Ceph performance

Ссылки сюда (1) →

General benchmarking principles

Main test cases for benchmarking are:

• Linear read and write (big blocks, big queue) in MB/s
• Highly parallel random read and write of small blocks (4-8kb, iodepth=32-128) in IOPS (Input/Output ops per second)
• Single-threaded transactional random write (4-8kb, iodepth=1) and read (though single-threaded reads are more rare) in IOPS

Single-threaded random read and write is where the latency matters, and the latency doesn’t scale with the number of servers. Whenever you’re benchmarking your cluster with iodepth=1 you’re benchmarking only ONE placement group (triplet or pair of OSDs) at a time. The result is only affected by how fast 1 OSD is responding to 1 request. In fact, with only one parallel request IOPS = 1/latency.

The latency really matters because not many applications can do random writes with high parallelism/iodepth. For example, a DBMS can’t, because it’s transactional and it needs to serialize its writes to the journal.

The naive expectation is that Ceph should be almost as fast as drives and network are, because everyone is used to the idea that I/O is slow and the software is fast. And this is true with Ceph only until you don’t use SSDs.

The general rule is: Ceph is an SDS. With Ceph it’s hard to achieve random read latencies less than 0.5ms and random write latencies less than 1ms, no matter what drives or network you use. This stands for only 2000 iops random read and 1000 iops random write, and even this result is good if you manage to achieve it. With BIS hardware and some tuning you may be able to improve it, but only twice or so.

There is Nick Fisk’s presentation titled «Low-latency Ceph». By «low-latency» he means 0.7ms, which is only ~1500 iops.

Test your disks

Run `fio` on your drives before deploying Ceph:

WARNING! For those under a rock — fio write test is DESTRUCTIVE. Don’t dare to run it on disks which have important data… for example, OSD journals (I’ve seen such cases).

• Try to disable drive cache before testing: hdparm -W 0 /dev/sdX (SATA drives), sdparm --set WCE=0 /dev/sdX (SAS drives). This is usually ABSOLUTELY required for server SSDs like Micron 5100 or Seagate Nytro (see #Drive cache is slowing down) as it increases random write iops more than by two magnitudes (from 288 iops to 18000 iops!). In some cases it may not improve anything, so try both options -W0 and -W1.
• Linear read: fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4M -iodepth=32 -rw=read -runtime=60 -filename=/dev/sdX
• Linear write: fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4M -iodepth=32 -rw=write -runtime=60 -filename=/dev/sdX
• Peak parallel random read: fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=128 -rw=randread -runtime=60 -filename=/dev/sdX
• Single-threaded read latency: fio -ioengine=libaio -sync=1 -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=1 -rw=randread -runtime=60 -filename=/dev/sdX
• Peak parallel random read: fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=128 -rw=randwrite -runtime=60 -filename=/dev/sdX
• Journal write latency: fio -ioengine=libaio -sync=1 -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=1 -rw=write -runtime=60 -filename=/dev/sdX. Also try it with -fsync=1 instead of -sync=1 and write down the worst result, because sometimes one of sync or fsync is ignored by messy hardware.
• Single-threaded random write latency: fio -ioengine=libaio -sync=1 -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=1 -rw=randwrite -runtime=60 -filename=/dev/sdX

You wanna ask why it's so slow? See below.

A useful habit is to leave an empty partition for later benchmarking on each SSD you deploy Ceph OSDs on, because some SSDs tend to slow down when filled.

