diff options
| author | Benjamin Coddington <bcodding@redhat.com> | 2024-11-22 10:11:12 -0500 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2024-12-05 14:03:09 +0100 |
| commit | bff8460376e53de3f549e90666f9c0e9d2c6c981 (patch) | |
| tree | a7e881843e9b76ed4fd8b8409e647eb45a86dbd8 /fs | |
| parent | faa4bacfaeed827a4ca8cb8529a3ce65a9e8ef46 (diff) | |
| download | linux-bff8460376e53de3f549e90666f9c0e9d2c6c981.tar.gz linux-bff8460376e53de3f549e90666f9c0e9d2c6c981.tar.bz2 linux-bff8460376e53de3f549e90666f9c0e9d2c6c981.zip | |
nfs/blocklayout: Limit repeat device registration on failure
[ Upstream commit 614733f9441ed53bb442d4734112ec1e24bd6da7 ]
Every pNFS SCSI IO wants to do LAYOUTGET, then within the layout find the
device which can drive GETDEVINFO, then finally may need to prep the device
with a reservation. This slow work makes a mess of IO latencies if one of
the later steps is going to fail for awhile.
If we're unable to register a SCSI device, ensure we mark the device as
unavailable so that it will timeout and be re-added via GETDEVINFO. This
avoids repeated doomed attempts to register a device in the IO path.
Add some clarifying comments as well.
Fixes: d869da91cccb ("nfs/blocklayout: Fix premature PR key unregistration")
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'fs')
| -rw-r--r-- | fs/nfs/blocklayout/blocklayout.c | 15 |
1 files changed, 14 insertions, 1 deletions
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 0becdec12970..47189476b553 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -571,19 +571,32 @@ retry: if (!node) return ERR_PTR(-ENODEV); + /* + * Devices that are marked unavailable are left in the cache with a + * timeout to avoid sending GETDEVINFO after every LAYOUTGET, or + * constantly attempting to register the device. Once marked as + * unavailable they must be deleted and never reused. + */ if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) { unsigned long end = jiffies; unsigned long start = end - PNFS_DEVICE_RETRY_TIMEOUT; if (!time_in_range(node->timestamp_unavailable, start, end)) { + /* Uncork subsequent GETDEVINFO operations for this device */ nfs4_delete_deviceid(node->ld, node->nfs_client, id); goto retry; } goto out_put; } - if (!bl_register_dev(container_of(node, struct pnfs_block_dev, node))) + if (!bl_register_dev(container_of(node, struct pnfs_block_dev, node))) { + /* + * If we cannot register, treat this device as transient: + * Make a negative cache entry for the device + */ + nfs4_mark_deviceid_unavailable(node); goto out_put; + } return node; |