How did this workout? I am considering getting the Dell PowerEdge 2950. <br><br>
<div><span class="gmail_quote">On 11/5/07, <b class="gmail_sendername">Steven</b> <<a href="mailto:asterisk@tescogroup.com">asterisk@tescogroup.com</a>> wrote:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div bgcolor="#ffffff">
<div>
<div>
<div><font face="Arial" size="2">2950s work fine.</font></div>
<div><font face="Arial" size="2"></font> </div>
<div><font face="Arial" size="2">I have had the parity error for over a year with no noticable problems. It is working fine.</font></div>
<div><font face="Arial" size="2"></font> </div>
<div><font face="Arial" size="2">I did have to make some IRQ changes to clean up the system.</font></div>
<div><font face="Arial" size="2"></font> </div>
<div><font face="Arial" size="2">I did these on my <span class="st" id="st" name="st">Dell</span> 1750 test machine, but have made the same changes on my production machine.</font></div>
<div><font face="Arial" size="2">The changes basically redue the IRQ load from other cards, like the RAID card, which will reduce the bus's capacity for processing all of the TDM IRQs.</font></div>
<div><font face="Arial" size="2">It also allocates just one CPU full time for all of the TDM IRQs.</font></div>
<div><font face="Arial" size="2"></font> </div>
<div><font face="Arial" size="2">The changes are below:</font></div>
<div><font face="Arial" size="2"></font> </div>
<div><font face="Arial" size="2"></font> </div>
<div><font face="Arial" size="2">ref:</font></div>
<div>FYI on zttool output on SMP system </div>
<div><font face="Arial" size="2"></font> </div>
<div>--- Results after 56 passes --- </div>
<div>Best: 100.000000 -- Worst: 99.987793 -- Average: 99.999564 </div>
<div>Only 2 were 99.987793, the 54 others were all 100.000000. </div>
<div> </div></div>
<div>I got this by making the changes below on my dual proc <span class="st" id="st" name="st">Dell</span> 1750. </div>
<div> </div>
<div>setpci -v -s 01:08.1 LATENCY_TIMER=8 </div>
<div>setpci -v -s 00:0f.1 LATENCY_TIMER=8 </div>
<div>setpci -v -s 01:04.0 LATENCY_TIMER=8 </div>
<div>setpci -v -s 01:02.0 LATENCY_TIMER=8 </div>
<div>setpci -v -s 00:0f.2 LATENCY_TIMER=8 </div>
<div>setpci -v -s 01:04.0 LATENCY_TIMER=8 (these are USB, SCSI HW RAID driver, Ethernet, Video, etc. I did not alter ZAP cards, nor any </div>
<div>bridges or buses) </div>
<div> </div>
<div>echo 1 > /proc/irq/17/smp_affinity (Ethernet) </div>
<div>echo 1 > /proc/irq/18/smp_affinity (SCSI HW RAID Driver) </div>
<div>echo 2 > /proc/irq/20/smp_affinity (TDM) </div>
<div>echo 2 > /proc/irq/24/smp_affinity (TE411P) </div>
<div> </div>
<div>I also turned of the startup of irqbalance. </div>
<div> </div>
<div>The setpci changes did the most work concerning reaching 100% in zttest. </div>
<div> </div>
<div>Irqbalance was causing the the processor handling the interrupts of the zap cards to change very often. </div>
<div>This would impose a delay during the change and cause the zttest numbers to drop/be inconsistent. </div>
<div> </div>
<div>Because I turned irqbalance off, the irqs are processed round robin style, which is also not good. </div>
<div>Therefore, I hard coded the processor affinity for the zap cards to one proc and all other high load irqs to the other proc. </div>
<div>If you have more than 2 procs, you can spread them out even more. If you do not turn off irqbalance, the affinity changes will be </div>
<div>overwritten by it. </div>
<div> </div>
<div>I made these changes on a live system without issue. </div>
<div>I set these changes in /etc/rc.d/rc.local to reset them after reboots. </div></div>
<div><br>-- <br>-- <br>Steven</div>
<div> </div>
<div><a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.glimasoutheast.org/" target="_blank">http://www.glimasoutheast.org</a></div>
