c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2025-02-07 07:43:21 +03:00
Code Issues Packages Projects Releases Wiki Activity

Reduce and handle EAGAIN errors on AIO label reads

Browse Source 
At least FreeBSD has a limit of 256 simultaneous AIO requests per
process. Attempt to issue more results in EAGAIN errors. Since we
issue 4 requests per disk/partition from 2xCPUs threads, it is
quite easy to reach that limit on large systems, that results in
random pool import failures.  It annoyed me for quite a while on
a system with 64 CPUs and 70+ partitioned disks.

This patch from one side limits the number of threads to avoid the
error, while from another should softly fall back to sync reads in
case of error.  It takes into account _SC_AIO_MAX as a system-wide
AIO limit and _SC_AIO_LISTIO_MAX as a closest value to per-process
limit.  The last not exactly right, but it is the best I found.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored by: iXsystems, Inc.
Closes #16551
This commit is contained in:
Alexander Motin 2024-09-21 13:36:25 -04:00 committed by Tony Hutter
parent 94a571b3d9
commit 54278533a4
1 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
lib/libzutil/zutil_import.c
View File

@ -1071,6 +1071,7 @@ zpool_read_label(int fd, nvlist_t **config, int *num_labels)
* Try the slow method. * Try the slow method.
*/ */
zfs_fallthrough; zfs_fallthrough;
case EAGAIN:
case EOPNOTSUPP: case EOPNOTSUPP:
case ENOSYS: case ENOSYS:
do_slow = B_TRUE; do_slow = B_TRUE;
@ -1464,7 +1465,21 @@ zpool_find_import_impl(libpc_handle_t *hdl, importargs_t *iarg,
* validating labels, a large number of threads can be used due to * validating labels, a large number of threads can be used due to
* minimal contention. * minimal contention.
*/ */
t = tpool_create(1, 2 * sysconf(_SC_NPROCESSORS_ONLN), 0, NULL); long threads = 2 * sysconf(_SC_NPROCESSORS_ONLN);
#ifdef HAVE_AIO_H
long am;
#ifdef _SC_AIO_LISTIO_MAX
am = sysconf(_SC_AIO_LISTIO_MAX);
if (am >= VDEV_LABELS)
threads = MIN(threads, am / VDEV_LABELS);
#endif
#ifdef _SC_AIO_MAX
am = sysconf(_SC_AIO_MAX);
if (am >= VDEV_LABELS)
threads = MIN(threads, am / VDEV_LABELS);
#endif
#endif
t = tpool_create(1, threads, 0, NULL);
for (slice = avl_first(cache); slice; for (slice = avl_first(cache); slice;
(slice = avl_walk(cache, slice, AVL_AFTER))) (slice = avl_walk(cache, slice, AVL_AFTER)))
(void) tpool_dispatch(t, zpool_open_func, slice); (void) tpool_dispatch(t, zpool_open_func, slice);