| To: | P@xxxxxxxxxxxxxx |
|---|---|
| Subject: | Re: gettimeofday scalability |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Tue, 5 Oct 2004 11:35:12 -0700 |
| Cc: | netdev@xxxxxxxxxxx, mingo@xxxxxxx, andrea@xxxxxxx |
| In-reply-to: | <4162CD76.4070204@xxxxxxxxxxxxxx> |
| References: | <4162CD76.4070204@xxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Tue, 05 Oct 2004 17:36:06 +0100 P@xxxxxxxxxxxxxx wrote: > So can anyone summarise the relative merits of these locking > mechanisms, before I start benchmarking? Seq locks plus the timer interpolator layer found in 2.6.x kernels is the most scalable gettimeofday() implementation currently. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | [PATCH] [IPVS] Fix endian problem on sync message size, Wensong Zhang |
|---|---|
| Next by Date: | Re: [PATCH] [IPVS] Fix endian problem on sync message size, David S. Miller |
| Previous by Thread: | gettimeofday scalability, P |
| Next by Thread: | Re: gettimeofday scalability, Stephen Hemminger |
| Indexes: | [Date] [Thread] [Top] [All Lists] |