Timer-based delays are more robust on systems that use frequency scaling to dynamically adjust the processor's speed at runtime, as loops_per_jiffies values may not necessarily scale linearly. This implementation was released in Version 3.6 of the Linux kernel.
In 2012, ARM contributed a new udelay implementation allowing the system timer built into many ARMv7 CPUs to be used instead of a busy-wait loop. Static void delay_loop ( long loops ) įull and complete information and details about BogoMips, and hundreds of reference entries can be found in the (outdated) BogoMips mini-Howto. For i386 architecture delay_loop is implemented in /usr/src/linux/arch/i386/lib/delay.c as: Note that a busy waiting technique is used, so the kernel is effectively blocked when executing ndelay/ udelay functions.
#Chart of cpuinfo model vs name drivers
These functions are needed by some drivers to wait for hardware. Loops_per_jiffy is used to implement udelay (delay in microseconds) and ndelay (delay in nanoseconds) functions. * check whether any asynchronous event happened or not * Now, by looking at post_start and pre_start difference, we can * Note, we don't know anything about order of 2 and 3. post_start <- When we are sure that jiffy switch has happened start <- timer value before or after jiffy switch pre_start <- When we are sure that jiffy switch hasn't happened * event can happen between these two events introducing errors in lpj. * happened first or timer_value was read first. As we don't really know whether jiffy switch It computes the Linux kernel timing parameter loops_per_jiffy (see jiffy) value. With kernel 2.6.x, BogoMIPS are implemented in the /usr/src/linux/init/calibrate.c kernel source file. In Linux, BogoMips can be easily obtained by searching the cpuinfo file: The changed BogoMips outcome had no effect on real processor performance. Although the BogoMips algorithm itself wasn't changed, from that kernel onward the BogoMips rating for then current Pentium CPUs was twice that of the rating before the change. With the 2.2.14 Linux kernel, a caching setting of the CPU state was moved from behind to before the BogoMips calculation. Intel Xeon MP (32-bit) ( hyper-threading) The index is the ratio of "BogoMips per clock speed" for any CPU to the same for an Intel 386DX CPU, for comparison purposes. The given rating is typical for that CPU with the then current and applicable Linux version.
Proper BogoMips ratings Īs a very approximate guide, the BogoMips can be pre-calculated by the following table. The reasons (there are two) it is printed during boot-up is that a) it is slightly useful for debugging and for checking that the computers caches and turbo button work, and b) Linus loves to chuckle when he sees confused people on the news. Hence, the BogoMips value gives some indication of the processor speed, but it is way too unscientific to be called anything but BogoMips. "Bogo" comes from "bogus", i.e, something which is a fake. Hence, the kernel measures at boot time how fast a certain kind of busy loop runs on a computer. The linux kernel version 0.99.11 (dated 11 July 1993) needed a timing loop (the time is too short and/or needs to be too exact for a non-busy-loop method of waiting), which must be calibrated to the processor speed of the machine. Like most such measures, it is more often abused than used properly (it is very difficult to justly compare MIPS for different kinds of computers). It is a measure for the computation speed of a processor. MIPS is short for Millions of Instructions Per Second. In 1993, Lars Wirzenius posted a Usenet message explaining the reasons for its introduction in the Linux kernel on comp.os.linux:
0 kommentar(er)
