Scott Finley University of Wisconsin – Madison CS 736 Project
Basic, default Linux file system Almost exactly the same as FFS ◦ Disk broken into “block groups” ◦ Super-block, inode/block bitmaps, etc.
New from the ground up Reliability as #1 goal Reevaluate conventional OS structure Leverage advances of the last 20 years ◦ Languages and compilers ◦ Static analysis of whole system
Implement Ext2 on Singularity Focus on read support with caching Investigate how Singularity design impact FS integration Investigate performance implications
I have a Ext2 “working” on Singularity ◦ Reading fully supported ◦ Caching improves performance! ◦ Limited write support Singularity design ◦ Garbage collection hurts performance ◦ Reliability is good: I couldn’t crash it.
1. Singularity Details 2. Details of my Ext2 implementation 3. Results
Everything is written in C# ◦ Small pieces of kernel (< 5%) in assembly and C++ as needed Kernel and processes are garbage collected No virtual machine ◦ Compiled to native code Very aggressive optimizing compiler
Singularity is a micro kernel Everything else is a SIP ◦ “Software Isolated Process” No hardware based memory isolation ◦ SIP “Object Space” isolation guaranteed by static analysis and safe language (C#) ◦ Context switches are much faster
All SIP communication is via message channels No shared memory Messages and data passed via Exchange Heap Object ownership is tracked Zero copy data passing via pointers
Application creates buffer in ExHeap AppFile SystemDisk Driver Exchange Heap Empty Buffer
Application send read request to file system ◦ File system owns the buffer AppFile SystemDisk Driver Exchange Heap Empty Buffer
File system sends read request to driver ◦ Driver owns the buffer AppFile SystemDisk Driver Exchange Heap Empty Buffer
Driver fills buffer and replies to file system AppFile SystemDisk Driver Exchange Heap Full Buffer
File system replies to application AppFile SystemDisk Driver Exchange Heap Full Buffer
Application consumes the buffer AppFile SystemDisk Driver Exchange Heap
Ext2Control: Command line application Ext2ClientManager: Manages mount points Ext2FS: Core file system functionality Ext2Contracts: Defines communication
System service (SIP) launched at boot Accessible at known location in /dev directory Does “Ext2 stuff” Operates on Ext2 volumes and mount points Exports “Mount” and “Unmount” ◦ Would also provide “Format” if implemented 300 lines of code
Command line application Allows Ext2 Client Manger interface access Not used by other applications 500 lines of code
Core Ext2 file system. Separate instance (SIP) for each mount point. ◦ Exports “Directory Service Provider” interface Clients open files and directories by attaching a communication channel ◦ Internally paired with an Inode. Reads implemented, Writes in progress 2400 Lines of code
Client wants to read file “/mnt/a/b.txt” ◦ Ext2 mounted at “/mnt” 1. App --CH0-->SNS: 2. App 3. App --CH0-->SNS: 4. App
5. App --CH1-->Ext2Fs: 6. App 7. App --CH2-->Ext2Fs: 8. App 9. …
1. Inodes: Used on every access 2. Block Numbers: Very important for large files 3. Data Blocks: Naturally captures others All use LRU replacement Large files unusable without caching ◦ 8300X faster reading 350 MB file
Athlon , 1 GB RAM Disk: 120GB, 7200 RPM, 2 MB buffer, PATA Measured sequential reads Varied read buffer size from 4 KB to 96 MB Timed each request File sizes ranged from 13 MB to 350 MB
Linux is faster ◦ Not clear that this is fundamental Performance is not horrible ◦ “Good enough” objective met ◦ Garbage collection hurts, but not “too bad” Not sensitive to file size
System programming in a modern language System programming with no crashes Micro kernel is feasible ◦ Hurts feature integration: mmap, cache sharing ◦ Clean, simple interfaces