<html> <head> <meta content="text/html; charset=UTF-8" http-equiv="Content-Type"> </head> <body bgcolor="#FFFFFF" text="#000000"> <div class="moz-cite-prefix"><br> <br> Hi Fred. <br> <br> Definitely, the ashift parameter has been around on the illumos for a couple of years. <br> <br> thanks,<br> <br> Geoff <br> <br> On 16-03-20 05:21 PM, Fred Liu wrote:<br> </div> <blockquote cite="mid:41D8AF3D9B6AA27A.795B8F4C-9D18-4DBA-938E-32ED3D6C19F4@mail.outlook.com" type="cite"> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> <meta name="Generator" content="Microsoft Exchange Server">  <style></style> <div>The ashift parameter doesn't apply in illumos if my memory serves me well. It was introduced by ZoL.</div> <div><br> </div> <div>Thanks.</div> <div><br> </div> <div>Fred</div> <div><br> <br> <div class="acompli_signature"><br> </div> <br> </div> <br> <br> <br> <div class="gmail_quote">On Sun, Mar 20, 2016 at 1:37 PM -0700, "Geoff Nordli" <span dir="ltr"><<a moz-do-not-send="true" href="mailto:geoffn@gnaa.net" target="_blank">geoffn@gnaa.net</a>></span> wrote:<br> <br> </div> <font size="2"> <div class="PlainText">Quick, question.<br> <br> Any performance differences between 4Kn and 512e with ashift=12?<br> <br> I am thinking there should not be, since they will both write the full <br> 4K block size.<br> <br> The workload will be virtual machines using a zvol.<br> <br> thanks,<br> <br> Geoff<br> _______________________________________________<br> OmniOS-discuss mailing list<br> <a class="moz-txt-link-abbreviated" href="mailto:OmniOS-discuss@lists.omniti.com">OmniOS-discuss@lists.omniti.com</a><br> <a moz-do-not-send="true" href="http://lists.omniti.com/mailman/listinfo/omnios-discuss">http://lists.omniti.com/mailman/listinfo/omnios-discuss</a><br> </div> </font> </blockquote> <br> </body> </html>