<div dir="ltr">Dear all,<div><br></div><div style>I have installed DRBD 8.3.11 compiled from sources. However the backend block will freeze if there is high IO load. I use Remus to support high availability and checkpointing is controlled by remus for each 400ms.</div>
<div style><br></div><div style>If I check the Iostat I got the idle CPU will decreasing extremely each checkpointing and when its reach 0% of idle cpu the local backing device will freeze and damage the replication.</div>
<div style><br></div><div style><br></div><div style><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 0.00 0.00 0.00 0 0</div><div><br>
</div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 1.52 0.00 6.09 0.00 0.00 92.39</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div>
<div>drbd1 0.00 0.00 0.00 0 0</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 41.24 0.00 12.37 0.00 0.52 45.88</div>
<div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 55.15 131.96 1327.84 256 2576</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div>
<div> 70.85 0.00 29.15 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 50.25 128.64 711.56 256 1416</div>
<div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 54.73 0.00 45.27 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div>
<div>drbd1 5.97 127.36 37.81 256 76</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 39.50 0.00 60.50 0.00 0.00 0.00</div>
<div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 2.50 68.00 0.00 136 0</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div>
<div> 35.00 0.00 65.00 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 15.00 138.00 66.00 276 132</div>
<div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 32.50 0.00 67.50 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div>
<div>drbd1 77.50 138.00 1890.00 276 3780</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 33.00 0.00 67.00 0.00 0.00 0.00</div>
<div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 14.50 128.00 264.00 256 528</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div>
<div> 27.64 0.00 72.36 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 31.66 72.36 470.35 144 936</div>
<div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 32.00 0.00 68.00 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div>
<div>drbd1 0.00 0.00 0.00 0 0</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 26.37 0.00 73.63 0.00 0.00 0.00</div>
<div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 6.47 127.36 33.83 256 68</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div>
<div> 27.50 0.00 72.50 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div><div>drbd1 4.00 128.00 0.00 256 0</div>
<div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 27.50 0.00 72.50 0.00 0.00 0.00</div><div><br></div><div>Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn</div>
<div>drbd1 4.00 128.00 0.00 256 0</div><div><br></div><div>avg-cpu: %user %nice %system %iowait %steal %idle</div><div> 29.50 0.00 70.50 0.00 0.00 0.00</div>
<div><br></div></div><div style>I am also considering drbd optimization but its came with no luck. Hopefully some one would shared his experience.</div><div style><br></div><div style>Best Regards,</div><div style><br></div>
<div style>Agya</div></div>