Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

An Overview of Kernel Lock Improvements [pdf]

events.linuxfoundation.org

Post reply on HN
Print view View original

11–12 of 12 posts

Re: An Overview of Kernel Lock Improvements [pdf]

#11

Post by ck2 »

yxhuvud wrote: post #7

It would be interesting to see the same benchmarks for more normal amounts of cores. Most system does not have 240 cores, after all..

You can get 20core/40thread servers for $400/mo these days:

http://www.ovh.com/us/dedicated-servers/enterprise/2014-MG-2...

or 16core/32thread for $270

http://www.ovh.com/us/dedicated-servers/enterprise/2014-MG-1...

So double socket performance drop is a realistic concern.

Re: An Overview of Kernel Lock Improvements [pdf]

#12

Post by davidlohr »

yxhuvud wrote: post #7

It would be interesting to see the same benchmarks for more normal amounts of cores. Most system does not have 240 cores, after all..

Most of these optimizations imply scaling by number of cores. Thus the more cores (and thus sockets/NUMA nodes), the more the benefit. Desktop-ish systems with ~4 cores don't see much gain, but nor did we introduce performance degradations.
Post reply on HN