Hard State Revisited: Network FilesystemsHard State Revisited: Network Filesystems

Jeff Chase

CPS 212, Fall 2000

Network File System (NFS)Network File System (NFS)

syscall layer

*FS

NFSserver

VFS

VFS

NFSclient

*FS

syscall layer

client

user programs

RPC over UDP or TCP

server

NFS VnodesNFS Vnodes

syscall layer

*FS

NFSserver

VFS

RPC

network

nfsnode

NFS client stubs

nfs_vnodeops

The nfsnode holds client state needed to interact with the serverto operate on the file.

struct nfsnode* np = VTONFS(vp);

The NFS protocol has an operation type for (almost) every vnode operation, with similar arguments/results.

File HandlesFile Handles

Question: how does the client tell the server which file or directory the operation applies to?

• Similarly, how does the server return the result of a lookup?

More generally, how to pass a pointer or an object reference as an argument/result of an RPC call?

In NFS, the reference is a file handle or fhandle, a token/ticket whose value is determined by the server.

• Includes all information needed to identify the file/object on the server, and find it quickly.

volume ID inode # generation #

NFS: From Concept to ImplementationNFS: From Concept to Implementation

Now that we understand the basics, how do we make it fast?

• caching

data blocks

file attributes

lookup cache (dnlc): name->fhandle mappings

directory contents?

• read-ahead and write-behind

file I/O at wire speed

And of course we want the full range of other desirable “*ility” properties....

NFS as a “Stateless” ServiceNFS as a “Stateless” Service

A classical NFS server maintains no in-memory hard state.The only hard state is the stable file system image on disk.

• no record of clients or open files

• no implicit arguments to requests

E.g., no server-maintained file offsets: read and write requests must explicitly transmit the byte offset for each operation.

• no write-back caching on the server

• no record of recently processed requests

• etc., etc....

Statelessness makes failure recovery simple and efficient.

Recovery in Stateless NFSRecovery in Stateless NFS

If the server fails and restarts, there is no need to rebuild in-memory state on the server.• Client reestablishes contact (e.g., TCP connection).

• Client retransmits pending requests.

Classical NFS uses a connectionless transport (UDP).• Server failure is transparent to the client; no connection to

break or reestablish.A crashed server is indistinguishable from a slow server.

• Sun/ONC RPC masks network errors by retransmitting a request after an adaptive timeout.

A dropped packet is indistinguishable from a crashed server.

Drawbacks of a Stateless ServiceDrawbacks of a Stateless Service

The stateless nature of classical NFS has compelling design advantages (simplicity), but also some key drawbacks:• Recovery-by-retransmission constrains the server interface.

ONC RPC/UDP has execute-at-least-once semantics (“send and pray”), which compromises performance and correctness.

• Update operations are disk-limited.Updates must commit synchronously at the server.

• NFS cannot (quite) preserve local single-copy semantics.Files may be removed while they are open on the client.

Server cannot help in client cache consistency.

Let’s explore these problems and their solutions...

Problem 1: Retransmissions and IdempotencyProblem 1: Retransmissions and Idempotency

For a connectionless RPC transport, retransmissions can saturate an overloaded server.

Clients “kick ‘em while they’re down”, causing steep hockey stick.

Execute-at-least-once constrains the server interface.

• Service operations should/must be idempotent.

Multiple executions should/must have the same effect.

• Idempotent operations cannot capture the full semantics we expect from our file system.

remove, append-mode writes, exclusive create

Solutions to the Retransmission ProblemSolutions to the Retransmission Problem

1. Hope for the best and smooth over non-idempotent requests.E.g., map ENOENT and EEXIST to ESUCCESS.

2. Use TCP or some other transport protocol that produces reliable, in-order delivery.

higher overhead...and we still need sessions.

3. Implement an execute-at-most once RPC transport.TCP-like features (sequence numbers)...and sessions.

4. Keep a retransmission cache on the server [Juszczak90].Remember the most recent request IDs and their results,

and just resend the result....does this violate statelessness?

DAFS persistent session cache.

Problem 2: Synchronous WritesProblem 2: Synchronous Writes

Stateless NFS servers must commit each operation to stable storage before responding to the client.

• Interferes with FS optimizations, e.g., clustering, LFS, and disk write ordering (seek scheduling).

Damages bandwidth and scalability.

• Imposes disk access latency for each request.

Not so bad for a logged write; much worse for a complex operation like an FFS file write.

The synchronous update problem occurs for any storage service with reliable update (commit).

Speeding Up Synchronous NFS WritesSpeeding Up Synchronous NFS Writes

Interesting solutions to the synchronous write problem, used in high-performance NFS servers:• Delay the response until convenient for the server.

E.g., NFS write-gathering optimizations for clustered writes (similar to group commit in databases).

Relies on write-behind from NFS I/O daemons (iods).

• Throw hardware at it: non-volatile memory (NVRAM)Battery-backed RAM or UPS (uninterruptible power

supply).

Use as an operation log (Network Appliance WAFL)...

...or as a non-volatile disk write buffer (Legato).

• Replicate server and buffer in memory (e.g., MIT Harp).

NFS V3 Asynchronous WritesNFS V3 Asynchronous Writes

NFS V3 sidesteps the synchronous write problem by adding a new asynchronous write operation.

• Server may reply to client as soon as it accepts the write, before executing/committing it.

If the server fails, it may discard any subset of the accepted but uncommitted writes.

• Client holds asynchronously written data in its cache, and reissues the writes if the server fails and restarts.

When is it safe for the client to discard its buffered writes?

How can the client tell if the server has failed?

NFS V3 CommitNFS V3 Commit

NFS V3 adds a new commit operation to go with async-write.

• Client may issue a commit for a file byte range at any time.

• Server must execute all covered uncommitted writes before replying to the commit.

• When the client receives the reply, it may safely discard any buffered writes covered by the commit.

• Server returns a verifier with every reply to an async write or commit request.

The verifier is just an integer that is guaranteed to change if the server restarts, and to never change back.

• What if the client crashes?

Problem 3: File Cache ConsistencyProblem 3: File Cache Consistency

Problem: Concurrent write sharing of files.Contrast with read sharing or sequential write sharing.

Solutions:

• Timestamp invalidation (NFS).

Timestamp each cache entry, and periodically query the server: “has this file changed since time t?”; invalidate cache if stale.

• Callback invalidation (AFS, Sprite, Spritely NFS).

Request notification (callback) from the server if the file changes; invalidate cache and/or disable caching on callback.

• Leases (NQ-NFS) [Gray&Cheriton89,Macklem93,NFS V4]

• Later: distributed shared memory

File Cache Example: NQ-NFS LeasesFile Cache Example: NQ-NFS Leases

In NQ-NFS, a client obtains a lease on the file that permits the client’s desired read/write activity.

“A lease is a ticket permitting an activity; the lease is valid until some expiration time.”

• A read-caching lease allows the client to cache clean data.

Guarantee: no other client is modifying the file.

• A write-caching lease allows the client to buffer modified data for the file.

Guarantee: no other client has the file cached.

Allows delayed writes: client may delay issuing writes to improve write performance (i.e., client has a writeback cache).

Using NQ-NFS LeasesUsing NQ-NFS Leases

1. Client NFS piggybacks lease requests for a given file on I/O operation requests (e.g., read/write).

NQ-NFS leases are implicit and distinct from file locking.

2. The server determines if it can safely grant the request, i.e., does it conflict with a lease held by another client.

read leases may be granted simultaneously to multiple clients

write leases are granted exclusively to a single client

3. If a conflict exists, the server may send an eviction notice to the holder of the conflicting lease.

If a client is evicted from a write lease, it must write back.

Grace period: server grants extensions while the client writes.

Client sends vacated notice when all writes are complete.

NQ-NFS Lease RecoveryNQ-NFS Lease Recovery

Key point: the bounded lease term simplifies recovery.

• Before a lease expires, the client must renew the lease.

• What if a client fails while holding a lease?

Server waits until the lease expires, then unilaterally reclaims the lease; client forgets all about it.

If a client fails while writing on an eviction, server waits for write slack time before granting conflicting lease.

• What if the server fails while there are outstanding leases?

Wait for lease period + clock skew before issuing new leases.

• Recovering server must absorb lease renewal requests and/or writes for vacated leases.

NQ-NFS Leases and Cache ConsistencyNQ-NFS Leases and Cache Consistency

• Every lease contains a file version number.

Invalidation cache iff version number has changed.

• Clients may disable client caching when there is concurrent write sharing.

no-caching lease

• What consistency guarantees do NQ-NFS leases provide?

Does the server eventually receive/accept all writes?

Does the server accept the writes in order?

Are groups of related writes atomic?

How are write errors reported?

What is the relationship to NFS V3 commit?

The Distributed Lock LabThe Distributed Lock Lab

The lock implementation is similar to DSM systems, with reliability features similar to distributed file caches.

• use Java RMI

• lock token caching with callbacks

lock tokens passed through server, not peer-peer as DSM

• synchronizes multiple threads on same client

• state bit for pending callback on client

• server must reissue callback each lease interval (or use RMI timeouts to detect a failed client)

• client must renew token each lease interval

Background: Unix Filesystem InternalsBackground: Unix Filesystem Internals

A Typical Unix File TreeA Typical Unix File Tree

/

tmp usretc

File trees are built by graftingvolumes from different volumesor from network servers.

Each volume is a set of directories and files; a host’s file tree is the set ofdirectories and files visible to processes on a given host.

bin vmunix

ls sh project users

packages

(volume root)

tex emacs

In Unix, the graft operation isthe privileged mount system call,and each volume is a filesystem.

mount pointmount (coveredDir, volume)

coveredDir: directory pathnamevolume: device specifier or network volume

volume root contents become visible at pathname coveredDir

FilesystemsFilesystems

Each file volume (filesystem) has a type, determined by its disk layout or the network protocol used to access it.

ufs (ffs), lfs, nfs, rfs, cdfs, etc.

Filesystems are administered independently.

Modern systems also include “logical” pseudo-filesystems in the naming tree, accessible through the file syscalls.

procfs: the /proc filesystem allows access to process internals.

mfs: the memory file system is a memory-based scratch store.

Processes access filesystems through common system calls.

VFS: the Filesystem SwitchVFS: the Filesystem Switch

syscall layer (file, uio, etc.)

user space

Virtual File System (VFS)networkprotocol

stack(TCP/IP) NFS FFS LFS etc.*FS etc.

device drivers

Sun Microsystems introduced the virtual file system interface in 1985 to accommodate diverse filesystem types cleanly.

VFS allows diverse specific file systems to coexist in a file tree, isolating all FS-dependencies in pluggable filesystem modules.

VFS was an internal kernel restructuringwith no effect on the syscall interface.

Incorporates object-oriented concepts:a generic procedural interface withmultiple implementations.

Based on abstract objects with dynamicmethod binding by type...in C.Other abstract interfaces in the kernel: device drivers,

file objects, executable files, memory objects.

VnodesVnodes

In the VFS framework, every file or directory in active use is represented by a vnode object in kernel memory.

syscall layer

NFS UFS

free vnodes

Each vnode has a standardfile attributes struct.

Vnode operations aremacros that vector tofilesystem-specificprocedures.

Generic vnode points atfilesystem-specific struct(e.g., inode, rnode), seenonly by the filesystem.

Each specific file system maintains a cache of its resident vnodes.

Vnode Operations and AttributesVnode Operations and Attributes

directories onlyvop_lookup (OUT vpp, name)vop_create (OUT vpp, name, vattr)vop_remove (vp, name)vop_link (vp, name)vop_rename (vp, name, tdvp, tvp, name)vop_mkdir (OUT vpp, name, vattr)vop_rmdir (vp, name)vop_symlink (OUT vpp, name, vattr, contents)vop_readdir (uio, cookie)vop_readlink (uio)

files onlyvop_getpages (page**, count, offset)vop_putpages (page**, count, sync, offset)vop_fsync ()

vnode attributes (vattr)type (VREG, VDIR, VLNK, etc.)mode (9+ bits of permissions)nlink (hard link count)owner user IDowner group IDfilesystem IDunique file IDfile size (bytes and blocks)access timemodify timegeneration number

generic operationsvop_getattr (vattr)vop_setattr (vattr)vhold()vholdrele()

V/Inode CacheV/Inode Cache

HASH(fsid, fileid)VFS free list head

Active vnodes are reference- counted by the structures that hold pointers to them.

- system open file table

- process current directory

- file system mount points

- etc.

Each specific file system maintains its own hash of vnodes (BSD).

- specific FS handles initialization

- free list is maintained by VFSvget(vp): reclaim cached inactive vnode from VFS free listvref(vp): increment reference count on an active vnodevrele(vp): release reference count on a vnode vgone(vp): vnode is no longer valid (file is removed)

Pathname TraversalPathname Traversal

When a pathname is passed as an argument to a system call, the syscall layer must “convert it to a vnode”.

Pathname traversal is a sequence of vop_lookup calls to descend the tree to the named file or directory.

open(“/tmp/zot”)vp = get vnode for / (rootdir)vp->vop_lookup(&cvp, “tmp”);vp = cvp;vp->vop_lookup(&cvp, “zot”);

Issues:1. crossing mount points2. obtaining root vnode (or current dir)3. finding resident vnodes in memory4. caching name->vnode translations5. symbolic (soft) links6. disk implementation of directories7. locking/referencing to handle races with name create and delete operations

NFS ProtocolNFS Protocol

NFS is a network protocol layered above TCP/IP.

• Original implementations (and most today) use UDP datagram transport for low overhead.

Maximum IP datagram size was increased to match FS block size, to allow send/receive of entire file blocks.

Some implementations use TCP as a transport.

• The NFS protocol is a set of message formats and types.

Client issues a request message for a service operation.

Server performs requested operation and returns a reply message with status and (perhaps) requested data.

Network Block StorageNetwork Block Storage

One approach to scalable storage is to attach raw block storage to a network.

• abstraction: OS addresses storage by <volume, sector>.

iSCSI, Petal, FC: access through souped-up device driver

• dedicated Storage Area Network or general-purpose network

FibreChannel vs. Ethernet

• shared access with scalable bandwidth and capacity

• volume-based administrative tools

backup, volume replication, remote sharing

• Called “raw” or “block”, “storage volumes” or just “SAN”.

““NAS vs. SAN”NAS vs. SAN”

In the commercial sector there is a raging debate today about “NAS vs. SAN”.

• Network-Attached Storage has been the dominant approach to shared storage since NFS.

NAS == NFS or CIFS: named files over Ethernet/Internet.

Network Appliance “filers”

• Proponents of FibreChannel SANs market them as a fundamentally faster way to access shared storage.

no “indirection through a file server” (“SAD”)

lower overhead on clients

network is better/faster (if not cheaper) and dedicated/trusted

Brocade, HP, Emulex are some big players.

NAS vs. SAN: Cutting through the BSNAS vs. SAN: Cutting through the BS

• FibreChannel a high-end technology incorporating NIC enhancements to reduce host overhead....

...but bogged down in interoperability problems.

• Ethernet is getting faster faster than FibreChannel.

gigabit, 10-gigabit, + smarter NICs, + smarter/faster switches

• Future battleground is Ethernet vs. Infiniband.

• The choice of network is fundamentally orthogonal to storage service design.

Well, almost: flow control, RDMA, user-level access (DAFS/VI)

• The fundamental questions are really about abstractions.

shared raw volume vs. shared file volume vs. private disks

Storage AbstractionsStorage Abstractions

• relational database (IBM and Oracle)

tables, transactions, query language

• file system

hierarchical name space with ACLs

• block storage

SAN, Petal, RAID-in-a-box (e.g., EMC)

• object storage

object == file, with a flat name space: NASD, DDS

• persistent objects

pointer structures, requires transactions: OODB, ObjectStore

Storage ArchitectureStorage Architecture

Any of these abstractions can be built using any, some, or all of the others.

Use the “right” abstraction for your application.

The fundamental questions are:

• What is the best way to build the abstraction you want?

division of function between device, network, server, and client

• What level of the system should implement the features and properties you want?

How does Frangipani answer them?

Cluster File SystemsCluster File Systems

shared block storage service (FC/SAN, Petal, NASD)

xFS [Dahlin95]Petal/Frangipani [Lee/Thekkath]GFSVeritasEMC Celerra

storage client

cluster FS cluster FSstorage client

issuestrustcompatibility with NAS protocolssharing, coordination, recovery

Sharing and CoordinationSharing and Coordination

storage service + lock manager

*FS client *FS client

*FS svc *FS svc

block allocation and layout

locking/leases, granularity

shared access

separate lock service

logging and recovery

network partitions

reconfiguration

NAS

“SAN”

What does Frangipani need from Petal? How does Petal contribute to F’s *ility?Could we build Frangipani without Petal?