[dpdk-dev] [PATCH v3 13/15] vhost: cache address translation result

[Liu, Yong]

> -----Original Message-----
> From: Bie, Tiwei
> Sent: Thursday, September 26, 2019 1:32 PM
> To: Liu, Yong <yong.liu at intel.com>
> Cc: maxime.coquelin at redhat.com; Wang, Zhihong <zhihong.wang at intel.com>;
> stephen at networkplumber.org; gavin.hu at arm.com; dev at dpdk.org
> Subject: Re: [PATCH v3 13/15] vhost: cache address translation result
> 
> On Thu, Sep 26, 2019 at 01:13:27AM +0800, Marvin Liu wrote:
> > Cache address translation result and use it in next translation. Due
> > to limited regions are supported, buffers are most likely in same
> > region when doing data transmission.
> >
> > Signed-off-by: Marvin Liu <yong.liu at intel.com>
> >
> > diff --git a/lib/librte_vhost/rte_vhost.h b/lib/librte_vhost/rte_vhost.h
> > index 7fb172912..d90235cd6 100644
> > --- a/lib/librte_vhost/rte_vhost.h
> > +++ b/lib/librte_vhost/rte_vhost.h
> > @@ -91,10 +91,18 @@ struct rte_vhost_mem_region {
> >  	int fd;
> >  };
> >
> > +struct rte_vhost_mem_region_cache {
> > +	uint64_t guest_phys_addr;
> > +	uint64_t guest_phys_addr_end;
> > +	int64_t host_user_addr_offset;
> > +	uint64_t size;
> > +};
> > +
> >  /**
> >   * Memory structure includes region and mapping information.
> >   */
> >  struct rte_vhost_memory {
> > +	struct rte_vhost_mem_region_cache cache_region;
> 
> This breaks ABI.
> 
Got, will remove it as no clear performance gain with this patch.

> >  	uint32_t nregions;
> >  	struct rte_vhost_mem_region regions[];
> >  };
> > @@ -232,11 +240,30 @@ rte_vhost_va_from_guest_pa(struct rte_vhost_memory
> *mem,
> >  	struct rte_vhost_mem_region *r;
> >  	uint32_t i;
> >
> > +	struct rte_vhost_mem_region_cache *r_cache;
> > +	/* check with cached region */
> > +	r_cache = &mem->cache_region;
> > +	if (likely(gpa >= r_cache->guest_phys_addr && gpa <
> > +		   r_cache->guest_phys_addr_end)) {
> > +		if (unlikely(*len > r_cache->guest_phys_addr_end - gpa))
> > +			*len = r_cache->guest_phys_addr_end - gpa;
> > +
> > +		return gpa - r_cache->host_user_addr_offset;
> > +	}
> 
> Does this help a lot in performance?
> We can implement this caching for builtin backend first.
> 
Tiwei,

It won’t help too much in performance as region number will be 1 at most of times.
Will remove cache function in next version.

Thanks,
Marvin
> 
> > +
> > +
> >  	for (i = 0; i < mem->nregions; i++) {
> >  		r = &mem->regions[i];
> >  		if (gpa >= r->guest_phys_addr &&
> >  		    gpa <  r->guest_phys_addr + r->size) {
> >
> > +			r_cache->guest_phys_addr = r->guest_phys_addr;
> > +			r_cache->guest_phys_addr_end = r->guest_phys_addr +
> > +						       r->size;
> > +			r_cache->size = r->size;
> > +			r_cache->host_user_addr_offset = r->guest_phys_addr -
> > +							 r->host_user_addr;
> > +
> >  			if (unlikely(*len > r->guest_phys_addr + r->size - gpa))
> >  				*len = r->guest_phys_addr + r->size - gpa;
> >
> > --
> > 2.17.1
> >