| To: | Thomas Graf <tgraf@xxxxxxx> |
|---|---|
| Subject: | Re: [RESEND PATCH 2/3] NET: Generic rate estimator |
| From: | jamal <hadi@xxxxxxxxxx> |
| Date: | 04 Oct 2004 16:07:01 -0400 |
| Cc: | "David S. Miller" <davem@xxxxxxxxxxxxx>, netdev@xxxxxxxxxxx |
| In-reply-to: | <20041004193016.GD15898@postel.suug.ch> |
| Organization: | jamalopolous |
| References: | <20041003213124.GG14344@postel.suug.ch> <20041003213954.GI14344@postel.suug.ch> <20041003161436.50293f9a.davem@davemloft.net> <20041003233647.GN14344@postel.suug.ch> <1096852582.1046.378.camel@jzny.localdomain> <20041004125300.GA15898@postel.suug.ch> <1096896256.1072.4.camel@jzny.localdomain> <20041004141532.GB15898@postel.suug.ch> <1096901984.1073.9.camel@jzny.localdomain> <20041004193016.GD15898@postel.suug.ch> |
| Reply-to: | hadi@xxxxxxxxxx |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Mon, 2004-10-04 at 15:30, Thomas Graf wrote: > Resend of generic rate estimator patch. The HZ%4 check has been removed > and jiffies calculation has been adapted to avoid carrying on unacuracy. > Small variance for 250ms interval happens with HZ values of 122 and 50. Ok, I did some test as well here - and the change you made gives better results. Can you also change net/sched/estimator.c to behave the same way? BTW, anything else that changed since last time other than the timer adjustment ? cheers, jamal |
| Previous by Date: | [PATCH 2.6.9-rc3-mm2 5/5] r8169: cleanup, Francois Romieu |
|---|---|
| Next by Date: | Re: bad TSO performance in 2.6.9-rc2-BK, David S. Miller |
| Previous by Thread: | [RESEND PATCH 2/3] NET: Generic rate estimator, Thomas Graf |
| Next by Thread: | Re: [RESEND PATCH 2/3] NET: Generic rate estimator, Thomas Graf |
| Indexes: | [Date] [Thread] [Top] [All Lists] |