search for: io_wait

Although tapdisk has been instead of tapdisk-ioemu, but it still used on some old xen-3.2. So fix a performance problem here. -- Kernel aio will retry when encounter a block doesn''t allocated, then do async io, but O_DIRECT flag was there, so io_wait on sync data. And clean a little code style. Signed-off-by: Wei Kong <weikong.cn@gmail.com> _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

...tricky to describe or even log effectively. Occasionally a node basically receives more connections than it is able to handle. The connection count goes through the roof for that node. It will go up way beyond 150 dovecot authentication threads and 100 or so active POP/IMAP dovecot threads. The IO_wait/cpu and memory usage also tends to be spiking at this point. The server gets to the tipping point where it can no longer serve it's POP/IMAP requests fast enough compared to the number of connections it's getting. I'd be fine with this but this creates some less than desirable sympt...

...Z/10; ++ timeout = 1; + queue_delayed_work(aio_wq, &ctx->wq, timeout); + } + +@@ -1435,6 +1437,9 @@ static ssize_t aio_setup_iocb(struct kio + if (file->f_op->aio_fsync) + kiocb->ki_retry = aio_fsync; + break; ++ case IOCB_CMD_EPOLL_WAIT: ++ kiocb->ki_retry = eventpoll_aio_wait; ++ break; + default: + dprintk("EINVAL: io_submit: no operation provided\n"); + ret = -EINVAL; +diff --git a/fs/eventpoll.c b/fs/eventpoll.c +index 4284cd3..3aca096 100644 +--- a/fs/eventpoll.c ++++ b/fs/eventpoll.c +@@ -34,6 +34,7 @@ #include <linux/wait.h> + #include <li...

depends on "autoconf: regenerate configure scripts with 4.4 version" This series removes some of the really old deadwood from the tools build and makes some other things which are on their way out configurable at build time with a default depending on how far down the slope I judge them to be. * nuke in tree copy of libaio * nuke obsolete tools: xsview, miniterm, lomount & sv *