Concurrent hits limitation

[sthaug at nethelp.no]

> We are using dynamic DNS update and running two scsi disk on RAID-1. We are having  IBM X3650 server with 4 gb RAM.

The 4 GB of RAM won't help you much (dhcpd for 200K IP addresses needs
considerably less than that). But two SCSI disks with RAID-1 - is this
software RAID or do you have a hardware RAID controller with battery
backed cache? The difference can be dramatic.

> How many IP addresses do you have among your 800 subnets? What's your
> lease time? What's your *target* for DHCP updates (Request/Ack) per
> second?
>  
> We have around 2, 00,000 Ip's. Our lease time is 4 days, Target hits (DORA) will be 5000 per second.

I find it hard to believe that you'll see 5000 DORAs per second, unless
all of your clients come online at the same time. Do they?

As a comparison, we have around 100K IP addresses with a 1 day lease, in
a failover configuration. *Expected* number of Request/Ack from this
load is around 100.000 * 2 / 86400 = 2.3 Request/Ack per second.

Actual number of Request/Ack that we see on our servers is around 4.3
per second (so almost double the expected load), and the number of
Discover is more than double that again - but we're still at several
orders of magnitude less than your target of 5000 DORAs per second.
Note that we use the "--enable-delayed_ack" configure option which is
not enabled by default, but which helps to reduce the load on the
disk subsystem in connection with failover. Seems to work fine for us.

Also note that with your 200K IPs and 4 days leases you should only see
around half the number of Request/Ack per second that we see.

> Also Please suggest is the server failover for the huge IP database is good or  we will put the servers (without running failover protocol) behind the Loadbalance in Active Standby state.

Well, that depends on what you want to achieve with DHCP failover, I
guess...

Steinar Haug, Nethelp consulting, sthaug at nethelp.no