| Kibioctets (Kio) | Petaoctets (Po) |
|---|---|
| 1 Kibioctet | 1.024 × 10-12 Po |
| 2 Kibioctets | 2.048 × 10-12 Po |
| 3 Kibioctets | 3.072 × 10-12 Po |
| 4 Kibioctets | 4.096 × 10-12 Po |
| 5 Kibioctets | 5.12 × 10-12 Po |
| 10 Kibioctets | 1.024 × 10-11 Po |
| 20 Kibioctets | 2.048 × 10-11 Po |
| 25 Kibioctets | 2.56 × 10-11 Po |
| 50 Kibioctets | 5.12 × 10-11 Po |
| 100 Kibioctets | 1.024 × 10-10 Po |
| Reference | Kibioctets (Kio) | Petaoctets (Po) |
|---|---|---|
| A plain text message (160 characters) | 0.15625 Kio | 1.6 × 10-13 Po |
| A three-minute MP3 | 2929.69 Kio | 0.000000003 Po |
| A smartphone photo | 3906.25 Kio | 0.000000004 Po |
| A high-definition film | 3906250 Kio | 0.000004 Po |
| A dual-layer Blu-ray disc | 48828125 Kio | 0.00005 Po |
The kibioctet is a unit of digital information equal to 1,024 octets, and therefore to 8,192 bits. Its symbol is Kio. It is the binary counterpart of the kilooctet, and although the two differ by only 2.4 per cent, this is the unit in which a great deal of a computer's internal organisation is actually measured.
The most important example is the memory page. Processors do not manage memory octet by octet but in fixed-size blocks, and on almost every architecture in common use that block is 4 kibioctets. Every allocation a program makes is rounded up to a multiple of that, every entry in the page tables describes one of them, and the performance of a program often depends on how well its access pattern fits that four-kibioctet grid.
Disc sectors tell a similar story. Hard drives used 512-octet sectors for decades, and modern drives use 4 kibioctets, matching the memory page so that a page can be read or written in a single operation. Filesystems then allocate space in blocks that are themselves powers of two, usually 4 kibioctets, which is why a one-octet file consumes four kibioctets of disc.
Network protocols use the unit too. Buffer sizes, window sizes and the maximum size of many protocol structures are powers of two, and the 64-kibioctet limit appears repeatedly: it is the largest value a 16-bit length field can express, and it therefore caps the size of a UDP datagram, an IP packet and several older file formats.
That is the general pattern: wherever a limit comes from the width of a binary field, the limit is a power of two, and the honest way to write it is with a binary prefix. Writing 64 KB for the datagram limit is not wrong by much, but writing 64 KiB is exactly right and says where the number came from.
In everyday use the difference is invisible. A 200-kilooctet file and a 200-kibioctet file are 4.8 kibioctets apart, which nobody notices. The value of the distinction is that it makes the arithmetic behind a figure legible, which matters far more as the numbers grow.
One kibioctet equals 1,024 octets, 8,192 bits, 8 kibibits, or 1.024 kilooctets.
The petaoctet is a unit of digital information equal to a thousand teraoctets, or a million gigaoctets. Its symbol is Po. It is the unit of institutional storage: the scale at which data belongs to an organisation rather than to a person, and at which keeping it becomes a budget line rather than an afterthought.
A petaoctet is roughly the storage of a thousand large consumer hard drives, or the text of every book ever published several times over. In video terms it is about twenty thousand hours in ultra-high definition, or two and a half years of continuous viewing. The entire catalogue of a large streaming service, held once at each quality level, comes to a few petaoctets.
Science reached this scale first. The Large Hadron Collider at CERN records tens of petaoctets a year after its trigger systems have already discarded more than 99.99 per cent of what the detectors see, and the full archive runs to several hundred petaoctets. Astronomy, genomics and climate modelling all keep archives of comparable size, and the discipline of managing them became a research field of its own.
Commercially the petaoctet describes a single data centre's storage rather than a company's total. A large organisation holds tens or hundreds of petaoctets across many sites, and the largest cloud providers hold exaoctets. At this size the practical problems are not capacity but the electricity to keep the drives spinning, the cooling, and the certainty that a fraction of the hardware is failing at any moment.
That last point drives the design. In a petaoctet array, drive failures are not exceptional events but a continuous background rate, so the system is built to lose devices constantly and rebuild without interruption. Data is stored with erasure coding across many machines, and no single copy of anything is trusted.
Reading a petaoctet is itself a problem. Even at ten gigaoctets per second, a rate few systems sustain, a full pass takes more than a day. This is why analysis at this scale is designed to move the computation to the data rather than the data to the computation, an inversion that shaped the whole field of distributed processing.
One petaoctet equals 1,000 teraoctets, 1,000,000 gigaoctets, 8 petabits, or about 0.8882 pebioctets.