Differences

This shows you the differences between two versions of the page.

--- proc:io_accounting_fields [2017/04/06 14:58] – created peter
+++ proc:io_accounting_fields [2020/07/15 09:30] (current) – external edit 127.0.0.1
@@ Line 1: / Line 1: @@
 ====== Proc - IO Accounting Fields ======
+**/proc/<pid>/io** display the IO accounting fields, which are IO statistics for each running process.
+<code bash>
+dd if=/dev/zero of=/tmp/test.dat &
+[1] 3828
+cat /proc/3828/io
+rchar: 323934931
+wchar: 323929600
+syscr: 632687
+syscw: 632675
+read_bytes: 0
+write_bytes: 323932160
+cancelled_write_bytes: 0
+</code>
+where:
+  * **rchar** is count of chars read.  The number of bytes which this task has caused to be read from storage.  This is simply the sum of bytes which this process passed to **read()** and **pread()**.  It includes things like tty IO and it is unaffected by whether or not actual physical disk IO was required (the read might have been satisfied from pagecache)
+  * **wchar** is count of chars written. The number of bytes which this task has caused, or shall cause to be written to disk. Similar caveats apply here as with **rchar**.
+  * **syscr** is a count of read syscalls.  Attempt to count the number of read I/O operations, i.e. syscalls like **read()** and **pread()**.
+  * **syscw** is a count of writen syscalls.  Attempt to count the number of write I/O operations, i.e. syscalls like **write()** and **pwrite()**.
+  * **read_bytes** is count of bytes read.  Attempt to count the number of bytes which this process really did cause to be fetched from the storage layer.  Done at the **submit_bio()** level, so it is accurate for block-backed filesystems.  TODO:  Add status regarding NFS and CIFS at a later time.
+  * **write_bytes** is count of bytes written.  Attempt to count the number of bytes which this process caused to be sent to the storage layer.  This is done at **page-dirtying** time.
+  * **cancelled_write_bytes** The big inaccuracy here is truncate.  If a process writes 1MB to a file and then deletes the file, it will in fact perform no writeout.  But it will have been accounted as having caused 1MB of write.  In other words:  The number of bytes which this process caused to not happen, by truncating pagecache.  A task can cause "negative" IO too.  If this task truncates some dirty pagecache, some IO which another task has been accounted for (in its write_bytes) will not be happening.  We _could_ just subtract that from the truncating task's write_bytes, but there is information loss in doing that.
+<WRAP warning>
+**WARNING:**  At its current implementation state, this is a bit racy on 32-bit machines: if process A reads process B's **/proc/pid/io** while process B is updating one of those 64-bit counters, process A could see an intermediate result.
+More information about this can be found within the taskstats documentation in Documentation/accounting.
+</WRAP>