun 15 17:11:01 cluster kernel: [ 1243.965449] aoe: device 52.23 is not up Jun 15 17:11:01 cluster kernel: [ 1244.126390] aoe: device 50.23 is not up Jun 15 17:11:01 cluster kernel: [ 1244.126395] end_request: I/O error, dev etherd/e50.23, sector 1953524240 Jun 15 17:11:01 cluster kernel: [ 1244.177397] aoe: device 50.23 is not up Jun 15 17:11:01 cluster kernel: [ 1244.177401] end_request: I/O error, dev etherd/e50.23, sector 528 Jun 15 17:11:01 cluster kernel: [ 1244.226678] aoe: device 50.23 is not up Jun 15 17:11:01 cluster kernel: [ 1244.226681] aoe: device 50.23 is not up Jun 15 17:11:01 cluster kernel: [ 1244.226697] end_request: I/O error, dev etherd/e52.22, sector 1953523728 Jun 15 17:11:01 cluster kernel: [ 1244.274831] aoe: device 52.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.274834] end_request: I/O error, dev etherd/e52.22, sector 1953524240 Jun 15 17:11:01 cluster kernel: [ 1244.321528] aoe: device 52.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.321531] end_request: I/O error, dev etherd/e52.22, sector 528 Jun 15 17:11:01 cluster kernel: [ 1244.366733] aoe: device 52.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.366736] aoe: device 52.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.366760] end_request: I/O error, dev etherd/e50.22, sector 1953523728 Jun 15 17:11:01 cluster kernel: [ 1244.410629] aoe: device 50.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.410633] end_request: I/O error, dev etherd/e50.22, sector 1953524240 Jun 15 17:11:01 cluster kernel: [ 1244.453077] aoe: device 50.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453082] aoe: device 50.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453084] aoe: device 50.22 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453100] aoe: device 52.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453104] aoe: device 52.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453107] aoe: device 52.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453109] aoe: device 52.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453116] aoe: device 50.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453121] aoe: device 50.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453125] aoe: device 50.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453127] aoe: device 50.21 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453133] aoe: device 52.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453145] aoe: device 52.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453156] aoe: device 52.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453163] aoe: device 52.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453190] aoe: device 50.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453200] aoe: device 50.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453219] aoe: device 50.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453222] aoe: device 50.20 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453230] aoe: device 52.19 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453235] aoe: device 52.19 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453239] aoe: device 52.19 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453241] aoe: device 52.19 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453249] aoe: device 52.18 is not up Jun 15 17:11:01 cluster kernel: [ 1244.453260] aoe: device 52.18 is not up

y aoe-stat command actually told the system could found the disks:

# aoe-stat e50.0 1000.204GB em1 8704 up e50.10 1000.204GB em1 8704 up e50.1 1000.204GB em1 8704 up e50.11 1000.204GB em1 8704 up e50.12 1000.204GB em1 8704 up e50.13 1000.204GB em1 8704 up e50.14 1000.204GB em1 8704 up e50.15 1000.204GB em1 8704 up e50.16 1000.204GB em1 8704 up e50.17 1000.204GB em1 8704 up e50.18 1000.204GB em1 8704 up e50.19 1000.204GB em1 8704 up e50.20 1000.204GB em1 8704 up e50.2 1000.204GB em1 8704 up e50.21 1000.204GB em1 8704 up e50.22 1000.204GB em1 8704 up e50.23 1000.204GB em1 8704 up e50.3 1000.204GB em1 8704 up e50.4 1000.204GB em1 8704 up e50.5 1000.204GB em1 8704 up e50.6 1000.204GB em1 8704 up e50.7 1000.204GB em1 8704 up e50.8 1000.204GB em1 8704 up e50.9 1000.204GB em1 8704 up e52.0 1000.204GB em1 8704 up e52.10 1000.204GB em1 8704 up e52.1 1000.204GB em1 8704 up e52.11 1000.204GB em1 8704 up e52.12 1000.204GB em1 8704 up e52.13 1000.204GB em1 8704 up e52.14 1000.204GB em1 8704 up e52.15 1000.204GB em1 8704 up e52.16 1000.204GB em1 8704 up e52.17 1000.204GB em1 8704 up e52.18 1000.204GB em1 8704 up e52.19 1000.204GB em1 8704 up e52.20 1000.204GB em1 8704 up e52.2 1000.204GB em1 8704 up e52.21 1000.204GB em1 8704 up e52.22 1000.204GB em1 8704 up e52.23 1000.204GB em1 8704 up e52.3 1000.204GB em1 8704 up e52.4 1000.204GB em1 8704 up e52.5 1000.204GB em1 8704 up e52.6 1000.204GB em1 8704 up e52.7 1000.204GB em1 8704 up e52.8 1000.204GB em1 8704 up e52.9 1000.204GB em1 8704 up

