<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=utf-8">
<STYLE>
BLOCKQUOTE {
MARGIN-TOP: 0px; MARGIN-BOTTOM: 0px; MARGIN-LEFT: 2em
}
OL {
MARGIN-TOP: 0px; MARGIN-BOTTOM: 0px
}
UL {
MARGIN-TOP: 0px; MARGIN-BOTTOM: 0px
}
P {
MARGIN-TOP: 0px; MARGIN-BOTTOM: 0px
}
BODY {
FONT-SIZE: 10.5pt; COLOR: #000080; LINE-HEIGHT: 1.5; FONT-FAMILY: 宋体
}
</STYLE>
<META content="MSHTML 6.00.2900.6197" name=GENERATOR></HEAD>
<BODY style="MARGIN: 10px">
<DIV>hi，Felix, many thanks. </DIV>
<DIV> </DIV>
<DIV style="TEXT-INDENT: 2em">I used this cmd, here is my result:</DIV>
<DIV style="TEXT-INDENT: 2em">machine 1：</DIV>
<DIV style="TEXT-INDENT: 2em">
<DIV>resource r0 {</DIV>
<DIV> options {</DIV>
<DIV> }</DIV>
<DIV> net {</DIV>
<DIV> max-epoch-size 20000;</DIV>
<DIV> max-buffers 80000;</DIV>
<DIV> sndbuf-size 1048576; # bytes</DIV>
<DIV> }</DIV>
<DIV> _remote_host {</DIV>
<DIV> address ipv4 192.168.100.231:7788;</DIV>
<DIV> }</DIV>
<DIV> _this_host {</DIV>
<DIV> address ipv4 192.168.100.213:7788;</DIV>
<DIV> volume 0 {</DIV>
<DIV> device minor 0;</DIV>
<DIV> disk "/dev/sdd1";</DIV>
<DIV> meta-disk internal;</DIV>
<DIV> disk {</DIV>
<DIV> al-extents 3389;</DIV>
<DIV> }</DIV>
<DIV> }</DIV>
<DIV> }</DIV>
<DIV>}</DIV>
<DIV> </DIV></DIV>
<DIV style="TEXT-INDENT: 2em">machine 2：</DIV>
<DIV>
<DIV>resource r0 {</DIV>
<DIV> options {</DIV>
<DIV> }</DIV>
<DIV> net {</DIV>
<DIV> max-epoch-size 20000;</DIV>
<DIV> max-buffers 80000;</DIV>
<DIV> sndbuf-size 1048576; # bytes</DIV>
<DIV> }</DIV>
<DIV> _remote_host {</DIV>
<DIV> address ipv4 192.168.100.213:7788;</DIV>
<DIV> }</DIV>
<DIV> _this_host {</DIV>
<DIV> address ipv4 192.168.100.231:7788;</DIV>
<DIV> volume 0 {</DIV>
<DIV> device minor 0;</DIV>
<DIV> disk "/dev/sdc1";</DIV>
<DIV> meta-disk internal;</DIV>
<DIV> disk {</DIV>
<DIV> al-extents 3389;</DIV>
<DIV> }</DIV>
<DIV> }</DIV>
<DIV> }</DIV>
<DIV>}</DIV>
<DIV> </DIV>
<DIV>and when I retest, the results of 3 sequential tests are:</DIV>
<DIV>
<DIV> </DIV>
<DIV># dd if=/dev/zero of=test3 bs=1M count=800 conv=fdatasync</DIV>
<DIV>800+0 records in</DIV>
<DIV>800+0 records out</DIV>
<DIV>838860800 bytes (839 MB) copied, 24.6033 seconds, 34.1 MB/s</DIV>
<DIV> </DIV>
<DIV># dd if=/dev/zero of=test3 bs=1M count=800 conv=fdatasync</DIV>
<DIV>800+0 records in</DIV>
<DIV>800+0 records out</DIV>
<DIV>838860800 bytes (839 MB) copied, 22.9287 seconds, 36.6 MB/s</DIV>
<DIV> </DIV>
<DIV>
<DIV># dd if=/dev/zero of=test3 bs=1M count=800 conv=fdatasync</DIV>
<DIV>800+0 records in</DIV>
<DIV>800+0 records out</DIV>
<DIV>838860800 bytes (839 MB) copied, 10.151 seconds, 82.6 MB/s</DIV></DIV>
<DIV> </DIV>
<DIV>So, the first and second times write-performance is so
slow, </DIV>
<DIV>but the 3rd performance is better ? what problem may induced this,</DIV>
<DIV>is my test method incorrect?</DIV>
<DIV> </DIV>
<DIV>BRs,</DIV>
<DIV>feng</DIV>
<DIV> </DIV>
<DIV> </DIV>
<DIV> </DIV>
<DIV> </DIV>
<DIV> </DIV></DIV></DIV>
<HR style="WIDTH: 210px; HEIGHT: 1px" align=left color=#b5c4df SIZE=1>
<DIV> </DIV>
<DIV
style="BORDER-RIGHT: medium none; PADDING-RIGHT: 0cm; BORDER-TOP: #b5c4df 1pt solid; PADDING-LEFT: 0cm; PADDING-BOTTOM: 0cm; BORDER-LEFT: medium none; PADDING-TOP: 3pt; BORDER-BOTTOM: medium none">
<DIV
style="PADDING-RIGHT: 8px; PADDING-LEFT: 8px; FONT-SIZE: 12px; BACKGROUND: #efefef; PADDING-BOTTOM: 8px; COLOR: #000000; PADDING-TOP: 8px">
<DIV><B>From:</B> <A href="mailto:ff@mpexnet.de">Felix Frank</A></DIV>
<DIV><B>Date:</B> 2012-04-30 22:38</DIV>
<DIV><B>To:</B> <A href="mailto:zf5984599@gmail.com">zf5984599</A></DIV>
<DIV><B>CC:</B> <A
href="mailto:drbd-user@lists.linbit.com">drbd-user</A></DIV>
<DIV><B>Subject:</B> Re: [DRBD-user] drbd write performance slow, per disk
40M/s by dd command</DIV></DIV></DIV>
<DIV>
<DIV>Hi,</DIV>
<DIV> </DIV>
<DIV>On 04/26/2012 03:24 AM, zf5984599 wrote:</DIV>
<DIV>> I had turned off disk-barrier and disk-flushes in config file, but there</DIV>
<DIV>> is no difference.</DIV>
<DIV> </DIV>
<DIV>did you make sure your tunings were applied correctly?</DIV>
<DIV>It's advisable to check using "drbdsetup 0 show" (if 0 is indeed the</DIV>
<DIV>minor number of the resource under test).</DIV>
<DIV> </DIV>
<DIV>Your 100MBps result looks suspicious to me. Hum.</DIV>
<DIV> </DIV>
<DIV>HTH,</DIV>
<DIV>Felix</DIV></DIV></BODY></HTML>