... . It will greatly reduce the speed at which > ramback can flush dirty data because ... in the noise (either one could be faster, depending on the exact conditions) you ... for example, are inherently more > reliable than a Linux based solution. Well guess ...

linux-kernel - david - Mar 15 2008 - 19:22

... this: Is it really 25 times faster than > > > >> ext3 with an equally huge ... tar; time sync > > Thats cheating. Your ramback ignores sync. > > Just time it against ... these transaction speeds together with data durability. I have mentioned a number of ...

linux-kernel - Daniel Phillips - Mar 15 2008 - 16:22

... able to recover data after a system crash, power outage or ... reduces uptime. These are > potential ramback users, and in fact I ... presented at CES2008, with sales announced for Q3. So clearly this ... solution to replace a disk in a RAM-speed appliance. Willy ...

linux-kernel - Willy Tarreau - Mar 15 2008 - 17:54

... I want to know is this: Is it really 25 times faster than > > >> ext3 with an equally huge ... 10 times normal speed, and still more reliable than ramback. Pavel -- (english) ... linux-kernel" in the body of a message to majordomo@vger.kernel.org ...

linux-kernel - Pavel Machek - Mar 15 2008 - 09:32

... : Is it really 25 times faster than > > > > > >> ext3 with an equally huge ... ; time sync > > > > > > Thats cheating. Your ramback ignores sync. > > > > > > Just time it against ... missing features that ramback supplies before you have a filesystem-level ...

linux-kernel - Daniel Phillips - Mar 15 2008 - 17:47

... . It will greatly reduce the speed at which > ramback can flush dirty data because ... for example, are inherently more > reliable than a Linux based solution. Well guess ... been presented at CES2008, with sales announced > > for Q3. So clearly this will ...

linux-kernel - Willy Tarreau - Mar 15 2008 - 19:22

... business against them if being a few milliseconds slower on the ... saying that my driver is faster than any script you can ... supplies with independent UPS backup * Ramback driver My proposition is, you ... and set them up as a failover cluster. (Helps that the ...

linux-kernel - Daniel Phillips - Mar 13 2008 - 05:16

... : Is it really 25 times faster than > > > > >> ext3 with an equally huge ... ; time sync > > > > Thats cheating. Your ramback ignores sync. > > > > Just time it against ... to implement, either in kernelor as a LD_PRELOAD hack. So... untar with sync ...

linux-kernel - Pavel Machek - Mar 15 2008 - 17:33

... will greatly reduce the speed at which ramback can flush dirty ... example, are inherently more reliable than a Linux based solution. Well ... presented at CES2008, with sales announced > for Q3. So clearly this ... the same company has got a 5 TB flash box coming ...

linux-kernel - Daniel Phillips - Mar 15 2008 - 18:33

... 25 performance increase really helps. > > Ramback is a new virtual device with the ... seek-intensive applications. > > The difference between ramback and an ordinary ramdisk is: ... operations once again run at ramdisk speed. > > So now you can ask some ...

linux-kernel - Grzegorz Kulewski - Mar 10 2008 - 03:51

... saying that my driver is faster than any script you can ... supplies with independent UPS backup > * Ramback driver > > My proposition is, you ... system. if you're running a datacenter that cares about uptime ... t always work, and as a result you figure out how ...

linux-kernel - david - Mar 13 2008 - 12:25

... until flushing completes. This allows only a small amount of application traffic, something ... during shutdown > + find / | xargs cat > > ...is ramback, right? Should have same performance, ... ext2+tweaks is slower than ramback, we have a bug to fix, ...

linux-kernel - Daniel Phillips - Mar 15 2008 - 16:51

... > > because it is not populated yet. > > > > > > Wouldn't a raid-1 set comprising disk + ramdisk do that with ... disk speed. Reads run at ramdisk > > speed, so your proposal sounds useful, but ramback aims for high > > write performance as well. > > ...

linux-kernel - Daniel Phillips - Mar 15 2008 - 17:05

... or > similar interfaces and honour them. Ramback should obviously respect barriers, and it does, ... > That is why I keep recommending that a ramback setup be replicated or > > ... apparently do not need or want the speed. Anyway, please do not get the ...

linux-kernel - Daniel Phillips - Mar 15 2008 - 18:00

... GB ramdisk > > * Handle chunk size other than PAGE_SIZE. > > If you are prepared to ... IMHO The finer the granularity the faster the ramdisk syncs to backing store. ... the ramback design: the backing store is not expected to represent a consistent ...

linux-kernel - Daniel Phillips - Mar 10 2008 - 23:50

... >> project appealing to a lot more people than it would appeal ... even give you that you're doing D2D backups) or other ... engineers time by getting them faster disks, more disk space, bigger ... that the consequences of a single RamBack system failure aren't ...

linux-kernel - John Stoffel - Mar 14 2008 - 10:00

... >> > because it is not populated yet. >> >> Wouldn't a raid-1 set comprising disk + ramdisk do that with ... disk speed. Reads run at ramdisk > speed, so your proposal sounds useful, but ramback aims for high > write performance as well. Ramback could ...

linux-kernel - Jeff Moyer - Mar 14 2008 - 13:53

... intermediate > > > writes. It isn't a normal failure mode and there ... uptime > and downtime. We're more facing a problem of MTBF, ... reduces uptime. These are potential ramback users, and in fact I ... have the speed of RAM with the reliability of a properly ...

linux-kernel - Daniel Phillips - Mar 15 2008 - 17:17

... have a steady, heavy write load onto ramback. Eventually, the entire ramdisk will be dirty ... but your proposal does. It gets worse than that. Suppose somebody writes the same ... > I want the speed and reliability. Without that ramback is a distraction > ...

linux-kernel - Daniel Phillips - Mar 16 2008 - 17:57

... 46:16PM -0800, Daniel Phillips wrote: > Set ramback to flush mode: > > echo 1 >/proc/ ... > > watch -n1 cat /proc/driver/ramback/ Use debugfs for stuff like debug ... linux-kernel" in the body of a message to majordomo@vger.kernel.org More ...

linux-kernel - Greg KH - Mar 11 2008 - 01:06