<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-size:small">On Wed, Sep 3, 2025 at 7:17\u202fAM Ron <<a href="mailto:ron@bclug.ca">ron@bclug.ca</a>> wrote:</div></div><div class="gmail_quote gmail_quote_container"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">So, in this situation (perhaps a flawed test?), there's a dramatic <br>
speedup going above bs=1, a significant speed improvement going above <br>
bs=1000, and slight decreases in speed going above bs=1,000,000.<br>
<br>
Similar results on an SSD, but *slower* on the low end and faster at <br>
bs=1000000 (1M).<br>
<br>
SSD results also slowly decline above bs=1M:<br></blockquote></div><div><span class="gmail_signature_prefix"><br></span></div><div>L<span class="gmail_default" style="font-size:small">ooks like bs=1M is the sweet spot, regardless of disk technology. <br></span></div><div><span class="gmail_default" style="font-size:small">Perhaps it is about round trips into the kernel and out (as Chris Frey said <br></span></div><div><span class="gmail_default" style="font-size:small">in the other thread).</span></div><div><span class="gmail_default" style="font-size:small"><br></span></div><div><span class="gmail_default" style="font-size:small">Thanks for doing the tests ...<br></span></div><div><span class="gmail_default" style="font-size:small"></span></div><div><span class="gmail_signature_prefix">-- </span></div><div dir="ltr" class="gmail_signature">Khalid M. Baheyeldin<br><br></div></div>