search for: 10msec

...parent 1: prio 5 u32 match ip dport 20 0xffff flowid 1:3 .... and same for eth1. Now i need to add shapers for some client connecting from eth1 via vpn and gain real ip addresses (like 218.33.x.x) I think, it must looks like this: tc qdisc add dev ppp7 root tbf rate 150kbit buffer 1600 latency 10msec it''s shape outgoing traffic from client, right? But how to shape incoming traffic? I think, it must be class on eth0 with parent 1:1(tbf qdisc), but tbf is classless, so i need to replace it? For example, with htb. I have 2 questions: a) Which qdisc i should use to replace tbf and save...

...Lesperance wrote: > Hdparm didn?t get far: > > [root at r1k1 ~] # hdparm -tT /dev/sda > > /dev/sda: > Timing cached reads: Alarm clock > [root at r1k1 ~] # Hi Kelly, Try running 'iostat -xdmc 1'. Look for a single drive that has substantially greater await than ~10msec. If all the drives except one are taking 6-8msec, but one is very much more, you've got a drive that drags down the whole array's performance. Ignore the very first output from the command - it's an average of the disk subsystem since boot. Post a representative output along with the...

The HBA is an HP H220. We haven?t really benchmarked individual drives ? all 12 drives are utilized in one RAID-10 array, I?m unsure how we would test individual drives without breaking the array. Trying ?hdparm -tT /dev/sda? now ? it?s been running for 25 minutes so far? Kelly On 2016-05-25, 2:12 PM, "centos-bounces at centos.org on behalf of Dennis Jacobfeuerborn"