network, system and driver information:


root <at> cluster:/home/d# ifconfig 

em1       Link encap:Ethernet  HWaddr 5c:f9:dd:b9:48:a8  

          inet addr:10.200.0.20  Bcast:10.200.0.255  Mask:255.255.255.0

          inet6 addr: fe80::5ef9:ddff:feb9:48a8/64 Scope:Link

          UP BROADCAST RUNNING MULTICAST  MTU:9000  Metric:1

          RX packets:392548 errors:0 dropped:337 overruns:0 frame:0

          TX packets:311526 errors:0 dropped:0 overruns:0 carrier:0

          collisions:0 txqueuelen:1000 

          RX bytes:164961826 (164.9 MB)  TX bytes:20663984 (20.6 MB)


lo        Link encap:Local Loopback  

          inet addr:127.0.0.1  Mask:255.0.0.0

          inet6 addr: ::1/128 Scope:Host

          UP LOOPBACK RUNNING  MTU:65536  Metric:1

          RX packets:1325 errors:0 dropped:0 overruns:0 frame:0

          TX packets:1325 errors:0 dropped:0 overruns:0 carrier:0

          collisions:0 txqueuelen:0 

          RX bytes:23850 (23.8 KB)  TX bytes:23850 (23.8 KB)


root <at> cluster:/home/d# uname -a

Linux cluster 3.13.0-32-generic #57-Ubuntu SMP Tue Jul 15 03:51:08 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux

root <at> cluster:/home/d# aoe-version 

              aoetools: 36

  installed aoe driver: 85

    running aoe driver: 85



Daofeng
------------------------------------------------------------------------------
_______________________________________________
Aoetools-discuss mailing list
Aoetools-discuss@...
https://lists.sourceforge.net/lists/listinfo/aoetools-discuss
Pongrácz István | 11 Jun 19:09 2015
Picon

ping

just a test, I did not receive emails for a looooong time

Bye,

Steve

------------------------------------------------------------------------------
_______________________________________________
Aoetools-discuss mailing list
Aoetools-discuss@...
https://lists.sourceforge.net/lists/listinfo/aoetools-discuss
Daofeng Li | 26 May 05:35 2015
Picon

change eth2 to eth0, only part of disks appear

Dear list members,

I am using Ubuntu 12.04 with aoetools 81 for my Coraid box.
I used to use a 10Gb switch with CX-4 cable to connect the Coraid.
Somehow my switch failed and I had to use the Ethernet port with Rj45 cable.
But my issue is that only some of my disks show up when I use aoe-stat, I tried reboot both server and Coraid for few time but without lucky.
my shelf could be accessed through eth0 using cec command.

Did anyone have some suggestions? Thanks a lot in advance.

root <at> server1:~# uname -a
Linux server1 3.2.0-23-generic #36-Ubuntu SMP Tue Apr 10 20:39:51 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux
root <at> server1:~# aoe-version
              aoetools: 34
  installed aoe driver: 81
                      : 81
    running aoe driver: 81


root <at> corona:~# cec eth0
Probing for shelves ... done.
SHELF | EA
50      00259005BA18
51      002590053BF8
52      003048DD4D24
[#qp]: 50
connecting ... done.
Escape is Ctrl-\

SRX shelf 50> disks
DISK             SIZE                      MODEL  FIRMWARE              MODE
50.0       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.1       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.2       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.3       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.4       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.5       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.6       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.7       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.8       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.9       1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.10      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.11      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.12      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.13      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.14      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.15      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.16      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.17      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.18      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.19      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.20      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.21      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.22      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
50.23      1000.204GB      WDC WD1002FBYS-02A6B0  03.00C06      sata 3.0Gb/s
SRX shelf 50> list
 0 1000.205GB online
 1 1000.205GB online
 2 1000.205GB online
 3 1000.205GB online
 4 1000.205GB online
 5 1000.205GB online
 6 1000.205GB online
 7 1000.205GB online
 8 1000.205GB online
 9 1000.205GB online
10 1000.205GB online
11 1000.205GB online
12 1000.205GB online
13 1000.205GB online
14 1000.205GB online
15 1000.205GB online
16 1000.205GB online
17 1000.205GB online
18 1000.205GB online
19 1000.205GB online
20 1000.205GB online
21 1000.205GB online
22 1000.205GB online
23 1000.205GB online
SRX shelf 50> >>>
        (q)uit, (i)nterrupt, (.)continue
>>> q
SHELF | EA
50      00259005BA18
51      002590053BF8
52      003048DD4D24
[#qp]: root <at> server1:~#
root <at> server1:~# aoe-discover
root <at> server1:~# aoe-stat
    e51.14      2000.398GB       eth0 1024  up
    e51.16      2000.398GB       eth0 1024  up
    e51.17      2000.398GB       eth0 1024  up
    e51.19      2000.398GB       eth0 1024  up
    e51.20      2000.398GB       eth0 1024  up
     e51.2      2000.398GB       eth0 1024  up
    e51.22      2000.398GB       eth0 1024  up
    e51.23      2000.398GB       eth0 1024  up
     e51.4      2000.398GB       eth0 1024  up
     e51.6      2000.398GB       eth0 1024  up
     e51.8      2000.398GB       eth0 1024  up


Daofeng
------------------------------------------------------------------------------
One dashboard for servers and applications across Physical-Virtual-Cloud 
Widest out-of-the-box monitoring support with 50+ applications
Performance metrics, stats and reports that give you Actionable Insights
Deep dive visibility with transaction tracing using APM Insight.
http://ad.doubleclick.net/ddm/clk/290420510;117567292;y
_______________________________________________
Aoetools-discuss mailing list
Aoetools-discuss@...
https://lists.sourceforge.net/lists/listinfo/aoetools-discuss
Ed Cashin | 14 Apr 03:31 2015
Picon

v86pre1 adds compatibility with new kernels

Hi.

This prerelease,

   https://github.com/OpenAoE/aoe/releases/tag/aoe6-86pre1

... at the new github project for OpenAoE,

   http://www.openaoe.org/

... is compile-tested to be compatible with new kernels.  It has 
backward compatibility with older kernels.

The changes are significant but are intended to closely mirror upstream 
changes in the upstream kernel's built-in aoe driver.  As usual, they're 
accompanied by backwards-compatibility tests and patches that allow the 
driver to work on older kernels as well.

Please try out this prerelease and let me or the list know how it works.

--

-- 
   Ed

------------------------------------------------------------------------------
BPM Camp - Free Virtual Workshop May 6th at 10am PDT/1PM EDT
Develop your own process in accordance with the BPMN 2 standard
Learn Process modeling best practices with Bonita BPM through live exercises
http://www.bonitasoft.com/be-part-of-it/events/bpm-camp-virtual- event?utm_
source=Sourceforge_BPM_Camp_5_6_15&utm_medium=email&utm_campaign=VA_SF
Joshua J. Kugler | 19 Feb 05:39 2015
X-Face

Re: vblade chs boundary warning

You might argue that people are more likely to read the logs than the 
docs...but then, a lot of people read neither until something goes wrong.  But 
maybe finding that message in the logs is more likely to happen when something 
goes wrong, rather than "Hmm, something is wrong, I think I'll go look for 
warnings in the docs."

But maybe that's just me. :)

j

On Wednesday, February 18, 2015 22:51:47 Ed Cashin wrote:
> Would you consider a pull request that includes an addition to the 
documentation? That seems like a more appropriate place for a warning. On Feb 
18, 2015 10:01 PM, Catalin Salgau <csalgau@...> wrote:
> > Hi.
> > 
> > While I haven't gotten around to testing any of the "recent" changes, a
> > colleague finally tracked down one of our long-standing corruption
> > issues some time ago and I think I should suggest a change that might
> > help others.
> > WinAoE has some code in the GettingsSize state that truncates a disk to
> > CHS geometry. Prior to Vista, Windows enforced CHS alignment for
> > partition boundaries, so this was not a problem.
> > However, if you installed a newer OS (one using 1MB boundaries) then
> > moved it to AoE storage, truncating at a partition boundary could cause
> > sectors to be missing under WinAoE, corrupting your data. Windows
> > probably never actually relied on this behaviour, since it was enforcing
> > alignment itself.
> > 
> > I would like to request a warning along the lines of (while the 512 byte
> > sector size is superfluous, I include it for clarity)
> > #define CHSALIGN 255*63*512
> > if ((size*512) % CHSALIGN) {
> >     vlong recsz = (size*512) + CHSALIGN - (size*512)%CHSALIGN;
> >     printf("Exported size (%llu) is not aligned to usual CHS
> > geometry.\n", size*512)
> >     printf("Consider truncating to %llu bytes to prevent issues.\n",
> > recsz); }
> > Please excuse the lack of a pull request.
> > I'll try getting back to the other changes I was proposing at a later
> > time.
> > Thanks!
> > 
> > --------------------------------------------------------------------------
> > ---- Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
> > from Actuate! Instantly Supercharge Your Business Reports and Dashboards
> > with Interactivity, Sharing, Native Excel Exports, App Integration & more
> > Get technology previously reserved for billion-dollar corporations, FREE
> > http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clkt
> > rk _______________________________________________
> > Aoetools-discuss mailing list
> > Aoetools-discuss@...
> > https://lists.sourceforge.net/lists/listinfo/aoetools-discuss
> 
> ----------------------------------------------------------------------------
> -- Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
> from Actuate! Instantly Supercharge Your Business Reports and Dashboards
> with Interactivity, Sharing, Native Excel Exports, App Integration & more
> Get technology previously reserved for billion-dollar corporations, FREE
> http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clktrk
> _______________________________________________
> Aoetools-discuss mailing list
> Aoetools-discuss@...
> https://lists.sourceforge.net/lists/listinfo/aoetools-discuss

--

-- 
Joshua J. Kugler - Fairbanks, Alaska
Azariah Enterprises - Programming and Website Design
joshua@... - Jabber: pedahzur@...
PGP Key: http://pgp.mit.edu/  ID 0x73B13B6A

------------------------------------------------------------------------------
Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
from Actuate! Instantly Supercharge Your Business Reports and Dashboards
with Interactivity, Sharing, Native Excel Exports, App Integration & more
Get technology previously reserved for billion-dollar corporations, FREE
http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clktrk
Catalin Salgau | 19 Feb 04:01 2015
Picon
Picon

vblade chs boundary warning

Hi.

While I haven't gotten around to testing any of the "recent" changes, a 
colleague finally tracked down one of our long-standing corruption 
issues some time ago and I think I should suggest a change that might 
help others.
WinAoE has some code in the GettingsSize state that truncates a disk to 
CHS geometry. Prior to Vista, Windows enforced CHS alignment for 
partition boundaries, so this was not a problem.
However, if you installed a newer OS (one using 1MB boundaries) then 
moved it to AoE storage, truncating at a partition boundary could cause 
sectors to be missing under WinAoE, corrupting your data. Windows 
probably never actually relied on this behaviour, since it was enforcing 
alignment itself.

I would like to request a warning along the lines of (while the 512 byte 
sector size is superfluous, I include it for clarity)
#define CHSALIGN 255*63*512
if ((size*512) % CHSALIGN) {
    vlong recsz = (size*512) + CHSALIGN - (size*512)%CHSALIGN;
    printf("Exported size (%llu) is not aligned to usual CHS 
geometry.\n", size*512)
    printf("Consider truncating to %llu bytes to prevent issues.\n", recsz);
}
Please excuse the lack of a pull request.
I'll try getting back to the other changes I was proposing at a later time.
Thanks!

------------------------------------------------------------------------------
Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
from Actuate! Instantly Supercharge Your Business Reports and Dashboards
with Interactivity, Sharing, Native Excel Exports, App Integration & more
Get technology previously reserved for billion-dollar corporations, FREE
http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clktrk
Picon

question about file system

Hi,
I am using  Coraid (Model: ST3750330NS)
OS is CentOS:

Distributor ID: CentOS
Description:    CentOS release 6.6 (Final)
Release:        6.6
Codename:       Final


kernel:

Linux 2.6.32-71.el6.x86_64 #1 SMP Fri May 20 03:51:51 BST 2011 x86_64 x86_64 x86_64 GNU/Linux

8 GB RAM, 2 x Intel(R) Pentium(R) D CPU 3.00GHz

I use this server (directory connected to shelf through crossover cable) os mail server.
Mail's spool in on etherd device.
I am having big load problems (> 200!)
I would like to investigate if this can be related to file system issue or network issue

