好像大家都在说 ET 要比 LT 快哈,曾经我也是这一派的。但是另一派的人有说,就连那些“古董级”人物都不敢说自己有把握用好 ET,然后结合我自己对 ET 和 LT 的理解和认知,在看到这个议题的时候,我还真有点犹豫。
说说我的理解哈:
1、内核把就绪队列的任务拷贝到用户态,并清空就绪列表。这一点大家已经达成了共识。
2、ET 也就到此为止了,LT 不一定到此为止。这一点应该也是达成共识了吧,不会有人认为 LT 到此一定不止吧?那我们可以从这里来唠嗑唠嗑。
3、如果任务没处理完,LT 会把 fd 拷贝回就绪链表。下一次任务从内核态拷贝到用户态时这些任务会再次被发送给业务处理。这里就不知道我们是不是共识了哈。
那如果是这样,我是不是可以说:只要任务每次都处理完了,其实 LT 和 ET 就不知道区别在哪里了?
我是不是还可以说:如果业务没处理完,ET 就丢任务了。
那这么一看,我的猜想就很明显了。
但是吧,猜想归猜想,epoll 的源码又不长,以前也不是没看过。网上下一份,网上关于 epoll 源码剖析的文章也不少,阅读起来难度不会很高,那就花这么一两个小时的时间解决一下这个问题吧。
我记得我曾经有一份 epoll 源码的,后来博客删着删着就给没了。。。
咱是要整份源码来一遍还是直击要害?
直击要害吧,今晚还有两个课题要做,一个叫:nginx 里的 epoll 是 ET 还是 LT?因为有人说,nginx的应用场景是可以把 ET 喂饱的。
另一个课题,叫:我今晚要把我的衣服都手洗了,不是洗衣机洗。
要源码剖析来这篇:深入了解epoll模型 – 开卷有益,早期做的一篇,优化过五六次,是我最喜欢的一篇博客。都是干货不像这里这么多废话。
ET 体现在哪里?
// 实际执行复制到用户空间的工作是由该函数体负责
static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head,void *priv)
{
struct ep_send_events_data *esed = priv;
__poll_t revents;
struct epitem *epi, *tmp;
struct epoll_event __user *uevent = esed->events;
struct wakeup_source *ws;
poll_table pt;
init_poll_funcptr(&pt, NULL);
esed->res = 0;
/*
* We can loop without lock because we are passed a task private list.
* Items cannot vanish during the loop because ep_scan_ready_list() is
* holding "mtx" during this call.
*/
lockdep_assert_held(&ep->mtx);
// lambda表达式
list_for_each_entry_safe(epi, tmp, head, rdllink) {
if (esed->res >= esed->maxevents)
break;
/*
* Activate ep->ws before deactivating epi->ws to prevent
* triggering auto-suspend here (in case we reactive epi->ws
* below).
*
* This could be rearranged to delay the deactivation of epi->ws
* instead, but then epi->ws would temporarily be out of sync
* with ep_is_linked().
*/
ws = ep_wakeup_source(epi);
if (ws) {
if (ws->active)
__pm_stay_awake(ep->ws);
__pm_relax(ws);
}
list_del_init(&epi->rdllink);
/*
* If the event mask intersect the caller-requested one,
* deliver the event to userspace. Again, ep_scan_ready_list()
* is holding ep->mtx, so no operations coming from userspace
* can change the item.
*/
revents = ep_item_poll(epi, &pt, 1);
if (!revents)
continue;
// 复制到用户空间
if (__put_user(revents, &uevent->events) ||
__put_user(epi->event.data, &uevent->data)) {
list_add(&epi->rdllink, head);
ep_pm_stay_awake(epi);
if (!esed->res)
esed->res = -EFAULT;
return 0;
}
esed->res++;
uevent++;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
else if (!(epi->event.events & EPOLLET)) {
/*
* If this file has been added with Level
* Trigger mode, we need to insert back inside
* the ready list, so that the next call to
* epoll_wait() will check again the events
* availability. At this point, no one can insert
* into ep->rdllist besides us. The epoll_ctl()
* callers are locked out by
* ep_scan_ready_list() holding "mtx" and the
* poll callback will queue them in ep->ovflist.
*/
list_add_tail(&epi->rdllink, &ep->rdllist);
ep_pm_stay_awake(epi);
}
}
return 0;
}
好,这时候就有一个疑问了是吧,那如果我读完了,是不是也被添加到 rdlist 里面了?
对啊,一视同仁啊。
那什么时候被清理掉?总不能一直在里面,然后每次提交给我的 fd 有一堆都要报错吧?
对啊,of course. Why not? 当然是要善后的,怎么能让它这么消耗性能?
(英语不太好,找这段整整花了我半个小时时间,然后我就纳闷儿了,检查 rd 链表上是否有空 fd,那空 fd 是因为 LT,这里为什么对 LT/ET一视同仁了?难道 ET 也会产生空 fd?)先存疑吧,说不定哪天我就懂了,现在能力只能看到这一步了。哪天有机会遇上大佬可以请教请教。
/**
* ep_scan_ready_list - Scans the ready list in a way that makes possible for
* the scan code, to call f_op->poll(). Also allows for
* O(NumReady) performance.
*
* @ep: Pointer to the epoll private data structure.
* @sproc: Pointer to the scan callback.
* @priv: Private opaque data passed to the @sproc callback.
* @depth: The current depth of recursive f_op->poll calls.
* @ep_locked: caller already holds ep->mtx
*
* Returns: The same integer error code returned by the @sproc callback.
*/
static __poll_t ep_scan_ready_list(struct eventpoll *ep,
__poll_t (*sproc)(struct eventpoll *,
struct list_head *, void *),void *priv,
int depth, bool ep_locked)
{
__poll_t res;
int pwake = 0;
struct epitem *epi, *nepi;
LIST_HEAD(txlist);
lockdep_assert_irqs_enabled();
/*
* We need to lock this because we could be hit by
* eventpoll_release_file() and epoll_ctl().
*/
if (!ep_locked)
mutex_lock_nested(&ep->mtx, depth);
/*
* Steal the ready list, and re-init the original one to the
* empty list. Also, set ep->ovflist to NULL so that events
* happening while looping w/out locks, are not lost. We cannot
* have the poll callback to queue directly on ep->rdllist,
* because we want the "sproc" callback to be able to do it
* in a lockless way.
*/
write_lock_irq(&ep->lock);
// 把就绪链表rdllist赋给临时的txlist,执行该操作后rdllist会被清空,
// 因为rdllist需要腾出来给其他进程继续往上放内容,
// 从而把txlist内epitem对应fd的就绪events复制到用户空间
list_splice_init(&ep->rdllist, &txlist);
WRITE_ONCE(ep->ovflist, NULL);
write_unlock_irq(&ep->lock);
/*
* sproc就是前面设置好的ep_poll_callback,事件到来了执行该回调体,
* sproc会把就绪的epitem放入rdllist或ovflist上
* Now call the callback function.
*/
res = (*sproc)(ep, &txlist, priv);
write_lock_irq(&ep->lock);
/*
* During the time we spent inside the "sproc" callback, some
* other events might have been queued by the poll callback.
* We re-insert them inside the main ready-list here.
*/
for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL;
nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
/*
* We need to check if the item is already in the list.
* During the "sproc" callback execution time, items are
* queued into ->ovflist but the "txlist" might already
* contain them, and the list_splice() below takes care of them.
*/
if (!ep_is_linked(epi)) {
/*
* ->ovflist is LIFO, so we have to reverse it in order
* to keep in FIFO.
*/
list_add(&epi->rdllink, &ep->rdllist);
ep_pm_stay_awake(epi);
}
}
/*
* We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
* releasing the lock, events will be queued in the normal way inside
* ep->rdllist.
*/
WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR);
/*
* 把水平触发EPOLLLT属性的epitem依旧挂回到rdllist,
* 因为我们希望即使没有新的数据到来,只要数据还没被用户空间读完,就继续上报
* Quickly re-inject items left on "txlist".
*/
list_splice(&txlist, &ep->rdllist);
__pm_relax(ep->ws);
if (!list_empty(&ep->rdllist)) {
/*
* Wake up (if active) both the eventpoll wait list and
* the ->poll() wait list (delayed after we release the lock).
* wake_up唤醒epoll_wait的调用者
*/
if (waitqueue_active(&ep->wq))
wake_up(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
write_unlock_irq(&ep->lock);
if (!ep_locked)
mutex_unlock(&ep->mtx);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&ep->poll_wait);
return res;
}
最后,我想说一句:验证真理唯一的渠道就是亲身实验。上面这些只不过是培养我看源码的习惯和能力罢了,并不能说明什么,最后还是要落实到实地的。
所以我把标题改了,原先的标题是:epoll 的 ET模式就一定比 LT要快吗?