Revision 78076bb64aa8ba5b7207c38b2660a9e10ffa8cc7 authored by Jens Axboe on 05 December 2019, 02:56:40 UTC, committed by Jens Axboe on 05 December 2019, 03:12:58 UTC
We recently changed this from a single list to an rbtree, but for some real life workloads, the rbtree slows down the submission/insertion case enough so that it's the top cycle consumer on the io_uring side. In testing, using a hash table is a more well rounded compromise. It is fast for insertion, and as long as it's sized appropriately, it works well for the cancellation case as well. Running TAO with a lot of network sockets, this removes io_poll_req_insert() from spending 2% of the CPU cycles. Reported-by: Dan Melnic <dmm@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
1 parent 08bdcc3
| File | Mode | Size |
|---|---|---|
| apparmor | ||
| integrity | ||
| keys | ||
| loadpin | ||
| lockdown | ||
| safesetid | ||
| selinux | ||
| smack | ||
| tomoyo | ||
| yama | ||
| Kconfig | -rw-r--r-- | 10.7 KB |
| Kconfig.hardening | -rw-r--r-- | 7.9 KB |
| Makefile | -rw-r--r-- | 1.2 KB |
| commoncap.c | -rw-r--r-- | 38.9 KB |
| device_cgroup.c | -rw-r--r-- | 20.8 KB |
| inode.c | -rw-r--r-- | 10.6 KB |
| lsm_audit.c | -rw-r--r-- | 10.6 KB |
| min_addr.c | -rw-r--r-- | 1.3 KB |
| security.c | -rw-r--r-- | 59.7 KB |
Computing file changes ...