Test your Ceph cluster

Recommended benchmarking tools:

• The first recommended tool is again `fio` with `-ioengine=rbd -pool=<your pool> -rbdname=<your image>`. All of the above tests valid for raw drives can be repeated for RBD and they mean the same things. Sync, direct and invalidate flags can be omitted, because RBD has no concept of «sync» — all operations are always «sync». And there’s no page cache involved either, so «direct» also doesn’t mean anything.
• The second recommended tool, especially useful for hunting performance problems, comes in the several improved varieties of «Mark’s bench» from russian Ceph chat: https://github.com/rumanzo/ceph-gobench or https://github.com/vitalif/ceph-bench. Both use a non-replicated Ceph pool (size=1), create several 4MB objects (16 by default) in each separate OSD and do random single-thread 4kb writes in randomly selected objects within one OSD. This mimics random writes to RBD and allows to determine the problematic OSDs by benchmarking them separately. Original Mark’s bench (outdated) was here: https://github.com/socketpair/ceph-bench

  To create the non-replicated benchmark pool use ceph osd pool create bench 128 replicated; ceph osd pool set bench size 1; ceph osd pool set bench min_size 1. Just note that 128 (PG count) should be enough for all OSDs to get at least one PG each.

• Do not use `rados bench`. It creates a small number of objects (1-2 for a thread) so all of them always reside in cache and improve the results far beyond they should be.
• You can also use the simple `fio -ioengine=libaio` with a kernel-mounted RBD. However, that requires to disable some features of that RBD, because kernel client still lacks their support. Note that regardless of the overhead of moving data in and out the kernel, the kernel client is actually faster.
• And you can also use it from inside your VMs, the results are usually similar to the above. Just note that the result also depends on the storage driver being used. Virtio is the fastest, virtio-scsi is slightly slower and everything else (like LSI emulation) is terribly slow. Results are also considerably affected by whether the RBD cache is enabled or not (RBD cache turns on automatically with cache=writeback/none). For random reads or writes, disabling RBD cache is faster.

WHY SO SLOW

Bad news: All writes in Ceph are transactional, even ones that aren’t specifically requested to be. It means that write operations do not finish until they are written into all OSD journals and fsync()'ed to disks. This is to prevent RAID WRITE HOLE-like (see #RAID Write Hole) situations.

RAID Write Hole

Even if we’re talking about RAID, the thing that is much simpler than distributed software-defined storage like Ceph, we’re still talking about a distributed storage system — every system that has multiple physical drives is distributed, because each drive behaves and commits the data (or doesn’t commit it) independently of others.

Write Hole is the name for several situations in RAID arrays when drives go out of sync. Suppose you have a simple RAID1 array of two disks. You write a sector. You send a write command to both drive. And then a power failure occurs before commands finish. Now, after the system boots again, you don’t know if your replicas contain same data, because you don’t know which drive had succeeded to write it and which didn’t.

You say OK, I don’t care. I’ll just read from both drives and if I encounter different data I’ll just pick one of the copies, and I’ll either get the old data or the new.

But then imagine that you have RAID 5. Now you have three drives: two for data and one for parity. Now suppose that you overwrite a sector again. Before writing your disks contain: (A1), (B1) and (A1 XOR B1). You overwrite (B1) with (B2). To do so you write (B2) to the second disk and (A1 XOR B2) to the third. A power failure occurs again… And then, on the next boot, you also find out that disk 1 (one that you didn’t write anything to) is dead. You might think that you can still reconstruct your data because you have RAID 5 and 2 disks out of 3 are still alive.

But imagine that disk 2 succeeded to write new data, while disk 3 failed. Now you have: (lost disk), (B2) and (A1 XOR B1). If you try to reconstruct A from these copies you’ll get (A1 XOR B1 XOR B2) which is obviously not equal to A1. Bang! Your RAID5 has corrupted the data that you didn’t even write at the time of the power loss.

Because of this problem, Linux `mdadm` refuses at all to start an incomplete array after unclean shutdown. There’s no solution to this problem except full data journaling at the level of each disk drive. And this is… exactly what Ceph does! So, Ceph is actually safer than RAID. :)

Quick insight into SSD and flash memory organization

Although flash memory allows fast random writes in small blocks (usually 512 to 4096 bytes), its distinctive feature is that every block must be erased before being written to. But erasing is slow compared to reading and writing, so manufacturers design memory chips so that they always erase a large group of blocks at once, as this takes almost the same time as erasing one block could take. This group of blocks called «erase unit» is typically 2-4 megabytes in size. Another distinctive feature is that the total number of erase/program cycles is physically limited — after several thousands cycles (a usual number for MLC memory) the block becomes faulty and stops accepting new writes or even loses the data previously written to it. Denser and cheaper (MLC/TLC/QLC, 2/3/4 bits per cell) memory chips have smaller erase limits, while sparser and more expensive ones (SLC, 1 bit per cell) have bigger limits (up to 100000 rewrites). However, all limits are still finite, so stupidly overwriting the same block would be very slow and would break SSD very rapidly.

But that’s not the case with modern SSDs - even cheap models are very fast and usually very durable. But why? The credit goes to SSD controllers: SSDs contain very smart and powerful controllers, usually with at least 4 cores and 1-2 GHz clock frequency, which means they’re as powerful as mobile phones' processors. All that power is required to make FTL firmware run smoothly. FTL stands for «Flash Translation Layer» and it is the firmware responsible for translating addresses of small blocks into physical addresses on flash memory chips. Every write request is always put into a space freed in advance, and FTL just remembers the new physical location of the data. This makes writes very fast. FTL also defragments free space and moves blocks around to achieve uniform wear across all memory cells. This feature is called Wear Leveling. SSDs also usually have some extra physical space reserved to add even more endurance and to make wear leveling easier; this is called overprovisioning. Pricier server SSDs have a lot of space overprovisioned, for example, Micron 5100 Max has 37,5 % of physical memory reserved (extra 60 % is added to the user-visible capacity inside).

And this is also the FTL which makes power loss protection a problem. Mapping tables are metadata which must also be forced into non-volatile memory when you flush the cache, and it’s what makes desktop SSDs slow with fsync… In fact, as I wrote it I thought that they could use RocksDB or similar LSM-tree based system to store mapping tables and that could make fsyncs fast even without the capacitors. It would lead to some waste of journal space and some extra write amplification (as every journal block would only contain 1 write), but still it would make writes fast. So… either they don’t know about LSM trees or the FTL metadata is not the only problem for fsync.

When I tried to lecture someone in the mailing list about «all SSDs doing fsyncs correctly» I got this as the reply: https://www.usenix.org/system/files/conference/fast13/fast13-final80.pdf. Long story short, it says that in 2013 a common scenario was SSDs not syncing metadata on fsync calls at all which led to all kinds of funny things on a power loss, up to (!!!) total failures of some SSDs.

There also exist some very old SSDs without capacitors (OCZ Vector/Vertex) which are capable of very large sync iops numbers. How do they work? Nobody knows, but I suspect that they just don’t do safe writes :). The core principle of flash memory overwrites didn’t change in the last years, and SSDs were also based on FTLs just as they do now.

So it seems there are two kinds of «power loss protection»: simple PLP means «we do fsyncs and don’t die or lose your data when a power loss occurs», and advanced PLP means that fsync’ed writes are just as fast as non-fsynced. It also seems that in the current years (2018—2019) simple PLP is already a standard and most SSDs don’t lose data on power failure.

A bonus: USB thumb drives

Why are USB flash drives so slow then? In terms of small random writes they usually only deliver 2-3 operations per second, while being powered by similar flash memory chips — maybe slightly cheaper and worse ones, but obviously not 1000 times worse.

The answer also lies in the FTL. Thumb drives also have FTL and they even have some Wear Leveling, but it’s very small and dumb compared to SSD FTLs. It has a slow CPU and only a little memory. Thus it doesn’t have place to store a full mapping table for small blocks and thus it translates the positions of big blocks (1-2 megabytes or even bigger) instead. Writes are buffered and then flushed one block at a time; there is a small limit on number of blocks that can be buffered at once. The limit is usually only between 3 and 6 blocks.

This limit is always sufficient to copy big files to a flash drive formatted in any of common filesystems. One opened block receives metadata and another receives data, then it just moves on. But if you start doing random writes you stop hitting the opened blocks and this is where lags come in.