> > RAID controllers do not have half a terabyte of RAM.It makes a lot of difference, and in addition raid controllers (good ones) respect barrier ordering in their RAM cache so they'll take tags or similar interfaces and honour them. Either you keep a mirror in sync and get normal data rates or you keep the mirror out of sync and then you need to sort your writeback process out to preserve ordering. If you want ramback to be taken seriously then that is the interesting problem to solve and clearly has multiple solutions if you would start to take an objective look at your work. --
| Junio C Hamano | [ANNOUNCE] GIT 1.6.0 |
| Linus Torvalds | Re: [ANNOUNCE] mdb: Merkey's Linux Kernel Debugger 2.6.27-rc4 released |
| Bart Van Assche | Integration of SCST in the mainstream Linux kernel |
| Paul Menage | Re: [RFC][PATCH 6/7] Account for the number of tasks within container |
git: | |
| Nicolas Pitre | Re: pack operation is thrashing my server |
| Scott Chacon | Git Community Book |
| Greg KH | Re: [ANNOUNCE] pg - A patch porcelain for GIT |
| Lars Hjemli | [PATCH] git-merge: add option --no-ff |
| GVG GVG | ssh_exchange_identification: Connection closed by remote host |
| Nick Guenther | Re: Real men don't attack straw men |
| Travers Buda | Re: Important OpenBSD errata |
| Gregory Edigarov | How to re-build openssl with SHA1 support? |
| Al Boldi | [RFC] VM: I have a dream... |
| Dave Kleikamp | Re: [RFC] Heads up on sys_fallocate() |
| Jörn | Review status (Re: [PATCH] LogFS take three) |
| Chris Mason | [ANNOUNCE] Btrfs v0.12 released |
