| To: | Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> |
|---|---|
| Subject: | [patch/RFC]: Asynchronous IPsec processing benchmark. |
| From: | Evgeniy Polyakov <johnpol@xxxxxxxxxxx> |
| Date: | Tue, 03 May 2005 17:38:27 +0400 |
| Cc: | netdev@xxxxxxxxxxx, Patrick McHardy <kaber@xxxxxxxxx>, "David S. Miller" <davem@xxxxxxxxxxxxx>, Jamal Hadi Salim <hadi@xxxxxxxxxx> |
| In-reply-to: | <1115117728.3414.48.camel@uganda> |
| Organization: | MIPT |
| References: | <20050429144103.A23268@2ka.mipt.ru> <20050503095312.GA29788@gondor.apana.org.au> <1115115502.3414.22.camel@uganda> <20050503101447.GA29973@gondor.apana.org.au> <1115116295.3414.30.camel@uganda> <20050503102929.GA30097@gondor.apana.org.au> <1115117728.3414.48.camel@uganda> |
| Reply-to: | johnpol@xxxxxxxxxxx |
| Sender: | netdev-bounce@xxxxxxxxxxx |
Here are some numbers:
./netperf -l 60 -H gw -t TCP_STREAM -i 10,2 -I 99,5 -- -m 4096 -s 57344
-S 57344
TCP STREAM TEST to gw : +/-2.5% @ 99% conf.
async-ipsec, 10^6bits/sec: 35.42
sync-ipsec, 10^6bits/sec: 37.11
So even with existing timer deferring it is not noticebly slower [about
4%].
And I think that benefits it provides definitely cost that price and
compile time option.
--
Evgeniy Polyakov
Crash is better than data corruption -- Arthur Grabowski
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: icmp_unreachable uses wrong ip, Hasso Tepper |
|---|---|
| Next by Date: | Re: IPsec performance, Dave Dillow |
| Previous by Thread: | Re: [patch/RFC]: Asynchronous IPsec processing., Evgeniy Polyakov |
| Next by Thread: | Re: [patch/RFC]: Asynchronous IPsec processing benchmark., jamal |
| Indexes: | [Date] [Thread] [Top] [All Lists] |
