[PATCH] Add option for terse parseable output
[fio.git] / README
diff --git a/README b/README
index c951504eb52925c46678195d1783abd219ebf01f..d6ff1096ce4c8482adab333b626e8aac2f2fd07c 100644 (file)
--- a/README
+++ b/README
@@ -48,6 +48,7 @@ $ fio
        -w Generate per-job bandwidth logs
        -f <file> Read <file> for job descriptions
        -o <file> Log output to file
+       -m Minimal (terse) output
        -h Print help info
        -v Print version information and exit
 
@@ -303,6 +304,31 @@ util=              The disk utilization. A value of 100% means we kept the disk
                busy constantly, 50% would be a disk idling half of the time.
 
 
+Terse output
+------------
+
+For scripted usage where you typically want to generate tables or graphs
+of the results, fio can output the results in a comma seperated format.
+The format is one long line of values, such as:
+
+client1,0,0,936,331,2894,0,0,0.000000,0.000000,1,170,22.115385,34.290410,16,714,84.252874%,366.500000,566.417819,3496,1237,2894,0,0,0.000000,0.000000,0,246,6.671625,21.436952,0,2534,55.465300%,1406.600000,2008.044216,0.000000%,0.431928%,1109
+
+Split up, the format is as follows:
+
+       jobname, groupid, error
+       READ status:
+               KiB IO, bandwidth (KiB/sec), runtime (msec)
+               Submission latency: min, max, mean, deviation
+               Completion latency: min, max, mean, deviation
+               Bw: min, max, aggreate percentage of total, mean, deviation
+       WRITE status:
+               KiB IO, bandwidth (KiB/sec), runtime (msec)
+               Submission latency: min, max, mean, deviation
+               Completion latency: min, max, mean, deviation
+               Bw: min, max, aggreate percentage of total, mean, deviation
+       CPU usage: user, system, context switches
+
+
 Author
 ------