> -----Original Message----- > From: Olivier Matz [mailto:olivier.matz at 6wind.com] > Sent: Friday, March 25, 2016 3:56 AM > To: Venkatesan, Venky <venky.venkatesan at intel.com>; Lazaros Koromilas > <l at nofutznetworks.com>; Wiles, Keith <keith.wiles at intel.com> > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH] mempool: allow for user-owned mempool > caches > > Hi Venky, > > >> The main benefit of having an external cache is to allow mempool > >> users > >> (threads) to maintain a local cache even though they don't have a > >> valid lcore_id (non-EAL threads). The fact that cache access is done > >> by indexing with the lcore_id is what makes it difficult... > > > > Hi Lazaros, > > > > Alternative suggestion: This could actually be very simply done via creating > an EAL API to register and return an lcore_id for a thread wanting to use > DPDK services. That way, you could simply create your pthread, call the > eal_register_thread() function that assigns an lcore_id to the caller (and > internally sets up the per_lcore variable. > > > > The advantage of doing it this way is that you could extend it to other > things other than the mempool that may need an lcore_id setup. > > From my opinion, externalize the cache structure as Lazaros suggests would > make things simpler, especially in case of dynamic threads > allocation/destruction. > > If a lcore_id regristration API is added in EAL, we still need a max lcore > value > when the mempool is created so the cache can be allocated. Moreover, the > API would not be as simple, especially if it needs to support secondary > processes. > Not really - the secondary process is simply another series of threads. They have their own caches. Yes, we will need a max lcore value, but we can make the allocations dynamic as opposed to static. That way, we will have MAX_LCORE pointers to store per mempool.
The approach that's suggested currently is workable (and if I were solving mempool alone, this is very likely what I would do too), but is limited to the mempool alone. Adding the API to the eal has a rather huge secondary advantage - you now no longer need to create DPDK threads explicitly any more - you can create pthreads, and manage them how you wish. Architecturally speaking, longer term for DPDK that would be bigger win. > > Regards, > Olivier
