| To: | pcp@xxxxxxxxxxx |
|---|---|
| Subject: | Re: [pcp] pmlogger performance |
| From: | Ken McDonell <kenj@xxxxxxxxxxxxxxxx> |
| Date: | Tue, 16 Jul 2013 17:50:40 +1000 |
| Delivered-to: | pcp@xxxxxxxxxxx |
| In-reply-to: | <51E4ADD0.6060806@xxxxxxxxxx> |
| References: | <51E374C4.5@xxxxxxxxxx> <51E4A12C.5000003@xxxxxxxxxxxxxxxx> <51E4A7DE.1090307@xxxxxxxxxx> <51E4A93F.4070505@xxxxxxxxxxxxxxxx> <51E4ADD0.6060806@xxxxxxxxxx> |
| User-agent: | Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130623 Thunderbird/17.0.7 |
On 16/07/13 12:20, Stan Cox wrote: On 07/15/2013 10:00 PM, Ken McDonell wrote:If the benchmark was using 80% of the available CPU cyclesHave a recommendation for a worthy benchmark? Perhaps mysql or postgres? If I am understanding the experiment correctly, the benchmark does not really matter ... you just want something to generate some background load. Simple is probably best IMHO.I'd suggest sysbench run with the attached script I hacked up ... it makes my 6 CPU machine 80% cpu busy and smacks the disks. Have fun.
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | pcp updates: unix domain sockets, Nathan Scott |
|---|---|
| Next by Date: | pcp updates - a few odds and sods, Ken McDonell |
| Previous by Thread: | Re: [pcp] pmlogger performance, Stan Cox |
| Next by Thread: | Re: [pcp] pmlogger performance, Stan Cox |
| Indexes: | [Date] [Thread] [Top] [All Lists] |