update user guide with IOPS and latency numbers for each iteration.
Signed-off-by: Mohamad Chaarawi <mohamad.chaarawi@intel.com>master
parent
12284ae04a
commit
0d0df855e6
|
@ -550,6 +550,17 @@ HOW DOES IOR CALCULATE PERFORMANCE?
|
||||||
operations (-g), the sum of the open, transfer, and close times may not equal
|
operations (-g), the sum of the open, transfer, and close times may not equal
|
||||||
the elapsed time from the first open to the last close.
|
the elapsed time from the first open to the last close.
|
||||||
|
|
||||||
|
After each iteration (-i) IOR reports performance for that iteration, and
|
||||||
|
those numbers include:
|
||||||
|
|
||||||
|
- Bandwidth (described above)
|
||||||
|
|
||||||
|
- IOPS: I/O rate (operations per second) achieved by all tasks given the total
|
||||||
|
time spent in reading and writing the data.
|
||||||
|
|
||||||
|
- Latency: computed by taking the average latency of all I/O operations from a
|
||||||
|
single task. If ior is run with multiple tasks, then the latency reported is
|
||||||
|
the minimum that was computed between all tasks.
|
||||||
|
|
||||||
HOW DO I ACCESS MULTIPLE FILE SYSTEMS IN IOR?
|
HOW DO I ACCESS MULTIPLE FILE SYSTEMS IN IOR?
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue