On the whole the current iteration of FSCache on Ceph has been quite stable for me. We've had it deployed on 4 clients running for a week in a row. I did run into two small issues. First one, I wasn't checking if the page was marked with private_2 before asking FSCache to write to it. I've never seen this before and I only seen this issue once. The second issue is similar to what I was seeing before with pages marked private_2 when we return them to the page cache. In this case the start_read() in addr.c was returning the pages in the error path of the code. I have plugged that issue. I only seen this one a handful of times across all clients. As usual please apply the changes from repo located at: https://bitbucket.org/adfin/linux-fs.git branch: wip-ceph-fscache Cheers, - Milosz Milosz Tanski (2): ceph: ceph_readpage_to_fscache didn't check if marked ceph: page still marked private_2 fs/ceph/addr.c | 1 + fs/ceph/cache.c | 3 +++ fs/ceph/cache.h | 14 +++++++++++++- 3 files changed, 17 insertions(+), 1 deletion(-) -- 1.8.1.2 -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
