Sharding the Ceph RADOS Gateway bucket index

Sharding is the process of breaking down data onto multiple locations so as to increase parallelism, as well as distribute load. This is a common feature used in databases. Read more on this at Wikipedia.

The concept of sharding is used in Ceph, for splitting the bucket index in a RADOS Gateway.

RGW or RADOS Gateway keeps an index for all the objects in its buckets for faster and easier lookup. For each RGW bucket created in a pool, the corresponding index is created in the XX.index pool.

For example, for each of the buckets created in .rgw pool, the bucket index is created in .rgw.buckets.index pool. For each bucket, the index is stored in a single RADOS object.

When the number of objects increases, the size of the RADOS object increases as well. Two problems arise due to the increased index size.

  1. RADOS does not work good with large objects since it’s not designed as such. Operations such as recovery, scrubbing etc.. work on a single object. If the object size increases, OSDs may start hitting timeouts because reading a large object may take a long time. This is one of the reason that all RADOS client interfaces such as RBD, RGW, CephFS use a standard 4MB object size.
  2. Since the index is stored in a single RADOS object, only a single operation can be done on it at any given time. When the number of objects increases, the index stored in the RADOS object grows. Since a single index is handling a large number of objects, and there is a chance the number of operations also increase, parallelism is not possible which can end up being a bottleneck. Multiple operations will need to wait in a queue since a single operation is possible at a time.

In order to work around these problems, the bucket index is sharded into multiple parts. Each shard is kept on a separate RADOS object within the index pool.

Sharding is configured with the tunable bucket_index_max_shards . By default, this tunable is set to 0 which means that there are no shards.

How to check if Sharding is set?

  1. List the buckets
    # radosgw-admin metadata bucket list
    [
     "my-new-bucket"
    ]
    
  2. Get information on the bucket in question
    
    # radosgw-admin metadata get bucket:my-new-bucket
    {
        "key": "bucket:my-new-bucket",
        "ver": {
            "tag": "_bGZAVUgayKVwGNgNvI0328G",
            "ver": 1
        },
        "mtime": 1458940225,
        "data": {
            "bucket": {
                "name": "my-new-bucket",
                "pool": ".rgw.buckets",
                "data_extra_pool": ".rgw.buckets.extra",
                "index_pool": ".rgw.buckets.index",
                "marker": "default.2670570.1",
                "bucket_id": "default.2670570.1"
            },
            "owner": "rgw_user",
            "creation_time": 1458940225,
            "linked": "true",
            "has_bucket_info": "false"
        }
    }
    
    
  3. Use the bucket ID to get more information, including the number of shards.
radosgw-admin metadata get bucket.instance:my-new-bucket:default.2670570.1
{
    "key": "bucket.instance:my-new-bucket:default.2670570.1",
    "ver": {
        "tag": "_xILkVKbfQD7reDFSOB4a5VU",
        "ver": 1
    },
    "mtime": 1458940225,
    "data": {
        "bucket_info": {
            "bucket": {
                "name": "my-new-bucket",
                "pool": ".rgw.buckets",
                "data_extra_pool": ".rgw.buckets.extra",
                "index_pool": ".rgw.buckets.index",
                "marker": "default.2670570.1",
                "bucket_id": "default.2670570.1"
            },
            "creation_time": 1458940225,
            "owner": "rgw_user",
            "flags": 0,
            "region": "default",
            "placement_rule": "default-placement",
            "has_instance_obj": "true",
            "quota": {
                "enabled": false,
                "max_size_kb": -1,
                "max_objects": -1
            },
            "num_shards": 0,
            "bi_shard_hash_type": 0
        },
        "attrs": [
            {
                "key": "user.rgw.acl",
                "val": "AgKPAAAAAgIaAAAACAAAAHJnd191c2VyCgAAAEZpcnN0IFVzZXIDA2kAAAABAQAAAAgAAAByZ3dfdXNlcg8AAAABAAAACAAAAHJnd191c2VyAwM6AAAAAgIEAAAAAAAAAAgAAAByZ3dfdXNlcgAAAAAAAAAAAgIEAAAADwAAAAoAAABGaXJzdCBVc2VyAAAAAAAAAAA="
            },
            {
                "key": "user.rgw.idtag",
                "val": ""
            },
            {
                "key": "user.rgw.manifest",
                "val": ""
            }
        ]
    }
}

Note that `num_shards` is set to 0, which means that sharding is not enabled.

How to configure Sharding?

To configure sharding, we need to first dump the region info.

NOTE: By default, RGW has a region named default even if regions are not configured.

# radosgw-admin region get > /tmp/region.txt 

# cat /tmp/region.txt
{
    "name": "default",
    "api_name": "",
    "is_master": "true",
    "endpoints": [],
    "hostnames": [],
    "master_zone": "",
    "zones": [
        {
            "name": "default",
            "endpoints": [],
            "log_meta": "false",
            "log_data": "false",
            "bucket_index_max_shards": 0
        }
    ],
    "placement_targets": [
        {
            "name": "default-placement",
            "tags": []
        }
    ],
    "default_placement": "default-placement"
}

Edit the file /tmp/region.txt, change the value for `bucket_index_max_shards` to the needed shard value (we’re setting it to 8 in this example), and inject it back to the region.

# radosgw-admin region set < /tmp/region.txt
{
    "name": "default",
    "api_name": "",
    "is_master": "true",
    "endpoints": [],
    "hostnames": [],
    "master_zone": "",
    "zones": [
        {
            "name": "default",
            "endpoints": [],
            "log_meta": "false",
            "log_data": "false",
            "bucket_index_max_shards": 8
        }
    ],
    "placement_targets": [
        {
            "name": "default-placement",
            "tags": []
        }
    ],
    "default_placement": "default-placement"
}

Reference:

  1. Red Hat Ceph Storage 1.3 Rados Gateway documentation
  2. https://en.wikipedia.org/wiki/Shard_(database_architecture)

Ceph OSD heartbeats

Ceph OSD daemons need to ensure that the neighbouring OSDs are functioning properly so that the cluster remains in a healthy state.

For this, each Ceph OSD process (ceph-osd) sends a heartbeat signal to the neighbouring OSDs. By default, the heartbeat signal is sent every 6 seconds [1], which is configurable of course.

If the heartbeat check from one OSD doesn’t hear from the other within the set value for `osd_heartbeat_grace` [2], which is set to 20 seconds by default, the OSD that sends the heartbeat check reports the other OSD (the one that didn’t respond within 20 seconds) as down, to the MONs. Once an OSD reports three times that the non-responding OSD is indeed `down`, the MON acknowledges it and mark the OSD as down.

The Monitor will update the Cluster map and send it over to the participating nodes in the cluster.

OSD-heartbeat-1

When an OSD can’t reach another OSD for a heartbeat, it reports the following in the OSD logs:

osd.510 1497 heartbeat_check: no reply from osd.11 since back 2016-04-28 20:49:42.088802

In Ceph Jewel, the MONs require a minimum of two ceph OSDs report a specific OSD as down from two nodes which are in different CRUSH subtrees, in order to actually mark the OSD as down. These are controlled by the following tunables :

From ‘common/config_opts.h’:

[1] OPTION(mon_osd_min_down_reporters, OPT_INT, 2) // number of OSDs from different subtrees who need to report a down OSD for it to count

[2] OPTION(mon_osd_reporter_subtree_level , OPT_STR, “host”) // in which level of parent bucket the reporters are counted

Image Courtsey : Red Hat Ceph Storage 1.3.2 Configuration guide

`ceph-check` – A Ceph installation checker

Many a user wants to know if a Ceph cluster installation has been done to a specific suggested guideline.

Technologies like RAID is better avoided in Ceph due to an additional layer, which Ceph already takes care of.

I’ve started writing a tool which can be run from the Admin node, and it aims to check various such points.

The code can be seen at https://github.com/arvimal/ceph_check

The work is slow, really slow, due to my daily work, procrastination, and what not, even though I intend to finish this fast.

How to get a Ceph MON/OSD map at a specific epoch?

To get a MON map or an OSD map of a specific epoch, use:

# ceph osd getmap <epoch-value>
# ceph mon getmap <epoch-value>

The map can be forwarded to a file as following:

# ceph osd getmap <epoch-value> -o /tmp/ceph_osd_getmap.bin

This would be in a binary format, and hence will need to be dumped to a human-readable form.

# osdmaptool –print /tmp/ceph-osd-getmap.bin

This will print the current OSD map, similar to the output of ‘ceph osd dump’.

Where this command shines is when you can fetch maps from previous epochs, and pull information on specific placement groups in those epochs.

For example, I’ve had all the OSDs on one of my node down some time back (in a previous epoch). The ability to query a previous epoch gives the administrator the power to understand how exactly the cluster was at a specific time period.

List RBD images, snapshots, and clones in Ceph pools

This is a crude bash one-liner I did to get the details of all the RBD images, as well as the information on snapshots and clones created from them.

# for pool in `rados lspools`;
    do echo "POOL :" $pool;
       rbd ls -l $pool;
       echo "-----";
    done

This will print an output similar to the following:

POOL : rbd
NAME                             SIZE        PARENT  FMT PROT LOCK
test_img                        10240M                    1
test_img2                      1024M                      2
test_img2@snap2      1024M                      2                    yes
-----
POOL : .rgw.root
-----
POOL : .rgw.control
-----
POOL : .rgw
-----
POOL : .rgw.gc
-----
POOL : .users.uid
-----
POOL : .users
-----
POOL : .users.swift
-----
POOL : .users.email
-----
POOL : .rgw.buckets.index
-----
POOL : images
NAME           SIZE      PARENT                               FMT PROT LOCK
clone1           1024M  rbd/test_img2@snap2             2
-----

Ceph and unfound objects

In certain cases, a Ceph cluster may move away from an HEALTHY state due to “unfound” objects.

A “ceph -s” should show if you have any unfound objects. So, what are unfound objects? How does an object become “unfound”? This article tries to explain why/how “unfound” objects come into existence.

Let’s look into the life cycle of a write to a pool.

  • The client contacts a Ceph monitor and fetches the CRUSH map, which includes:
    • MON map
    • OSD map
    • PG map
    • CRUSH map
    • MDS map

Once the client has the maps, the Ceph client-side algorithm breaks the data being written into objects (the object size depends on the client side configuration). Clients such as RBD and RGW uses a 4MB object size, but RADOS doesn’t actually have such a limitation.

Each pool has a set of Placement Groups (PG) assigned to it at the time of creation, and the client always writes to a pool. Since the client has the maps which talks about the entire cluster, it knows the placement groups within the pool which it is writing to, and the OSDs assigned for each placement group. The client talks to the OSDs directly without going over any other path, such as a monitor.

The PG map will have the ACTING and UP OSD sets for each PG. To understand the ACTING set and UP set for the PGs, as well as a plethora of other information, use :

# ceph pg dump

The ACTING set is the current active set of OSDs that stores the replica sets for that particular PG. The UP set is the set of OSDs that are currently up and running. Usually, the ACTING set and UP set are the same. When an OSD in the ACTING set is not reachable, other OSDs wait for 5 minutes (which is configurable) for it to come back online (this is checked with a hearbeat).

The said OSD is removed out of the UP set when it is not accessible. If it doesn’t come back online within the configured period, the said OSD is marked out of the ACTING set, as well as the UP set. When it comes back, it is added back to the ACTING/UP set and a peering happens where the data is synced back.

Let’s discuss the scenario where an “unfound” object came come into existence. Imagine a pool with a two replica configuration. A write that goes into the pool is split into objects and stored in the OSDs which are in the ACTIVE set of a PG.

  • One OSD in the ACTING set goes down.
  • The write is done on the second OSD which is UP and ACTING.
  • The first OSD which went down, came back up.
  • The peering process started between the first OSD (that came back), and the second OSD (that serviced the write).
    • Peering refers to the process of arriving at an understanding on the object states between the OSDs in an ACTING set, and sync up the metadata/data between them.
  • Both the OSDs reach an understanding on which objects needs to be synced.
  • The second OSD that had the objects ready to be synced, went down before the sync process starts or is in midway.

In this situation, the first OSD knows about the objects that was written to the second OSD, but cannot probe it. The first OSD will try to probe possible locations for copies, provided there are more replicas. If the OSD is able to find other locations, the data will be synced up.

But in case there are no other copies, and the OSD with the only copy is not coming up anytime soon (perhaps a disk crash, file system corruption etc..) the only way is to either mark the object as “lost”, or revert it back to the previous version. Reverting to a previous version may not be possible for a new object, and in such cases the only way would be to mark it as “lost” or copy from a backup.

1. For a new object without a previous version:

# ceph pg {pg.num} mark_unfound_lost delete

2. For an object which is likely to have a previous version:

# ceph pg {pg.num} mark_unfound_lost revert

NOTE: The upstream Ceph documentation has an excellent write-up about “unfound” objects here.

I suggest reading the documentation prior taking any sort of action in a case where you see “unfound” objects in your cluster.

Ceph Rados Block Device (RBD) and TRIM

I recently came across a scenario where the objects in a RADOS pool used for an RBD block device doesn’t get removed, even if the files created through the mount point were removed.

I had an RBD image from an RHCS1.3 cluster mapped to a RHEL7.1 client machine, with an XFS filesystem created on it, and mounted locally. Created a 5GB file, and I could see the objects being created in the rbd pool in the ceph cluster.

1.RBD block device information

# rbd info rbd_img
rbd image 'rbd_img':
size 10240 MB in 2560 objects
order 22 (4096 kB objects)
block_name_prefix: rb.0.1fcbe.2ae8944a
format: 1

An XFS file system was created on this block device, and mounted at /test.

2.Write a file onto the RBD mapped mount point. Used ‘dd’ to write a 5GB file.

# dd if=/dev/zero of=/mnt/rbd_image.img bs=1G count=5
 5+0 records in
 5+0 records out
 5368709120 bytes (5.4 GB) copied, 8.28731 s, 648 MB/s

3.Check the objects in the backend RBD pool

# rados -p rbd ls | wc -l
 &lt; Total number of objects in the 'rbd' pool&gt;

4.Delete the file from the mount point.

# rm /test/rbd_image.img -f
 # ls /test/
 --NO FILES LISTED--

5.List the objects in the RBD pool

# rados -p rbd ls | wc -l
< Total number of objects in the 'rbd' pool >

The number of objects doesn’t go down as we expect, after the file deletion. It remains the same, wrt to step 3.

Why does this happen? This is due to the fact that traditional file systems do not delete the underlying data blocks even if the files are deleted.

The process of writing a file onto a file system involves several steps like finding free blocks and allocating them for the new file, creating an entry in the directory entry structure of the parent folder, setting the name and inode number in the directory entry structure, setting pointers from the inode to the data blocks allocated for the file etc..

When data is written to the file, the data blocks are used to store the data. Additional information such as the file size, access times etc.. are updated in the inode after the writes.

Deleting a file involves removing the pointers from the inode to the corresponding data blocks, and also clearing the name<->inode mapping from the directory entry structure of the parent folder. But, the underlying data blocks are not cleared off, since that is a high I/O intensive operation. So, the data remains on the disk, even if the file is not present. A new write will make the allocator take these blocks for the new data, since they are marked as not-in-use.

This applies for the files created on an RBD device as well. The files created on top of the RBD-mapped mount point will ultimately be mapped to objects in the RADOS cluster. When the file is deleted from the mount point, since the entry is removed, it doesn’t show up in the mount point.

But, since the file system doesn’t clear off the underlying block device, the objects remain in the RADOS pool. These would be normally over-written when a new file is created via the mount point.

But this has a catch though. Since the pool contains the objects even if the files are deleted, it consumes space in the rados pool (even if they’ll be overwritten). An administrator won’t be able to get a clear understanding on the space usage, if the pool is used heavily, and multiple writes are coming in.

In order to clear up the underlying blocks, or actually remove them, we can rely on the TRIM support most modern disks offer. Read more about TRIM at Wikipedia.

TRIM is a set of commands supported by HDD/SSDs which allow the operating systems to let the disk know about the locations which are not currently being used. Upon receiving a confirmation from the file system layer, the disk can go ahead and mark the blocks as not used.

For the TRIM commands to work, the disks and the file system has to have the support. All the modern file systems have built-in support for TRIM. Mount the file system with the ‘discard‘ option, and you’re good to go.

# mount -o discard /dev/rbd{X}{Y} /{mount-point}