-----Original Message----- From: Vincent Fu [mailto:Vincent.Fu@xxxxxxxxxxx] Sent: Tuesday, September 22, 2015 10:29 AM To: Jon Tango <cheerios123@xxxxxxxxxxx>; fio@xxxxxxxxxxxxxxx Subject: Re: Latency Output Question On 2015-9-19 1:33 PM, Jon Tango wrote: > Hello All, I took a measurement with an 4k workload with a 90% mixture > of reads and 10 % writes. > > The latency output in the test result is: > > Read lat avg=490.27 > Write lat avg=191.78 > > Is this the correct way to calculate the latency? 490+192 is 682, and > then 682/2? > > Or, do I need to account for the 90/10 distribution when I calculate > latency? > > Alos, is there a way to just get one average latency output, instead > of a separate one for read, and write? > -- > To unsubscribe from this list: send the line "unsubscribe fio" in the > body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at > http://vger.kernel.org/majordomo-info.html > Use the option below to combine reads and writes in the latency output: unified_rw_reporting=bool Fio normally reports statistics on a per data direction basis, meaning that read, write, and trim are accounted and reported separately. If this option is set, the fio will sum the results and report them as "mixed" instead.. ------------------- Thank you for the guidance. However, I have tested significantly with the unified_rw_reporting option, and it combines them in the group data outputs - but it does not combine read/write in the logs created with the write_iops_log or write_lat_log command. When parsing the latency data from the write_lat_log outputs, should I merely divide the results by 2, or should I use a weighted average that reflects the read/write mixture? Also, is there a way to get fio to combine read/write latency in the write_lat_log outputs? ________________________________ PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). -- To unsubscribe from this list: send the line "unsubscribe fio" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
