Re: [tipc-discussion] [PATCH 5/5] tipc: add ip/udp media type

[Erik H. <eri...@er...>]

On Mon, Jan 05, 2015 at 06:11:45PM +0100, Jon Maloy wrote:
> >  #define MAX_BEARERS	2
> 
> This has already been extended to 8 upstream.
> You will have a conflict.

No it's still 2 there.

> > +void tipc_udp_send(struct work_struct *work) {
> > +	struct msghdr msg;
> > +	struct kvec iov;
> > +	struct sk_buff *skb;
> > +	struct udp_skb_parms *parms;
> > +	struct udp_bearer *ub;
> > +	int err;
> > +
> > +	ub = container_of(work, struct udp_bearer, tx_work);
> > +	memset(&msg, 0, sizeof(struct msghdr));
> > +	while (!list_empty(&ub->txq)) {
> > +		spin_lock_bh(&ub->txq_lock);
> > +		parms = list_first_entry(&ub->txq, struct udp_skb_parms,
> > next);
> 
> Same objection as for the previous version: dynamic allocations on the
> critical data path should be avoided.  Why not use TIPC_SKB_CB for this,
> as I suggested?

Fixed, thanks.

> > +/**
> > + * tipc_send_msg - enqueue a send request
> > + *
> > + * The send request need to be deferred since we cannot call kernel
> > + * socket API functions while holding the node spinlock.
> > + */
> 
> Yes. Unfortunately this is necessary for now, but we should aim at
> releasing the node spinlock before sending the buffers, on all
> bearers. This will probably have some positive impact on performance.
>

What's holding me from sending another version now is the skb reallocation
from kernel_sendmsg().
On lowmem systems this is causing the kworker thread to spin heavily on memory
allocation because it has run out of memory in the kmalloc-2048 pool.
It should be possible to reuse the TIPC skb and pass that to the IP stack, but
i don't know exactly how to do this.

//E