![]() | |||||||||||||
Messages in this thread |
On Mon, 20 Nov 2006, Jens Axboe wrote: > > > Must we introduce memory allocations in srcu_read_lock()? It makes it > > > much harder and nastier for me to use. I'd much prefer a failing > > > init_srcu(), seems like a much better API. > > > > Paul agrees with you that allocation failures in init_srcu() should be > > passed back to the caller, and I certainly don't mind doing so. > > > > However we can't remove the memory allocation in srcu_read_lock(). That > > was the point which started this whole thread: the per-cpu allocation > > cannot be done statically, and some users of a static SRCU structure can't > > easily call init_srcu() early enough. > > > > Once the allocation succeeds, the overhead in srcu_read_lock() is minimal. > > It's not about the overhead, it's about a potentially problematic > allocation. I'm not sure what you mean by "problematic allocation". If you successfully call init_srcu_struct then the allocation will be taken care of. Later calls to srcu_read_lock won't experience any slowdowns or problems. If your call to init_srcu_struct isn't successful then you have to decide how to handle it. You can ignore the failure and live with degraded performance (caused by cache-line contention and repeated attempts to do the per-cpu allocation), or you can give up entirely. Does this answer your objection? If not, can you explain in more detail what other features you would like? Alan Stern - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ | ||||||||||||
| Last update: 2006-11-20 21:43 [from the cache] ©2003-2008 | |||||||||||||