Hi again, > > Hi > > On many links regarding user space hanlding of packets I have read > warnings about using libipq, speed wise .... "do this only if u dont want > ultra high speeds and all" ... this speed issue arises because we need to > copy things from kernel space to usr space and vice versa, or is there any > other reason for this. I mean suppose i want to make a process that gets > the packets from the kernel and plays with them and then reinjects them > into the kernel( my process has to be in user space) ... keeping this > constraint in mind (the process that tinkers with the packets has to be in > user space), is there any faster solution than using libipq i.e do these > warnings just mean that using libipq gives slower results when if packet > mangling is done in the kernel space itself .. which is quite obvious, or > do they mean that we can have better ways(faster) than libipq for user > space packet mangling. I think the speed penalty is caused by userspace processing and delivery from kernel to userspace and vice versa. This should not be particular for libipq. Jee > thanks > Amit > > "DISCLAIMER: This message is proprietary to Hughes Software Systems Limited > (HSS) and is intended solely for the use of the individual to whom it is > addressed. It may contain privileged or confidential information and > should not be circulated or used for any purpose other than for what it is > intended. If you have received this message in error, please notify the > originator immediately. If you are not the intended recipient, you are > notified that you are strictly prohibited from using, copying, altering, or > disclosing the contents of this message. HSS accepts no responsibility for > loss or damage arising from the use of the information transmitted by this > email including damage from virus." > > >
