On 04.11.19 16:49, Alberto Garcia wrote: > On Mon 04 Nov 2019 04:14:56 PM CET, Max Reitz wrote: > >>>> No, what I meant was that the original problem that led to >>>> c8bb23cbdbe would go away. >>> >>> Ah, right. Not quite, according to my numbers: >>> >>> |--------------+----------------+-----------------+-------------| >>> | Cluster size | subclusters=on | subclusters=off | fallocate() | >>> |--------------+----------------+-----------------+-------------| >>> | 256 KB | 10182 IOPS | 966 IOPS | 14007 IOPS | >>> | 512 KB | 7919 IOPS | 563 IOPS | 13442 IOPS | >>> | 1024 KB | 5050 IOPS | 465 IOPS | 13887 IOPS | >>> | 2048 KB | 2465 IOPS | 271 IOPS | 13885 IOPS | >>> |--------------+----------------+-----------------+-------------| >>> >>> There's obviously no backing image, and only the last column uses >>> handle_alloc_space() / fallocate(). >> >> Thanks for providing some numbers! >> >> It was my impression, too, that subclusters wouldn’t solve it. But it >> didn’t seem like that big of a difference to me. Did you run this >> with aio=native? (Because that’s where we have the XFS problem) > > Here's with aio=native > > |--------------+----------------+-----------------+-------------| > | Cluster size | subclusters=on | subclusters=off | fallocate() | > |--------------+----------------+-----------------+-------------| > | 256 KB | 19897 IOPS | 891 IOPS | 32194 IOPS | > | 512 KB | 17881 IOPS | 436 IOPS | 33092 IOPS | > | 1024 KB | 17050 IOPS | 341 IOPS | 32768 IOPS | > | 2048 KB | 7854 IOPS | 207 IOPS | 30944 IOPS | > |--------------+----------------+-----------------+-------------|
OK, thanks again. :-) So it seems right not to revert the commit and just work around the XFS bug in file-posix. Max
signature.asc
Description: OpenPGP digital signature