Forget the presentations and the tours with all the impressive blinking lights tapering off to the horizon. It's all about what happens when things go wrong! We've had Alex answer the phone on a weekend and refuse to do anything with a windows server because he only likes Linux, wait for the Windows guys on Mondays. No help, no escalation. End of contract there. Failed mirrored disk? - don't be surprised if they replace the good one. Be aware that the fancy network status websites only include a sample of the actual errors, power outages and faults. Rebuild a simple server? three shifts to do it and the last guy left without leaving the root password. Ignore the data center review sites. They insist you provide a URL that they can track back to the hosting company's network. A brilliant way to ensure happy reviews only because no current customer is going to let the world know their servers are at a horrible hosting site. Make sure the escalation process works. Use fire drills on them to figure out if it really works. Another great question to ask - is their phone system VOIP? If they get a DDOS attack then you can't call them because it takes out their phone system too. The above mentioned analysis of power and cooling is wonderful but if the NOC manager decides not to pay overtime then maintenance gets done in business hours. These are not bottom-feeder companies, these are mid-range or higher price ranges. Either you have to deal with these problems and set the right expectation in their minds, or be prepared to have plenty of backups and be able to move to another company when required.

There's plenty of unschooling in the area I live. My kid meets other kids in the park who are homeschooled but the parents don't teach. 'Go do a craftwork' is fun for small children but it's not going to amuse a 12 y.o. or help them get a job or prepare them for life. That said, very little that I learnt in school applies to my job but I learnt social skills, don't bite, don't fight, don't spit, how to make friends, how to lose friends, how to help friends with problems in their life, how to ask for help. I also learnt about responsibility, deadlines, homework and why you have to do things you don't like. Around here the homeschooling is sometimes motivated by a parent's desire to isolate their children from people not like themselves. Life can't be like that. A school helps you meet different/strange/weird people and you learn they are just like you. I agree with giving kids lots of extra experiences and challenges. If you can do that for your kids then be grateful that you have the time, money and ability to do it. There's lots of struggling parents that want to but can't

Nothing new. I recall reading a software review 10-15 years ago of a system that would review/simulate evacuations of large venues. One of the issues was crowd exits and pillars. Adding pillars to a wide door way created more edges, and more people can slip through on the edges of a doorway than those lined up in an orderly queue. The other issues I recall were that people often wanted to exit the way they entered rather than using the closest exit, so signs had to be clear. And people would like to gather their family or group together first, then exit.

Completely un-ironic - the Computer History musuem in San Jose is in the old SGI building. Do not recall seeing any SGI boxes there tho.

I think you're correct. Modified pages are written to the t-log and the database file is read-only. If a page read is requested the t-log file is checked for a copy otherwise it is read from the database file. When a checkpoint occurs all processing halts and the t-log pages are written to the database file. The checkpoint occurs either at specified times or when a threshold of transactions is reached. So the backup can be a sequential read of the database file plus a read of the t-log and checkpoints are prevented (or run as part of the backup job). The restore process will handle applying the t-log to the restored database. HTH

Maybe they had the same problem we had with our former Tampa/Atlanta based hosting company. When a drive in the RAID 1 failed they jumped in to replace the drive. But they replaced the good drive, not the bad drive. (And don't ask about their SAN where we had a backup and it went offline every few days. Excuse-of-the-minute included they had to replaced all the hard disks, or it cost $200,000 so it must be working, or they "replaced all the wires" because they might have cracked when they moved it from Tampa to Atlanta, even though it was still in Atlanta. Then it wasn't their problem any more because they couldn't do anything about it (except keep billing us $100 per month). Absolutely unbelievable what excuses they could pull out of the air. Thanks idrive.com for clean, reliable off-site backups. ) There is some computer usability study out there where they instructed sys admins in RAID 5 then put them in front of a test server and created various fault scenarios. All the data loss was caused by people pulling out the wrong drive or doing the wrong thing.