diff options
Diffstat (limited to 'docs/htmldocs/speed.html')
| -rw-r--r-- | docs/htmldocs/speed.html | 281 |
1 files changed, 18 insertions, 263 deletions
diff --git a/docs/htmldocs/speed.html b/docs/htmldocs/speed.html index 85562e3e89..1a05706f92 100644 --- a/docs/htmldocs/speed.html +++ b/docs/htmldocs/speed.html @@ -5,7 +5,8 @@ >Samba performance issues</TITLE ><META NAME="GENERATOR" -CONTENT="Modular DocBook HTML Stylesheet Version 1.77"><LINK +CONTENT="Modular DocBook HTML Stylesheet Version 1.76b+ +"><LINK REL="HOME" TITLE="SAMBA Project Documentation" HREF="samba-howto-collection.html"><LINK @@ -72,17 +73,13 @@ WIDTH="100%"></DIV CLASS="CHAPTER" ><H1 ><A -NAME="SPEED" -></A ->Chapter 23. Samba performance issues</H1 +NAME="SPEED">Chapter 22. Samba performance issues</H1 ><DIV CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3065" -></A ->23.1. Comparisons</H1 +NAME="AEN3055">22.1. Comparisons</H1 ><P >The Samba server uses TCP to talk to the client. Thus if you are trying to see if it performs well you should really compare it to @@ -111,98 +108,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3071" -></A ->23.2. Oplocks</H1 -><DIV -CLASS="SECT2" -><H2 -CLASS="SECT2" -><A -NAME="AEN3073" -></A ->23.2.1. Overview</H2 -><P ->Oplocks are the way that SMB clients get permission from a server to -locally cache file operations. If a server grants an oplock -(opportunistic lock) then the client is free to assume that it is the -only one accessing the file and it will agressively cache file -data. With some oplock types the client may even cache file open/close -operations. This can give enormous performance benefits.</P -><P ->With the release of Samba 1.9.18 we now correctly support opportunistic -locks. This is turned on by default, and can be turned off on a share- -by-share basis by setting the parameter :</P -><P -><B -CLASS="COMMAND" ->oplocks = False</B -></P -><P ->We recommend that you leave oplocks on however, as current benchmark -tests with NetBench seem to give approximately a 30% improvement in -speed with them on. This is on average however, and the actual -improvement seen can be orders of magnitude greater, depending on -what the client redirector is doing.</P -><P ->Previous to Samba 1.9.18 there was a 'fake oplocks' option. This -option has been left in the code for backwards compatibility reasons -but it's use is now deprecated. A short summary of what the old -code did follows.</P -></DIV -><DIV -CLASS="SECT2" -><H2 -CLASS="SECT2" -><A -NAME="AEN3081" -></A ->23.2.2. Level2 Oplocks</H2 -><P ->With Samba 2.0.5 a new capability - level2 (read only) oplocks is -supported (although the option is off by default - see the smb.conf -man page for details). Turning on level2 oplocks (on a share-by-share basis) -by setting the parameter :</P -><P -><B -CLASS="COMMAND" ->level2 oplocks = true</B -></P -><P ->should speed concurrent access to files that are not commonly written -to, such as application serving shares (ie. shares that contain common -.EXE files - such as a Microsoft Office share) as it allows clients to -read-ahread cache copies of these files.</P -></DIV -><DIV -CLASS="SECT2" -><H2 -CLASS="SECT2" -><A -NAME="AEN3087" -></A ->23.2.3. Old 'fake oplocks' option - deprecated</H2 -><P ->Samba can also fake oplocks, by granting a oplock whenever a client -asks for one. This is controlled using the smb.conf option "fake -oplocks". If you set "fake oplocks = yes" then you are telling the -client that it may agressively cache the file data for all opens.</P -><P ->Enabling 'fake oplocks' on all read-only shares or shares that you know -will only be accessed from one client at a time you will see a big -performance improvement on many operations. If you enable this option -on shares where multiple clients may be accessing the files read-write -at the same time you can get data corruption.</P -></DIV -></DIV -><DIV -CLASS="SECT1" -><H1 -CLASS="SECT1" -><A -NAME="AEN3091" -></A ->23.3. Socket options</H1 +NAME="AEN3061">22.2. Socket options</H1 ><P >There are a number of socket options that can greatly affect the performance of a TCP based server like Samba.</P @@ -228,9 +134,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3098" -></A ->23.4. Read size</H1 +NAME="AEN3068">22.3. Read size</H1 ><P >The option "read size" affects the overlap of disk reads/writes with network reads/writes. If the amount of data being transferred in @@ -254,9 +158,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3103" -></A ->23.5. Max xmit</H1 +NAME="AEN3073">22.4. Max xmit</H1 ><P >At startup the client and server negotiate a "maximum transmit" size, which limits the size of nearly all SMB commands. You can set the @@ -277,56 +179,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3108" -></A ->23.6. Locking</H1 -><P ->By default Samba does not implement strict locking on each read/write -call (although it did in previous versions). If you enable strict -locking (using "strict locking = yes") then you may find that you -suffer a severe performance hit on some systems.</P -><P ->The performance hit will probably be greater on NFS mounted -filesystems, but could be quite high even on local disks.</P -></DIV -><DIV -CLASS="SECT1" -><H1 -CLASS="SECT1" -><A -NAME="AEN3112" -></A ->23.7. Share modes</H1 -><P ->Some people find that opening files is very slow. This is often -because of the "share modes" code needed to fully implement the dos -share modes stuff. You can disable this code using "share modes = -no". This will gain you a lot in opening and closing files but will -mean that (in some cases) the system won't force a second user of a -file to open the file read-only if the first has it open -read-write. For many applications that do their own locking this -doesn't matter, but for some it may. Most Windows applications -depend heavily on "share modes" working correctly and it is -recommended that the Samba share mode support be left at the -default of "on".</P -><P ->The share mode code in Samba has been re-written in the 1.9.17 -release following tests with the Ziff-Davis NetBench PC Benchmarking -tool. It is now believed that Samba 1.9.17 implements share modes -similarly to Windows NT.</P -><P ->NOTE: In the most recent versions of Samba there is an option to use -shared memory via mmap() to implement the share modes. This makes -things much faster. See the Makefile for how to enable this.</P -></DIV -><DIV -CLASS="SECT1" -><H1 -CLASS="SECT1" -><A -NAME="AEN3117" -></A ->23.8. Log level</H1 +NAME="AEN3078">22.5. Log level</H1 ><P >If you set the log level (also known as "debug level") higher than 2 then you may suffer a large drop in performance. This is because the @@ -338,23 +191,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3120" -></A ->23.9. Wide lines</H1 -><P ->The "wide links" option is now enabled by default, but if you disable -it (for better security) then you may suffer a performance hit in -resolving filenames. The performance loss is lessened if you have -"getwd cache = yes", which is now the default.</P -></DIV -><DIV -CLASS="SECT1" -><H1 -CLASS="SECT1" -><A -NAME="AEN3123" -></A ->23.10. Read raw</H1 +NAME="AEN3081">22.6. Read raw</H1 ><P >The "read raw" operation is designed to be an optimised, low-latency file read operation. A server may choose to not support it, @@ -374,9 +211,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3128" -></A ->23.11. Write raw</H1 +NAME="AEN3086">22.7. Write raw</H1 ><P >The "write raw" operation is designed to be an optimised, low-latency file write operation. A server may choose to not support it, @@ -391,56 +226,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3132" -></A ->23.12. Read prediction</H1 -><P ->Samba can do read prediction on some of the SMB commands. Read -prediction means that Samba reads some extra data on the last file it -read while waiting for the next SMB command to arrive. It can then -respond more quickly when the next read request arrives.</P -><P ->This is disabled by default. You can enable it by using "read -prediction = yes".</P -><P ->Note that read prediction is only used on files that were opened read -only.</P -><P ->Read prediction should particularly help for those silly clients (such -as "Write" under NT) which do lots of very small reads on a file.</P -><P ->Samba will not read ahead more data than the amount specified in the -"read size" option. It always reads ahead on 1k block boundaries.</P -></DIV -><DIV -CLASS="SECT1" -><H1 -CLASS="SECT1" -><A -NAME="AEN3139" -></A ->23.13. Memory mapping</H1 -><P ->Samba supports reading files via memory mapping them. One some -machines this can give a large boost to performance, on others it -makes not difference at all, and on some it may reduce performance.</P -><P ->To enable you you have to recompile Samba with the -DUSE_MMAP option -on the FLAGS line of the Makefile.</P -><P ->Note that memory mapping is only used on files opened read only, and -is not used by the "read raw" operation. Thus you may find memory -mapping is more effective if you disable "read raw" using "read raw = -no".</P -></DIV -><DIV -CLASS="SECT1" -><H1 -CLASS="SECT1" -><A -NAME="AEN3144" -></A ->23.14. Slow Clients</H1 +NAME="AEN3090">22.8. Slow Clients</H1 ><P >One person has reported that setting the protocol to COREPLUS rather than LANMAN2 gave a dramatic speed improvement (from 10k/s to 150k/s).</P @@ -455,9 +241,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3148" -></A ->23.15. Slow Logins</H1 +NAME="AEN3094">22.9. Slow Logins</H1 ><P >Slow logins are almost always due to the password checking time. Using the lowest practical "password level" will improve things a lot. You @@ -468,9 +252,7 @@ CLASS="SECT1" ><H1 CLASS="SECT1" ><A -NAME="AEN3151" -></A ->23.16. Client tuning</H1 +NAME="AEN3097">22.10. Client tuning</H1 ><P >Often a speed problem can be traced to the client. The client (for example Windows for Workgroups) can often be tuned for better TCP @@ -545,11 +327,13 @@ turned out I was better off without any!!!!!</P and a DX2-66 20MB server with a crappy NE2000 compatible and old IDE drive (Kernel 2.0.30). The transfer rate was reasonable for 10 baseT.</P ><P ->FIXME -The figures are: Put Get +><PRE +CLASS="PROGRAMLISTING" +>The figures are: Put Get P166 client 3Com card: 420-440kB/s 500-520kB/s P100 client 3Com card: 390-410kB/s 490-510kB/s -DX4-75 client NE2000: 370-380kB/s 330-350kB/s</P +DX4-75 client NE2000: 370-380kB/s 330-350kB/s</PRE +></P ><P >I based these test on transfer two files a 4.5MB text file and a 15MB textfile. The results arn't bad considering the hardware Samba is @@ -567,35 +351,6 @@ upwards). I suppose there is more going on in the samba protocol, but if it could get up to the rate of FTP the perfomance would be quite staggering.</P ></DIV -><DIV -CLASS="SECT1" -><H1 -CLASS="SECT1" -><A -NAME="AEN3183" -></A ->23.17. My Results</H1 -><P ->Some people want to see real numbers in a document like this, so here -they are. I have a 486sx33 client running WfWg 3.11 with the 3.11b -tcp/ip stack. It has a slow IDE drive and 20Mb of ram. It has a SMC -Elite-16 ISA bus ethernet card. The only WfWg tuning I've done is to -set DefaultRcvWindow in the [MSTCP] section of system.ini to 16384. My -server is a 486dx3-66 running Linux. It also has 20Mb of ram and a SMC -Elite-16 card. You can see my server config in the examples/tridge/ -subdirectory of the distribution.</P -><P ->I get 490k/s on reading a 8Mb file with copy. -I get 441k/s writing the same file to the samba server.</P -><P ->Of course, there's a lot more to benchmarks than 2 raw throughput -figures, but it gives you a ballpark figure.</P -><P ->I've also tested Win95 and WinNT, and found WinNT gave me the best -speed as a samba client. The fastest client of all (for me) is -smbclient running on another linux box. Maybe I'll add those results -here someday ...</P -></DIV ></DIV ><DIV CLASS="NAVFOOTER" |