Wanted to chat basketball and couldn't get on?

Gts is working on changing the URL to realignmentbbs.com

It wasn't down. it tried to commit suicide. someone posted the 20,000,000th "screw the big east/conference usa sucks" grudgehump thread, and it just couldn't take it anymore

(01-20-2013 03:52 PM)EagleX Wrote:  It wasn't down. it tried to commit suicide. someone posted the 20,000,000th "screw the big east/conference usa sucks" grudgehump thread, and it just couldn't take it anymore

It looks like it'll be down again tonight (for maintenance)

http://csnbbs.com/announcements.php?aid=207

(01-20-2013 10:38 PM)tyler90wm Wrote:  It looks like it'll be down again tonight (for maintenance)

http://csnbbs.com/announcements.php?aid=207

an hour and a half. not bad. this is a huge board.

Yesterday it dropped out around 1:30 AM ET due to a power failure in the UPS on the rack. I'm waiting on the datacenter to rectify that situation. It was down for about an hour -- which is how long it took my wasted ass to wake up to all the phone alerts and re-enable a few services. By default if the server crashes uncleanly, the database will not come back live until I've manually inspected it to make sure there is no corruption. Trying to run this site on a corrupted database would create quite a horror show.

Tonight's downtime was for an enormous leap forward in kernel versions on all servers, and to enable some PHP features for some of my partners in crime in the Skunkworks team.

I'll let it sit as is this week to make sure there are no performance regressions, then next weekend I'll take it down for a few hours again to go to the latest kernels, install some special patchsets on those kernels, and bring userspace up to date to match.

it sounds like you need a flux capacitor

Next time the board goes down, we need fake pics

(01-21-2013 01:23 AM)EagleX Wrote:  an hour and a half. not bad. this is a huge board.

Wasn't complaining; just giving a heads up.

(01-21-2013 02:37 AM)randaddyminer Wrote:  Next time the board goes down, we need fake pics

+1

Best. Upgrade. Ever.

Left: Old kernel, less traffic. Right: New kernel, more traffic.

(01-21-2013 12:51 PM)georgia_tech_swagger Wrote:  Best. Upgrade. Ever.

Left: Old kernel, less traffic. Right: New kernel, more traffic.

Yeah, but there is more blood dripping down on the second graph. That's gotta be worrisome, right?

(01-21-2013 07:04 PM)Luckyshot Wrote:  

(01-21-2013 12:51 PM)georgia_tech_swagger Wrote:  Best. Upgrade. Ever.

Left: Old kernel, less traffic. Right: New kernel, more traffic.

Yeah, but there is more blood dripping down on the second graph. That's gotta be worrisome, right?

Nope. The red is CPU waiting on stuff to come in from disk. The huge spikes are from routine flushing of the database replication logs and the big one is from coming back after reboot. For about 5 minutes after initial startup, the database is pretty much going "I NEED EVERYTHING FROM DISK YESTERDAY!!!!!!11". Until we cache out the database into RAM it crawls.

(01-21-2013 12:51 PM)georgia_tech_swagger Wrote:  Best. Upgrade. Ever.

Left: Old kernel, less traffic. Right: New kernel, more traffic.

Decidedly NOT the fake picture we wanted

(01-21-2013 07:34 PM)PirateTreasureNC Wrote:  Decidedly NOT the fake picture we wanted

Guy in a black helicopter said I couldn't do it.

(01-21-2013 07:45 PM)georgia_tech_swagger Wrote:  

(01-21-2013 07:34 PM)PirateTreasureNC Wrote:  Decidedly NOT the fake picture we wanted

Guy in a black helicopter said I couldn't do it.

OTM doesn't have his pilots license.

CUSA board reached the 1 million post recently..... Nice.

I understand very little of this...

I know that the internet is a series of tubes but past that I'm lost.