I set mtu 9000 to dedicated ethernet:
0a:00.0 Ethernet controller: Intel Corporation 82572EI Gigabit Ethernet Controller (Copper) (rev 06)


eth2      Link encap:Ethernet  HWaddr 00:15:17:CB:57:AB
          inet6 addr: fe80::215:17ff:fecb:57ab/64 Scope:Link
          UP BROADCAST RUNNING MULTICAST  MTU:9000  Metric:1

In /var/log/messages I see this:


Call Trace:
 [<ffffffff8120051f>] ? security_inode_permission+0x1f/0x30
 [<ffffffff8117ab4d>] ? __link_path_walk+0xfd/0x1040
 [<ffffffff814c97ae>] __mutex_lock_slowpath+0x13e/0x180
 [<ffffffff811794b1>] ? path_put+0x31/0x40
 [<ffffffff814c964b>] mutex_lock+0x2b/0x50
 [<ffffffff81178b7f>] lock_rename+0x3f/0xe0
 [<ffffffff8117c133>] sys_renameat+0x113/0x260
 [<ffffffff81135837>] ? handle_pte_fault+0xf7/0xad0
 [<ffffffff81171b14>] ? cp_new_stat+0xe4/0x100
 [<ffffffff81180210>] ? filldir+0x0/0xe0
 [<ffffffff810d40a2>] ? audit_syscall_entry+0x272/0x2a0
 [<ffffffff8117c29b>] sys_rename+0x1b/0x20
 [<ffffffff81013172>] system_call_fastpath+0x16/0x1b


and this is the output of "top" command:

top - 17:15:32 up  1:29,  1 user,  load average: 160.25, 164.19, 242.60
Tasks: 597 total,   2 running, 595 sleeping,   0 stopped,   0 zombie
Cpu(s): 10.2%us,  5.2%sy,  0.0%ni,  0.0%id, 84.1%wa,  0.0%hi,  0.5%si,  0.0%st
Mem:   8059612k total,  5515976k used,  2543636k free,  1737132k buffers
Swap: 10289144k total,        0k used, 10289144k free,  2254068k cached


(notice high I/O wait)

# aoe-version
              aoetools: 35
  installed aoe driver: 47
    running aoe driver: 47

Do you have any suggestion?
Thank you very much!

------------------------------------------------------------------------------
Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
from Actuate! Instantly Supercharge Your Business Reports and Dashboards
with Interactivity, Sharing, Native Excel Exports, App Integration & more
Get technology previously reserved for billion-dollar corporations, FREE
http://pubads.g.doubleclick.net/gampad/clk?id=164703151&iu=/4140/ostg.clktrk
_______________________________________________
Aoetools-discuss mailing list
Aoetools-discuss@...
https://lists.sourceforge.net/lists/listinfo/aoetools-discuss
Keri Alleyne | 28 Aug 02:24 2014

AoE Tools malfunction following aoe6-85 drive compilation

Good day.

I would like to report that we are running into some difficulty 
executing commands from AoE Tools following aoe6-85 driver compilation 
on Ubuntu 14.04.1 LTS Server (i386).

Applied Ubuntu patches.

sudo apt-get install build-essential linux-headers-`uname -r`

Extracted aoe6-85.tar.gz

make

sudo make install

sudo modprobe aoe

dmesg shows:

[  109.114933] aoe: module verification failed: signature and/or 
required key missing - tainting kernel
[  109.132450] aoe: AoE v85 initialised.
[  109.134865] aoe: e0.0: setting 1024 byte data frames
[  109.135635] aoe: 00e04cd770c5 e0.0 v4014 has 20480000 sectors
[  109.138386]  etherd/e0.0: unknown partition table

sudo aoe-stat
       e0.0        10.485GB       eth0 1024  up

sudo aoe-discover
aoe-discover: /dev/etherd/discover does not exist or is not writeable.

sudo aoe-flush
aoe-flush: /dev/etherd/flush does not exist or is not writeable.

-----------------------------------------------------

As you see, there are some problems running aoe-discover and aoe-flush.
In addition, the tainting of the kernel is a little strange.

Anyway, when this process is repeated on a Ubuntu 12.04 LTS system, the 
AoE Tools work just fine. So there is something different in how AoE 
compiles on 14.04.1.

Any suggestions?

Thanks.