<div> </div>
<div><br> </div>
<blockquote style="PADDING-RIGHT: 0px; PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #000000 2px solid; MARGIN-RIGHT: 0px">
<div>"Brian Hutchinson" <<a onclick="return top.js.OpenExtLink(window,event,this)" href="mailto:b.hutchman@gmail.com" target="_blank">b.hutchman@gmail.com</a>> wrote in message <a onclick="return top.js.OpenExtLink(window,event,this)" href="news:3d1967ab0710250333r62643f08nc8efa99ec6c6e2a0@mail.gmail.com" target="_blank">news:3d1967ab0710250333r62643f08nc8efa99ec6c6e2a0@mail.gmail.com</a>...</div>
You guys are scaring me! I'm building a <span class="st" id="st" name="st">2950</span> with SAS RAID 5 on the new PERC and it will have 2 TE420P's. I hope it works or my bacon will fry.<br><br>
<div><span class="gmail_quote">On 10/25/07, <b class="gmail_sendername">Joseph Begumisa</b> <<a onclick="return top.js.OpenExtLink(window,event,this)" href="mailto:joe@cfi.co.ug" target="_blank">joe@cfi.co.ug</a>> wrote:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0pt 0pt 0pt 0.8ex; BORDER-LEFT: rgb(204,204,204) 1px solid">> <br>> Has anyone had any compatibility issues with a TE110P card installed<br>> on a <span class="st" id="st" name="st">Dell</span> <span class="st" id="st" name="st">Poweredge</span> 1950?I noted the following error on the LCD<br>
> display of the <span class="st" id="st" name="st">Dell</span> <span class="st" id="st" name="st">Poweredge</span> 1950:<br>><br>><br>><br>> E1711 PCI PErr Slot 1 E171F PCIE Fatal Error B0 D4 F0.<br><br>>Yes, I have had this problem with a <span class="st" id="st" name="st">dell</span> PE1650, 1850, SC1400, and PE650. I<br>
have a TE410P that does it. It may not be wise, but I just ignore the orange <br>blinking LCD display (or light, >depending on the model). I did try<br>reseating the card, and it "works" for a few weeks, and then goes back to<br>
the same old thing.<br><br>Yes, that happened too. Digium has graciously offered to send me a TE120P <br>with the Digium VoiceBus technology which I will test out on the <span class="st" id="st" name="st">Dell</span> 1950.<br>
Will post my findings thereafter.<br><br>Joseph.<br><br><br><br><br>_______________________________________________<br>--Bandwidth and Colocation Provided by <a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.api-digital.com--/" target="_blank">http://www.api-digital.com--</a><br>
<br>asterisk-users mailing list<br>To UNSUBSCRIBE or update options visit:<br> <a onclick="return top.js.OpenExtLink(window,event,this)" href="http://lists.digium.com/mailman/listinfo/asterisk-users" target="_blank">http://lists.digium.com/mailman/listinfo/asterisk-users</a><br>
</blockquote></div><br>
<p>
<hr>
<p></p>_______________________________________________<br>--Bandwidth and Colocation Provided by <a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.api-digital.com--/" target="_blank">http://www.api-digital.com--</a><br>
<br>asterisk-users mailing list<br>To UNSUBSCRIBE or update options visit:<br> <a onclick="return top.js.OpenExtLink(window,event,this)" href="http://lists.digium.com/mailman/listinfo/asterisk-users" target="_blank">http://lists.digium.com/mailman/listinfo/asterisk-users</a>
<p></p></p></blockquote></div><br>_______________________________________________<br>--Bandwidth and Colocation Provided by <a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.api-digital.com--/" target="_blank">http://www.api-digital.com--</a><br>
<br>asterisk-users mailing list<br>To UNSUBSCRIBE or update options visit:<br> <a onclick="return top.js.OpenExtLink(window,event,this)" href="http://lists.digium.com/mailman/listinfo/asterisk-users" target="_blank">http://lists.digium.com/mailman/listinfo/asterisk-users</a><br>
</blockquote></div><br>