why is it that every company that has a blog either, a) doesn't have a link or b) buries the link to their main product site on their blog?
MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
21–30 of 30 posts
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#22why is it that every company that has a blog either, a) doesn't have a link or b) buries the link to their main product site on their blog?
Often because the blog is run on a separate software platform from the main site.
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#23Nice product. I'll try this out. It seems like the isolation level is Read Committed. Are there plans to support higher isolation levels (Serialisability)?
This is in the books. It's tricky to do it on the cluster and has perf implications, but it is doable and we have a design for that.
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#24I blogged about this in some detail this morning.
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#25why is it that every company that has a blog either, a) doesn't have a link or b) buries the link to their main product site on their blog?
Often because the blog is run on a separate software platform from the main site.
Still no excuse.
I've educated multiple vendors on the subject. E.g., see the last point on http://www.strategicmessaging.com/marketing-communications-t... :)
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#26Earlier quoted context omitted.
kdb+ is compressed columnar in memory on a single box with a very exotic language called Q. memsql is row-based in memory across n-machines using SQL.
kdb+ is also very fast for real-time time series analysis and signal generation. Seeing Morgan Stanley and Credit Suisse in the customer list made me wonder if memsql could become a competitor in the niche that kdb+ currently dominates?
Yes, if we note that there are core niches where nobody will replace kdb+ any time soon.
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#27I'm surprised these guys haven't been sued by Microsoft yet. I think the founder himself worked on a similar project at MSFT called Hekaton and moved out. Atleast that is what I heard from a couple of devs he tried to recruit out of sql. I'd advise startups to be weary of jumping ship.
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#28Looks great!
Quick question: since data is uniformly spread across n leaf nodes, do queries that require checking a number of rows >> n hit nearly every leaf? If so, does this create latency problems when n is large? (since it'd only take one slow request out of n to cause high latency)
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#29Earlier quoted context omitted.
Try again - I found the bottom ticks were 8 cores and 256GB.
Fair enough - I had considered that to be on the axis since it's the minimum value, and thus not a tick, but visually it certainly is represented as a tick. At any rate, the point I was trying to make is that they clearly expect you to throw a lot of hardware at these systems.
Sure, but a lot of projects LIKE this have an open source project for those people NOT in the enterprise, and who probably won't be running more than 8-24 cores or so.
On a related note, changing the amount of RAM seems to only change the amount of RAM, not any of the other numbers. I guess that's their point, but I would rather they just SAY that than make me try a bunch of options to show that RAM doesn't matter. :|
Re: MemSQL ships 2.0, scales across hundreds of nodes, thousands of cores
#30Looks great! Quick question: since data is uniformly spread across n leaf nodes, do queries that require checking a number of rows >> n hit nearly every leaf? If so, does this create latency problems when n is large? (since it'd only take one slow request out of n to cause high latency)
Yes, we will fan out queries when necessary. In a hard core oltp workload this will affect latency across the system by flooding the network (if you send too many of these queries at once) but we expose knobs that let you limit these queries' parallelism to keep the rest of the system really fast.