------------------------------------------------------------------------------
Slashdot TV.  
Video for Nerds.  Stuff that matters.
http://tv.slashdot.org/
Catalin Salgau | 10 Jun 19:55 2014
Picon
Picon

further vblade bpf tweaking

So I'm going to throw some statistics here, and I'd like somebody to 
correct me if they think I'm wrong.
As I see it, the general use-case for AoE deployment consists of one or 
more mostly dedicated machines serving several initiators on one or more 
interfaces (or vlans). This would mean that most, if not all, of the 
traffic would consist of AoE frames.
Let's assume that we are running several targets on the same interface 
(let's say 5, differing by their major number and having 0 as their minor).
If I take a normal sample of traffic under said conditions and pass it 
trough the filter, we would see:
- check Frame type - 2 ops - 0% of frames removed - 100% of frames pass this
- check Response flag - 3 ops - 2 ops - 50% of frames removed - 50% of 
frames pass this
- check Major - 2/4 ops - 80% of frames removed - 10% of frames pass this
- check Minor - 2/4 ops - 0 % of frames removed - 10% of frames pass this

If I were to reorder the checks and move the major/minor checks first, 
response after that and leave the frame type to the end:
- check Major - 2/4 ops - 80% of frames removed - 20% of frames pass this
- check Minor - 2/4 ops - 0 % of frames removed - 20% of frames pass this
- check Response flag - 3 ops - 2 ops - 50% of frames removed - 10% of 
frames pass this
- check Frame type - 2 ops - 0% of frames removed - 10% of frames pass this

This would lead to a fast-fail path for 80% of vblade traffic in 4 ops, 
versus the 9 ops used currently.

If we were to include a moderate amount of other kinds of traffic into 
the mix, major and minor have the nice effect of sitting on top of the 
Total Length and Identification fields of IP, which vary wildly and have 
a small chance of collision.
This is not shared, unfortunately, by IPv6, where it would collide with 
part of Flow Label and part of Payload Length. In normal environments 
these bytes would probably be 0, and so would the response flag. If both 
our major and minor are set to 0, we would have a fail in 9 ops to find 
that out, instead of 2 ops in the current case, for said vblade 
instance, but all other instances would fail in 4 ops.
This trade-off would not be convenient in an environment with more 
non-AoE traffic than AoE traffic, but, as stated, I'd argue that that is 
not the general case.

Implementation-wise I would argue against the need to keep both version, 
as the latency difference is small, but flipping between these by a 
command-line argument would be an option that wouldn't cost anything at 
runtime (something like - favour dedicated or mixed environments with a 
flag)

One more note - since I'm deploying this on FreeBSD (and I believe Linux 
also has something similar) I can make sure I don't see frames sent by 
this machine, so I can drop the removed count for the Response flag to 
0% in certain conditions. I'm about to follow this up with freebsd-net <at>  
and maybe raise a question on linux-net <at> .

I submit this for your consideration, and will provide the needed changes.

Cheers,
  Catalin Salgau

------------------------------------------------------------------------------
HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions
Find What Matters Most in Your Big Data with HPCC Systems
Open Source. Fast. Scalable. Simple. Ideal for Dirty Data.
Leverages Graph Analysis for Fast Processing & Easy Data Exploration
http://p.sf.net/sfu/hpccsystems
Killer{R} | 9 Jun 23:18 2014

another proposed protocol optimization...

Hello aoetools-discuss,

  ..coalesced read requests. Its quite an expensive to send 60-bytes
  packet per every MTU-sized read. I did experimental read requests
  coalesting in my forked project and it noticable decreased
  packets-per-second rate and also reduced target's CPU usage.
  I did this by appending bunch of such structures prepended by uchar
  indicated their count just after normal Read command packet:
  struct AtaCoalescedRead
  {
        uchar   tag[4];
        uchar   lba[6];
        uchar   resvd[5];
        uchar   sectors;
  };
  + added feature negotiation command so initiator can negitiate with
  target using of that improvement without losing backward compatibility

--

-- 
Best regards,
 Killer{R}                          mailto:support@...

------------------------------------------------------------------------------
HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions
Find What Matters Most in Your Big Data with HPCC Systems
Open Source. Fast. Scalable. Simple. Ideal for Dirty Data.
Leverages Graph Analysis for Fast Processing & Easy Data Exploration
http://p.sf.net/sfu/hpccsystems

Gmane