Databases
StackOverflow2013
Postsdbo
PO
 

Note that there are some explanatory texts on larger screens.

plurals
  1. PO
    primarykey
    data
    text
    <h1>POSIX Clocks</h1> <p>I wrote a benchmark for POSIX clock sources:</p> <ul> <li>time (s) => 3 cycles</li> <li>ftime (ms) => 54 cycles</li> <li>gettimeofday (us) => 42 cycles</li> <li>clock_gettime (ns) => 9 cycles (CLOCK_MONOTONIC_COARSE)</li> <li>clock_gettime (ns) => 9 cycles (CLOCK_REALTIME_COARSE)</li> <li>clock_gettime (ns) => 42 cycles (CLOCK_MONOTONIC)</li> <li>clock_gettime (ns) => 42 cycles (CLOCK_REALTIME)</li> <li>clock_gettime (ns) => 173 cycles (CLOCK_MONOTONIC_RAW)</li> <li>clock_gettime (ns) => 179 cycles (CLOCK_BOOTTIME)</li> <li>clock_gettime (ns) => 349 cycles (CLOCK_THREAD_CPUTIME_ID)</li> <li>clock_gettime (ns) => 370 cycles (CLOCK_PROCESS_CPUTIME_ID)</li> <li>rdtsc (cycles) => 24 cycles</li> </ul> <p>These numbers are from an Intel Core i7-4771 CPU @ 3.50GHz on Linux 4.0. These measurements were taken using the TSC register and running each clock method thousands of times and taking the minimum cost value.</p> <p>You'll want to test on the machines you intend to run on though as how these are implemented varies from hardware and kernel version. The code can be found <a href="https://github.com/dterei/Scraps/blob/master/intel_tsc/eval_clocks.c">here</a>. It relies on the TSC register for cycle counting, which is in the same repo (<a href="https://github.com/dterei/Scraps/blob/master/intel_tsc/tsc.h">tsc.h</a>).</p> <h1>TSC</h1> <p>Access the TSC (processor time-stamp counter) is the most accurate and cheapest way to time things. Generally, this is what the kernel is using itself. It's also quite straight-forward on modern Intel chips as the TSC is synchronized across cores and unaffected by frequency scaling. So it provides a simple, global time source. You can see an example of using it <a href="https://github.com/dterei/Scraps/blob/master/intel_tsc/tsc.h">here</a> with a walkthrough of the assembly code <a href="https://github.com/dterei/Scraps/blob/master/intel_tsc/using_tsc.c">here</a>.</p> <p>The main issue with this (other than portability) is that there doesn't seem to be a good way to go from cycles to nanoseconds. The Intel docs as far as I can find state that the TSC runs at a fixed frequency, but that this frequency may differ from the processors stated frequency. Intel doesn't appear to provide a reliable way to figure out the TSC frequency. The Linux kernel appears to solve this by testing how many TSC cycles occur between two hardware timers (see <a href="http://lxr.free-electrons.com/source/arch/x86/kernel/tsc.c?v=2.6.31#L399">here</a>).</p> <h1>Memcached</h1> <p>Memcached bothers to do the cache method. It may simply be to make sure the performance is more predictable across platforms, or scale better with multiple cores. It may also no be a worthwhile optimization.</p>
    singulars
    1. This table or related slice is empty.
    1. POfaster equivalent of gettimeofday
      singulars
      1. PTQuestion
    1. PTAnswer
    1. USDavid Terei
    1. USDavid Terei
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    2. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    3. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    1. COOn your github link you have the same results, but in nanoseconds, differing from what you write here by factor 1000.
      singulars
      1. PO
      1. USnh2
    2. COsorry, fixed time notation.
      singulars
      1. PO
      1. USDavid Terei
    3. COYour cached_clock method is just hiding in another thread the time consumed by the measuring. Plus it's far way inaccurate compared to other methods. See, if your main loop goes well and current_time==2, you're adding 2 msec each time you loop.
      singulars
      1. PO
      1. USGull_Code
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload