Mixing memory unit messages

By
One of my pet hates is developers messing up units of memory.  In general, the difference doesn't matter much, or you can work out what they meant to say, but it does annoy me when developers who should know better appear to be confused about what they are trying to say.

From Wikipedia's Byte page, here is a cheat sheet of units

"b" means bits
"B" means bytes
"k" or kilo- is standard prefix meaning 1000
"K" or "Ki", sometimes called kibi- is 1024
"m" or mill-, means 1/1000th
"M" or mega-, means 1000^2
"Mi" or mebi-, means 1024^2

 Unit      Meaning      In bytes
mb    
milli-bits1/8000th of a byte
mB    
milli-bytes1/1000th of a byte
kb    
kilo-bits
125 bytes
kB    
kilo-bytes
1000 bytes
Kb or Kib    
kibi-bits
128 bytes
KB or KiB    
kibi-bytes
1024 bytes
Mb    
mega-bits
125,000 bytes
MB    
mega-bytes
1,000,000 bytes
Mib    
mebi-bits
131,072 bytes
MiB    
mebi-bytes
1,048,576 bytes

What annoys me is when professionals confuse these terms.

In UNIX:

In top on Unix it states
KiB Mem:  32893900

but when I do "head -1 /proc/meminfo" it states
MemTotal:       32893900 kB
this is 2.4% less.

I suspect top is correct as it is closer the amount of memory installed and they used "KiB" which lends credibility, but I can't be sure.

In the JVM

The default translation for "KBYTES" is "kbytes" but in Japanese and Chinese it is "KB" which is 2.4% more.

While the JVM appears to be using KiB or kibibytes every where, it refers to "KiB" only three times, but uses "kB" in twice, "Kb" in seven places, "KB" in 127 places and "kilobytes" in three cases.

Similarly "MiB" appears 4 times, "MB" in 87 places, "Mb" three times and "mb" three times.

Puzzle

Question: A computer program writes to memory at 49 mb/s, to disk at 50 mb/s and to the network at 100 mb/s. Which is it writing data at a higher rate to; the memory, the disk or the network?

Answer: It is probably writing to memory most and the network least.  This is because it might be read as "... to memory at 49 MiB/s, to disk at 50 MB/s and to the network at 100 Mb/s. " and one MiB/s is almost 8.4 Mb/s

Conclusion

If you don't know what units you have in mind and which ones you don't, it shouldn't be surprising if someone reading your output is confused as well.

I encourage everyone to use standard units in their code so when you see units you know exactly what they mean.


Comments

Post a Comment

Popular posts from this blog

Java is Very Fast, If You Don’t Create Many Objects

By
Image
  You still have to watch how many objects you create. This article looks at a benchmark passing events over TCP/IP at 4 billion events per minute using the net.openhft.chronicle.wire.channel package in Chronicle Wire and why we still avoid object allocations..  One of the key optimisations is creating almost no garbage. Allocation is a very cheap operation and collection of very short-lived objects is also very cheap. Does this really make a difference? What difference does one small object per event (44 bytes) make to the performance in a throughput test where GC pauses are amortised? While allocation is as efficient as possible, it doesn’t avoid the memory pressure on the L1/L2 caches of your CPUs and when many cores are busy, they are contending for memory in the shared L3 cache.  Results Benchmark on a Ryzen 5950X with Ubuntu 22.10. JVM Vendor, Version No objects Throughput, Average Latency* One object per event Throughput, Average Latency* Azul Zulu 1.8.0_322 60.6 M event/s, 528
Read more

System wide unique nanosecond timestamps

By
A Unique Identifier can be very useful for tracing. Those ids are even more useful when they contain a high-resolution timestamp.  Not only do they record the time of an event, but if unique can help trace events as they pass through the system. Such unique timestamps however can be expensive depending on how they are implemented.   This post explores a lightweight means of producing a unique, monotonically increasing system-wide nano-second resolution timestamp available in our open-source library. Uses for Unique Identifiers Unique identifiers can be useful to associate with a piece of information so that information can be referred to later unambiguously. This could be an event, a request, an order id, or a customer id. They can naturally be used as a primary key in a database or key/value store to retrieve that information later. One of the challenges of generating these identifiers is avoiding creating duplicates while not having an increasing cost.  You could record every identi
Read more

Comparing Approaches to Durability in Low Latency Messaging Queues

By
Image
  A significant feature of Chronicle Queue Enterprise is support for TCP replication across multiple servers to ensure the high availability of application infrastructure. I generally believe that replicating data to a secondary system is faster than syncing to disk, assuming the round trip network delay wasn’t high due to quality networks and co-located redundant servers. This is the first time I have benchmarked it with a realistic example. Little’s Law and Why Latency Matters In many cases, the assumption is that the latency won't be a problem as long as throughput is high enough. However, latency is often a key factor in why the throughput isn’t high enough. Little’s law states, “ the long-term average number  L  of customers in a  stationary  system is equal to the long-term average effective arrival rate  λ  multiplied by the average time  W  that a customer spends in the system”. In computer terminology, the level of concurrency or parallelism a system has to support must be
Read more